School of Software Technology, Dalian University of Technology, Dalian, China.
Department of Digestive Endoscopy, Central Hospital of Dalian University of Technology, Dalian, China.
Ann Med. 2024 Dec;56(1):2418963. doi: 10.1080/07853890.2024.2418963. Epub 2024 Nov 5.
The risk of gastric cancer can be predicted by gastroscopic manifestation recognition and the Kyoto Gastritis Score. This study aims to validate the applicability of AI approaches for recognizing gastroscopic manifestations according to the definition of Kyoto Gastritis Score, with the goal of improving early gastric cancer detection and reducing gastric cancer mortality.
In this retrospective study, 29013 gastric endoscopy images were collected and carefully annotated into five categories according to the Kyoto Gastritis Score, i.e. atrophy (A), diffuse redness (DR), enlarged folds (H), intestinal metaplasia (IM), and nodularity (N). As a multi-label recognition task, we propose a deep learning approach composed of five GAM-EfficientNet models, each performing a multiple classification to quantify gastroscopic manifestations, i.e. no presentation or the severity score 0-2. This approach was compared with endoscopists of varying years of experience in terms of accuracy, specificity, precision, recall, and F1 score.
The approach demonstrated good performance in identifying the five manifestations of the Kyoto Gastritis Score, with an average accuracy, specificity, precision, recall, and F1 score of 78.70%, 91.92%, 80.23%, 78.70%, and 0.78, respectively. The average performance of five experienced endoscopists was 72.63%, 90.00%, 77.68%, 72.63%, and 0.73, while that of five less experienced endoscopists was 66.60%, 87.44%, 70.88%, 66.60%, and 0.66, respectively. The sample t-test indicates that the approach's average accuracy, specificity, precision, recall, and F1 score for identifying the five manifestations were significantly higher than those of less experienced endoscopists, experienced endoscopists, and all endoscopists on average ( < 0.05).
Our study demonstrates the potential of deep learning approaches on gastric manifestation recognition over junior, even senior endoscopists. Thus, the deep learning approach holds potential as an auxiliary tool, although prospective validation is still needed to assess its clinical applicability.
通过胃镜表现识别和京都胃炎评分，可以预测胃癌风险。本研究旨在验证 AI 方法根据京都胃炎评分的定义识别胃镜表现的适用性，以期提高早期胃癌的检出率，降低胃癌死亡率。
在这项回顾性研究中，共收集了 29013 例胃内镜图像，并根据京都胃炎评分仔细标注为五个类别，即萎缩（A）、弥漫性红斑（DR）、皱襞粗大（H）、肠上皮化生（IM）和结节（N）。作为一个多标签识别任务，我们提出了一种由五个 GAM-EfficientNet 模型组成的深度学习方法，每个模型进行多项分类以量化胃镜表现，即无表现或严重程度评分 0-2。我们比较了该方法与不同经验内镜医生在准确性、特异性、精确性、召回率和 F1 评分方面的表现。
该方法在识别京都胃炎评分的五种表现方面表现良好，平均准确性、特异性、精确性、召回率和 F1 评分分别为 78.70%、91.92%、80.23%、78.70%和 0.78。五位经验丰富的内镜医生的平均表现分别为 72.63%、90.00%、77.68%、72.63%和 0.73，而五位经验较少的内镜医生的平均表现分别为 66.60%、87.44%、70.88%、66.60%和 0.66。样本 t 检验表明，该方法识别五种表现的平均准确性、特异性、精确性、召回率和 F1 评分均显著高于经验较少的内镜医生、经验丰富的内镜医生和所有内镜医生的平均水平（ < 0.05）。
本研究表明，深度学习方法在胃表现识别方面优于初级甚至高级内镜医生。因此，尽管还需要前瞻性验证来评估其临床适用性，但深度学习方法作为一种辅助工具具有一定的潜力。
