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. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 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] [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
|
Dornblaser D, Young S, Shaukat A. Colon polyps: updates in classification and management. Curr Opin Gastroenterol 2024; 40:14-20. [PMID: 37909928 DOI: 10.1097/mog.0000000000000988] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/03/2023]
Abstract
PURPOSE OF REVIEW Colon polyps are potential precursors to colorectal cancer (CRC), which remains one of the most common causes of cancer-associated death. The proper identification and management of these colorectal polyps is an important quality measure for colonoscopy outcomes. Here, we review colon polyp epidemiology, their natural history, and updates in endoscopic classification and management. RECENT FINDINGS Colon polyps that form from not only the adenoma, but also the serrated polyp pathway have significant risk for future progression to CRC. Therefore, correct identification and management of sessile serrated lesions can improve the quality of screening colonoscopy. Malignant polyp recognition continues to be heavily reliant on well established endoscopic classification systems and plays an important role in intraprocedural management decisions. Hot snare remains the gold standard for pedunculated polyp resection. Nonpedunculated noninvasive lesions can be effectively removed by large forceps if diminutive, but cold snare is preferred for colon polyps 3-20 mm in diameter. Larger lesions at least 20 mm require endoscopic mucosal resection. Polyps with the endoscopic appearance of submucosal invasion require surgical referral or advanced endoscopic resection in select cases. Advances in artificial intelligence may revolutionize endoscopic polyp classification and improve both patient and cost-related outcomes of colonoscopy. SUMMARY Clinicians should be aware of the most recent updates in colon polyp classification and management to provide the best care to their patients initiating screening colonoscopy.
Collapse
Affiliation(s)
- David Dornblaser
- Division of Gastroenterology, Department of Medicine, NYU Grossman School of Medicine, New York, New York, USA
| | | | | |
Collapse
|
3
|
Biscaglia G, Cocomazzi F, Gentile M, Loconte I, Mileti A, Paolillo R, Marra A, Castellana S, Mazza T, Di Leo A, Perri F. Real-time, computer-aided, detection-assisted colonoscopy eliminates differences in adenoma detection rate between trainee and experienced endoscopists. Endosc Int Open 2022; 10:E616-E621. [PMID: 35571479 PMCID: PMC9106428 DOI: 10.1055/a-1783-9678] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/22/2021] [Accepted: 01/03/2022] [Indexed: 12/31/2022] Open
Abstract
Background and study aims Adenoma detection rate (ADR) is a well-accepted quality indicator of screening colonoscopy. In recent years, the added value of artificial intelligence (AI) has been demonstrated in terms of ADR and adenoma miss rate (AMR). To date, there are no studies evaluating the impact of AI on the performance of trainee endoscopists (TEs). This study aimed to assess whether AI might eliminate any difference in ADR or AMR between TEs and experienced endoscopists (EEs). Patients and methods We performed a prospective observational study in 45 subjects referred for screening colonoscopy. A same-day tandem examination was carried out for each patient by a TE with the AI assistance and subsequently by an EE unaware of the lesions detected by the TE. Besides ADR and AMR, we also calculated for each subgroup of endoscopists the adenoma per colonoscopy (APC), polyp detection rate (PDR), polyp per colonoscopy (PPC) and polyp miss rate (PMR). Subgroup analyses according to size, morphology, and site were also performed. Results ADR, APC, PDR, and PPC of AI-supported TEs were 38 %, 0.93, 62 %, 1.93, respectively. The corresponding parameters for EEs were 40 %, 1.07, 58 %, 2.22. No significant difference was found for each analysis between the two groups ( P > 0.05). AMR and PMR for AI-assisted TEs were 12.5 % and 13 %, respectively. Sub-analyses did not show any significant difference ( P > 0.05) between the two categories of operators. Conclusions In this single-center prospective study, the possible impact of AI on endoscopist quality training was demonstrated. In the future, this could result in better efficacy of screening colonoscopy by reducing the incidence of interval or missed cancers.
Collapse
Affiliation(s)
- Giuseppe Biscaglia
- Division of Gastroenterology and Endoscopy, “Casa Sollievo della Sofferenza” Hospital, IRCCS, San Giovanni Rotondo, Italy
| | - Francesco Cocomazzi
- Division of Gastroenterology and Endoscopy, “Casa Sollievo della Sofferenza” Hospital, IRCCS, San Giovanni Rotondo, Italy
| | - Marco Gentile
- Division of Gastroenterology and Endoscopy, “Casa Sollievo della Sofferenza” Hospital, IRCCS, San Giovanni Rotondo, Italy
| | - Ilaria Loconte
- Section of Gastroenterology, Department of Emergency and Organ Transplantation, University of Bari, Italy
| | - Alessia Mileti
- Section of Gastroenterology, Department of Emergency and Organ Transplantation, University of Bari, Italy
| | - Rosa Paolillo
- Section of Gastroenterology, Department of Emergency and Organ Transplantation, University of Bari, Italy
| | - Antonella Marra
- Division of Gastroenterology and Endoscopy, “Casa Sollievo della Sofferenza” Hospital, IRCCS, San Giovanni Rotondo, Italy
| | - Stefano Castellana
- Laboratory of Bioinformatics, Fondazione IRCCS Casa Sollievo della Sofferenza, San Giovanni Rotondo, Italy
| | - Tommaso Mazza
- Laboratory of Bioinformatics, Fondazione IRCCS Casa Sollievo della Sofferenza, San Giovanni Rotondo, Italy
| | - Alfredo Di Leo
- Section of Gastroenterology, Department of Emergency and Organ Transplantation, University of Bari, Italy
| | - Francesco Perri
- Division of Gastroenterology and Endoscopy, “Casa Sollievo della Sofferenza” Hospital, IRCCS, San Giovanni Rotondo, Italy
| |
Collapse
|
4
|
Hamada Y, Tanaka K, Katsurahara M, Horiki N, Yamada R, Yamada T, Takei Y. Utility of the narrow-band imaging international colorectal endoscopic classification for optical diagnosis of colorectal polyp histology in clinical practice: a retrospective study. BMC Gastroenterol 2021; 21:336. [PMID: 34454417 PMCID: PMC8401034 DOI: 10.1186/s12876-021-01898-z] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/18/2021] [Accepted: 08/03/2021] [Indexed: 12/24/2022] Open
Abstract
BACKGROUND Narrow-band imaging (NBI) highlights the surface structures and vessels of colorectal polyps and is useful for determining the polyp histology. The narrow-band imaging international colorectal endoscopic (NICE) classification is a diagnostic tool for determining colorectal polyp histology based on NBI without optical magnification. In this study, we aimed to investigate the value of each type of the NICE classification for determining colorectal polyp histology using endoscopy data accumulated in a clinical setting. METHODS Endoscopy data for 534 colorectal polyps (316 patients) treated at our facility were retrospectively analyzed. First, we investigated the diagnostic performance of each type of the NICE classification for the optical diagnosis of colorectal polyp histology. The procedures were performed by experienced endoscopists using high-definition colonoscopy without optical magnification. Second, inter-observer and intra-observer agreements were assessed after providing experts and non-experts with a short lecture on the NICE classification. Using 50 fine NBI images of colorectal polyps without optical magnification, the inter-observer and intra-observer agreements between five experts and five non-experts were assessed. RESULTS The sensitivity, specificity, and accuracy values were 86.0%, 99.6%, and 98.5% for NICE type 1 lesions; 99.2%, 85.2%, and 97.8% for NICE type 2 lesions; and 81.8%, 99.6%, and 99.3% for NICE type 3 lesions, respectively. The inter-observer and intra-observer agreements ranged from substantial to excellent for both experts and non-experts. CONCLUSIONS The NICE classification had good diagnostic ability in terms of determining the polyp histology and demonstrated a high level of reproducibility among experts and non-experts. Thus, the NICE classification is a useful clinical tool that can be used without optical magnification.
Collapse
Affiliation(s)
- Yasuhiko Hamada
- Department of Gastroenterology and Hepatology, Mie University Hospital, 2-174 Edobashi, Tsu, Mie, 514-8507, Japan.
| | - Kyosuke Tanaka
- Department of Endoscopy, Mie University Hospital, Tsu, Japan
| | | | - Noriyuki Horiki
- Department of Endoscopy, Mie University Hospital, Tsu, Japan
| | - Reiko Yamada
- Department of Gastroenterology and Hepatology, Mie University Hospital, 2-174 Edobashi, Tsu, Mie, 514-8507, Japan
| | - Tomomi Yamada
- Department of Medical Innovation, Osaka University Hospital, Suita, Japan
| | - Yoshiyuki Takei
- Department of Gastroenterology and Hepatology, Mie University Hospital, 2-174 Edobashi, Tsu, Mie, 514-8507, Japan
| |
Collapse
|