Abstract：
OBJECTIVE: To develop deep learning models using thoracoscopic images to identify visceral pleural invasion (VPI) in patients with clinical stage I lung adenocarcinoma, and to verify if these models can be applied clinically.
METHODS: Two deep learning models, one based on a convolutional neural network (CNN) and the other based on a vision transformer (ViT), were applied and trained via 463 images (VPI negative: 269 images, VPI positive: 194 images) captured from surgical videos of 81 patients. Model performances were validated via an independent test dataset containing 46 images (VPI negative: 28 images, VPI positive: 18 images) from 46 test patients.
RESULTS: The areas under the receiver operating characteristic curves of the CNN-based and ViT-based models were 0.77 and 0.84 (p = 0.304), respectively. The accuracy, sensitivity, specificity, and positive and negative predictive values were 73.91, 83.33, 67.86, 62.50, and 86.36% for the CNN-based model and 78.26, 77.78, 78.57, 70.00, and 84.62% for the ViT-based model, respectively. These models\' diagnostic abilities were comparable to those of board-certified thoracic surgeons and tended to be superior to those of non-board-certified thoracic surgeons.
CONCLUSIONS: The deep learning model systems can be utilized in clinical applications via data expansion.
METHODS: Two deep learning models, one based on a convolutional neural network (CNN) and the other based on a vision transformer (ViT), were applied and trained via 463 images (VPI negative: 269 images, VPI positive: 194 images) captured from surgical videos of 81 patients. Model performances were validated via an independent test dataset containing 46 images (VPI negative: 28 images, VPI positive: 18 images) from 46 test patients.
RESULTS: The areas under the receiver operating characteristic curves of the CNN-based and ViT-based models were 0.77 and 0.84 (p = 0.304), respectively. The accuracy, sensitivity, specificity, and positive and negative predictive values were 73.91, 83.33, 67.86, 62.50, and 86.36% for the CNN-based model and 78.26, 77.78, 78.57, 70.00, and 84.62% for the ViT-based model, respectively. These models\' diagnostic abilities were comparable to those of board-certified thoracic surgeons and tended to be superior to those of non-board-certified thoracic surgeons.
CONCLUSIONS: The deep learning model systems can be utilized in clinical applications via data expansion.
摘要：
目的：使用胸腔镜图像开发深度学习模型，以识别临床I期肺腺癌患者的内脏胸膜侵犯（VPI），并验证这些模型是否可以在临床上应用。
方法：两种深度学习模型，一个基于卷积神经网络(CNN)，另一个基于视觉变换器(ViT)，通过463张图像应用和训练(VPI阴性：269张图像，VPI阳性：194张图像）从81名患者的手术视频中捕获。通过包含46张图像的独立测试数据集验证了模型性能(VPI阴性：28张图像，VPI阳性：18张图像）来自46名测试患者。
结果：基于CNN和基于ViT的模型的接收器工作特性曲线下的面积分别为0.77和0.84（p=0.304），分别。准确性,灵敏度,特异性，基于CNN的模型的阳性预测值和阴性预测值分别为73.91、83.33、67.86、62.50和86.36%，基于ViT的模型为78.26、77.78、78.57、70.00和84.62%，分别。这些模型的诊断能力与经过董事会认证的胸外科医师相当，并且往往优于未经董事会认证的胸外科医师。
结论：深度学习模型系统可以通过数据扩展用于临床应用。
方法：两种深度学习模型，一个基于卷积神经网络(CNN)，另一个基于视觉变换器(ViT)，通过463张图像应用和训练(VPI阴性：269张图像，VPI阳性：194张图像）从81名患者的手术视频中捕获。通过包含46张图像的独立测试数据集验证了模型性能(VPI阴性：28张图像，VPI阳性：18张图像）来自46名测试患者。
结果：基于CNN和基于ViT的模型的接收器工作特性曲线下的面积分别为0.77和0.84（p=0.304），分别。准确性,灵敏度,特异性，基于CNN的模型的阳性预测值和阴性预测值分别为73.91、83.33、67.86、62.50和86.36%，基于ViT的模型为78.26、77.78、78.57、70.00和84.62%，分别。这些模型的诊断能力与经过董事会认证的胸外科医师相当，并且往往优于未经董事会认证的胸外科医师。
结论：深度学习模型系统可以通过数据扩展用于临床应用。
