Objective To construct metabolic brain networks in patients with diffuse large B-cell lymphoma (DLBCL) before and after chemotherapy using ¹⁸F-FDG PET imaging, and investigate the effect of the disease and R-CHOP chemotherapy regimen on brain function by analyzing differences in hub nodes and modularity. Methods A total of 51 DLBCL patients who underwent whole-body ¹⁸F-FDG PET scans before and after chemotherapy at the Nuclear Medicine Department of the Second Hospital of Lanzhou University from June 2021 to July 2024 were included retrospectively, along with 30 age- and sex-matched healthy controls. Inter-regional brain correlations were calculated using the Pearson correlation coefficient to construct the metabolic brain network. Graph theory-based analysis and 1000 permutation tests were subsequently employed to compare the differences in global metrics, Hub nodes, and modularity between DLBCL patients and healthy controls. Results Within the sparsity range of 0.1 to 0.5, DLBCL patients exhibited significant differences in the number and distribution of Hub nodes compared to healthy controls (P<0.05), while maintaining small-world properties (Sigma>1.1). Regarding modularity, alterations in node module assignments were noted in the metabolic brain networks of DLBCL patients at baseline, and the modular structure underwent significant reorganization following chemotherapy. Nevertheless, no significant difference in modularity (Q value) was found when compared to the control group (P>0.05). Conclusion The disease, coupled with R-CHOP chemotherapy regimen, disrupts Hub nodes and modularity of metabolic brain network in DLBCL patients, affecting brain function.

Objective To establish a qualitative diagnostic nomogram for cervical lymph nodes (CLNs) based on ultrasonographic characteristics. Methods A retrospective study was conducted on 2,697 patients who underwent fine needle aspiration of CLNs at West China Hospital of Sichuan University from January 2020 to December 2023. The analysis encompassed a total of 3014 enlarged CLNs, which were categorised into 1489 benign and 1525 malignant cases based on pathological findings. Clinicopathplogical information, B-mode ultrasound images, and color Doppler ultrasound images were systematically collected. Two experienced radiologists independently reviewed the imaging features of the lymph nodes. The patients were randomly assigned to a training cohort and a validation cohort at a ratio of 7:3. In the validation cohort, univariate analysis and multivariate logistic regression analysis were performed to identify candidate features associated with benign or malignant CLN. The construction of the nomogram model was facilitated by the identified candidate features. ROC curves were plotted in both the training and validation sets to evaluate diagnostic performance by calculating sensitivity, specificity, and accuracy. Calibration curves were utilised to evaluate the concordance between predicted probabilities and observed outcomes, while clinical decision curve analysis was employed to assess the clinical utility of the model. Results Based on univariate and multivariate analysis, ten features were integrated into the nomogram model ultimately. This model exhibited an AUC of 0.942 in the training cohort and 0.925 in the validation cohort, significantly exceeding the performance of conventional ultrasound qualitative diagnosis (AUC=0.656, P<0.001). The ultrasound features incorporated into the model included the long-axis diameter, short-axis diameter, long-to-short axis ratio, cortical echogenicity pattern, cortical homogeneity, corticomedullary demarcation, hilum visualization, margin, shape, and calcification. Conclusion The ultrasonography-based nomogram demonstrates superior diagnostic performance in the qualitative assessment of CLN compared to conventional ultrasonographic diagnostic methods, thereby offering valuable guidance for formulating subsequent clinical management strategies in patients presenting with cervical lymphadenopathy.

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.

Objective To explore the application value of low-dose expiratory phase scanning scheme in dual-gas phase quantitative CT diagnosis of chronic obstructive pulmonary disease (COPD) and qantitative analysis by reducing the radiation dose of expiratory phase during dual-gas phase scanning. Methods Sixty-seven patients with COPD confirmed by clinical pulmonary function tests at Affiliated Hospital of Shaanxi University of Chinese Medicine from October 2023 to March 2024 were prospectively included. The first expiratory and inspiratory phase scans were performed with a standard radiation dose (NI=14) and the second expiratory phase was scanned with a low radiation dose (NI=28). Both CT examinations used 60% ASIR. The CT value and the SD value of adipose tissue, muscle tissue and aorta were measured, and signal noise ratio were calculated. The thin-slice reconstruction images from the standard-dose group and the low-dose group were imported into the "Digital Lung" data analysis platform for dual-phase matching, and quantitative parameters were measured (lung volume, emphysema volume, Emph%, functional-small airways volume, fSAD%, LAA-910%, LAA-950%). The radiation dose, quantitative CT parameters and image subjective score were compared between low-dose group and standard-dose group. Results The radiation dose of the expiratory low-dose group was lower than that of standard-dose group (P<0.05). There was no significant difference in the two-gas phase registration parameters between the low-dose group and the standard-dose groups (P>0.05). The SD value in the expiratory phase of the low-dose group was greater than that in the standard-dose group (P<0.05). There was no significant difference in the ratings between the two groups (P>0.05). Conclusion The use of a low-dose scanning protocol for expiratory-phase scanning in the quantitative evaluation of COPD patients by dual-phase scanning ensures that the quantitative CT evaluation results are consistent with the standard-dose, meeting the needs of the evaluation while significantly reducing the radiation dose received by the patient.

Objective To compare the value of high-frequency ultrasound and MRI in the diagnosis of anterior talofibular ligament (ATFL) injury and early detection of chronic ankle instability (CAI). Methods Eighty patients with unilateral ankle injuries who receive treatment at Gansu Provincial People's Hospital from January 2020 to August 2024 were selected. All patients underwent both high-frequency ultrasound and MRI, with injury severity classified into three grades. The thickness and length of the ATFL, as well as the angle of the talofibular joint space, were measured and compared between the healthy and affected sides. Surgical outcomes were used as the gold standard, and ROC curves for ATFL injury diagnosis by both high-frequency ultrasound and MRI were plotted to evaluate diagnostic efficacy. Results Among the 80 patients, high-frequency ultrasound detected 13 cases of grade I, 39 cases of grade II, and 28 cases of grade III injuries, while MRI detected 24 cases of grade I, 42 cases of grade II, and 14 cases of grade III. The detection rate of grade I injury by high-frequency ultrasound was significantly lower than MRI, with grade II detection slightly lower and grade III detection significantly higher than MRI (P<0.001). Conclusion The thickness of the affected ATFL was positively correlated with injury grade. The angle of the affected ATFL relative to the talofibular joint space and its length were positively correlated with the diagnostic concordance rate for chronic ankle instability. Combining multiple ultrasonographic parameters proved more valuable for diagnosing chronic ankle instability, providing an objective basis for surgical repair of ligament injuries.

Objective To explore the clinical reference value of a nomogram prediction model based on multimodal ultrasound features in predicting high Ki-67 expression in patients with invasive ductal carcinoma (IDC) of the breast. Methods Multimodal ultrasound imaging features and Ki-67 expression levels were collected from 180 patients with pathologically confirmed IDC who underwent surgery in our hospital from January 2020 to August 2024. Patients were divided into a high Ki-67 expression group (n=130) and a low Ki-67 expression group (n=50) based on a Ki-67 positivity rate of ≥20%. Multimodal ultrasound parameters and clinical characteristics were compared between the two groups. Significant variables were screened through univariate analysis, and multivariate Logistic regression was further conducted to explore independent influencing factors. The final variables were selected through LASSO and stepwise regression methods, and a nomogram prediction model was constructed. Results The results of univariate and multivariate Logistic regression showed that the maximum diameter of the mass (OR=1.068, 95% CI: 1.022-1.115, P=0.003), microcalcification (OR=9.960, 95% CI: 4.183-23.715, P<0.001), virtual touch tissue imaging (VTI) (OR=7.937, 95% CI: 1.949-32.258, P=0.004), and the moth-eaten sign (OR=28.571, 95% CI: 4.808-166.667, P<0.001) were independent risk factors for high Ki-67 expression. A nomogram prediction model for high Ki-67 expression was established using variables such as the maximum diameter of the mass, microcalcification, VTI score≥4, and the moth-eaten sign. The results showed that the C-index of this model was 0.852. Internal validation through Bootstrap resampling suggested high consistency of the model, and clinical decision curve analysis indicated that the model had significant clinical net benefit. Conclusion Maximum tumor diameter, microcalcifications, VTI score≥4, and moth-eaten sign are independent factors influencing high Ki-67 expression in IDC patients. The nomogram prediction model for high Ki-67 expression, constructed based on these factors, demonstrates good predictive performance and provides a reference for clinical decision-making in IDC patients, potentially contributing to improved prognosis.

Objective To propose a diagnosis method for pneumonia infection based on improved Boosting integration model. Methods A total of 315 patients with pneumonia infection who were examined by CT in Shaanxi Provincial People's Hospital from September 2023 to May 2024 were selected, and CT diagnosis was carried out for all patients. In the preprocessing stage of CT images, image enhancement technology was applied to improve the image quality and ensure that the model acquired clearer image information during feature extraction. In the feature extraction process, texture features, shape features and pixel intensity information are extracted through the XGBoost framework, and the principal component analysis is used to reduce the feature dimensions. In addition, the sample imbalance problem is solved by introducing a focus loss function to ensure that the model has a more balanced focus on benign and malignant samples. Meanwhile, Bayesian optimisation is used in the hyperparameter optimisation process to construct a Gaussian process regression model to adjust the hyperparameters, thus ensuring that the optimal parameter combinations are selected to further improve the prediction accuracy of the model. Results The diagnostic method proposed in this study has a mean area under the curve (mAUC) value of 0.9649 and an F1 score of 0.9423 in the test set, which significantly outperforms the comparative models such as lightweight gradient booster, random forest, and K-nearest neighbour. Conclusion The diagnostic method proposed in this study provides an effective tool to improve the identification and early intervention of pneumonia infections, helping physicians to identify high-risk patients earlier and develop personalised treatment plans.

Objective To explore the clinical value of MRI in identifying high-risk factors for placenta accreta and postpartum hemorrhage in patients with complete placenta previa. Methods A total of 50 patients with complete placenta previa admitted to the First Affiliated Hospital of Bengbu Medical University from November 2020 to October 2024 were selected as the study subjects. Based on pathological results, the patients were divided into a placenta accreta group (n=41) and a non-placenta accreta group (n=9). According to the occurrence of postpartum hemorrhage, the patients were further divided into a postpartum hemorrhage group (n=42) and a non-postpartum hemorrhage group (n=8). The relationship between MRI features and the occurrence of placenta accreta and postpartum hemorrhage in patients with complete placenta previa was analyzed. The Kappa consistency test was used to evaluate the diagnostic efficacy of prenatal MRI. Multivariate logistic regression analysis was performed to assess MRI features as independent risk factors for postpartum hemorrhage. Results Prenatal MRI findings showed good consistency with pathological results (Kappa=0.675). Comparisons between the placenta accreta group and the non-placenta accreta group, as well as between the postpartum hemorrhage group and the non-postpartum hemorrhage group, revealed statistically significant differences in six out of seven MRI features (P<0.05), except for the sign of thickened and irregular bladder wall. Multivariate logistic regression analysis indicated that the T2WI low-signal band and placental thickness in the lower uterine segment were independent risk factors for postpartum hemorrhage (P<0.05). Conclusion Prenatal MRI demonstrates high consistency with pathological results in diagnosing placenta accreta. The T2WI low-signal band and placental thickness in the lower uterine segment are independent risk factors for predicting postpartum hemorrhage, providing valuable predictive insights for clinical diagnosis and treatment.

Objective To compare the diagnostic value of ¹⁸F-FDG PET/CT versus conventional imaging methods in patients with postoperative peritoneal metastasis of ovarian cancer based on elevated CA125 levels. Methods This study retrospectively analyzed 87 postoperative patients diagnosed with ovarian cancer at the Affiliated Hospital of Xinjiang Medical University from January 2022 to December 2023. The diagnostic performance of four imaging modalities were investigated: ¹⁸F-FDG PET/CT, transabdominal ultrasound (TAUS), transvaginal ultrasound (TVUS), contrast-enhanced computed tomography (CECT) or MRI, in detecting peritoneal metastasis in patients with elevated postoperative CA125 levels exceeding 35 U/mL. The parameters compared include sensitivity, specificity, accuracy, positive predictive value, and negative predictive value for each diagnostic method in the context of postoperative peritoneal metastasis in ovarian cancer patients. Results The sensitivities of ¹⁸F-FDG PET/CT, TAUS, TVUS, CECT or MRI for diagnosing postoperative peritoneal metastasis in ovarian cancer patients were 96.67%, 37.70%, 56.67%, 79.37%, respectively; specificities were 85.19%, 88.46%, 92.59%, 54.17%, respectively; accuracies were 93.10%, 52.87%, 67.82%, 72.41%, respectively; positive predictive values were 93.54%, 88.46%, 94.44%, 81.97%, respectively; negative predictive values were 92.00%, 37.70%, 49.02%, 50.00%, respectively. Conclusion The accuracy of ¹⁸F-FDG PET/CT in diagnosing peritoneal metastasis or recurrence in patients with elevated CA125 levels following ovarian cancer surgery is high, enabling the early detection of peritoneal metastatic lesions.

Objective To investigate the qualitative and quantitative diagnostic value of dual-source CT dual-energy pulmonary perfusion imaging (DEPI) for acute pulmonary embolism (APE). Methods A retrospective analysis was conducted on the dual-source CT pulmonary angiogram (CTPA) and DEPI-based reconstructed lung perfusion blood volume (PBV) images of 96 patients with suspected APE treated at our hospital from January 2021 to April 2024. Using expert panel interpretations as the reference standard, the impact of two physicians independently analyzing CTPA images versus combining DEPI with CTPA analysis on thrombus detection, while also the diagnostic consistency between the two physicians were compared and evaluated. Quantitative analyses were performed to compare the differences in perfusion CT and iodine density between normal lung tissues and those with varying severities of peripheral pulmonary embolism. ROC curves were plotted to compare the diagnostic efficiency of quantitative parameters for peripheral APE, and the DeLong test was used to assess differences. Results The retrospective analysis of CTPA and reconstructed Lung PBV images identified more peripheral pulmonary emboli than that of CTPA alone, with statistically significant differences in the detection of subsegmental emboli and the total number of emboli (P<0.05). The mean perfusion CT and iodine density values of fully occluded pulmonary tissues at the segmental and subsegmental levels were lower than those of partially occluded pulmonary tissues; the values for partially and fully occluded pulmonary tissues were both lower than those for normal pulmonary tissues; these pairwise comparisons all exhibited statistically significant differences (P<0.01). The diagnostic consistency between the two physicians was good when analyzing CTPA alone and was excellent when correlations were made with PBV images (Kappa=0.671, 0.797). The ROC curve analysis of quantitative parameters showed that mean perfusion CT value and iodine density were two effective diagnostic indicators for APE. The diagnostic threshold for perfusion CT value was ≤40 HU, with an AUC of 0.953, sensitivity of 86.16%, specificity of 99.31%, and Youden index of 0.8547. The diagnostic threshold for iodine density was ≤1.7 mg/mL, with an AUC of 0.923, sensitivity of 83.74%, specificity of 98.62%, and Youden index of 0.8235. Conclusion The combined use of DEPI and CTPA can help detect more peripheral pulmonary arterial emboli. When DEPI is ordered, the mean perfusion CT and iodine density values of lung tissues can serve as effective diagnostic indicators for APE, with the mean perfusion CT value being more clinically significant in evaluating the condition.

Objective To investigate the clinical efficacy of modified minimally invasive lumbar interbody fusion (mis-TLIF) in the treatment of lumbar degenerative diseases. Methods A retrospective analysis was conducted on 39 patients with lumbar degenerative diseases treated with modified mis-TLIF surgery at the Department of Orthopedics, the Affiliated Guangzhou Hospital of TCM of Guangzhou University of Chinese Medicine from January 2021 to November 2022, including 15 males and 24 females, aged from 28-90(66.08±13.95) years old. 12 patients underwent modified mis-TLIF surgery, while 27 patients underwent modified mis-TLIF combined with ULBD surgery. Surgical time, intraoperative bleeding volume, and complications were recorded. Visual analog scale (VAS) scores for low back and leg pain, as well as Oswestry disability index (ODI), were collected before surgery, 1 week and 3 months after surgery, and at the final follow-up. The MacNab criteria were employed to evaluate the clinical efficacy at the final follow-up. Results All patients underwent surgery successfully and were followed up for 12-28(17.49±5.05) months. The operation time ranged from 76-190(106.67±33.01) min, and the intraoperative bleeding volume ranged from 110-447(225.38±87.90) mL. One case of dural matter tear occurred during the surgery, which was repaired with an absorbable dural patch without subsequent cerebrospinal fluid leakage. No nerve injuries were observed in all cases. Postoperatively, 37 cases achieved primary healing of wounds; 1 case developed superficial infection at the incision site, and the wound healed after receiving sensitive antibiotics and symptomatic debridement; Another case presented with a suture reaction at the incision, which resolved after symptomatic debridement alone; Deep infection did not occur in either case. No cardiovascular or cerebrovascular accidents occurred in any patient during or after surgery.The VAS scores for low back pain at preoperative, 1 week postoperative, 3 months postoperative, and the final follow-up were 8.27±0.76, 2.49±0.76, 1.46±0.64, 0.94±0.48, respectively. The VAS scores for leg pain were 8.69±0.68, 1.91±0.63, 1.16±0.54, 0.78±0.43, respectively. The ODI scores(%) were 81.98±10.07, 27.47±9.31, 18.98±7.37, 14.66±5.54, respectively. At all postoperative time points, there were statistically significant improvements in VAS scores for low back and leg pain, as well as ODI scores, compared to preoperative values (P<0.05). Pairwise comparisons of VAS scores for low back and leg pain between each postoperative time point also showed statistical significance (P<0.05). At the final follow-up, according to the MacNab criteria, 20 cases were excellent, 16 cases were good, 3 cases were acceptable, resulting in an excellent and good rate of 92.31%. Conclusion The modified mis-TLIF surgery for the treatment of lumbar degenerative diseases is a minimally invasive, safe and effective surgical method, but its long-term clinical efficacy still needs further follow-up observation.

Objective To explore the application value of SonoLiver contrast - enhanced quantitative analysis and dynamic vascular model (DVP) in the diagnosis of prostate lesions. Methods A total of 103 patients who visited our hospital and underwent prostate biopsy were selected. According to the pathological results, they were divided into prostate cancer group (n=56), benign prostatic hyperplasia group (n=22), and prostatitis group (n=25). The contrast-enhanced patterns (contrast-enhanced intensity, enhancement pattern, whether the enhancement was uniform, and wash-out time), contrast-enhanced parameters [maximum echo intensity ratio (Imax), time to peak (TTP), rise time (RT), 50% point of the rising slope (Rs50), 10%-90% point of the rising slope (Rs1090), fall time (FT), 50% point of the falling slope (Fs50), fall half time (FHT), mean transit time (mTT), area under the curve during the perfusion phase (WinAUC), perfusion rate (WinR), wash-out rate (WoutR)] and DVP curve waveforms were compared among the groups. Results When comparing the contrast-enhanced patterns between the benign prostatic hyperplasia group and the prostate malignancy group, the differences in contrast-enhanced intensity, enhancement pattern, and wash-out time were statistically significant (P<0.05), while the difference in whether the enhancement was uniform was not statistically significant (P>0.05). When comparing the contrast-enhanced parameters between the prostate cancer group and the prostatitis group, the difference in contrast-enhanced intensity was statistically significant (P<0.05), while the differences in enhancement pattern, whether the enhancement was uniform, and wash - out time were not statistically significant (P>0.05). When comparing the contrast-enhanced parameters between the prostate cancer group and the benign prostatic hyperplasia group, the differences in Imax, TTP, RT, Rs50, Rs1090, FT, Fs50, FHT, mTT, WinAUC, WinR, and WoutR were all statistically significant (P>0.05). When comparing the contrast-enhanced parameters between the prostate cancer group and the prostatitis group, the differences in Imax, TTP, RT, Rs50, Rs1090, Fs50, AUC, WinAUC, WinR, and WoutR were all statistically significant (P<0.05). When comparing the contrast-enhanced parameters between the prostatitis group and the benign prostatic hyperplasia group, the difference in TTP was statistically significant (P<0.05). In the prostate cancer group, the DVP curve waveforms were mainly positive waveforms accounting for 33.93% (19/56) and positive-negative bidirectional waveforms accounting for 57.14% (32/56). In the benign prostatic hyperplasia group, the negative-positive bidirectional waveforms accounted for 50.00% (11/22). In the prostatitis group, the negative waveforms accounted for 32% (8/25) and the negative-positive bidirectional waveforms accounted for 40% (10/25). The differences in DVP curve waveforms between the prostate cancer group and the other two groups were statistically significant (P<0.05). Conclusion SonoLiver contrast-enhanced quantitative analysis and dynamic vascular model have certain reference value in the diagnosis of prostate lesions.

Objective To explore the relationship between CT fat attenuation index (FAI) of pericoronary adipose tissue (PCAT) and coronary atherosclerosis, plaque properties. Methods A total of 138 patients undergoing coronary CT angiography (CTA) in the hospital from January 2022 to December 2024 were retrospectively analyzed. FAI value of PCAT in all patients was measured to analyze its relationship with coronary atherosclerosis and plaque properties. Results There were 206 lesions in all the 138 patients. FAI value of PCAT has certain relationship with coronary stenosis and plaque properties. FAI value in plaques with mild, moderate and severe coronary stenosis was greater than that with slight stenosis, and which was gradually decreased in non-calcification plaques, mixed plaques and calcification plaques (P<0.05). The results of multiple linear regression analysis showed that FAI value was positively correlated with plaque properties (P<0.05). Conclusion FAI value of PCAT has certain correlation with coronary atherosclerosis and plaque properties. Measuring FAI value around plaques with high risk of unstable inflammation is beneficial to clinically evaluate the risk of coronary heart disease.

Objective To explore the value of the automatic segmentation model of computed tomography angiography (CTA) based on ResUNet and PSPNet in helping to evaluate carotid atherosclerotic plaques. Methods This study retrospectively included 647 patients with carotid atherosclerotic plaque formation who underwent head and neck CTA examinations. They were randomly divided into training set (n=475), validation set (n=86) and test set (n=86) at a ratio of 7:1.5:1.5. The images marked by radiologists in the training set were used to develop the automatic segmentation model based on ResUNet and PSPNet. Parameters such as precision, sensitivity, and recall were used in the validation set and the test set to evaluate the diagnostic performance of the model for carotid plaques. Results In the training set, the automatic segmentation model had already demonstrated good performance in the segmentation of atherosclerotic plaques. Its practicability was further verified in the validation set and the test set. In addition, a subgroup analysis of different plaque types was conducted on the test set, and the results showed that the deep learning model based on CTA images demonstrated good plaque diagnostic accuracy for different plaque types. Conclusion The automatic segmentation model based on ResUNet and PSPNet has relatively high accuracy in assisting the diagnosis of carotid atherosclerotic plaques and is clinically feasible.

Objective To explore the diagnostic value of a radiomics model based on the intratumoral and peritumoral regions in contrast-enhanced CT for peritumoral tumor deposits (TDs) in colorectal cancer (CRC). Methods A retrospective analysis was conducted on contrast-enhanced CT images of 330 CRC patients, confirmed by surgical pathology, from our hospital and the TCIA database between January 2017 and September 2024. Based on postoperative pathology, patients were classified into TDs-positive and TDs-negative groups. Using random sampling, patients were split into a training set (n=231) and a testing set (n=99) in a 7:3 ratio. Regions of interest (ROI) were manually delineated layer by layer on contrast-enhanced venous-phase images to generate volume of interest. The peritumoral ROIs were expanded outward by 2, 4 and 6 mm. Radiomic features were extracted from each ROI using pyradiomics, and LASSO was employed for feature selection. XGBoost machine learning algorithm was used to construct separate prediction models for intratumoral, peritumoral, and combined intratumoral-peritumoral features. The diagnostic performance of each model was evaluated using ROC curves, and the DeLong test was used to compare the predictive performance of different models. Results The area under the ROC curve (AUC) for the intratumoral model was 0.937 in the training set and 0.828 in the testing set. Among the peritumoral models, the 4 mm peritumoral region exhibited the best diagnostic performance, achieving an AUC of 0.933 in the training set and 0.830 in the testing set. The combined intratumoral-peritumoral model demonstrated the highest predictive performance, with an AUC of 0.951 in the training set and 0.883 in the testing set. Decision curve analysis indicated that the combined model provided the highest net benefit for predicting TDs. Conclusion The radiomics model integrating intratumoral and peritumoral regions based on contrast-enhanced CT effectively predicts peritumoral TDs in CRC, offering the highest net benefit for TDs prediction. This model can assist clinicians in decision-making and outperforms traditional radiomics models based on either intratumoral or peritumoral features alone.

Objective An electromics model for habitat imaging was proposed to predict sentinel lymph node metastasis in early breast cancer. Methods The MRI characteristics of 176 patients in our hospital from August 2016 to November 2022 were collected pretreatment, and whether there was metastasis in the sentinel lymph nodes was confirmed by pathological biopsy. Multiple sequences of MRI of the breast tumor region pretreatment were used for habitat imaging in all patients. Results The stepwise multivariate analysis results indicated that the factors associated with sentinel lymph node metastasis include vascular invasion and spiculation (P<0.05). With K=3 as the optimal number of clusters, the region of interest was divided into three subregions for the extraction of radiomics features to construct a habitat model. The habitat prediction model outperformed the single-modality radiomics prediction model in both the training cohort (AUC=0.876, 95% CI: 0.815-0.938) and the validation cohort (AUC=0.824, 95% CI: 0.683-0.964). The clinical nomogram constructed by combining clinical risk factors with habitat radiomics demonstrated superior performance in the training cohort (AUC=0.920, 95% CI: 0.875-0.965) and the validation cohort (AUC=0.908, 95% CI: 0.810-1.000). Conclusion The radiomics-based habitat nomogram shows outstanding diagnostic effectiveness and has the potential to act as a valuable auxiliary tool for preoperative assessment of sentinel lymph node metastasis in patients with breast cancer.

Objective To investigate the value of multimodal ultrasound characteristics and quantitative measurement parameters in predicting the risk of cervical lymph node metastasis of thyroid papillary carcinoma (PTC). Methods Clinical data of 117 patients with PTC confirmed by surgery and pathology from October 2022 to October 2024 at Baoji People's Hospital were retrospectively analyzed. The quantitative parameters of E_mean and ER of SWE, SE_mean and SR of SE, and the ascending slope, peak intensity (PKI), rising time (RT), peak time (TTP), mTIC and area under time intensity curve (TIC-AUC) of CEUS were analyzed. The postoperative pathological results were divided into two groups (non-metastatic group and metastatic group) to compare the diagnostic value of each quantitative parameter between the two groups.Univariate and multivariate binary Logistic regression analysis was used to compare the risk factors of cervical lymph node metastasis between the two groups. Results In the cervical lymph node metastasis group, the proportion of male, fuzzy nodule edge, small intracodular calcification and nodular invasion capsule was higher than that in the non-metastatic group, with statistical significance (P<0.05). Among the quantitative parameters of multimodal ultrasound in the two groups, the strain elastic imaging strain ratio SR in the non-metastasis group was significantly different from the quantitative parameters of CEUS PKI and TIC-AUC in the metastasis group (P<0.05).When the optimal threshold value SR≤2.77, PKI≤14.00dB, TIC-AUC≤1668.09 dB·s, the risk of cervical lymph node metastasis was greater.Multivariate binary Logistic regression analysis of the two groups of patients showed that males, intra nodular fine calcification, nodular invasion capsule and CEUS parameters PKI, TIC-AUC were independent risk factors for cervical lymph node metastasis of PTC (P<0.05). Conclusion Male, intratodular fine calcification, nodular invasion capsule and CEUS parameters PKI≤14.00 dB and TIC-AUC≤1668.09 dB·s have certain value in predicting the risk of cervical lymph node metastasis of PTC, and can provide certain reference for clinical decision-making.

Objective To explore the diagnostic efficacy of a machine learning model based on clinically-ultrasound radiomics in preoperatively differentiating combined hepatocellular-cholangiocarcinoma (cHCC-CC) from hepatocellular carcinoma (HCC). Methods A retrospective analysis was conducted on 42 patients with pathologically confirmed cHCC-CC in Xuzhou Central Hospital from January 2010 to October 2024. The control group consisted of 84 patients with pathologically confirmed HCC during the same period, selected using propensity score matching at a 1:2 ratio. Radiomic features were extracted from both the tumor and peritumoral regions, and the Rad-score was calculated. Independent risk factors associated with cHCC-CC were identified through univariate and multivariate logistic regression analyses. Three machine learning algorithms, including support vector machine (SVM), random forest (RF), and logistic regression (LR), were employed to develop predictive models. The model with the highest AUC value was selected as the optimal model. Patients were randomly divided into a training set (n=89) and a testing set (n=37) in a 7:3 ratio, and the performance of the best model was validated using the 10-fold cross-validation method. Results Tumor shape, cirrhosis, CA19-9 levels, Rad-score_tumor, and Rad-score_{10 mm} were identified as independent factors for differentiating the two tumor types. Among the three machine learning models, the LR model demonstrated the best performance, achieving an AUC of 0.883(95%CI: 0.826-0.951). The LR model achieved AUCs of 0.888(95%CI: 0.805-0.971), 0.841(95%CI: 0.633-0.994), and 0.893(95%CI: 0.793-0.992) on the training, validation, and test sets, respectively. The calibration curve indicated good consistency, and the decision curve analysis revealed a high net benefit. Conclusion The LR model based on clinically-ultrasound radiomics demonstrates significant preoperative diagnostic value in differentiating cHCC-CC from HCC, contributing to precise clinical diagnosis and treatment.

Vascular dementia (VaD) is the second most common type of dementia, characterized primarily by impairments in attention, information processing, and executive function. Accurate differential diagnosis and early intervention remain challenging. MRI with its non-invasive and reproducible features, plays a crucial role in the diagnosis and monitoring of VaD. Structural MRI can identify white matter hyperintensities, gray matter atrophy, ventricular enlargement, and perivascular space changes. Resting-state functional MRI reveals alterations in local brain activity and functional connectivity in VaD patients. Diffusion tensor imaging quantitatively assesses white matter tract abnormalities, while arterial spin labeling enables non-invasive measurement of cerebral perfusion. Additionally, magnetic resonance spectroscopy detects concentrations of brain metabolites. The integration of multimodal MRI analyses further enhances the diagnostic and monitoring potential of MRI for VaD. This review summarizes recent advancements in multimodal MRI applications for the diagnosis of VaD, providing new strategies for early diagnosis, differential diagnosis, disease monitoring, and intervention.

With the rapid development of artificial intelligence and machine learning technology, medical imaging equipment is undergoing unprecedented changes. Intelligence and digitization have become key factors in promoting the advancement of medical imaging technology. This article reviews the research progress of magnetic resonance imaging systems in the field of intelligence and digitalization, and explores their potential in improving diagnostic accuracy, optimizing workflow, and enhancing patient experience. The purpose of this review is to analyze the current technological advancements in order to provide insights for future innovative applications of MRI technology. This aims to drive technological innovation in the field of medical imaging,enhance the quality and efficiency of medical services,and ultimately improve patients'diagnostic experience and health outcomes.