[Automatic identification algorithm of meniscus tear based on radiomics of knee MRI].

To establish a classification model based on knee MRI radiomics, realize automatic identification of meniscus tear, and provide reference for accurate diagnosis of meniscus injury.A total of 228 patients (246 knees) with meniscus injury who were admitted between July 2018 and March 2021 were selected as the research objects. There were 146 males and 82 females; the age ranged from 9 to 76 years, with a median age of 53 years. There were 210 cases of meniscus injury in one knee and 18 cases in both knees. All the patients were confirmed by arthroscopy, among which 117 knees with meniscus tear and 129 knees with meniscus non-tear injury. The proton density weighted-spectral attenuated inversion recovery (PDW-SPAIR) sequence images of sagittal MRI were collected, and two doctors performed radiomics studies. The 246 knees were randomly divided into training group and testing group according to the ratio of 7∶3. First, ITK-SNAP3.6.0 software was used to extract the region of interest (ROI) of the meniscus and radiomic features. After retaining the radiomic features with intraclass correlation coefficient (ICC)>0.8, the max-relevance and min-redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) were used for filtering the features to establish an automatic identification model of meniscus tear. The receiver operator characteristic curve (ROC) and the corresponding area under the ROC curve (AUC) was obtained; the model performance was comprehensively evaluated by calculating the accuracy, sensitivity, and specificity.A total of 1 316-dimensional radiomic features were extracted from the meniscus ROI, and the ICC within the group and ICC between the groups of the 981-dimensional radiomic features were both greater than 0.80. The redundant information in the 981-dimensional radiomic features was eliminated by mRMR, and the 20-dimensional radiomic features were retained. The optimal feature subset was further selected by LASSO, and 8-dimensional radiomic features were selected. The average ICC within the group and the average ICC between the groups were 0.942 and 0.920, respectively. The AUC of the training group was 0.889±0.036 [95% CI (0.845, 0.942), P<0.001], and the accuracy, sensitivity, and specificity were 0.873, 0.869, and 0.842, respectively; the AUC of the testing group was 0.876±0.036 [95% CI (0.875, 0.984), P<0.001], and the accuracy, sensitivity, and specificity were 0.862, 0.851, and 0.845, respectively.The model established by the radiomics method has good automatic identification performance of meniscus tear.基于膝关节MRI影像组学建立鉴别模型，以实现半月板撕裂自动鉴别，为精确诊断半月板损伤提供参考。.以2018年7月—2021年3月收治的228例（246膝）半月板损伤患者为研究对象。男146例，女82例；年龄9～76岁，中位年龄53岁。其中，单膝210例，双膝18例。患者均经关节镜检查明确诊断，其中撕裂半月板117膝、非撕裂半月板129膝。收集患者MRI矢状位质子密度加权频率衰减翻转恢复（proton density weighted-spectral attenuated inversion recovery，PDW-SPAIR）序列，由2名医生进行影像组学研究。将246膝按照7∶3比例随机分成训练组及测试组。首先，使用ITK-SNAP3.6.0软件提取半月板感兴趣区域（region of interest，ROI），进行影像组学特征提取。保留组内和组间相关系数（intraclass correlation coefficient，ICC）>0.8的特征后，使用最大相关-最小冗余（max-relevance and min-redundancy，mRMR）和套索算法（least absolute shrinkage and selection operator，LASSO）进行筛选，建立半月板撕裂自动鉴别模型，绘制受试者工作特征曲线（receiver operator characteristic curve，ROC），并获取相对应曲线下面积（area under ROC curve，AUC）；通过计算准确率、灵敏度、特异度对模型性能进行综合评估。.基于MRI矢状位PDW-SPAIR序列，于半月板ROI共提取1 316维影像组学特征，其中981维组内和组间ICC>0.80。通过mRMR将981维影像组学特征中的冗余信息进行消除，保留20维。进一步通过LASSO选择最优特征子集、确定选用8维最显著影像组学特征，平均组内、组间ICC分别为0.942、0.920。训练组AUC为0.889±0.036 ［95% CI（0.845，0.942）， P<0.001］，准确率、灵敏度、特异度分别为0.873、0.869、0.842；测试组AUC为0.876±0.036 ［95% CI（0.875，0.984）， P<0.001］，准确率、敏感度、特异度分别为0.862、0.851、0.845。.采用影像组学方法建立的鉴别模型具有良好的半月板撕裂自动鉴别性能。.