Unique ID issued by UMIN | UMIN000044609 |
---|---|
Receipt number | R000050954 |
Scientific Title | Evaluation of computer-aided diagnosis system for colonic narrow-band imaging using artificial intelligence |
Date of disclosure of the study information | 2021/08/01 |
Last modified on | 2021/06/21 14:23:30 |
Evaluation of AI-assisted diagnosis software for colonoscopy images.
Evaluation of AI-assisted diagnosis software
Evaluation of computer-aided diagnosis system for colonic narrow-band imaging using artificial intelligence
Evaluation of AI for colonic NBI images
Japan |
Colonic epithelial lesion
Gastroenterology |
Malignancy
NO
To develop and evaluate a CAD system that presents whether the target lesion is an adenoma, non-adenoma, or sessile serrated adenoma when non-magnified and near-magnified images of NBI.
Efficacy
Sensitivity of AI for colonic adenoma (=<10mm)
1. Specificity, accuracy, NPV and PPV of AI for colonic adenoma (=<10mm)
2. Sensitivity, specificity, accuracy, NPV and PPV of AI for colonic non-neoplasms (=<10mm)
3. Sensitivity, specificity, accuracy, NPV and PPV of AI for colonic sesile serrated adenoma/polyp (=<10mm)
4. Sensitivity, specificity, accuracy, NPV and PPV of AI by the morphology of the lesions.
Observational
20 | years-old | <= |
Not applicable |
Male and Female
1. 20 years old or older at the time of examination
2. Lesions with clear NBI images
3. Lesions that have been resected and pathological diagnosis has been obtained
1. Patients who refuse to participate.
2. Lesions in patients with inflammatory bowel disease in a broad sense
3. Lesions not captured by NBI imaging
400
1st name | Masashi |
Middle name | |
Last name | Misawa |
Showa Universit Northen Yokohama Hospital
Digestive Disease Center
224-8503
Chigasaki chuo 35-1, Tsuduki, Yokohama
045-949-7000
mmisawa@med.showa-u.ac.jp
1st name | Masashi |
Middle name | |
Last name | Misawa |
Showa University Northern Yokohama Hospital
Digestive Disease Center
2248503
Chigasaki-chuo 35-1, Tsuduki, Yokohama
045-949-7000
mmisawa@med.showa-u.ac.jp
Showa University Northern Yokohama Hospital
JSPS KAKENHI
Japanese Governmental office
Showa University Northern Yokohama Hospital
Chigasaki-chuo 35-1, Tsuduki, Yokohama
045-949-7000
irb02syh@ofc.showa-u.ac.jp
NO
2021 | Year | 08 | Month | 01 | Day |
Unpublished
Open public recruiting
2020 | Year | 08 | Month | 19 | Day |
2020 | Year | 09 | Month | 16 | Day |
2021 | Year | 06 | Month | 01 | Day |
2021 | Year | 12 | Month | 31 | Day |
Colonoscopy images taken from January 2015 to the end of June 2021 will be included in the study. A part of the images (except for the last month of the study period) will be used for training of the CAD. The lesions taken during the last month of the study period that are not used for training will be used as test images for the CAD. The test images will be selected in accordance with the following criteria. Pathological diagnosis must be obtained for the test images, but pathological diagnosis is not required for the training images.
2021 | Year | 06 | Month | 21 | Day |
2021 | Year | 06 | Month | 21 | Day |
Value
https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000050954