Takemoto Satoko, Hori Keisuke, Yoshimasa Sakai, Nishimura Masaomi, Nakajo Keiichiro, Inaba Atsushi, Sasabe Maasa, Aoyama Naoki, Watanabe Takashi, Minakata Nobuhisa, Ikematsu Hiroaki, Yokota Hideo, Yano Tomonori
Image Processing Research Team, Center for Advanced Photonics, RIKEN, 2-1 Hirosawa, Wako-shi, Saitama, 351-0198, Japan.
Department of Gastroenterology and Endoscopy, National Cancer Center Hospital East, Kashiwa, Japan.
J Gastroenterol. 2023 Aug;58(8):741-750. doi: 10.1007/s00535-023-02001-x. Epub 2023 May 31.
Precise area diagnosis of early gastric cancer (EGC) is critical for reliable endoscopic resection. Computer-aided diagnosis (CAD) shows strong potential for detecting EGC and reducing cancer-care disparities caused by differences in endoscopists' skills. To be used in clinical practice, CAD should enable both the detection and the demarcation of lesions. This study proposes a scheme for the detection and delineation of EGC under white-light endoscopy and validates its performance using 1-year consecutive cases.
Only 300 endoscopic images randomly selected from 68 consecutive cases were used for training a convolutional neural network. All cases were treated with endoscopic submucosal dissection, enabling the accumulation of a training dataset in which the extent of lesions was precisely determined. For validation, 462 cancer images and 396 normal images from 137 consecutive cases were used. From the validation results, 38 randomly selected images were compared with those delineated by six endoscopists.
Successful detections of EGC in 387 cancer images (83.8%) and the absence of lesions in 307 normal images (77.5%) were achieved. Positive and negative predictive values were 81.3% and 80.4%, respectively. Successful detection was achieved in 130 cases (94.9%). We achieved precise demarcation of EGC with a mean intersection over union of 66.5%, showing the extent of lesions with a smooth boundary; the results were comparable to those achieved by specialists.
Our scheme, validated using 1-year consecutive cases, shows potential for demarcating EGC. Its performance matched that of specialists; it might therefore be suitable for clinical use in the future.
早期胃癌（EGC）的精确区域诊断对于可靠的内镜切除至关重要。计算机辅助诊断（CAD）在检测EGC以及减少因内镜医师技能差异导致的癌症治疗差异方面显示出强大潜力。为了应用于临床实践，CAD应能够检测和划定病变范围。本研究提出了一种在白光内镜下检测和描绘EGC的方案，并使用连续1年的病例验证其性能。
仅从68例连续病例中随机选择300张内镜图像用于训练卷积神经网络。所有病例均接受内镜黏膜下剥离术治疗，从而能够积累一个精确确定病变范围的训练数据集。为了进行验证，使用了来自137例连续病例的462张癌症图像和396张正常图像。从验证结果中，随机选择38张图像与六位内镜医师划定的图像进行比较。
在387张癌症图像中成功检测出EGC（83.8%），在307张正常图像中未检测到病变（77.5%）。阳性和阴性预测值分别为81.3%和80.4%。在130例病例中成功检测（94.9%）。我们实现了EGC的精确划定，平均交并比为66.5%，显示出边界平滑的病变范围；结果与专家的结果相当。
我们的方案通过连续1年的病例验证，显示出划定EGC的潜力。其性能与专家相当；因此，它可能适合未来的临床应用。
