A colonial serrated polyp classification model using white-light ordinary endoscopy images with an artificial intelligence model and TensorFlow chart
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 ordi...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-03-01
|
| Series: | BMC Gastroenterology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12876-024-03181-3 |
| _version_ | 1797274452209172480 |
|---|---|
| author | Tsung-Hsing Chen Yu-Tzu Wang Chi-Huan Wu Chang-Fu Kuo Hao-Tsai Cheng Shu-Wei Huang Chieh Lee |
| author_facet | Tsung-Hsing Chen Yu-Tzu Wang Chi-Huan Wu Chang-Fu Kuo Hao-Tsai Cheng Shu-Wei Huang Chieh Lee |
| author_sort | Tsung-Hsing Chen |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-07T14:58:34Z |
| format | Article |
| id | doaj.art-8b0c5c3fbbac4727bfc43b3d37d9d848 |
| institution | Directory Open Access Journal |
| issn | 1471-230X |
| language | English |
| last_indexed | 2024-03-07T14:58:34Z |
| publishDate | 2024-03-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Gastroenterology |
| spelling | doaj.art-8b0c5c3fbbac4727bfc43b3d37d9d8482024-03-05T19:17:58ZengBMCBMC Gastroenterology1471-230X2024-03-0124111110.1186/s12876-024-03181-3A colonial serrated polyp classification model using white-light ordinary endoscopy images with an artificial intelligence model and TensorFlow chartTsung-Hsing Chen0Yu-Tzu Wang1Chi-Huan Wu2Chang-Fu Kuo3Hao-Tsai Cheng4Shu-Wei Huang5Chieh Lee6Department of Gastroenterology and Hepatology, Linkou Medical Center, Chang Gung Memorial HospitalBusiness Futures Co., LTDDepartment of Gastroenterology and Hepatology, Linkou Medical Center, Chang Gung Memorial HospitalDivision of Rheumatology, Allergy, and Immunology, Chang Gung Memorial Hospital- Linkou and Chang Gung University College of MedicineDepartment of Gastroenterology and Hepatology, Linkou Medical Center, Chang Gung Memorial HospitalDepartment of Gastroenterology and Hepatology, Linkou Medical Center, Chang Gung Memorial HospitalDepartment of Information and Management, College of Business, National Sun Yat-sen UniversityAbstract 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.https://doi.org/10.1186/s12876-024-03181-3Colonial polypsSerrated-type colon polypsArtificial intelligenceClassification modeling |
| spellingShingle | Tsung-Hsing Chen Yu-Tzu Wang Chi-Huan Wu Chang-Fu Kuo Hao-Tsai Cheng Shu-Wei Huang Chieh Lee A colonial serrated polyp classification model using white-light ordinary endoscopy images with an artificial intelligence model and TensorFlow chart BMC Gastroenterology Colonial polyps Serrated-type colon polyps Artificial intelligence Classification modeling |
| title | A colonial serrated polyp classification model using white-light ordinary endoscopy images with an artificial intelligence model and TensorFlow chart |
| title_full | A colonial serrated polyp classification model using white-light ordinary endoscopy images with an artificial intelligence model and TensorFlow chart |
| title_fullStr | A colonial serrated polyp classification model using white-light ordinary endoscopy images with an artificial intelligence model and TensorFlow chart |
| title_full_unstemmed | A colonial serrated polyp classification model using white-light ordinary endoscopy images with an artificial intelligence model and TensorFlow chart |
| title_short | A colonial serrated polyp classification model using white-light ordinary endoscopy images with an artificial intelligence model and TensorFlow chart |
| title_sort | colonial serrated polyp classification model using white light ordinary endoscopy images with an artificial intelligence model and tensorflow chart |
| topic | Colonial polyps Serrated-type colon polyps Artificial intelligence Classification modeling |
| url | https://doi.org/10.1186/s12876-024-03181-3 |
| work_keys_str_mv | AT tsunghsingchen acolonialserratedpolypclassificationmodelusingwhitelightordinaryendoscopyimageswithanartificialintelligencemodelandtensorflowchart AT yutzuwang acolonialserratedpolypclassificationmodelusingwhitelightordinaryendoscopyimageswithanartificialintelligencemodelandtensorflowchart AT chihuanwu acolonialserratedpolypclassificationmodelusingwhitelightordinaryendoscopyimageswithanartificialintelligencemodelandtensorflowchart AT changfukuo acolonialserratedpolypclassificationmodelusingwhitelightordinaryendoscopyimageswithanartificialintelligencemodelandtensorflowchart AT haotsaicheng acolonialserratedpolypclassificationmodelusingwhitelightordinaryendoscopyimageswithanartificialintelligencemodelandtensorflowchart AT shuweihuang acolonialserratedpolypclassificationmodelusingwhitelightordinaryendoscopyimageswithanartificialintelligencemodelandtensorflowchart AT chiehlee acolonialserratedpolypclassificationmodelusingwhitelightordinaryendoscopyimageswithanartificialintelligencemodelandtensorflowchart AT tsunghsingchen colonialserratedpolypclassificationmodelusingwhitelightordinaryendoscopyimageswithanartificialintelligencemodelandtensorflowchart AT yutzuwang colonialserratedpolypclassificationmodelusingwhitelightordinaryendoscopyimageswithanartificialintelligencemodelandtensorflowchart AT chihuanwu colonialserratedpolypclassificationmodelusingwhitelightordinaryendoscopyimageswithanartificialintelligencemodelandtensorflowchart AT changfukuo colonialserratedpolypclassificationmodelusingwhitelightordinaryendoscopyimageswithanartificialintelligencemodelandtensorflowchart AT haotsaicheng colonialserratedpolypclassificationmodelusingwhitelightordinaryendoscopyimageswithanartificialintelligencemodelandtensorflowchart AT shuweihuang colonialserratedpolypclassificationmodelusingwhitelightordinaryendoscopyimageswithanartificialintelligencemodelandtensorflowchart AT chiehlee colonialserratedpolypclassificationmodelusingwhitelightordinaryendoscopyimageswithanartificialintelligencemodelandtensorflowchart |