1
|
Wang Y, Ni H, Zhou J, Liu L, Lin J, Yin M, Gao J, Zhu S, Yin Q, Zhu J, Li R. A Semi-Supervised Learning Framework for Classifying Colorectal Neoplasia Based on the NICE Classification. J Imaging Inform Med 2024:10.1007/s10278-024-01123-9. [PMID: 38653910 DOI: 10.1007/s10278-024-01123-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/21/2024] [Revised: 04/02/2024] [Accepted: 04/12/2024] [Indexed: 04/25/2024]
Abstract
Labelling medical images is an arduous and costly task that necessitates clinical expertise and large numbers of qualified images. Insufficient samples can lead to underfitting during training and poor performance of supervised learning models. In this study, we aim to develop a SimCLR-based semi-supervised learning framework to classify colorectal neoplasia based on the NICE classification. First, the proposed framework was trained under self-supervised learning using a large unlabelled dataset; subsequently, it was fine-tuned on a limited labelled dataset based on the NICE classification. The model was evaluated on an independent dataset and compared with models based on supervised transfer learning and endoscopists using accuracy, Matthew's correlation coefficient (MCC), and Cohen's kappa. Finally, Grad-CAM and t-SNE were applied to visualize the models' interpretations. A ResNet-backboned SimCLR model (accuracy of 0.908, MCC of 0.862, and Cohen's kappa of 0.896) outperformed supervised transfer learning-based models (means: 0.803, 0.698, and 0.742) and junior endoscopists (0.816, 0.724, and 0.863), while performing only slightly worse than senior endoscopists (0.916, 0.875, and 0.944). Moreover, t-SNE showed a better clustering of ternary samples through self-supervised learning in SimCLR than through supervised transfer learning. Compared with traditional supervised learning, semi-supervised learning enables deep learning models to achieve improved performance with limited labelled endoscopic images.
Collapse
Affiliation(s)
- Yu Wang
- Department of Hepatobiliary Surgery, Jintan Affiliated Hospital of Jiangsu University, Changzhou, Jiangsu, 213200, China
| | - Haoxiang Ni
- Department of Gastroenterology, The First Affiliated Hospital of Soochow University, # 899 Pinghai St., Suzhou, Jiangsu, 215006, China
- Suzhou Clinical Center of Digestive Disease, Suzhou, Jiangsu, 215006, China
| | - Jielu Zhou
- Department of Gastroenterology, The First Affiliated Hospital of Soochow University, # 899 Pinghai St., Suzhou, Jiangsu, 215006, China
- Department of Geriatrics, Kowloon Affiliated Hospital of Shanghai Jiao Tong University, Suzhou, Jiangsu, 215006, China
| | - Lihe Liu
- Department of Gastroenterology, The First Affiliated Hospital of Soochow University, # 899 Pinghai St., Suzhou, Jiangsu, 215006, China
- Suzhou Clinical Center of Digestive Disease, Suzhou, Jiangsu, 215006, China
| | - Jiaxi Lin
- Department of Gastroenterology, The First Affiliated Hospital of Soochow University, # 899 Pinghai St., Suzhou, Jiangsu, 215006, China
- Suzhou Clinical Center of Digestive Disease, Suzhou, Jiangsu, 215006, China
| | - Minyue Yin
- Department of Gastroenterology, Beijing Friendship Hospital, Capital Medical University, Beijing, 100050, China
- National Clinical Research Center for Digestive Disease, Beijing Digestive Disease Center, State Key Laboratory of Digestive Health, Beijing, 100050, China
| | - Jingwen Gao
- Department of Gastroenterology, The First Affiliated Hospital of Soochow University, # 899 Pinghai St., Suzhou, Jiangsu, 215006, China
- Suzhou Clinical Center of Digestive Disease, Suzhou, Jiangsu, 215006, China
| | - Shiqi Zhu
- Department of Gastroenterology, The First Affiliated Hospital of Soochow University, # 899 Pinghai St., Suzhou, Jiangsu, 215006, China
- Suzhou Clinical Center of Digestive Disease, Suzhou, Jiangsu, 215006, China
| | - Qi Yin
- Department of Anesthesiology, Jintan Affiliated Hospital of Jiangsu University, Changzhou, Jiangsu, 213200, China
| | - Jinzhou Zhu
- Department of Gastroenterology, The First Affiliated Hospital of Soochow University, # 899 Pinghai St., Suzhou, Jiangsu, 215006, China.
- Suzhou Clinical Center of Digestive Disease, Suzhou, Jiangsu, 215006, China.
- Key Laboratory of Hepatosplenic Surgery, Ministry of Education, The First Affiliated Hospital of Harbin Medical University, Harbin, 150001, China.
| | - Rui Li
- Department of Gastroenterology, The First Affiliated Hospital of Soochow University, # 899 Pinghai St., Suzhou, Jiangsu, 215006, China.
- Suzhou Clinical Center of Digestive Disease, Suzhou, Jiangsu, 215006, China.
| |
Collapse
|
2
|
Okamoto Y, Yoshida S, Izakura S, Katayama D, Michida R, Koide T, Tamaki T, Kamigaichi Y, Tamari H, Shimohara Y, Nishimura T, Inagaki K, Tanaka H, Yamashita K, Sumimoto K, Oka S, Tanaka S. Development of multi-class computer-aided diagnostic systems using the NICE/JNET classifications for colorectal lesions. J Gastroenterol Hepatol 2022; 37:104-110. [PMID: 34478167 DOI: 10.1111/jgh.15682] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/22/2021] [Revised: 07/22/2021] [Accepted: 08/30/2021] [Indexed: 12/15/2022]
Abstract
BACKGROUND AND AIM Diagnostic support using artificial intelligence may contribute to the equalization of endoscopic diagnosis of colorectal lesions. We developed computer-aided diagnosis (CADx) support system for diagnosing colorectal lesions using the NBI International Colorectal Endoscopic (NICE) classification and the Japan NBI Expert Team (JNET) classification. METHODS Using Residual Network as the classifier and NBI images as training images, we developed a CADx based on the NICE classification (CADx-N) and a CADx based on the JNET classification (CADx-J). For validation, 480 non-magnifying and magnifying NBI images were used for the CADx-N and 320 magnifying NBI images were used for the CADx-J. The diagnostic performance of the CADx-N was evaluated using the magnification rate. RESULTS The accuracy of the CADx-N for Types 1, 2, and 3 was 97.5%, 91.2%, and 93.8%, respectively. The diagnostic performance for each magnification level was good (no statistically significant difference). The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of the CADx-J were 100%, 96.3%, 82.8%, 100%, and 96.9% for Type 1; 80.3%, 93.7%, 94.1%, 79.2%, and 86.3% for Type 2A; 80.4%, 84.7%, 46.8%, 96.3%, and 84.1% for Type 2B; and 62.5%, 99.6%, 96.8%, 93.8%, and 94.1% for Type 3, respectively. CONCLUSIONS The multi-class CADx systems had good diagnostic performance with both the NICE and JNET classifications and may aid in educating non-expert endoscopists and assist in diagnosing colorectal lesions.
Collapse
Affiliation(s)
- Yuki Okamoto
- Department of Gastroenterology and Metabolism, Hiroshima University Hospital, Hiroshima, Japan
| | - Shigeto Yoshida
- Department of Gastroenterology, JR Hiroshima Hospital, Hiroshima, Japan
| | - Seiji Izakura
- Research Institute for Nanodevice and Bio Systems, Hiroshima University, Hiroshima, Japan
| | - Daisuke Katayama
- Research Institute for Nanodevice and Bio Systems, Hiroshima University, Hiroshima, Japan
| | - Ryuichi Michida
- Research Institute for Nanodevice and Bio Systems, Hiroshima University, Hiroshima, Japan
| | - Tetsushi Koide
- Research Institute for Nanodevice and Bio Systems, Hiroshima University, Hiroshima, Japan
| | - Toru Tamaki
- Department of Computer Science, Nagoya Institute of Technology, Nagoya, Japan
| | - Yuki Kamigaichi
- Department of Gastroenterology and Metabolism, Hiroshima University Hospital, Hiroshima, Japan
| | - Hirosato Tamari
- Department of Gastroenterology and Metabolism, Hiroshima University Hospital, Hiroshima, Japan
| | - Yasutsugu Shimohara
- Department of Gastroenterology and Metabolism, Hiroshima University Hospital, Hiroshima, Japan
| | - Tomoyuki Nishimura
- Department of Gastroenterology and Metabolism, Hiroshima University Hospital, Hiroshima, Japan
| | - Katsuaki Inagaki
- Department of Gastroenterology and Metabolism, Hiroshima University Hospital, Hiroshima, Japan
| | - Hidenori Tanaka
- Department of Endoscopy, Hiroshima University Hospital, Hiroshima, Japan
| | - Ken Yamashita
- Department of Endoscopy, Hiroshima University Hospital, Hiroshima, Japan
| | - Kyoku Sumimoto
- Department of Endoscopy, Hiroshima University Hospital, Hiroshima, Japan
| | - Shiro Oka
- Department of Gastroenterology and Metabolism, Hiroshima University Hospital, Hiroshima, Japan
| | - Shinji Tanaka
- Department of Endoscopy, Hiroshima University Hospital, Hiroshima, Japan
| |
Collapse
|
3
|
Komeda Y, Kashida H, Sakurai T, Asakuma Y, Tribonias G, Nagai T, Kono M, Minaga K, Takenaka M, Arizumi T, Hagiwara S, Matsui S, Watanabe T, Nishida N, Chikugo T, Chiba Y, Kudo M. Magnifying Narrow Band Imaging (NBI) for the Diagnosis of Localized Colorectal Lesions Using the Japan NBI Expert Team (JNET) Classification. Oncology 2017; 93 Suppl 1:49-54. [PMID: 29258091 DOI: 10.1159/000481230] [Citation(s) in RCA: 47] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/19/2022]
Abstract
OBJECTIVE The Japan NBI Expert Team (JNET) proposed a new narrow band imaging (NBI) classification system for colorectal tumors in June 2014. In this classification system, types 1, 2A, 2B, and 3 correspond to hyperplastic polyps (HPs) including sessile serrated polyps (SSPs), low-grade dysplasia (LGD), high-grade dysplasia (HGD) to shallow submucosal invasive (SM-s) carcinomas, and deep submucosal invasive (SM-d) carcinomas, respectively. METHODS To validate this system, we performed a retrospective image evaluation study, in which 199 colorectal tumors previously assessed by NBI magnifying endoscopy were classified by 3 blinded experienced colonoscopists using the JNET system. The results were compared with the final pathological diagnoses to determine the JNET classification's accuracy. The interobserver agreement was calculated, and the intraobserver agreement was assessed after 6 months. RESULTS The final pathological diagnoses identified 14 HPs/SSPs, 127 LGDs, 22 HGDs, 19 SM-s carcinomas, and 17 SM-d carcinomas. The respective sensitivities, specificities, positive predictive value, negative predictive value, and accuracies were as follows: Type 1, 85.7, 99.5, 92.3, 98.9, and 98.5%; Type 2A, 96.0, 81.9, 90.3, 92.1, and 90.9%; Type 2B, 75.6%, 90.5, 67.3, 93.4, and 87.4%; and Type 3, 29.4%, 100, 100, 93.8, and 94.0%. The interobserver agreement and the intraobserver agreement were moderate (κ value: 0.52) and excellent (κ value: 0.88), respectively. Lesions presenting as Type 2B during NBI comprised a range of colorectal tumors, including HGDs, SM-s, and SM-d. CONCLUSIONS The JNET classification was useful for the diagnosis of HPs/SSPs, LGDs, and SM-d, but not SM-s lesions. For low-confidence cases, magnified chromoendoscopy is recommended to ensure correct diagnoses.
Collapse
Affiliation(s)
- Yoriaki Komeda
- Department of Gastroenterology and Hepatology, Kindai University Faculty of Medicine, Osaka-Sayama, Japan
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|