AI-based visualization of loose connective tissue as a dissectable layer in gastrointestinal surgery
Abstract We aimed to develop an AI model that recognizes and displays loose connective tissue as a dissectable layer in real-time during gastrointestinal surgery and to evaluate its performance, including feasibility for clinical application. Training data were created under the supervision of gastr...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-84044-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract We aimed to develop an AI model that recognizes and displays loose connective tissue as a dissectable layer in real-time during gastrointestinal surgery and to evaluate its performance, including feasibility for clinical application. Training data were created under the supervision of gastrointestinal surgeons. Test images and videos were randomly sampled and model performance was evaluated visually by 10 external gastrointestinal surgeons. The mean Dice coefficient of the 50 images was 0.46. The AI model could detect at least 75% of the loose connective tissue in 91.8% of the images (459/500 responses). False positives were found for 52.6% of the images, but most were not judged significant enough to affect surgical judgment. When comparing the surgeon’s annotation with the AI prediction image, 5 surgeons judged the AI image was closer to their own recognition. When viewing the AI video and raw video side-by-side, surgeons judged that in 99% of the AI videos, visualization was improved and stress levels were acceptable when viewing the AI prediction display. The AI model developed demonstrated performance at a level approaching that of a gastrointestinal surgeon. Such visualization of a safe dissectable layer may help to reduce intraoperative recognition errors and surgical complications. |
|---|---|
| ISSN: | 2045-2322 |