Evaluating the artificial intelligence named algorithm DRAID™ endo in detecting gastric cancer on endoscopic images
Main Article Content
Abstract
This study aims to evaluate the accuracy of the AI algorithm named DrAid™ Endo in detecting and segmenting gastric cancer (GC) lesions on endoscopic images. A cross-sectional study was conducted at the Institute of Gastroenterology and Hepatology (IGH) from April 2024 to December 2024. The algorithm was validated on an endoscopic image dataset comprising of 934 non-lesion images and 122 GC images under 4 light modes (WLI, BLI, LCI, and FICE), which was annotated by endoscopists as the gold standard. Diagnostic performance was assessed using sensitivity (Se), specificity (Sp), and accuracy (Acc). The AI correctly detected 89.5% of GC lesions. The Se, Sp, and Acc were 90.2%, 100%, and 98.7%, respectively. In 22/122 images (18.3%), the AI’s lesion bounding area were either broader or narrower than experts’ annotations. The DrAid™ Endo algorithm for GC lesion detection demonstrated high diagnostic accuracy. Conducting further studies under real-time conditions and expanding the dataset to include precancerous lesions are needed for more comprehensive system evaluation.
Article Details
Keywords
Artificial intelligence, gastrointestinal endoscopy, gastric cancer, diagnostic accuracy
References
2. Viện Ung thư Quốc gia. Tình hình bệnh ung thư tại Việt Nam theo GLOBOCAN 2022. 2024; https://nci.vn/tin-tuc/tinh-hinh-benh-ung-thu-tai-viet-nam-theo-globocan-2022-58.
3. Ezoe Y, Muto M, Uedo N, et al. Magnifying narrowband imaging is more accurate than conventional white-light imaging in diagnosis of gastric mucosal cancer. Gastroenterology. 2011; 141(6): 2017-2025 e2013. Doi:10.1053/j.gastro.2011.08.007.
4. Hamashima C, Systematic Review G, Guideline Development Group for Gastric Cancer Screening G. Update version of the Japanese Guidelines for Gastric Cancer Screening. Jpn J Clin Oncol. 2018; 48(7): 673-683. Doi:10.1093/jjco/hyy077.
5. Zhang Z, Gao N, Liu K, et al. Risk factors of missed early gastric cancer in endoscopic resected population: a retrospective, case-control study. Surg Endosc. 2024; 38(8): 4380-4389. Doi:10.1007/s00464-024-10970-0.
6. Shimodate Y, Mizuno M, Doi A, et al. Gastric superficial neoplasia: high miss rate but slow progression. Endosc Int Open. 2017; 5(8): E722-e726. Doi:10.1055/s-0043-110076
7. Quách Trọng Đức, Hà Văn Đến. Tần suất và đặc điểm carcinôm dạ dày giai đoạn tiến triển ở bệnh nhân đã từng được nội soi dạ dày nhưng chưa xác định bệnh. Tạp chí Y học Thành phố Hồ Chí Minh. 2018; 22(6): 56-62.
8. Dohi O, Yagi N, Majima A, et al. Diagnostic ability of magnifying endoscopy with blue laser imaging for early gastric cancer: a prospective study. Gastric Cancer. 2017; 20(2): 297-303. Doi:10.1007/s10120-016-0620-6.
9. Zhang Q, Wang F, Chen ZY, et al. Comparison of the diagnostic efficacy of white light endoscopy and magnifying endoscopy with narrow band imaging for early gastric cancer: a meta-analysis. Gastric Cancer. 2016; 19(2): 543-552. Doi:10.1007/s10120-015-0500-5.
10. Klang E, Sourosh A, Nadkarni GN, Sharif K, Lahat A. Deep Learning and Gastric Cancer: Systematic Review of AI-Assisted Endoscopy. Diagnostics (Basel). 2023; 13(24). Doi:10.3390/diagnostics13243613.
11. Dao HV, Nguyen BP, Nguyen TT, et al. Application of artificial intelligence in gastrointestinal endoscopy in Vietnam: a narrative review. Ther Adv Gastrointest Endosc. 2024; 17: 26317745241306562. Doi:10.1177/26317745241306562.
12. Lee GJ, Park SJ, Kim SJ, Kim HH, Park MI, Moon W. Effectiveness of Premedication with Pronase for Visualization of the Mucosa during Endoscopy: A Randomized, Controlled Trial. Clinical endoscopy. 2012; 45(2): 161-164. Doi:10.5946/ce.2012.45.2.161.
13. Reis D, Kupec J, Hong J, Daoudi A. Real-time flying object detection with YOLOv8. arXiv 2023. arXiv preprint arXiv:230509972. 2023.
14. Lin T-Y, Maire M, Belongie S, et al. Microsoft coco: Common objects in context. Paper presented at: European conference on computer vision2014.
15. Hu B, El Hajj N, Sittler S, Lammert N, Barnes R, Meloni-Ehrig A. Gastric cancer: Classification, histology and application of molecular pathology. J Gastrointest Oncol. 2012; 3(3): 251-261. Doi:10.3978/j.issn.2078-6891.2012.021.
16. Tamaki R, Amano F, Hashida T, Satake H, Yasui H, Tsuji A. The Outcome of Treatment for Patients with Borrmann Type 4 Advanced Gastric Cancer. Journal of Cancer Therapy. 2016; 7(12): 953-962. Doi:10.4236/jct.2016.712092.
17. Huang Q, Shi J Fau - Sun Q, Sun Q Fau - Gold JS, et al. Clinicopathological characterisation of small (2 cm or less) proximal and distal gastric carcinomas in a Chinese population. 2015(1465-3931 (Electronic)).
18. Zhang K, Wang H, Cheng Y, et al. Early gastric cancer detection and lesion segmentation based on deep learning and gastroscopic images. Sci Rep. 2024; 14(1): 7847. Doi:10.1038/s41598-024-58361-8.
19. Niikura R, Aoki T, Shichijo S, et al. Artificial intelligence versus expert endoscopists for diagnosis of gastric cancer in patients who have undergone upper gastrointestinal endoscopy. Endoscopy. 2022; 54(8): 780-784. Doi:10.1055/a-1660-6500.
20. Đào Việt Hằng, Nguyễn Thị Huyền Trang, Vũ Thị Thu Uyên, et al. Trải nghiệm và sự chấp nhận của các bác sĩ nội soi về việc triển khai hệ thống tích hợp thuật toán trí tuệ nhân tạo hỗ trợ trong nội soi tiêu hoá tại Việt Nam. Tạp chí Y học Việt Nam. 2024; 542:272-276. Doi:10.51298/vmj.v542i3.11223.
21. Jha D, Sharma V, Dasu N, et al. GastroVision: A Multi-class Endoscopy Image Dataset for Computer Aided Gastrointestinal Disease Detection. Paper presented at: Machine Learning for Multimodal Healthcare Data; Octobor 10th, 2024; Marrakech, Morocco.