III Medizinische Klinik, Universitätsklinikum Augsburg, Augsburg Germany.
Regensburg Medical Image Computing (ReMIC), Ostbayerische Technische Hochschule Regensburg (OTH Regensburg), Regensburg Germany.
Endoscopy. 2021 Sep;53(9):878-883. doi: 10.1055/a-1311-8570. Epub 2021 Feb 11.
The accurate differentiation between T1a and T1b Barrett's-related cancer has both therapeutic and prognostic implications but is challenging even for experienced physicians. We trained an artificial intelligence (AI) system on the basis of deep artificial neural networks (deep learning) to differentiate between T1a and T1b Barrett's cancer on white-light images.
Endoscopic images from three tertiary care centers in Germany were collected retrospectively. A deep learning system was trained and tested using the principles of cross validation. A total of 230 white-light endoscopic images (108 T1a and 122 T1b) were evaluated using the AI system. For comparison, the images were also classified by experts specialized in endoscopic diagnosis and treatment of Barrett's cancer.
The sensitivity, specificity, F1 score, and accuracy of the AI system in the differentiation between T1a and T1b cancer lesions was 0.77, 0.64, 0.74, and 0.71, respectively. There was no statistically significant difference between the performance of the AI system and that of experts, who showed sensitivity, specificity, F1, and accuracy of 0.63, 0.78, 0.67, and 0.70, respectively.
This pilot study demonstrates the first multicenter application of an AI-based system in the prediction of submucosal invasion in endoscopic images of Barrett's cancer. AI scored equally to international experts in the field, but more work is necessary to improve the system and apply it to video sequences and real-life settings. Nevertheless, the correct prediction of submucosal invasion in Barrett's cancer remains challenging for both experts and AI.
准确区分 T1a 和 T1b 型 Barrett 相关癌症具有治疗和预后意义，但即使是经验丰富的医生也难以做到这一点。我们基于深度人工神经网络（深度学习）开发了一种人工智能（AI）系统，用于区分白光图像中的 T1a 和 T1b Barrett 癌。
回顾性收集了来自德国三个三级护理中心的内镜图像。使用交叉验证原则对深度学习系统进行训练和测试。使用 AI 系统评估了总共 230 张白光内镜图像（108 张 T1a 和 122 张 T1b）。为了进行比较，这些图像也由专门从事 Barrett 癌症内镜诊断和治疗的专家进行分类。
AI 系统在区分 T1a 和 T1b 癌症病变方面的灵敏度、特异性、F1 评分和准确率分别为 0.77、0.64、0.74 和 0.71。AI 系统的性能与专家的性能之间没有统计学上的显著差异，专家的灵敏度、特异性、F1 和准确率分别为 0.63、0.78、0.67 和 0.70。
这项初步研究展示了首个基于 AI 的系统在预测 Barrett 癌症内镜图像黏膜下浸润方面的多中心应用。AI 的表现与该领域的国际专家相当，但仍需要进一步改进系统，并将其应用于视频序列和实际环境中。尽管如此，正确预测 Barrett 癌症的黏膜下浸润对专家和 AI 来说仍然具有挑战性。
