特征可视化浅表食管鳞状细胞癌浸润深度预测系统的构建及验证

Development and validation of a feature visualization prediction system for invasion depth of superficial esophageal squamous cell carcinoma

摘要:

目的 构建一个基于深度学习的窄带光成像放大内镜（magnifying endoscopy with narrow band imaging，ME‑NBI）下浅表食管鳞状细胞癌（superficial esophageal squamous cell carcinoma，SESCC）特征可视化系统，并评估ME‑NBI下该系统预测SESCC浸润深度的诊断效能。方法 特征可视化系统由4个模型构成，模型1、2分别用于分割SESCC病灶ME‑NBI图像中的上皮乳头内毛细血管袢（intrapapillary capillary loops，IPCL）区域和乏血管区（avascular area，AVA），模型3用于获取SESCC病灶ME‑NBI图像中的颜色主成分（principal component of color，PCC），模型4根据前三个模型提取到的特征自动预测SESCC浸润深度。2016年4月至2021年10月间的2 341张SESCC病灶的ME‑NBI图像用来开发特征可视化系统，分成3个数据集：数据集1（1 077张ME‑NBI图像），用于训练和测试模型1～3；数据集2（1 069张ME‑NBI图像），利用特征组合的方式将数据量扩充20倍，获得21 380张特征合成图像，然后用于训练和测试模型4；数据集3（195张ME‑NBI图像），其中病变浸润深度在上皮层至黏膜下层上1/3（EP-SM1）的ME‑NBI图像146张，在黏膜下层中1/3至下1/3（SM2-SM3）的ME‑NBI图像49张，用于验证特征可视化系统预测SESCC浸润深度（EP-SM1/SM2-SM3）的诊断效能。为了评估特征可视化系统的优越性，将传统深度学习系统（直接使用ME‑NBI图像进行训练）、单项特征模型（单项IPCL特征模型、单项AVA特征模型和单项PCC特征模型）的数据集3预测结果与特征可视化系统预测结果进行对比。为了评估特征可视化系统的临床实用性，邀请4名专家医师（内镜操作超过10年，专家医师组）和5名高年资医师（内镜操作超过5年，高年资医师组）参与人机大赛，对数据集3进行诊断，结果与特征可视化系统进行比较。结果 诊断SESCC浸润深度（EP-SM1/SM2-SM3）的准确率、敏感度和特异度方面，特征可视化系统分别为83.08%（162/195）、82.88%（121/146）和83.67%（41/49），传统深度学习系统分别为60.00%（117/195）、52.05%（76/146）和83.67%（41/49），单项IPCL特征模型分别为74.87%（146/195）、75.34%（110/146）和73.47%（36/49），单项AVA特征模型分别为58.97%（115/195）、60.27%（88/146）和55.10%（27/49），单项PCC特征模型分别为71.28%（139/195）、71.23%（104/146）和71.43%（35/49），高年资医师组分别为66.67%、78.22%和32.24%，专家医师组分别为72.31%、85.96%和31.63%。特征可视化系统诊断准确率明显高于其他6组（P<0.05）；特征可视化系统诊断敏感度略高于高年资医师组（χ2=1.59，P=0.21）和单项IPCL特征模型（χ2=2.51，P=0.11），略低于专家医师组（χ2=0.89，P=0.35），明显高于其他3组（P<0.05）；特征可视化系统诊断特异度与传统深度学习系统相同（χ2=0.00，P=1.00），略高于单项IPCL特征模型（χ2=1.52，P=0.22）和单项PCC特征模型（χ2=2.11，P=0.15），明显高于单项AVA特征模型（χ2=9.42，P<0.01）、高年资医师组（χ2=44.71，P<0.01）和专家医师组（χ2=43.57，P<0.01）。结论 开发出的这种基于深度学习的ME‑NBI下SESCC特征可视化系统，在预测ME‑NBI下SESCC浸润深度（EP-SM1/SM2-SM3）方面表现出良好的诊断效能，其诊断效能优于内镜操作超过10年的内镜医师。

Abstract:

Objective To construct a feature visualization system utilizing deep learning for superficial esophageal squamous cell carcinoma (SESCC) under magnifying endoscopy with narrow band imaging (ME-NBI) to predict the infiltration depth of SESCC. Methods The feature visualization system consisted of four models: two for segmenting the intrapapillary capillary loops (IPCL) area and avascular area (AVA) in ME-NBI images of SESCC lesions (models 1 and 2, respectively), one for obtaining the principal component of color (PCC) in ME-NBI images of SESCC lesions (model 3), and another for automatically predicting the depth of SESCC infiltration based on the features extracted from the first three models (model 4). A total of 2 341 ME-NBI images of SESCC lesions from April 2016 to October 2021 were used to develop the feature visualization system, which was divided into 3 datasets: dataset 1 (1 077 ME-NBI images) was used to train and test models 1-3, dataset 2 (1 069 ME-NBI images) was expanded by 20 times through feature combination to generate 21 380 feature synthetic images to train and test model 4, and dataset 3 (195 ME-NBI images), containing 146 ME-NBI images with lesion invasion depth from the epithelium to the upper 1/3 of the submucosa (EP‑SM1), and 49 ME-NBI images with lesion invasion depth from the middle 1/3 to the lower 1/3 of the submucosa (SM2‑SM3), was used to validate the diagnostic performance of the feature visualization system in predicting the invasion depth of SESCC (EP‑SM1/SM2‑SM3). In order to evaluate the superiority of the feature visualization system, the prediction results of dataset 3 of the traditional deep learning system (trained directly with ME-NBI images), single-item feature models (single-item IPCL feature model, single-item AVA feature model and single-item PCC feature model) were compared with the prediction results of the feature visualization system. In order to evaluate the clinical utility of the feature visualization system, 4 expert physicians (with more than 10 years of endoscopic operation, expert physician group) and 5 senior physicians (with more than 5 years of endoscopic operation, senior physician group) were invited to participate in the human-computer competition to diagnose dataset 3, and the results were compared with the feature visualization system. Results The accuracy, sensitivity and specificity of the feature visualization system in predicting the invasion depth of SESCC (EP‑SM1/SM2‑SM3) were 83.08% (162/195), 82.88% (121/146) and 83.67% (41/49), respectively. The above indicators were 60.00% (117/195), 52.05% (76/146) and 83.67% (41/49) for the traditional deep learning system, 74.87% (146/195), 75.34% (110/146) and 73.47% (36/49) for the single IPCL feature model, 58.97% (115/195), 60.27% (88/146) and 55.10% (27/49) for single AVA feature model, 71.28% (139/195), 71.23% (104/146) and 71.43% (35/49) for single PCC feature model, respectively. The results were 66.67%, 78.22% and 32.24% in senior physician group, and 72.31%, 85.96% and 31.63% in expert physician group, respectively. The accuracy of the feature visualization system in predicting the invasion depth of SESCC was significantly higher than that of the other 6 groups (P<0.05). The sensitivity of feature visualization system was slightly higher than that of senior physician group (χ2=1.59, P=0.21) and single-item IPCL feature model (χ2=2.51, P=0.11), slightly lower than that of expert physician group (χ2=0.89, P=0.35), and significantly higher than that of three other groups (P<0.05). The specificity of the feature visualization system was similar to the traditional deep learning system (χ2=0.00, P=1.00), slightly higher than that of single-item IPCL feature model (χ2=1.52, P=0.22) and single-item PCC feature model (χ2=2.11, P=0.15), and significantly higher than that of the single AVA feature model (χ2=9.42, P<0.01), senior physician group (χ2=44.71, P<0.01) and expert physician group (χ2=43.57, P<0.01). Conclusion The developed deep learning-based feature visualization system using ME-NBI shows excellent diagnostic performance in predicting the infiltration depth of SESCC (EP‑SM1/SM2‑SM3), surpassing the accuracy levels of experienced endoscopists with over 10 years of experience.