计算机辅助检测人工智能可降低MRI评估髋关节异常时的阅片者间差异。
Computer-Aided Detection AI Reduces Interreader Variability in Grading Hip Abnormalities With MRI.
作者信息
Tibrewala Radhika, Ozhinsky Eugene, Shah Rutwik, Flament Io, Crossley Kay, Srinivasan Ramya, Souza Richard, Link Thomas M, Pedoia Valentina, Majumdar Sharmila
机构信息
Department of Radiology and Biomedical Imaging, University of California, San Francisco, California, USA.
La Trobe Sport and Exercise Medicine Research Centre, College of Science, Health and Engineering, La Trobe University, Melbourne, Victoria, Australia.
出版信息
J Magn Reson Imaging. 2020 Oct;52(4):1163-1172. doi: 10.1002/jmri.27164. Epub 2020 Apr 15.
BACKGROUND
Accurate interpretation of hip MRI is time-intensive and difficult, prone to inter- and intrareviewer variability, and lacks a universally accepted grading scale to evaluate morphological abnormalities.
PURPOSE
To 1) develop and evaluate a deep-learning-based model for binary classification of hip osteoarthritis (OA) morphological abnormalities on MR images, and 2) develop an artificial intelligence (AI)-based assist tool to find if using the model predictions improves interreader agreement in hip grading.
STUDY TYPE
Retrospective study aimed to evaluate a technical development.
POPULATION
A total of 764 MRI volumes (364 patients) obtained from two studies (242 patients from LASEM [FORCe] and 122 patients from UCSF), split into a 65-25-10% train, validation, test set for network training.
FIELD STRENGTH/SEQUENCE: 3T MRI, 2D T FSE, PD SPAIR.
ASSESSMENT
Automatic binary classification of cartilage lesions, bone marrow edema-like lesions, and subchondral cyst-like lesions using the MRNet, interreader agreement before and after using network predictions.
STATISTICAL TESTS
Receiver operating characteristic (ROC) curve, area under curve (AUC), specificity and sensitivity, and balanced accuracy.
RESULTS
For cartilage lesions, bone marrow edema-like lesions and subchondral cyst-like lesions the AUCs were: 0.80 (95% confidence interval [CI] 0.65, 0.95), 0.84 (95% CI 0.67, 1.00), and 0.77 (95% CI 0.66, 0.85), respectively. The sensitivity and specificity of the radiologist for binary classification were: 0.79 (95% CI 0.65, 0.93) and 0.80 (95% CI 0.59, 1.02), 0.40 (95% CI -0.02, 0.83) and 0.72 (95% CI 0.59, 0.86), 0.75 (95% CI 0.45, 1.05) and 0.88 (95% CI 0.77, 0.98). The interreader balanced accuracy increased from 53%, 71% and 56% to 60%, 73% and 68% after using the network predictions and saliency maps.
DATA CONCLUSION
We have shown that a deep-learning approach achieved high performance in clinical classification tasks on hip MR images, and that using the predictions from the deep-learning model improved the interreader agreement in all pathologies.
LEVEL OF EVIDENCE
3 TECHNICAL EFFICACY STAGE: 1 J. Magn. Reson. Imaging 2020;52:1163-1172.
背景
准确解读髋关节磁共振成像（MRI）耗时且困难，容易出现不同阅片者之间以及同一阅片者不同时间的差异，并且缺乏一个普遍接受的分级量表来评估形态学异常。
目的
1）开发并评估一种基于深度学习的模型，用于对髋关节骨关节炎（OA）MRI图像上的形态学异常进行二元分类；2）开发一种基于人工智能（AI）的辅助工具，以确定使用模型预测是否能提高髋关节分级中阅片者之间的一致性。
研究类型
旨在评估技术开发的回顾性研究。
研究对象
从两项研究中获取的总共764个MRI容积数据（364例患者）（来自洛杉矶西奈医学中心[FORCE]的242例患者和来自加州大学旧金山分校的122例患者），分为65 - 25 - 10%的训练集、验证集和测试集用于网络训练。
场强/序列：3T MRI，二维快速自旋回波（T FSE），质子密度加权脂肪抑制（PD SPAIR）。
评估
使用MRNet对软骨损伤、骨髓水肿样损伤和软骨下囊肿样损伤进行自动二元分类，使用网络预测前后阅片者之间的一致性。
统计检验
受试者操作特征（ROC）曲线、曲线下面积（AUC）、特异性和敏感性以及平衡准确性。
结果
对于软骨损伤、骨髓水肿样损伤和软骨下囊肿样损伤，AUC分别为：0.80（95%置信区间[CI] 0.65，0.95）、0.84（95% CI 0.67，1.00）和0.77（95% CI 0.66，0.85）。放射科医生进行二元分类的敏感性和特异性分别为：0.79（95% CI 0.65，0.93）和0.80（95% CI 0.59，1.02），0.40（95% CI -0.02，0.83）和0.72（95% CI 0.59，0.86），0.75（95% CI 0.45，1.05）和0.88（95% CI 0.77，0.98）。使用网络预测和显著性图后，阅片者之间的平衡准确性从53%、71%和56%分别提高到60%、73%和68%。
数据结论
我们已经表明，深度学习方法在髋关节MRI图像的临床分类任务中取得了高性能，并且使用深度学习模型的预测提高了所有病变中阅片者之间的一致性。
证据水平
3 技术效能阶段：1 《磁共振成像杂志》2020；52：1163 - 1172。
Zotero 插件