1
|
Chen Y, Xu W, Liu J, Zhao C, Cao X, Wang R, Feng D, Zhang R, Zhou X. Color-coded parametric imaging support display of vessel hemorrhage-an in vitro experiment and clinical validation study. Front Cardiovasc Med 2024; 11:1387421. [PMID: 38966753 PMCID: PMC11222601 DOI: 10.3389/fcvm.2024.1387421] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/22/2024] [Accepted: 06/04/2024] [Indexed: 07/06/2024] Open
Abstract
Background Digital Subtraction Angiography (DSA) is currently the most effective diagnostic method for vascular diseases, but it is still subject to various factors, resulting in uncertain diagnosis. Therefore, a new technology is needed to help clinical doctors improve diagnostic accuracy and efficiency. Purpose The objective of the study was to investigate the effect of utilizing color-coded parametric imaging techniques on the accuracy of identifying active bleeding through DSA, the widely accepted standard for diagnosing vascular disorders. Methods Several variables can delay the diagnosis and treatment of active bleeding with DSA. To resolve this, we carried out an in vitro simulation experiment to simulate vascular hemorrhage and utilized five color-coded parameters (area under curve, time to peak, time-of-arrival, transit time, and flow rate of contrast agent) to determine the optimal color coding parameters. We then verified it in a clinical study. Results Five different color-coded parametric imaging methods were compared and the time-of-arrival color coding was the most efficient technique for diagnosing active hemorrhage, with a statistically significant advantage (P < 0.001). In clinical study, 135 patients (101 with confirmed bleeding and 34 with confirmed no bleeding) were collected. For patients whose bleeding could not be determined using DSA alone (55/101) and whose no bleeding could not be diagnosed by DSA alone (35/55), the combination of time-of-arrival color parametric imaging was helpful for diagnosis, with a statistically significant difference (P < 0.01 and P = 0.01). Conclusions The time-of-arrival color coding imaging method is a valuable tool for detecting active bleeding. When combined with DSA, it improves the visual representation of active hemorrhage and improves the efficiency of diagnosis.
Collapse
Affiliation(s)
- Yi Chen
- Shanxi Bethune Hospital, Shanxi Academy of Medical Sciences, Tongji Shanxi Hospital, Third Hospital of Shanxi Medical University, Taiyuan, China
- Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
- Department of Oncology and Vascular Intervention, First Hospital of Shanxi Medical University, Taiyuan, Shanxi, China
- Shanxi Provincial Clinical Research Center for Interventional Medicine (202204010501004), Taiyuan, China
| | - Wenji Xu
- College of Medical Imaging, Shanxi Medical University, Taiyuan, Shanxi, China
| | - Jiaxin Liu
- College of Electronic Information Engineering, Beihang University, Beijing, China
| | - Chao Zhao
- Department of Oncology and Vascular Intervention, First Hospital of Shanxi Medical University, Taiyuan, Shanxi, China
- Shanxi Provincial Clinical Research Center for Interventional Medicine (202204010501004), Taiyuan, China
| | - Xiaojing Cao
- Department of Interventional Therapy, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Rong Wang
- Department of Oncology and Vascular Intervention, First Hospital of Shanxi Medical University, Taiyuan, Shanxi, China
- Shanxi Provincial Clinical Research Center for Interventional Medicine (202204010501004), Taiyuan, China
| | - Duiping Feng
- Department of Oncology and Vascular Intervention, First Hospital of Shanxi Medical University, Taiyuan, Shanxi, China
- Shanxi Provincial Clinical Research Center for Interventional Medicine (202204010501004), Taiyuan, China
| | - Ruiping Zhang
- The Radiology Department of Shanxi Provincial People's Hospital, The Fifth Hospital of Shanxi Medical University, Taiyuan, China
| | - Xiang Zhou
- Department of Interventional Therapy, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| |
Collapse
|
2
|
Chen TH, Wang YT, Wu CH, Kuo CF, Cheng HT, Huang SW, Lee C. A colonial serrated polyp classification model using white-light ordinary endoscopy images with an artificial intelligence model and TensorFlow chart. BMC Gastroenterol 2024; 24:99. [PMID: 38443794 PMCID: PMC10913269 DOI: 10.1186/s12876-024-03181-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/26/2023] [Accepted: 02/19/2024] [Indexed: 03/07/2024] Open
Abstract
In this study, we implemented a combination of data augmentation and artificial intelligence (AI) model-Convolutional Neural Network (CNN)-to help physicians classify colonic polyps into traditional adenoma (TA), sessile serrated adenoma (SSA), and hyperplastic polyp (HP). We collected ordinary endoscopy images under both white and NBI lights. Under white light, we collected 257 images of HP, 423 images of SSA, and 60 images of TA. Under NBI light, were collected 238 images of HP, 284 images of SSA, and 71 images of TA. We implemented the CNN-based artificial intelligence model, Inception V4, to build a classification model for the types of colon polyps. Our final AI classification model with data augmentation process is constructed only with white light images. Our classification prediction accuracy of colon polyp type is 94%, and the discriminability of the model (area under the curve) was 98%. Thus, we can conclude that our model can help physicians distinguish between TA, SSA, and HPs and correctly identify precancerous lesions such as TA and SSA.
Collapse
Affiliation(s)
- Tsung-Hsing Chen
- Department of Gastroenterology and Hepatology, Linkou Medical Center, Chang Gung Memorial Hospital, Taoyuan, Taiwan
- College of Medicine, Chang Gung University, Taoyuan, Taiwan
| | | | - Chi-Huan Wu
- Department of Gastroenterology and Hepatology, Linkou Medical Center, Chang Gung Memorial Hospital, Taoyuan, Taiwan
- College of Medicine, Chang Gung University, Taoyuan, Taiwan
| | - Chang-Fu Kuo
- Division of Rheumatology, Allergy, and Immunology, Chang Gung Memorial Hospital- Linkou and Chang Gung University College of Medicine, Taoyuan, Taiwan, ROC
- Center for Artificial Intelligence in Medicine, Chang Gung Memorial Hospital, Taoyuan, Taiwan, ROC
| | - Hao-Tsai Cheng
- Department of Gastroenterology and Hepatology, Linkou Medical Center, Chang Gung Memorial Hospital, Taoyuan, Taiwan
- College of Medicine, Chang Gung University, Taoyuan, Taiwan
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, New Taipei Municipal TuCheng Hospital, New Taipei City, Taiwan
- Graduate Institute of Clinical Medicine, College of Medicine, Chang Gung University, Taoyuan City, Taiwan
| | - Shu-Wei Huang
- Department of Gastroenterology and Hepatology, Linkou Medical Center, Chang Gung Memorial Hospital, Taoyuan, Taiwan
- College of Medicine, Chang Gung University, Taoyuan, Taiwan
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, New Taipei Municipal TuCheng Hospital, New Taipei City, Taiwan
| | - Chieh Lee
- Department of Information and Management, College of Business, National Sun Yat-sen University, Kaohsiung city, Taiwan.
| |
Collapse
|
3
|
Kato S, Kudo SE, Minegishi Y, Miyata Y, Maeda Y, Kuroki T, Takashina Y, Mochizuki K, Tamura E, Abe M, Sato Y, Sakurai T, Kouyama Y, Tanaka K, Ogawa Y, Nakamura H, Ichimasa K, Ogata N, Hisayuki T, Hayashi T, Wakamura K, Miyachi H, Baba T, Ishida F, Nemoto T, Misawa M. Impact of computer-aided characterization for diagnosis of colorectal lesions, including sessile serrated lesions: Multireader, multicase study. Dig Endosc 2024; 36:341-350. [PMID: 37937532 DOI: 10.1111/den.14612] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/23/2023] [Accepted: 06/06/2023] [Indexed: 11/09/2023]
Abstract
OBJECTIVES Computer-aided characterization (CADx) may be used to implement optical biopsy strategies into colonoscopy practice; however, its impact on endoscopic diagnosis remains unknown. We aimed to evaluate the additional diagnostic value of CADx when used by endoscopists for assessing colorectal polyps. METHODS This was a single-center, multicase, multireader, image-reading study using randomly extracted images of pathologically confirmed polyps resected between July 2021 and January 2022. Approved CADx that could predict two-tier classification (neoplastic or nonneoplastic) by analyzing narrow-band images of the polyps was used to obtain a CADx diagnosis. Participating endoscopists determined if the polyps were neoplastic or not and noted their confidence level using a computer-based, image-reading test. The test was conducted twice with a 4-week interval: the first test was conducted without CADx prediction and the second test with CADx prediction. Diagnostic performances for neoplasms were calculated using the pathological diagnosis as reference and performances with and without CADx prediction were compared. RESULTS Five hundred polyps were randomly extracted from 385 patients and diagnosed by 14 endoscopists (including seven experts). The sensitivity for neoplasia was significantly improved by referring to CADx (89.4% vs. 95.6%). CADx also had incremental effects on the negative predictive value (69.3% vs. 84.3%), overall accuracy (87.2% vs. 91.8%), and high-confidence diagnosis rate (77.4% vs. 85.8%). However, there was no significant difference in specificity (80.1% vs. 78.9%). CONCLUSIONS Computer-aided characterization has added diagnostic value for differentiating colorectal neoplasms and may improve the high-confidence diagnosis rate.
Collapse
Affiliation(s)
- Shun Kato
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Shin-Ei Kudo
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Yosuke Minegishi
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Yuki Miyata
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Yasuharu Maeda
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Takanori Kuroki
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Yuki Takashina
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Kenichi Mochizuki
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Eri Tamura
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Masahiro Abe
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Yuta Sato
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Tatsuya Sakurai
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Yuta Kouyama
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Kenta Tanaka
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Yushi Ogawa
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Hiroki Nakamura
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Katsuro Ichimasa
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
- Department of Gastroenterology and Hepatology, National University Hospital, Singapore City, Singapore
| | - Noriyuki Ogata
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Tomokazu Hisayuki
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Takemasa Hayashi
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Kunihiko Wakamura
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Hideyuki Miyachi
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Toshiyuki Baba
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Fumio Ishida
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Tetsuo Nemoto
- Department of Diagnostic Pathology and Laboratory Medicine, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Masashi Misawa
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| |
Collapse
|
4
|
Galati JS, Duve RJ, O'Mara M, Gross SA. Artificial intelligence in gastroenterology: A narrative review. Artif Intell Gastroenterol 2022; 3:117-141. [DOI: 10.35712/aig.v3.i5.117] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/09/2022] [Revised: 11/21/2022] [Accepted: 12/21/2022] [Indexed: 12/28/2022] Open
Abstract
Artificial intelligence (AI) is a complex concept, broadly defined in medicine as the development of computer systems to perform tasks that require human intelligence. It has the capacity to revolutionize medicine by increasing efficiency, expediting data and image analysis and identifying patterns, trends and associations in large datasets. Within gastroenterology, recent research efforts have focused on using AI in esophagogastroduodenoscopy, wireless capsule endoscopy (WCE) and colonoscopy to assist in diagnosis, disease monitoring, lesion detection and therapeutic intervention. The main objective of this narrative review is to provide a comprehensive overview of the research being performed within gastroenterology on AI in esophagogastroduodenoscopy, WCE and colonoscopy.
Collapse
Affiliation(s)
- Jonathan S Galati
- Department of Medicine, NYU Langone Health, New York, NY 10016, United States
| | - Robert J Duve
- Department of Internal Medicine, Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, Buffalo, NY 14203, United States
| | - Matthew O'Mara
- Division of Gastroenterology, NYU Langone Health, New York, NY 10016, United States
| | - Seth A Gross
- Division of Gastroenterology, NYU Langone Health, New York, NY 10016, United States
| |
Collapse
|