Unique ID issued by UMIN | UMIN000052891 |
---|---|
Receipt number | R000060350 |
Scientific Title | Analysis of Endoscopist's Visual Gaze Pattern during Artificial Intelligence Assisted Colorectal Polyp Detection |
Date of disclosure of the study information | 2023/11/25 |
Last modified on | 2024/03/30 06:44:49 |
Analysis of Endoscopist's Visual Gaze Pattern during Artificial Intelligence Assisted Colorectal Polyp Detection
Analysis of endoscopist's VGP during AI-assisted colorectal polyp detection
Analysis of Endoscopist's Visual Gaze Pattern during Artificial Intelligence Assisted Colorectal Polyp Detection
Analysis of endoscopist's VGP during AI-assisted colorectal polyp detection
Japan |
Colorectal polyp
Gastroenterology |
Others
NO
The aim of this study is to reveal the endoscopist's visual gaze pattern (VGP) in real time during the detection of colorectal polyps with computer-aided detection (CADe).
The detail targets for the analysis are followings;
1. Percentage of lesions automatically detected by CADe that were actually recognized by the endoscopist.
2. Time required for the endoscopist to recognize a lesion that CADe was able to detect automatically.
3. Characteristics of lesions automatically detected by CADe and recognized by the endoscopist.
4. Characteristics of lesions that CADe could automatically detect and the endoscopist could not recognize.
5. Characteristics of lesions that CADe could not automatically detect and endoscopist could recognize.
6. Probability that the endoscopist gazed at the area where CADe falsely detected bubbles or remaining stools.
The main objective of the study is to determine how many of the lesions identified by CADe can be followed by the endoscopist through these analyses. We also aim to characterize which lesions are or are not detectable by CADe. We also aim to evaluate the performance of currently available CADe systems.
Efficacy
Exploratory
Explanatory
Not applicable
Percentage of lesions that CADe was able to automatically detect that were actually recognized by the endoscopist
1. Time taken for the endoscopist to recognize lesions that were automatically detected by CADe
2. Analysis of features of lesions automatically detected by CADe but not recognized by the endoscopist
3. Analysis of lesion features that the endoscopist could recognize but CADe could not automatically detect
4. Percentage of endoscopists gazing at sites where CADe falsely detected bubbles or remaining stools (percentage of endoscopists gazing at CADe falsely detected sites)
5. Analysis of patients background in relation to the percentage that CADe falsely detected sites
6. Analysis of VGP of endoscopists during lesion detection by CADe
Interventional
Single arm
Non-randomized
Open -no one is blinded
Uncontrolled
1
Diagnosis
Device,equipment |
During colonoscopy, CADe (CAD-EYE, Fujifilm Corporation) and the VGP real-time analysis system we developed are operated simultaneously to record and store inspection movies with the endoscopist's VGP displayed on the endoscopic image.
20 | years-old | <= |
90 | years-old | > |
Male and Female
1. Patients who are undergoing colonoscopy.
2. Patients whose age is between 20 and 90 years old.
3. Patients with a performance status (ECOG) of 0 (no limitation in daily activities), 1 (able to perform light tasks but not physical labor), or 2 (able to walk and perform personal activities but not light tasks)
4. Patient's participation in the study has been fully explained to him/her and his/her written consent has been obtained.
1. Patients with a history of inflammatory bowel disease (ulcerative colitis, Crohn's disease, Behcet's disease).
2. Patients with hereditary or non-hereditary gastrointestinal polyposis. 3) Patients with hereditary non-polyposis colorectal cancer (Lynch syndrome).
3. Patients with hereditary non-polyposis colorectal cancer (Lynch syndrome).
4. Patients with known severe diverticular disease of the colon that makes colonoscopy difficult and dangerous.
5. Patients who are unable to take colonoscopy pretreatment medication (laxatives).
6. Patients who are allergic to colonoscopy pretreatment drugs or sedatives.
7. Pregnant women.
8. Those who are breast-feeding.
9. Those who have not obtained consent to participate in the study
10. Those who are deemed inappropriate by the study investigator.
60
1st name | Fumiaki |
Middle name | |
Last name | Ishibashi |
International University of Health and Welfare Ichikawa Hospital
Department of Gastroenterology
272-0827
6-1-14, Konodai, Ichikawa-shi, Chiba
047-375-1111
ishibashi-gast@iuhw.ac.jp
1st name | Fumiaki |
Middle name | |
Last name | Ishibashi |
International University of Health and Welfare Ichikawa Hospital
Department of Gastroenterology
272-0827
6-1-14, Konodai, Ichikawa-shi, Chiba
047-375-1111
ishibashi-gast@iuhw.ac.jp
International University of Health and Welfare
None
Other
International University of Health and Welfare, Chiba Area Ethics Committee
4-3, Kozunomori, Narita-shi, Chiba
0476-20-7708
rinri_md@iuhw.ac.jp
NO
2023 | Year | 11 | Month | 25 | Day |
Unpublished
No longer recruiting
2023 | Year | 08 | Month | 17 | Day |
2023 | Year | 10 | Month | 31 | Day |
2023 | Year | 11 | Month | 01 | Day |
2024 | Year | 03 | Month | 30 | Day |
2024 | Year | 03 | Month | 30 | Day |
2023 | Year | 11 | Month | 24 | Day |
2024 | Year | 03 | Month | 30 | Day |
Value
https://center6.umin.ac.jp/cgi-open-bin/icdr_e/ctr_view.cgi?recptno=R000060350
Research Plan | |
---|---|
Registered date | File name |
Research case data specifications | |
---|---|
Registered date | File name |
Research case data | |
---|---|
Registered date | File name |