Gastric Cancer. 2024;27(5):1088-1099.

An artificial intelligence system for comprehensive pathologic outcome prediction in early gastric cancer through endoscopic image analysis (with video).

, , , , , , , , , , , , ,

제1저자 이승한 · 교신저자 조수정

PMID 38954175 PMC11335909 DOI 10.1007/s10120-024-01524-3 IF 6.1 소화기내과

소속 (7)

Department of Internal Medicine and Liver Research Institute, Seoul National University College of Medicine, 101 Daehak-Ro, Jongno-Gu, Seoul, 03080, Republic of Korea.
Ainex Corporation, Seoul, Republic of Korea.
Department of Internal Medicine, Seoul National University Bundang Hospital, Seoungnam-Si, Gyeonggi-Do, Republic of Korea.
Center for Health Promotion and Optimal Aging, Seoul National University Hospital, Seoul, Republic of Korea.
Department of Surgery, Seoul National University College of Medicine, Seoul, Republic of Korea.
Department of Pathology, Seoul National University College of Medicine, Seoul, Republic of Korea.
Department of Internal Medicine and Liver Research Institute, Seoul National University College of Medicine, 101 Daehak-Ro, Jongno-Gu, Seoul, 03080, Republic of Korea. crystal5@snu.ac.kr.

Abstract

BACKGROUND Accurate prediction of pathologic results for early gastric cancer (EGC) based on endoscopic findings is essential in deciding between endoscopic and surgical resection. This study aimed to develop an artificial intelligence (AI) model to assess comprehensive pathologic characteristics of EGC using white-light endoscopic images and videos.

METHODS To train the model, we retrospectively collected 4,336 images and prospectively included 153 videos from patients with EGC who underwent endoscopic or surgical resection. The performance of the model was tested and compared to that of 16 endoscopists (nine experts and seven novices) using a mutually exclusive set of 260 images and 10 videos. Finally, we conducted external validation using 436 images and 89 videos from another institution.

RESULTS After training, the model achieved predictive accuracies of 89.7% for undifferentiated histology, 88.0% for submucosal invasion, 87.9% for lymphovascular invasion (LVI), and 92.7% for lymph node metastasis (LNM), using endoscopic videos. The area under the curve values of the model were 0.992 for undifferentiated histology, 0.902 for submucosal invasion, 0.706 for LVI, and 0.680 for LNM in the test. In addition, the model showed significantly higher accuracy than the experts in predicting undifferentiated histology (92.7% vs. 71.6%), submucosal invasion (87.3% vs. 72.6%), and LNM (87.7% vs. 72.3%). The external validation showed accuracies of 75.6% and 71.9% for undifferentiated histology and submucosal invasion, respectively.

CONCLUSIONS AI may assist endoscopists with high predictive performance for differentiation status and invasion depth of EGC. Further research is needed to improve the detection of LVI and LNM.

Keywords

Artificial intelligenceConvolutional neural networkEarly gastric cancerEndoscopy

Figures

**Fig. 1** Flow diagram of study design and datasets. *SNUH* Seoul National University Hospital, *SNUBH* Seoul National University Bundang Hospital, *EGC* early gastric cancer, *ESD* endoscopic submucosal dissection, AI artificial intelligence

**Fig. 2** Representative examples of pathologic predictions by the AI model in endoscopic images. Each endoscopic image contains one lesion of EGC with the following pathologic characteristics. a Differentiated-type EGC of mucosal invasion without both LVI and LNM. b Differentiated-type EGC of submucosal invasion with positive LVI and negative LNM. c Undifferentiated-type EGC of mucosal invasion without both LVI and LNM. d Undifferentiated-type EGC of submucosal invasion with both LVI and LNM. The provided confidence levels represent the probabilistic evaluation of the AI model for predicting postoperative pathologic results of EGC in the images. AI artificial intelligence, *EGC* early gastric cancer, *LVI* lymphovascular invasion, *LNM* lymph node metastasis

**Fig. 3** Schematic diagram for AI-based pathologic prediction in endoscopic videos. Initially, the gastric lesion is identified and outlined with red boundaries (cropped) with the lesion detection model. Subsequently, the cropped lesion is categorized as either cancer, adenoma, or non-neoplastic lesion by the lesion classification model. For lesions classified as cancer, the model computes confidence levels to predict differentiation status, invasion depth, lymphovascular invasion, and lymph node metastasis. Finally, the lesion is categorized into distinct pathologic classes utilizing a soft voting method. AI artificial intelligence, *EGC* early gastric cancer

**Fig. 4** Receiver operating characteristics curves for the AI model in the test set.a Prediction of undifferentiated histology (AUC = 0.992). b Prediction of submucosal invasion (AUC = 0.902). c Prediction of lymphovascular invasion (AUC = 0.706). d Prediction of lymph node metastasis (AUC = 0.680). Blue dots (n = 9) and red dots (n = 7) indicate the performance of the experts and novices, respectively. AI artificial intelligence, *AUC* area under the curve

그림 출처: PubMed Central 공개 논문 (PMC11335909)

Comment · 정정

Erratum in Gastric Cancer. 2024 Nov;27(6):1351. doi: 10.1007/s10120-024-01549-8.

그 밖의 정보