Validation of Artificial Intelligence Computer-Aided Detection on Gastric Neoplasm in Upper Gastrointestinal Endoscopy

Background/Objectives: Gastric cancer ranks fifth for incidence and fourth in the leading causes of mortality worldwide. In this study, we aimed to validate previously developed artificial intelligence (AI) computer-aided detection (CADe) algorithm, called ALPHAON<sup>®</sup> in detectin...

Full description

Saved in:
Bibliographic Details
Main Authors: Hannah Lee, Jun-Won Chung, Sung-Cheol Yun, Sung Woo Jung, Yeong Jun Yoon, Ji Hee Kim, Boram Cha, Mohd Azzam Kayasseh, Kyoung Oh Kim
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/14/23/2706
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846124302813888512
author Hannah Lee
Jun-Won Chung
Sung-Cheol Yun
Sung Woo Jung
Yeong Jun Yoon
Ji Hee Kim
Boram Cha
Mohd Azzam Kayasseh
Kyoung Oh Kim
author_facet Hannah Lee
Jun-Won Chung
Sung-Cheol Yun
Sung Woo Jung
Yeong Jun Yoon
Ji Hee Kim
Boram Cha
Mohd Azzam Kayasseh
Kyoung Oh Kim
author_sort Hannah Lee
collection DOAJ
description Background/Objectives: Gastric cancer ranks fifth for incidence and fourth in the leading causes of mortality worldwide. In this study, we aimed to validate previously developed artificial intelligence (AI) computer-aided detection (CADe) algorithm, called ALPHAON<sup>®</sup> in detecting gastric neoplasm. Methods: We used the retrospective data of 500 still images, including 5 benign gastric ulcers, 95 with gastric cancer, and 400 normal images. Thereby we validated the CADe algorithm measuring accuracy, sensitivity, and specificity with the result of receiver operating characteristic curves (ROC) and area under curve (AUC) in addition to comparing the diagnostic performance status of four expert endoscopists, four trainees, and four beginners from two university-affiliated hospitals with CADe algorithm. After a washing-out period of over 2 weeks, endoscopists performed gastric detection on the same dataset of the 500 endoscopic images again marked by ALPHAON<sup>®</sup>. Results: The CADe algorithm presented high validity in detecting gastric neoplasm with accuracy (0.88, 95% CI: 0.85 to 0.91), sensitivity (0.93, 95% CI: 0.88 to 0.98), specificity (0.87, 95% CI: 0.84 to 0.90), and AUC (0.962). After a washing-out period of over 2 weeks, overall validity improved in the trainee and beginner groups with the assistance of ALPHAON<sup>®</sup>. Significant improvement was present, especially in the beginner group (accuracy 0.94 (0.93 to 0.96) <i>p</i> < 0.001, sensitivity 0.87 (0.82 to 0.92) <i>p</i> < 0.001, specificity 0.96 (0.95 to 0.97) <i>p</i> < 0.001). Conclusions: The high validation performance state of the CADe algorithm system was verified. Also, ALPHAON<sup>®</sup> has demonstrated its potential to serve as an endoscopic educator for beginners improving and making progress in sensitivity and specificity.
format Article
id doaj-art-96e207a2b47f47c599031483c5bb39ee
institution Kabale University
issn 2075-4418
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-96e207a2b47f47c599031483c5bb39ee2024-12-13T16:24:44ZengMDPI AGDiagnostics2075-44182024-11-011423270610.3390/diagnostics14232706Validation of Artificial Intelligence Computer-Aided Detection on Gastric Neoplasm in Upper Gastrointestinal EndoscopyHannah Lee0Jun-Won Chung1Sung-Cheol Yun2Sung Woo Jung3Yeong Jun Yoon4Ji Hee Kim5Boram Cha6Mohd Azzam Kayasseh7Kyoung Oh Kim8Division of Gastroenterology, Department of Internal Medicine, Gachon University, Gil Medical Center, Incheon 21565, Republic of KoreaDivision of Gastroenterology, Department of Internal Medicine, Gachon University, Gil Medical Center, Incheon 21565, Republic of KoreaDivision of Biostatistics, Center for Medical Research and Information, University of Ulsan College of Medicine, Seoul 05505, Republic of KoreaDivision of Gastroenterology, Department of Internal Medicine, Korea University College of Medicine, Ansan 15355, Republic of KoreaCAIMI Co., Ltd., Incheon 22004, Republic of KoreaCAIMI Co., Ltd., Incheon 22004, Republic of KoreaDivision of Gastroenterology, Department of Internal Medicine, Inha University Hospital, Inha University School of Medicine, Incheon 22332, Republic of KoreaDivision of Gastroenterology, Dr. Sulaiman AI Habib Medical Group, Dubai Healthcare City, Dubai 51431, United Arab EmiratesDivision of Gastroenterology, Department of Internal Medicine, Gachon University, Gil Medical Center, Incheon 21565, Republic of KoreaBackground/Objectives: Gastric cancer ranks fifth for incidence and fourth in the leading causes of mortality worldwide. In this study, we aimed to validate previously developed artificial intelligence (AI) computer-aided detection (CADe) algorithm, called ALPHAON<sup>®</sup> in detecting gastric neoplasm. Methods: We used the retrospective data of 500 still images, including 5 benign gastric ulcers, 95 with gastric cancer, and 400 normal images. Thereby we validated the CADe algorithm measuring accuracy, sensitivity, and specificity with the result of receiver operating characteristic curves (ROC) and area under curve (AUC) in addition to comparing the diagnostic performance status of four expert endoscopists, four trainees, and four beginners from two university-affiliated hospitals with CADe algorithm. After a washing-out period of over 2 weeks, endoscopists performed gastric detection on the same dataset of the 500 endoscopic images again marked by ALPHAON<sup>®</sup>. Results: The CADe algorithm presented high validity in detecting gastric neoplasm with accuracy (0.88, 95% CI: 0.85 to 0.91), sensitivity (0.93, 95% CI: 0.88 to 0.98), specificity (0.87, 95% CI: 0.84 to 0.90), and AUC (0.962). After a washing-out period of over 2 weeks, overall validity improved in the trainee and beginner groups with the assistance of ALPHAON<sup>®</sup>. Significant improvement was present, especially in the beginner group (accuracy 0.94 (0.93 to 0.96) <i>p</i> < 0.001, sensitivity 0.87 (0.82 to 0.92) <i>p</i> < 0.001, specificity 0.96 (0.95 to 0.97) <i>p</i> < 0.001). Conclusions: The high validation performance state of the CADe algorithm system was verified. Also, ALPHAON<sup>®</sup> has demonstrated its potential to serve as an endoscopic educator for beginners improving and making progress in sensitivity and specificity.https://www.mdpi.com/2075-4418/14/23/2706artificial intelligencecomputer-aided detection (CADe) algorithmgastric neoplasm
spellingShingle Hannah Lee
Jun-Won Chung
Sung-Cheol Yun
Sung Woo Jung
Yeong Jun Yoon
Ji Hee Kim
Boram Cha
Mohd Azzam Kayasseh
Kyoung Oh Kim
Validation of Artificial Intelligence Computer-Aided Detection on Gastric Neoplasm in Upper Gastrointestinal Endoscopy
Diagnostics
artificial intelligence
computer-aided detection (CADe) algorithm
gastric neoplasm
title Validation of Artificial Intelligence Computer-Aided Detection on Gastric Neoplasm in Upper Gastrointestinal Endoscopy
title_full Validation of Artificial Intelligence Computer-Aided Detection on Gastric Neoplasm in Upper Gastrointestinal Endoscopy
title_fullStr Validation of Artificial Intelligence Computer-Aided Detection on Gastric Neoplasm in Upper Gastrointestinal Endoscopy
title_full_unstemmed Validation of Artificial Intelligence Computer-Aided Detection on Gastric Neoplasm in Upper Gastrointestinal Endoscopy
title_short Validation of Artificial Intelligence Computer-Aided Detection on Gastric Neoplasm in Upper Gastrointestinal Endoscopy
title_sort validation of artificial intelligence computer aided detection on gastric neoplasm in upper gastrointestinal endoscopy
topic artificial intelligence
computer-aided detection (CADe) algorithm
gastric neoplasm
url https://www.mdpi.com/2075-4418/14/23/2706
work_keys_str_mv AT hannahlee validationofartificialintelligencecomputeraideddetectionongastricneoplasminuppergastrointestinalendoscopy
AT junwonchung validationofartificialintelligencecomputeraideddetectionongastricneoplasminuppergastrointestinalendoscopy
AT sungcheolyun validationofartificialintelligencecomputeraideddetectionongastricneoplasminuppergastrointestinalendoscopy
AT sungwoojung validationofartificialintelligencecomputeraideddetectionongastricneoplasminuppergastrointestinalendoscopy
AT yeongjunyoon validationofartificialintelligencecomputeraideddetectionongastricneoplasminuppergastrointestinalendoscopy
AT jiheekim validationofartificialintelligencecomputeraideddetectionongastricneoplasminuppergastrointestinalendoscopy
AT boramcha validationofartificialintelligencecomputeraideddetectionongastricneoplasminuppergastrointestinalendoscopy
AT mohdazzamkayasseh validationofartificialintelligencecomputeraideddetectionongastricneoplasminuppergastrointestinalendoscopy
AT kyoungohkim validationofartificialintelligencecomputeraideddetectionongastricneoplasminuppergastrointestinalendoscopy