Objective To utilize ultrasound radiomics technology combined with clinical indicators and contrast-enhanced ultrasound (CEUS) to construct a combined model, thereby improving the diagnostic accuracy of PCa in the gray zone. Methods The diagnostic accuracy of prostate cancer (PCa) within the prostate-specific antigen gray zone (4-10 ng/mL) is relatively low, and traditional methods struggle to effectively differentiate between benign and malignant lesions. This study aims to utilize ultrasound radiomics technology combined with clinical indicators and contrast-enhanced ultrasound (CEUS) to construct a combined model, thereby improving the diagnostic accuracy of PCa in the gray zone. Results Among the 137 patients, 55 were diagnosed with prostate cancer and 82 had benign lesions. Multivariate logistic regression analysis showed that free prostate-specific antigen and peak intensity were independent predictors of PCa in the gray zone (P<0.05). The combined model achieved AUC values of 0.965 and 0.893 in the training and validation sets, respectively, significantly outperforming the single models. The DCA curve indicated that the combined model had a higher net benefit at low-risk thresholds, and the calibration curve further confirmed its accuracy. Conclusion The combined model constructed using ultrasound radiomics, clinical indicators, and CEUS significantly improves the diagnostic accuracy of PCa in the gray zone, providing an effective auxiliary diagnostic tool for clinical practice.

Objective To explore the feasibility and clinical value of low radiation dose scanning combined with deep learning reconstruction (DLIR) algorithm in CT-guided lung puncture biopsy. Methods Patients who underwent CT-guided lung puncture at the Affiliated Hospital of Shaanxi University of Traditional Chinese Medicine from September 2023 to March 2024 were selected, and according to the different scanning protocols, 60 lung puncture biopsy patients were divided into a conventional dose group (group A) and a low-dose group (group B). Group A was 100 kV, with a noise index (NI)=15; Group B had an NI=45; the rest of the scanning parameters were the same. The first and last whole-lung scans in the conventional dose group were scanned with the parameters of group A and B, respectively. They were used to evaluate the image quality improvement potential of the deep learning reconstruction algorithm (DLIR). The first whole-lung scan in group A was reconstructed with filtered back projection (FBP) and weighted 50% adaptive statistical iterative reconstruction-V (50% ASIR-V), and the last whole-lung scan was reconstructed with the three intensities of the deep learning reconstruction algorithm (DLIR-L, DLIR-M, DLIR-H) reconstructed images. The CT and SD values of paraspinal muscles, subcutaneous fat, and aortic vessels were measured, and the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated. The baseline characteristics of the patients, the total radiation dose during puncture, the pathological positivity rate, and the complication rate were compared between group A and B. Results The differences in CT values at muscle, subcutaneous fat, and aortic vessels in the reconstructed images under the five different conditions were not statistically significant (P>0.05). The differences in SD, SNR, and CNR values were statistically significant (P<0.05). The two-by-two comparative analyses between the groups showed that there were no statistically significant differences between the DLIR-H images and the 50% ASIR-V images in muscle, fat, and vessel SD and SNR (P>0.05); the differences in CNR values between FBP vs DLIR-H and DLIR-L vs DLIR-H groups were statistically significant (P<0.05). Compared with group A's total radiation dose, group B's total radiation dose was reduced by about 93.6% (P<0.001). The image quality of both groups could meet the needs of clinical puncture, and the differences in baseline characteristics, pathological positivity rate, and complication rate between the two groups were not statistically significant (P>0.05). Conclusion Low-dose CT scanning combined with DLIR reconstruction significantly reduces image noise and improves image quality without compromising the safety of puncture or pathology positivity.

Objective To investigate the relationship between contrast-enhanced ultrasound (CEUS) Liver imaging reporting and data system (LI-RADS) classification and the degree of pathological differentiation and microvascular invasion (MVI) in hepatocellular carcinoma (HCC) within the context of liver cirrhosis. Methods A retrospective analysis was conducted on 368 HCC patients who underwent liver CEUS at the Department of Ultrasound Medicine, West China Hospital, Sichuan University from June 2021 to December 2022, including 298 males and 70 females, aged 25-85(55.72±10.60) years old. Clinical features, CEUS characteristics, and LI-RADS classification were analyzed and compared in relation to the degree of pathological differentiation of the lesions and MVI. Results According to the Edmondson-Steiner grading system for pathological differentiation, 112 cases were classified as poorly differentiated, 239 as moderately differentiated, and 17 as well-differentiated. Pathological examination revealed 142 MVI-positive cases and 226 MVI-negative cases. The size of HCC lesions was inversely correlated with the degree of differentiation (P<0.001), with MVI-positive lesions being significantly larger than MVI-negative lesions (P<0.001). The proportions of HCC lesions presenting with mild or late washout were 59.8%, 67.4%, and 70.6% for poorly, moderately, well-differentiated lesions, respectively. Similarly, the proportions of lesions classified as LI-RADS 5 were 58.0%, 66.5%, 70.6%, respectively, with both proportions increasing with higher degrees of pathological differentiation. In contrast, the proportions of lesions presenting with early or marked washout were 38.4%, 28.0%, 5.9% for poorly, moderately, and well-differentiated HCC, respectively. The proportions classified as LI-RADS M were 40.2%, 28.9%, 5.9%, respectively, showing a decreasing trend with increasing differentiation. Furthermore, a higher degree of differentiation was associated with a greater proportion of patients without MVI (P<0.001). There were no statistically significant differences observed in CEUS features, including arterial phase enhancement, washout patterns, and LI-RADS classification between MVI-positive and MVI-negative patients (P>0.05). Conclusion In cirrhotic patients, a correlation was identified between the CEUS LI-RADS classification of HCC and the degree of tumor differentiation. Well-differentiated lesions were more frequently categorized as LI-RADS 5, whereas poorly differentiated lesions were predominantly classified as LI-RADS M.

Objective To evaluate the potential of deep learning image reconstruction (DLIR) in improving image quality and reducing radiation dose by comparing the noise power spectrum, task-based transfer function and lesion detection capability. Methods The ACR464 phantom was scanned using GE Revolution APEX CT and eight different noise indices (NI=10, 14, 16, 18, 20, 22, 24, 28) were set. The original data were subjected to image reconstruction using filtered back-projection (FBP), multi-model iterative reconstruction algorithms (ASiR-V) at 40%, ASiR-V at 60%, ASiR-V at 80%, and different levels of deep learning image reconstruction (DLIR-L, DLIR-M, DLIR-H) algorithms. The image quality was evaluated by using imQuest software to calculate the noise power spectrum (NPS), task-based transfer function (TTF), and detection capability index (d') of different reconstruction algorithms. Results Among all the reconstruction algorithms, the NPS peak of DLIR-H was the lowest. With the increase of noise index, both NPS and fav move towards low frequencies. The fav of DLIR-H (0.24-0.27 mm^-1) was only 40% lower than that of ASiR-V (0.26-0.28 mm^-1). The TTF_50% value was not affected by the DLIR level. The TTF_50% value was (37.44±10.85)% and (46.24±15.28)% higher than that of ASiR-V60% and 80%, respectively. The detection ability of both large and small features in deep learning image reconstruction was 40% higher than that of ASiR-V. When comparing the radiation doses with comparable lesions detection capabilities of 40% ASiR-V at NI=10 and DLIR-H, the radiation dose for small features decreased by approximately 76.48%, and that for large features decreased by approximately 72.59%. Conclusion Deep learning image reconstruction can not only reduce noise, improve spatial resolution and lesion detectibility without changing noise texture, but also has more powerful ability to reduce radiation dose than ASiR-V.

The tumor microenvironment plays an important role in tumorigenesis, development, metastasis, and drug sensitivity. Carbonic anhydrase IX (CAIX) is a metalloenzyme that is highly expressed in certain tumor microenvironments and is closely related to tumor cell genesis, development and drug resistance. Its high expression in tumors and low expression in normal tissues makes it a potential target for the diagnosis and treatment of a variety of tumors. With the in-depth research on antitumor drugs and radionuclide-targeted therapy targeting CAIX, the detection of CAIX expression using noninvasive radiopharmaceuticals has become more urgent in order to meet the strategy of diagnostic and therapeutic integration. In this paper, we summarize and review the research on CAIX-targeting radiopharmaceuticals in recent years, analyze and summarize the advantages and disadvantages of monoclonal antibodies, small molecules and peptides, as well as the prospects of their clinical application, so as to optimize the structure of the drugs, reduce the side effects and meet the clinical needs, and to accelerate the clinical application of these drugs.

Immune checkpoint inhibitors that target the programmed death receptor (PD-1) and its ligand (PD-L1) pathway have emerged as a promising strategy for cancer therapy. The expression level of PD-L1 in tumors is strongly correlated with the effectiveness of this form of immunotherapy. Clinically, PD-L1 expression is typically evaluated through immunohistochemistry, an invasive technique that has significant limitations due to the spatial and temporal heterogeneity of PD-L1 expression within tumor tissues. Consequently, this method may not provide a comprehensive assessment of PD-L1 expression. In contrast, molecular imaging techniques in nuclear medicine offer a non-invasive, real-time, and dynamic means of visualizing PD-L1 expression. Technetium-99m is the most commonly used radionuclide for single-photon emission computed tomography (SPECT) imaging, as it is inexpensive, easily available, and possesses suitable energy and half-life characteristics. SPECT is the most frequently employed imaging modality in nuclear medicine globally. Accordingly, technetium-99m-labeled molecular probes targeting PD-L1 hold significant potential for widespread clinical application. This review aims to summarize current advancements in the development of technetium-99m-labeled molecular probes for PD-L1 to guide future efforts to identify novel probes for SPECT imaging of PD-L1.

The proposal of the Brain Science Project has made brain- related research a hot topic, and its related neuromodulation is a frontier and hot topic of current research. Compared with traditional neuromodulation methods, Low Intensity Focused Ultrasound (LIFU), as an emerging neuromodulation technology, has the advantages of non- invasive, reversible, and targetable deep brain structures. It has been extensively studied by scholars at home and abroad. However, the specific mechanism of LIFU neuromodulation is not very clear, and the clarification of the mechanism has guiding significance for its application in related fields. This article briefly summarizes the research progress on the mechanism of LIFU neural modulation in recent years, and briefly outlines the application of ultrasound in the nervous system, aiming to provide references for the subsequent basic and clinical research on ultrasound neural modulation.

Objective To explore the uptake of tau PET in meningioma by ¹⁸F-PI-2620 PET brain imaging, its correlation with lesion size and calcification, and its potential application. Methods A retrospective analysis was performed on 311 subjects who underwent ¹⁸F-PI-2620 PET brain examinations at our hospital from January 2020 to December 2023. Patients with meningioma diagnosed by final MRI enhancement were screened. The size and maximum standardized uptake value (SUV_max) of the meningioma lesions were measured for all included subjects, and the SUV_max of the lesion to the background (T/N) were obtained using the normal cerebral cortex on the opposite side as the background. Statistical analysis was performed using SPSS 26.0 statistical software, and the correlation between SUV_max, T/N values and lesion size and calcification was compared. Results Eight meningioma patients were included, including 3 males and 5 females, aged at 65-78 (69.8±4.86) years old. There was a statistically significant difference in SUV_max between the meningioma and the background (P<0.05). The T/N in the meningioma group was higher than that of the background (P<0.001). There was no statistically significant difference in SUVmax and T/N ratio between the meningioma calcification group and the non-calcification group (P>0.05). The volume of the lesion was significantly correlated with the T/N ratio of uptake (R=0.89, P<0.01). Conclusion The tau uptake value of ¹⁸F-PI-2620 in meningioma is related to the size of the lesion, but not whether the lesion is calcified.

Objective To establish a predictive model by extracting radiomic features from multi-parametric MRI data and combining them with clinical characteristics, and identify the machine learning model with the highest predictive value for triple-negative breast cancer (TNBC). Methods A total of 175 breast cancer patients, including 40 cases of TNBC and 135 cases of non-triple negative breast cancer (NTNBC), were collected and divided into training set (n=123) and validation set (n=52)according to 7:3. Multiparameter predictive models were developed using various machine learning algorithms and combined with clinical features for joint modeling. The predictive performance of different models was assessed using ROC curves. Results In the training and validation sets, Boundary, WHO classification and T2WI signals of lesions were statistically different in TNBC and NTNBC (P<0.05), among the nine models established using rbf_SVM, including Model-T2WI, Model-DWI, Model-DCE_Phase2, Model-DCE_Phase7, Model-T2WI+DWI, Model-DCE_Phase7+T2WI, Model-DCE_Phase7+T2WI+DWI, and Model-DCE_Phase7+T2WI+DWI+Clinic, the radiomics-based predictive model of Model-DCE_Phase7+T2WI+DWI+Clinic demonstrated the highest performance, with areas under the curve (AUC) of 0.992 and 0.936 in the training and validation sets, respectively. Conclusion The radiomics model based on multi-parametric MRI can accurately predict TNBC, contributing to the clinical diagnosis and treatment management of TNBC.

Objective To explore the predictive value of imaging features, serological immune indicators, and clinical features for interstitial lung disease in Sj?gren's syndrome (SS-ILD). Methods A total of 161 patients with Sj?gren's Syndrome (SS) who were treated at the First Affiliated Hospital of Henan Medical University from July 2018 to February 2025 were retrospectively enrolled; through propensity score matching (PSM), the patients were divided into the SS without interstitial lung disease (ILD) group (n=56) and the SS with ILD group (n=29). Univariate analysis was used to screen for meaningful variables, the Spearman correlation coefficient was applied to analyze the correlation between these variables and SS-ILD, binary logistic regression was performed to construct a combined prediction model, the area under the receiver operating characteristic curve (AUC) and Delong test were used to verify the predictive performance of the combined model, a calibration curve was plotted to validate the value of imaging indicators incorporated into the combined model. Results Statistically significant differences were observed between the two groups in mean spleen density, percentage of CD4?T cells, complement C4, Dry mouth, Dry eyes, and oral symptoms, and these variables were all negatively correlated with the occurrence of SS-ILD (all P<0.05); Logistic regression analysis revealed that the mean splenic density (AUC=0.698, sensitivity=0.759, specificity=0.607), percentage of CD4⁺ T lymphocytes (AUC=0.677, sensitivity=0.982, specificity=0.310), and oral symptoms (AUC=0.635, sensitivity=0.339, specificity=0.931) all had independent predictive value. The three-factor combined model (AUC=0.781, sensitivity 0.862, specificity 0.554) was significantly superior to any single indicator (P<0.05). Conclusion Decreased mean splenic density, reduced percentage of CD4? T lymphocytes, and absence of oral symptoms are independent predictive factors for the development of SS-ILD. The combination of these three factors can effectively improve the predictive efficacy with high sensitivity, which is helpful for the early clinical identification of high-risk patients with SS-ILD.

Objective To explore the value of a Nomogram model based on CT radiomics with clinical parameters in differentiating non-small cell lung cancer from benign pulmonary lesions. Methods A retrospective study was conducted on 177 patients with benign pulmonary lesions and non-small cell lung cancer, confirmed by pathology, at the First Affiliated Hospital of Bengbu Medical Unversity from December 2020 to December 2023. The cases were randomly divided into a training group and a validation group in an 8:2 ratio. Radiomic features were extracted from contrast-enhanced CT images, and a stepwise dimensionality reduction was performed using the Relief-LASSO algorithm, ultimately selecting five optimal features from a total of 2264 radiomic features. Single and multiple factor Logistic regression was employed to screen independent clinical risk factors. Clinical, radiomics, and Nomogram models were constructed respectively. The performance of the Nomogram model was comprehensively evaluated using multiple metrics, including the area under the ROC curve (AUC), calibration curves, and decision curve analysis. Results The results indicated that the Nomogram model exhibited excellent predictive performance, with AUC values of 0.872 (95% CI: 0.817-0.928) in the training set and 0.788 (95% CI: 0.627-0.948) in the validation set. These values were significantly higher than those of the individual imaging model (0.811, 0.722) and the clinical model (0.797, 0.734). Conclusion The established Nomogram model serves as a non-surgical predictive tool for the differential diagnosis of non-small cell lung cancer and benign pulmonary lesions. Validation demonstrated that the Nomogram model exhibited excellent differentiation and calibration abilities, indicating its clinical utility in the early screening of lung cancer and providing important guidance for clinical decision-making prior to surgery.

Objective To explore the feasibility of constructing a machine learning model based on mammography signs and clinical informations to predict the histological grade in the ductal carcinoma in situ. Methods A retrospective analysis were conducted on the mammography signs and clinical informations of 239 patients who had histologically confirmed breast ductal carcinoma in situ (DCIS). Based on pathological results, these patients were categorized into : non-high-grade group (n=109) and high-grade group (n=130). The collected 10 clinical informations and 15 mammography signs were statistically analyzed, and the features with statistical differences were selected to construct three machine learning models, namely eXtreme Gradient Boosting, logistic regression and multinomial naive bayes, with the area under the ROC curve (AUC) was used as the main index to select the optimal mode. Results The AUC values for the training sets of eXtreme Gradient Boosting, logistic regression and multinomial Naive Bayes were 0.790, 0.794, 0.802, and the AUC values of text sets were 0.760, 0.758, 0.774, and the accuracies were 0.760, 0.759, 0.774,the sensitivities were 0.725, 0.825, 0.800, the specificities were 0.625, 0.434, 0.625. Conclusion The histological grade models of ductal carcinoma in situ based on machine learning have better prediction efficiency, and the multinomial naive Bayes has the best prediction efficiency.

Objective To develop a combined nomogram model based on enhanced CT imaging features and clinical indicators for predicting early recurrence (ER) in untreated intermediate-stage hepatocellular carcinoma (HCC) patients after transcatheter arterial chemoembolization (TACE), and to compare the performance of this model with radiomics and clinical models. Methods In this retrospective, two-center study, 55 HCC patients who underwent enhanced CT before TACE at Affiliated Hefei First People's Hospital from February 2020 to February 2024 were randomly divided into training and validation groups using five-fold cross-validation. Clinical data, CT radiomics data, pathological data, and serum markers collected within one week before TACE were collected and evaluated for all patients. Radiomic features were selected using univariate rank sum tests and Spearman correlation analysis. Radscore was calculated based on the linear product of logistic regression model coefficients and feature values. Significant variables were identified using univariate and multivariate logistic regression, and a nomogram was constructed. The model's performance was assessed using ROC curves and decision curve analysis. Results In both the training and validation groups, the combined nomogram model had AUCs of 0.787 (95% CI: 0.52-1.05) and 0.847 (95% CI: 0.54-1.14), respectively, for predicting early recurrence after TACE. Univariate and multivariate regression analysis indicated that prothrombin time (P<0.05) was an independent serum marker associated with early recurrence after TACE. In both the training and validation groups, the AUC, accuracy, sensitivity, and specificity of the clinical model and the radiomic nomogram model alone were lower than those of the combined clinical-radiomic nomogram model. Decision curve analysis showed that the combined nomogram model had greater net benefit. Conclusion The proposed combined nomogram model has the potential to accurately predict early recurrence in HCC patients after TACE.

Objective To investigate the comparative efficacy of T2 and T3 staging of rectal cancer based on conventional MRI signs and imaging histology. Methods A total of 272 patients with pathologically confirmed T2 and T3 stage rectal cancer were enrolled at the Lujiang Branch of the Tongji University Affiliated Oriental Hospital from December 2021 to December 2024, including 104 patients in the T2 stage and 168 patients in the T3 stage.First, we conducted a comparative analysis of the diagnostic efficacy of preoperative assessment for T2 versus T3 staging of rectal cancer based on multiparametric conventional MRI signs; Second, the enrolled patients were randomly divided into a training group (n=190) and a validation group (n=82) in a 7∶3 ratio; Imaging histological features associated with T2 and T3 staging of rectal cancer were extracted from non-lipid-suppressed T2-weighted sequences, diffusion-weighted imaging, and MRI-enhanced scanning images, respectively, to construct a joint imaging histology model;Finally, receiver operating characteristic curves were plotted for the multiparameter-based conventional MRI signs and the imaging histology model. The area under the curve, specificity, and sensitivity of the corresponding models were calculated to compare and analyze the efficacy of preoperative assessment for T2 and T3 staging of rectal cancer based on the two diagnostic modalities. Results Based on the diagnostic efficacy of conventional multiparametric MRI signs, the AUC was 0.905, the specificity and sensitivity were 0.917 and 0.894; while the highest efficacy was observed in the MRI imaging histology-based joint model training group,the AUC was 0.981,The specificity and sensitivity were 0.944 and 0.929, respectively;In the validation group, the AUC was 0.953, The specificity and sensitivity were 0.926 and 0.898, respectively; and the results were well-calibrated and statistically significant (P<0.05). Conclusion The efficacy of the preoperative assessment for T2 and T3 staging of rectal cancer using the MRI histology model is higher than that of traditional MRI signs, making it worthy of further promotion and application in clinical practice.

Objective This research focused on the synthesis and characterization of a dual-modal nanoprobe (Gal-MnO₂/CDDP@PDA-Cy5.5) for fluorescence and magnetic resonance imaging of hepatocellular carcinoma. The study further explored the probe's specific targeting efficacy against ASGPR-expressing Huh-7 cells and evaluated its performance in magnetic resonance imaging through in vitro experiments. Methods Potassium permanganate solution was added to silica and etched with anhydrous sodium carbonate. The resulting solution was conjugated with polydopamine (DA), galactosamine (Gal), and fluorescent Cy5.5 to obtain Gal-MnO₂@PDA-Cy5.5. Cisplatin (CDDP) was introduced into the solution, followed by overnight incubation at room temperature and subsequent centrifugation to remove unreacted CDDP. Cytotoxicity and cellular uptake were assessed using the CCK-8 assay and flow cytometry, respectively. The relaxation rate was measured by Niumag small-scale NMR spectroscopy, and the enhancement degree was evaluated using magnetic resonance imaging. Results The prepared nanoprobes, as observed by transmission electron microscopy, exhibited uniform size and granular morphology with a particle size of 185.0±6.3 nm. The hydrodynamic diameter was measured to be 185.1±16.4 nm, with a zeta potential of 22.5±0.3 mV and a relaxivity of 14.589 (mmol/L)^-1s^-1. The magnetic resonance imaging signal intensity progressively enhanced with increasing nanoprobe concentration. Cytotoxicity assays demonstrated minimal toxicity of the nanoprobes. Conclusion This study successfully synthesized a dual-modal nanoprobe targeting ASGPR, designated as Gal-MnO₂/CDDP@PDA-Cy5.5, which demonstrates specific binding to target cells in vitro. Validation results confirmed that the synthesized nanoprobe exhibits excellent stability and biosafety, along with specific targeting capability toward Huh-7 cells. Furthermore, it possesses imaging functionality that enhances T1 contrast in magnetic resonance imaging.

Objective To develop a novel multifunctional integrated diagnostic and therapeutic nanoprobes targeting breast cancer, MnO₂@DOX@Cancer Cell Membrane (MDC), evaluate its basic properties, and explore its magnetic resonance imaging (MRI) capabilities and chemotherapy effects. Methods MnO₂ with a favorable morphology was synthesized. The cell membrane of 4T1 mouse breast cancer cells was obtained using chemical lysis and ultrasonic fragmentation techniques. A lipid extrusion method was used to synthesize the cell membrane-modified nanoprobes MDC loaded with doxorubicin (DOX). Key properties of MDC, including morphology, surface potential, and particle size, were characterized, and its MRI capability was explored. The cytotoxic effects of MDC at different concentrations on tumor cells were observed to assess its inhibitory effect on breast cancer tumors in chemotherapy. The integrated diagnostic and therapeutic functions at the cellular level were also verified. Results The nanoprobes MDC with a nanoflower-like structure were successfully synthesized, with a Zeta potential of -20±1.5 mV and an average particle size of 151.2 nm. Transmission electron microscopy (TEM) imaging confirmed successful coating of the cell membrane onto the nanoprobes. MRI results showed that MDC exhibited excellent MRI T1 imaging ability in a simulated tumor microenvironment. Laser confocal microscopy experiments further confirmed that MDC had excellent homologous targeting capability. Cytotoxicity experiments indicated that MDC significantly killed cancer cells. Conclusion This study successfully synthesized a multifunctional integrated diagnostic and therapeutic nanoprobes MDC, which exhibited excellent homologous targeting and anti-tumor effects in chemotherapy, significantly enhanced MRI imaging, and demonstrated integrated diagnostic and therapeutic functions at the cellular level.

Breast cancer is one of the most common cancers worldwide and the leading cause of cancer death in women.In recent years, with the rapid improvement of computer performance, artificial intelligence shines in various fields, and artificial intelligence deep learning with automatic image analysis ability has also attracted more and more attention in the medical field, medical institutions have begun to pay attention to the collection of medical data, especially the accumulation of a large number of medical image data. At present, there are three conventional imaging methods for breast diseases: mammography, breast ultrasound and breast MRI.Artificial intelligence combined with breast imaging offers unprecedented opportunities for the diagnosis and treatment of breast cancer.This paper reviews the combination of artificial intelligence and breast image data in the diagnosis, treatment and prognosis prediction of breast cancer, hoping that artificial intelligence can be more widely and maturely applied to the imaging diagnosis and treatment of breast cancer, so as to provide ideas for promoting the transformation and application of precision medicine for breast cancer from theory to clinical practice by combining artificial intelligence with breast image data.

Vascular cognitive impairment (VCI) is a clinical syndrome characterized by cognitive impairment in at least one domain, caused by cerebrovascular lesions and their risk factors, with an increasing incidence among middle-aged and elderly populations. In recent years, advancements in MRI have provided new methods for the study of VCI. Among these, diffusion tensor imaging, which is currently the only non-invasive technique that allows visualization of the arrangement of white matter fiber tracts in living brains, has unique advantages in VCI research. This article will review the concept of diffusion tensor imaging and its various applications in VCI, including white matter lesions, diagnosis and classification, risk factor identification, and prevention and treatment, while also discussing its limitations and prospects for future development. This aims to provide new insights for the clinical diagnosis and pathological research of neurological diseases.

The Ki-67 index in breast cancer reflects the proliferative activity of tumor cells. High Ki-67 expression indicates greater proliferative activity, increased invasiveness, higher recurrence risk, and poorer prognosis. Therefore, Ki-67 expression status is essential for molecular subtyping, assessment of treatment efficacy, and prognosis prediction in breast cancer. Radiomics and deep learning have become prominent approaches in intelligent medical imaging, enabling comprehensive, non-invasive, and dynamic assessment of Ki-67 expression in breast cancer by extracting high-throughput imaging features that reflect tumor heterogeneity. This review summarizes recent progress in applying radiomics and deep learning to predict Ki-67 expression status in breast cancer.

Objective To develop and validate a 3D convolutional neural network (3D-CNN)-based CT-assisted diagnostic model for tuberculosis (TB) activity grading, aiming to improve diagnostic efficiency and accuracy. The model incorporates Grad-CAM visualization technology to provide interpretability analysis of its decision-making process. Methods Retrospective data were collected from 300 patients who underwent non-contrast chest CT scans at Jining Public Health Medical Center from January 2020 to December 2024. According to the Diagnostic Criteria for Pulmonary Tuberculosis (WS 288-2017) and comprehensive clinical evaluation (including sputum culture, pathological results, anti-TB treatment response, and follow-up imaging dynamics), patients were stratified into three groups, with 100 cases in each group: normal lung group, active TB group, inactive TB group. The 3D-CNN model was employed to extract spatial features from CT images, with model parameters optimized through cross-validation. Model performance was systematically evaluated. The Grad-CAM algorithm generated heatmaps to identify critical regions of model attention, with results validated against clinical diagnostic standards. Results The model achieved 95.00% of classification accuracy, 95.30% of sensitivity, and 95.60% of specificity on the test set. Grad-CAM visualizations demonstrated high spatial concordance between model-identified regions and expert-annotated lesion areas. Conclusion The 3D-CNN-based CT-assisted diagnostic model shows high performance in TB activity grading and may serve as an effective clinical decision-support tool. The integration of Grad-CAM enhances model transparency and credibility.

Objective To analyze the causes of trigeminal neuralgia without vascular compression by MRI. Methods The clinical data of 86 patients with trigeminal neuralgia diagnosed in the second neurosurgery ward of Zhoukou Central Hospital from January 2018 to September 2023, who underwent microvascular decompression without preoperative MRI findings of vascular compression, were retrospectively analyzed, and 74 of them met the inclusion criteria. Endoscopic images obtained during microvascular decompression and postoperative follow-up were used as reference standards, and the images were read separately by radiologists with more than five years of experience, and the images of responsible vessels not found in MRI preoperative examination were analyzed. Postoperative outcomes were assessed using the Barrow neurological institute pain intensity score, and the differences were compared using a repeated measures analysis of variance. Results Among the 74 patients with trigeminal neuralgia, 30 cases (40.5%) had intraoperative venous compression, 15 cases (20.3%) had venous compression with arachnoid adhesion, 12 cases (16.2%) had arterial branch compression, 11 cases (14.9%) had arachnoid adhesion, 3 cases (4.1%) had tumor compression, and 3 cases (4.1%) had no intraoperative vascular compression or arachnoid adhesion. Compared with before operation, the pain of patients was significantly relieved at all time points after operation, and the difference was statistically significant (P<0.05). Conclusion MRI is commonly used in the preoperative diagnosis of trigeminal neuralgia, which can clearly show the neurovascular interaction. Different surgical strategies should be adopted for different causes of trigeminal neuralgia.A specific test sequence is required for trigeminal neuralgia patients without vascular compression and whose secondary cause is unknown, and imaging doctors should check the medical history carefully and make comprehensive analysis to improve the diagnostic accuracy.

Lung cancer, being one of the cancers with the highest global incidence and the main reason for cancer deaths, usually exhibits as pulmonary nodules in the early stage. CT represents a crucial imaging examination approach for the assessment of pulmonary nodules. With the advancement of technology, dual-energy CT is widely used in clinical practice. By acquiring images at two different energy spectra, dual-energy CT enables material decomposition, allowing generation of material- and energy-specific images. Existing research has demonstrated that dual-energy CT can be employed not merely for differentiating between benign and malignant pulmonary nodules, predicting pathological types of lung cancer, assessing the degree of tumor differentiation as well as the gene expression, but also for assessing therapy response and prognosis of lung cancer. This article reviews the clinical applications of dual-energy CT material decomposition images in distinguishing between benign and malignant pulmonary nodules, predicting the pathological types of lung cancer, the degree of tumor differentiation, the gene expression of lung cancer, evaluating therapy response and prognosis of lung cancer. It aims to systematically sort out the clinical application progress of dual-energy CT material decomposition images in pulmonary nodules, provide a more scientific and accurate basis for clinical decision-making, and promote the further development of precision medicine for lung cancer.

Breast cancer is one of the most common types of cancer in women. The status of axillary lymph nodes plays a key role in clinical staging, treatment planning and prognosis evaluation of malignant tumors. At present, sentinel lymph node biopsy and axillary lymph node dissection are the gold standards for axillary lymph node assessment. Although it is widely used in clinical practice, its traumatic operation may cause a variety of postoperative complications. Therefore, evaluating the status of axillary lymph nodes by non-invasive methods before the operation is of great significance for formulating clinical diagnosis and treatment plans. Ultrasound imaging technology can precisely and non-invasively assess the status of axillary lymph nodes in breast cancer without radiation, and it is the main method for preoperative clinical assessment of the status of axillary lymph nodes in breast cancer. This article reviews the research progress of two-dimensional ultrasound, color Doppler flow imaging, elastography, contrast-enhanced ultrasound, ultrasound radiomics and deep learning techniques in predicting the status of axillary lymph nodes before breast cancer surgery, with the aim of providing a basis for formulating precise individualized treatment plans in clinical practice.

Objective To explore the value of a deep learning-based ultrasound radiomics nomogram in predicting Ki-67 expression levels in invasive breast cancer. Methods A retrospective single-center study was conducted, collecting complete preoperative clinical data and ultrasound images from 465 patients with pathologically confirmed invasive breast cancer at the First Affiliated Hospital of Bengbu Medical University from January to December 2024. Image acquisition was performed using Mindray Resona 7 and Samsung HS60 color Doppler ultrasound systems. Based on immunohistochemical results, patients were divided into high and low Ki-67 expression groups and randomly assigned to training (n=326) and validation (n=139) cohorts at a 7:3 ratio. ITK-SNAP software was used to segment tumors from the largest 2D ultrasound cross-sectional images, with interobserver consistency of ROI delineation assessed by ICC. Pyradiomics was employed to extract radiomics features from tumor tissues, and four deep learning networks were pretrained to construct clinical, ultrasound radiomics, fusion, and combined nomogram models. Diagnostic performance and clinical utility were evaluated using ROC curves, calibration curves, and decision curve analysis. Results Nineteen optimal ultrasound radiomics features and the DenseNet121 deep learning model showed the best performance (P<0.05). In the training cohort, the AUCs for the clinical model, ultrasound radiomics model, deep learning model, fusion model, and nomogram were 0.79 (95% CI: 0.74-0.84), 0.85 (95% CI: 0.81-0.90), 0.87(95% CI: 0.83-0.91), 0.94(95% CI: 0.91-0.97), and 0.95(95% CI: 0.93-0.98), respectively. In the validation cohort, the corresponding AUCs were 0.76(95% CI: 0.68-0.84), 0.78 (95% CI: 0.70-0.85), 0.81(95% CI: 0.74-0.88), 0.91(95% CI: 0.86-0.96), and 0.93(95% CI: 0.89-0.98). Conclusion The deep learning-based ultrasound radiomics nomogram can effectively predict Ki-67 expression in invasive breast cancer.

Magnetic resonance technology is safe and radiation-free, and has been widely used in the whole body. Multi-sequence and multi-parameter combined MRI imaging breaks the limitation of single imaging, and can reflect the information of lesion diffusion, perfusion and metabolism through quantitative analysis by DWI, IVIM, DCE-MRI,MRS And other technologies, so as to differentiate and evaluate the benign and malignant of isolated pulmonary nodules from the molecular level. Multi-parameter combined imaging significantly improved the sensitivity and specificity of single imaging, which is superior to single-parameter imaging. Additionally, it demonstrates potential for further analyzing pathological typing of lung cancer. MRI multi-parameter combined imaging is expected to improve the early diagnosis rate and specificity of pulmonary nodules, and provide a more reliable basis for individualized treatment.

Objective To validate the feasibility of the deep learning image reconstruction (DLIR) algorithm in coronary computed tomography angiography (CCTA) under low radiation dose and low contrast agent volume conditions. Methods This prospective study included 86 patients with normal BMI who underwent CCTA at the Affiliated BenQ Hospital of Nanjing Medical University from November 2021 to April 2022. The patients were randomly divided into group A and group B. Both groups employed Smart-mA tube current automatic control technology, Auto Gating, Smart Phase and Motion correction algorithm techniques, with a noise index set at 12.2 HU. Iodixanol (350 mgI/mL) was used as the contrast agent. The tube voltage was set to 70 kV, with the contrast agent volume calculated as (body weight ×0.275) mL in group A, and the tube voltage was set to 120 kV, the contrast agent volume was (body weight ×0.55) mL in group B. Group A used the DLIR algorithm for image reconstruction, while group B used the 50% ASIR-V algorithm. The CT values and noise levels of the aortic root, left main, left anterior descending artery, left circumflex artery, and right coronary artery proximal segments were measured and calculated. Objective evaluation parameters, including signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and edge rise distance were computed. A double-blind method was used to compare the subjective image quality of the two reconstruction methods. Results Except for no significant differences in CNR of the left main artery and SNR of the left circumflex artery proximal segment (P=0.358, 0.252), the CNR and SNR of all other regions of interest in group A were significantly higher than those in group B (P<0.001). The edge rise distance of the left anterior descending proximal segment in group A was smaller than in group B (P<0.001). Image quality in both groups met diagnostic requirements, but group A demonstrated significantly better subjective image quality than group B (P<0.001). Radiation dose: The effective dose in group A was 0.81±0.40 mSv, compared to 2.84±1.50 mSv in group B, with a statistically significant difference (P<0.001). Contrast agent volume: The volume in group A was 22.11±3.31 mL, while in group B it was 34.40±2.98 mL, with a statistically significant difference (P<0.001). Conclusion The DLIR algorithm can effectively reduce radiation dose and contrast agent volume in CCTA, demonstrating potential for wider application.

Objective To construct a staging prediction model on deep vein thrombosis (DVT) based on the deep learning and black-blood magnetic resonance thrombus imaging (BTI), and investigate its prediction value. Methods A retrospective observational study was conducted, where clinical data and BTI from 196 patients admitted to Guangzhou Panyu Central Hospital from November 2015 to July 2022 were collected and analyzed. The dataset was split into a training set (70%, n=136), a validation set (15%, n=30), and a test set (15%, n=30). The experimental group were annotated in rectangular boxes manually, then the corresponding minimum bounding rectangular boxes of the lesion areas were cropped, resized, and sliced, and input to the deep learning model. The three models, ResNet50, Vit and EfficientNet, were established for lower limb staging prediction. Their predict value were compared by accuracy rate and the area under the curve (AUC). Results The accuracy of ResNet50, Vit and EfficientNet-b0 in the testing set were 0.693, 0.733, 0.787. The EfficientNet-b0 outperforms than other two models in the test set. The area under the curve of the acute, sub-acute and chronic phase were 0.700(0.568-0.811), 0.778(0.652-0.875), 0.850(0.737-0.914), respectively. Conclusion Deep learning combined with BTI has certain application values in staging prediction of DVT. It provides an effective technique for the precisive staging for DVT.

Objective To analyze the risk factors for intracranial aneurysm (IA) rupture based on morphological parameters from computed tomography angiography (CTA), clinical characteristics of patients, and hematological inflammatory indicators. Methods A retrospective analysis was conducted on 176 IA patients treated at the Second Affiliated Hospital of Bengbu Medical University from November 2022 to September 2024. Based on the presence or absence of subarachnoid hemorrhage, patients were categorized into an unruptured group (n=72) and a ruptured group (n=104). Clinical data, hematological inflammatory indicators, and CTA-derived aneurysmal morphological parameters were compared between the two groups. Univariate and multivariate logistic regression analyses were employed to identify risk factors for IA rupture. Additionally, ROC curves and area under the curve (AUC) analyses were performed to evaluate the diagnostic efficacy of these risk factors. Results Irregular morphology (OR=3.079, 95%CI: 1.030-9.200, P=0.044), presence of daughter sacs (OR=3.271, 95% CI: 1.109-9.650, P=0.032), elevated size ratio (OR=2.117, 95%CI: 1.074-4.170, P=0.030), increased aspect ratio (OR=7.189, 95%CI: 1.242-41.619, P=0.028), and elevated systemic inflammatory response index (OR=1.500, 95%CI: 1.242-1.810, P<0.001) were identified as independent risk factors for IA rupture, with AUC values of 0.77, 0.75, 0.67, 0.75 and 0.93, respectively. Conclusion Analysis based on CTA morphological parameters combined with clinical factors and blood inflammation indicators reveals that IAs with irregular morphology, presence of daughter sacs, high size ratio, high aspect ratio, and elevated systemic inflammatory response index are all high-risk factors for aneurysm rupture. These factors hold immense importance in accurately predicting the risk of aneurysm rupture.

Near-infrared has better penetration depth and biocompatibility for living tissues, which minimizes the scattering and attenuation of irradiation in tissues. In recent years, it has been used in many aspects such as in vivo imaging, 3D image visualization, photothermal therapy, drug release and in vivo optogenetics. Near-infrared is now increasingly used in clinical medicine, combining with various molecular imaging modalities and using nano-probes to play a photoacoustic imaging role; developing photothermal agents with different properties to achieve near-infrared light therapy through the conversion of light and heat energy; combining with 3D printing, an emerging technology, to personalize stents or implants, using the spatio-temporal tunability of near-infrared light to enable simultaneous diagnosis and treatment, and achieving precision medicine.

Medical imaging is no longer just basic anatomical imaging, functional imaging, molecular imaging, etc. has become an important development trend in the current imaging field, due to the rapid advancement of medical imaging and technology. Radiomics technology has emerged, and artificial intelligence is also progressively altering the structure of the medical industry with its potent data analysis and pattern recognition capabilities. The diagnosis and differential diagnosis of cervical cancer, preoperative staging, evaluation of curative effects, and prognosis prediction are all significantly impacted by the combination of MRI-based radiomics and artificial intelligence. This paper will review the overview and development status of Radiomics and artificial intelligence, as well as the application, future challenges and limitations of radiomics combined with artificial intelligence in cervical cancer.

Objective To investigate the innovation and effectiveness of two-dimensional ultrasonography and shear wave elastography (SWE) combined with the XGBoost machine learning model in the differential diagnosis of benign and malignant thyroid nodules. Methods 2D-ultrasound images and SWE measurements were analyzed in 156 patients with thyroid nodules (209 nodules) from the North District of the First Affiliated Hospital of Anhui Medical University from May 2021 to September 2022 with pathology as the gold standard. A machine learning model based on two-dimensional ultrasonography and SWE was developed using the XGBoost algorithm. The feature importance was assessed using the Shapley additive interpretation method. ROC curves were plotted, and the AUC was calculated to assess the performance of the XGBoost model and SWE. Additionally, decision curve analysis and calibration curves were used to evaluate the application value and diagnostic efficacy of the XGBoost model. Results The AUC, accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the XGBoost model in the diagnosis of benign and malignant thyroid nodules were 0.890, 0.776, 89.6%, 65.7%, 83.3%, 76.7% in the training cohort and 0.913, 0.788, 92.7%, 64.9%, 82.9%, 82.8% in the validation cohort, respectively. Decision curve analysis and calibration curve analysis showed that the XGBoost model showed good clinical application value in the diagnosis of benign and malignant thyroid nodules, as well as high accuracy and reliability. Conclusion The XGBoost machine learning model based on two-dimensional ultrasound features and SWE has important application value in the differential diagnosis of benign and malignant thyroid nodules and provides a new and efficient tool for clinical decision-making.

Objective To investigate the value of uterine artery polyflow parameters combined with peripheral blood D-dimer (D-D) in the assessment of adverse pregnancy outcomes in pregnant women with recurrent miscarriage in early pregnancy. Methods Eighty cases of early pregnancy recurrent miscarriage admitted to Huai'an Maternal and Child Health Hospital from January 2021 to June 2023 were selected as the study group and followed up until 28 weeks of gestation, and they were categorized into the pregnancy loss group (n=35) and the pregnancy success group (n=45) according to the pregnancy outcome, and 92 pregnant women with normal pregnancies who underwent obstetric examination in the same period of time in the hospital were selected as the control group. The uterine artery early diastolic index (NI), resistance index (RI), ratio of maximum peak systolic flow rate to end-diastolic flow rate (S/D), pulsatility index (PI), and levels of peripheral blood D-D were compared between the study group and the control group, the pregnancy loss group and the pregnancy success group, and the pregnancy loss group was included as positive and the pregnancy success group was included as negative, and the predictive value of uterine artery NI, RI, S/D, PI, peripheral blood D-D single and combined tests for the diagnosis of adverse pregnancy outcomes in pregnant women with recurrent miscarriages in the early stages of pregnancy was analyzed by plotting the ROC curves. Results Uterine artery NI was lower in the study group than in the control group (P<0.05); uterine artery RI, S/D, PI and peripheral blood level of D-D were higher than in the control group (P<0.05). Uterine artery NI was lower in the pregnancy loss group than in the pregnancy success group (P<0.05); uterine artery RI, S/D, PI, and peripheral blood level of D-D were higher than those in the pregnancy success group (P<0.05). ROC curve analysis showed that the AUC value of the joint test for predicting adverse pregnancy outcomes in pregnant women with recurrent miscarriage in early pregnancy was higher than that of NI, RI, S/D, PI and peripheral blood D-D in a single test (P<0.05). Conclusion The combination of uterine artery multiflow parameters and peripheral blood D-D testing was more advantageous in predicting adverse pregnancy outcomes in women with recurrent miscarriages in early pregnancy, and the clinical follow-up could be carried out by means of the combination of uterine artery multiflow parameters and peripheral blood D-D testing for timely assessment of the adverse pregnancy outcomes of pregnant women with recurrent miscarriages, so as to promote the improvement of the pregnancy outcomes of pregnant women with recurrent miscarriages.

Type 1 diabetes mellitus (T1DM)-related cognitive dysfunction and potential brain impairment have attracted increasing attention with the rising incidence of T1DM and the extension of patient life expectancy. Several studies have demonstrated an association between T1DM and cognitive dysfunction. In recent years, the widespread application of MRI technology has provided objective imaging evidence for exploring the neuropathophysiological mechanisms of brain impairment in T1DM. This article reviews the manifestations of cognitive dysfunction, the application of MRI technology in brain impairment, and the underlying pathological mechanism in patients with T1DM. By summarizing previous research, it aims to help clinicians gain a deeper understanding of the relationship between T1DM and cognitive dysfunction, and to provide new perspectives for future research, with the hope of early identification and intervention for cognitive dysfunction in patients with T1DM.

Objective To investigate the advantages of incorporating morphological analyses of contrast-enhanced mammography (CEM) and ultrasound for various subtypes of papillary breast lesions, and to compare the diagnostic characteristics and performance of this imaging method in distinguishing between these subtypes. Methods This study involved 70 female patients diagnosed with papillary breast lesions from January 2020 to July 2024. For each patient, BI-RADS lesion features of the CEM and ultrasound were recorded. And the different measurements of diagnostic performance were recorded. Results Among the 70 female patients, 90 lesions were identified, including 18 malignant ones, 4 intraductal papillomas without atypical proliferation, and 48 benign papillary lesions. The areas under ROC curves for CEM combined with ultrasound was 0.863. Specificity and accuracy of CEM combined with ultrasound showed highest values was 79.1% and 84.2%, respectively. However, the sensitivity and negative predictive value of the CEM with ultrasound were similar to those of CEM alone. Conclusion For BI-RADS 3-5 papillary breast lesions, incorporating CEM combined with ultrasound can improved the confidence level in diagnosis.

Objective To explore the clinical value of a combined model constructed based on ultrasound radiomics features and clinicopathological features in predicting pathological complete response after neoadjuvant chemotherapy (NAC) for breast cancer. Methods Retrospective analysis included 160 breast cancer patients receiving NAC before surgery at the First Affiliated Hospital of Bengbu Medical College from August 2021 to July 2024. By analyzing the ultrasound images, the radiomics features were extracted, and the features with statistical significance were screened out for subsequent modeling. Multivariate Logistic regression analysis and the XGBoost algorithm were used to construct joint models based on ultrasound radiomics features, clinicopathological features, and their combination, respectively, and nomograms were drawn. Model performance for NAC response was evaluated using AUC and decision curve analysis, with calibration curves assessing prediction-actuality agreement in the combined model. Results Estrogen receptor (P=0.006), progesterone receptor (P=0.024), and human epidermal growth factor receptor-2 (P=0.034) emerged as independent predictors of NAC response among clinicopathological features. The integrated model combining these three clinical predictors with radiomics features demonstrated optimal predictive performance, achieving a training-set AUC of 0.863, significantly higher than individual models. Calibration curves confirmed robust agreement between predicted and observed outcomes, while decision curve analysis indicated substantial clinical net benefit. Conclusion The combined model constructed based on the characteristics of ultrasound radiomics and clinicopathological features can effectively predict the efficacy of NAC in breast cancer and provide strong support for clinical decision-making. This model has high predictive accuracy and clinical application value, and is expected to become an important tool for individualized treatment of breast cancer.

Objective To analyze the imaging features of pediatric diffuse midline glioma H3K27M variant (DMG-A). Methods The data of 22 children with DMG-A admitted to our hospital from February 2019 to October 2023 were retrospectively analyzed. Preoperative CT scan was performed in 12 cases (11 cases simultaneously with MRI). The images were independently read by two experienced pediatric imaging diagnostic doctors with over 10 years of working experience. Observed the lesion location, shape, size, density/signal characteristics of the solid part, signal intensity, restricted diffusion and MRS Manifestations, intratumoral calcification, hemorrhage and necrosis/cystic changes, enhancement features, whether there are blood vessels passing through the tumor, peritumoral edema, adjacent and secondary changes of the tumor, whether there is distant metastasis, and the metastatic site, etc. Results CT examinations were conducted in 10 cases. The brainstem lesions were mostly low/slightly low density shadows (9 cases), followed by equal or slightly high density shadows (1 case each). It is manifested as thickening of the brainstem, mostly centered on the pons, and partially involving the medulla oblongata, midbrain, cerebellar peduncle and cerebellar hemispheres. The thalamic lesion was a mass-like, uneven, slightly high-density shadow (1 case), extending towards the cisterns and the right side of the midbrain. MRI examination was conducted in 21 cases. The brainstem lesions were characterized by significant thickening and enlargement of the brainstem, with the pons being the most prominent. The main signal shadows were low on T1WI and slightly high on T2WI/FLAIR (15 cases). DWI could have diffuse limitation (9 cases), or no diffuse limitation (5 cases), and another case had no DWI examination. The lesions mostly surrounded the basilar artery (14 cases). Thalamic lesions were manifested as an increase in thalamic volume (6 cases), mainly low signal shadows on T1WI (5 cases), followed by isosignal shadows (1 case), and slightly high signal shadows on T2WI/FLAIR. DWI may have diffuse limitation (4 cases) or no limitation (2 cases). It partially affects the cerebellum, midbrain and other parts downward. After enhancement, most cases presented with obvious nodular, flower-shaped and patchy enhancement (13 cases), and could also show mild heterogeneous enhancement and no obvious enhancement (3 cases each). Additionally, 2 cases had no MRI enhancement examination. Nine cases underwent MRS Examination. The main manifestations were elevated Cho and Cr peaks, decreased NAA peak, and elevated Cho+Cr/NAA. Conclusion Although the imaging manifestations of DMG-A in children are varied, they still have certain characteristics. A comprehensive analysis of the age of occurrence, location of onset, whether the diffusion is limited, and the way and extent of intensification is helpful to improve the imaging diagnosis and differential diagnosis of the disease.

Pulmonary thromboembolism is an umbrella term for a group of diseases or clinical syndromes caused by thrombus blockage of the pulmonary artery and its branches, which can lead to circulatory instability or sudden death without timely treatment, with a mortality rate as high as 30%. Energy-spectrum CT can make qualitative and quantitative judgment on tissues through its attenuation characteristics under different X-ray energies, and through post-processing technology, it can generate images such as base matter map, single-energy image, effective atomic number, and energy-spectrum curve at one time, which overcomes the limitations of traditional CT in characterizing tissues and allows for a more comprehensive analysis of the disease. In recent years, energy spectrum CT has been widely used in the diagnosis and risk stratification assessment of pulmonary embolism disease. Its multiparameter quantitative analysis has shown significant advantages in improving the accuracy of PE diagnosis and optimizing image quality. The purpose of this paper is to review the imaging principle of energy spectrum CT and its application value in pulmonary embolism disease.