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!
|
| _version_ | 1841559599626321920 |
|---|---|
| author | Yuta Kumazu Nao Kobayashi Seigo Senya Yuya Negishi Kazuya Kinoshita Yudai Fukui Kazuhito Mita Tomohiko Osaragi Toshihiro Misumi Hisashi Shinohara |
| author_facet | Yuta Kumazu Nao Kobayashi Seigo Senya Yuya Negishi Kazuya Kinoshita Yudai Fukui Kazuhito Mita Tomohiko Osaragi Toshihiro Misumi Hisashi Shinohara |
| author_sort | Yuta Kumazu |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-657804ca819742b7ab2cdc6a499e8ebf |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-657804ca819742b7ab2cdc6a499e8ebf2025-01-05T12:20:55ZengNature PortfolioScientific Reports2045-23222025-01-011511810.1038/s41598-024-84044-5AI-based visualization of loose connective tissue as a dissectable layer in gastrointestinal surgeryYuta Kumazu0Nao Kobayashi1Seigo Senya2Yuya Negishi3Kazuya Kinoshita4Yudai Fukui5Kazuhito Mita6Tomohiko Osaragi7Toshihiro Misumi8Hisashi Shinohara9Anaut Inc.Anaut Inc.Anaut Inc.Anaut Inc.Department of Frontier Surgery, Graduate School of Medicine, Chiba UniversityDepartment of Gastroenterological Surgery, Toranomon HospitalDepartment of Surgery, Tsudanuma Central General HospitalDepartment of Surgery, Hadano Red Cross HospitalDepartment of Data Science, National Cancer Center Hospital EastDepartment of Gastroenterological Surgery, Hyogo Medical UniversityAbstract 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.https://doi.org/10.1038/s41598-024-84044-5GastrectomyColorectal surgeryInguinal hernia repairAIDissectable layerLoose connective tissue |
| spellingShingle | Yuta Kumazu Nao Kobayashi Seigo Senya Yuya Negishi Kazuya Kinoshita Yudai Fukui Kazuhito Mita Tomohiko Osaragi Toshihiro Misumi Hisashi Shinohara AI-based visualization of loose connective tissue as a dissectable layer in gastrointestinal surgery Scientific Reports Gastrectomy Colorectal surgery Inguinal hernia repair AI Dissectable layer Loose connective tissue |
| title | AI-based visualization of loose connective tissue as a dissectable layer in gastrointestinal surgery |
| title_full | AI-based visualization of loose connective tissue as a dissectable layer in gastrointestinal surgery |
| title_fullStr | AI-based visualization of loose connective tissue as a dissectable layer in gastrointestinal surgery |
| title_full_unstemmed | AI-based visualization of loose connective tissue as a dissectable layer in gastrointestinal surgery |
| title_short | AI-based visualization of loose connective tissue as a dissectable layer in gastrointestinal surgery |
| title_sort | ai based visualization of loose connective tissue as a dissectable layer in gastrointestinal surgery |
| topic | Gastrectomy Colorectal surgery Inguinal hernia repair AI Dissectable layer Loose connective tissue |
| url | https://doi.org/10.1038/s41598-024-84044-5 |
| work_keys_str_mv | AT yutakumazu aibasedvisualizationoflooseconnectivetissueasadissectablelayeringastrointestinalsurgery AT naokobayashi aibasedvisualizationoflooseconnectivetissueasadissectablelayeringastrointestinalsurgery AT seigosenya aibasedvisualizationoflooseconnectivetissueasadissectablelayeringastrointestinalsurgery AT yuyanegishi aibasedvisualizationoflooseconnectivetissueasadissectablelayeringastrointestinalsurgery AT kazuyakinoshita aibasedvisualizationoflooseconnectivetissueasadissectablelayeringastrointestinalsurgery AT yudaifukui aibasedvisualizationoflooseconnectivetissueasadissectablelayeringastrointestinalsurgery AT kazuhitomita aibasedvisualizationoflooseconnectivetissueasadissectablelayeringastrointestinalsurgery AT tomohikoosaragi aibasedvisualizationoflooseconnectivetissueasadissectablelayeringastrointestinalsurgery AT toshihiromisumi aibasedvisualizationoflooseconnectivetissueasadissectablelayeringastrointestinalsurgery AT hisashishinohara aibasedvisualizationoflooseconnectivetissueasadissectablelayeringastrointestinalsurgery |