南方医科大学学报

南方医科大学学报 ›› 2025, Vol. 45 ›› Issue (11): 2518-2526.doi: 10.12122/j.issn.1673-4254.2025.11.25

• • 上一篇    

人工智能辅助压缩感知加速技术对鼻咽癌MRI影像组学特征提取及分期诊断模型性能的影响

李欣洋1(), 许桂晓4,5,6,7, 刘洁宏1, 冯衍秋1,2,3()   

  1. 1.南方医科大学生物医学工程学院
    2.广东省医学图像处理重点实验室
    3.广东省医学影像诊断技术工程实验室，广东 广州 510515
    4.华南恶性肿瘤防治全国重点实验室
    5.广东省鼻咽癌诊治研究重点实验室
    6.广东省恶性肿瘤临床医学研究中心
    7.中山大学肿瘤防治中心影像科，广东 广州 510060
  • 收稿日期:2025-09-01 出版日期:2025-11-20 发布日期:2025-11-28
  • 通讯作者: 冯衍秋 E-mail:lixinyang91@163.com;foree@smu.edu.cn
  • 作者简介:李欣洋，在读硕士研究生，E-mail: lixinyang91@163.com
  • 基金资助:
    国家自然科学基金(U21A6005);国家自然科学基金(82372079)

Effect of AI-assisted compressed sensing acceleration on MRI radiomic feature extraction and staging model performance for nasopharyngeal carcinoma

Xinyang LI1(), Guixiao XU4,5,6,7, Jiehong LIU1, Yanqiu FENG1,2,3()   

  1. 1.School of Biomedical Engineering, Southern Medical University,
    2.Guangdong Provincial Key Laboratory of Medical Image Processing,
    3.Guangdong Provincial Engineering Laboratory for Medical Imaging and Diagnostic Technology, Guangzhou 510515, China
    4.State Key Laboratory of Oncology in South China,
    5.Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy,
    6.Guangdong Provincial Clinical Research Center for Cancer,
    7.Department of Radiology, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
  • Received:2025-09-01 Online:2025-11-20 Published:2025-11-28
  • Contact: Yanqiu FENG E-mail:lixinyang91@163.com;foree@smu.edu.cn
  • Supported by:
    National Natural Science Foundation of China(U21A6005)

RichHTML

1

PDF

32

摘要：

目的 评估人工智能辅助压缩感知（ACS）加速技术与传统磁共振并行成像（PI）加速技术相比，对鼻咽癌MRI影像组学特征提取及分期诊断模型性能的影响。 方法 纳入64例经3.0T MR扫描的初诊鼻咽癌患者。在关键成像参数保持一致的情况下，分别采用PI和ACS加速序列采集平扫T1加权、T2加权及增强T1加权图像。ACS组3种序列总扫描时间为227 s，较PI组（312 s）缩短约30%。使用开源工具Pyradiomics提取18个一阶特征和75个纹理特征，利用组内相关系数（ICC）评估ACS与PI图像组学特征的一致性。基于两组图像特征，分别采用最小绝对收缩与选择算子进行特征选择，并构建随机森林模型以区分鼻咽癌早期（T1-T2）与晚期（T3-T4）。通过受试者工作特征曲线下面积（AUC）评估模型的诊断性能，并使用DeLong检验比较两组模型性能的差异。 结果 ACS与PI图像提取的组学特征总体一致性较高，86.0%（240/279）的特征ICC值大于0.75。其中平扫T1加权、T2加权及增强T1加权图像平均ICC值分别为0.91±0.09、0.89±0.13和0.88±0.11。在鼻咽癌分期预测方面，基于ACS与PI图像特征所构建模型的AUC分别为0.89和0.90，DeLong检验显示两组模型性能差异无统计学意义（P=0.991）。 结论 ACS与PI加速序列所获图像在提取组学特征上具有较高的一致性，基于ACS图像构建的鼻咽癌分期预测模型与基于PI图像的模型在诊断效能上表现相当。ACS加速可显著缩短扫描时间，为鼻咽癌影像组学研究提供了一种可靠的磁共振高效加速采集方案。

关键词: 人工智能, 磁共振成像, 影像组学, 一致性, 鼻咽癌

Abstract:

Objective To evaluate the effect of artificial intelligence-assisted compressed sensing (ACS) acceleration on MRI radiomic feature extraction and performance of diagnostic staging models for nasopharyngeal carcinoma (NPC) in comparison with conventional parallel imaging (PI). Methods A total of 64 patients with newly diagnosed NPC underwent 3.0T MRI using axial T1-weighted (T1W), T2-weighted (T2W), and contrast-enhanced T1-weighted (CE-T1W) sequences. Both PI and ACS protocols were performed using identical imaging parameters. The total scan time for the 3 sequences in ACS group was 227 s, representing a 30% reduction from 312 s in the PI group. Eighteen first-order and 75 texture features were extracted using Pyradiomics. Intraclass correlation coefficients (ICCs) were calculated to assess the agreement between the two acceleration methods. After feature selection using the least absolute shrinkage and selection operator (LASSO), random forest regression models were constructed to distinguish early-stage (T1 and T2) from advanced-stage (T3 and T4) NPC. The diagnostic performance of the models was evaluated using the area under the receiver operating characteristic curve (AUC) and compared using the DeLong test. Results ACS-accelerated images demonstrated good radiomic reproducibility, with 86.0% (240/279) of features showing good agreement (ICC>0.75), with mean ICCs for T1W, T2W and CE-T1W sequences of 0.91±0.09, 0.89±0.13 and 0.88±0.11, respectively. The staging prediction models achieved similar AUCs for ACS and PI (0.89 vs 0.90, P=0.991). Conclusion The MRI radiomic features extracted using ACS and PI techniques are highly consistent, and the ACS-based model shows comparable diagnostic performance to the PI-based model, but ACS significantly reduces the scan time and provides an efficient and reliable acceleration strategy for radiomics in NPC.

Key words: artificial intelligence, magnetic resonance imaging, radiomics, agreement, nasopharyngeal carcinoma