A novel AI device for real-time optical characterization of colorectal polyps
Abstract Accurate in-vivo optical characterization of colorectal polyps is key to select the optimal treatment regimen during colonoscopy. However, reported accuracies vary widely among endoscopists. We developed a novel intelligent medical device able to seamlessly operate in real-time using conven...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-06-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-022-00633-6 |
| _version_ | 1827614422812590080 |
|---|---|
| author | Carlo Biffi Pietro Salvagnini Nhan Ngo Dinh Cesare Hassan Prateek Sharma GI Genius CADx Study Group Andrea Cherubini |
| author_facet | Carlo Biffi Pietro Salvagnini Nhan Ngo Dinh Cesare Hassan Prateek Sharma GI Genius CADx Study Group Andrea Cherubini |
| author_sort | Carlo Biffi |
| collection | DOAJ |
| description | Abstract Accurate in-vivo optical characterization of colorectal polyps is key to select the optimal treatment regimen during colonoscopy. However, reported accuracies vary widely among endoscopists. We developed a novel intelligent medical device able to seamlessly operate in real-time using conventional white light (WL) endoscopy video stream without virtual chromoendoscopy (blue light, BL). In this work, we evaluated the standalone performance of this computer-aided diagnosis device (CADx) on a prospectively acquired dataset of unaltered colonoscopy videos. An international group of endoscopists performed optical characterization of each polyp acquired in a prospective study, blinded to both histology and CADx result, by means of an online platform enabling careful video assessment. Colorectal polyps were categorized by reviewers, subdivided into 10 experts and 11 non-experts endoscopists, and by the CADx as either “adenoma” or “non-adenoma”. A total of 513 polyps from 165 patients were assessed. CADx accuracy in WL was found comparable to the accuracy of expert endoscopists (CADxWL/Exp; OR 1.211 [0.766–1.915]) using histopathology as the reference standard. Moreover, CADx accuracy in WL was found superior to the accuracy of non-expert endoscopists (CADxWL/NonExp; OR 1.875 [1.191–2.953]), and CADx accuracy in BL was found comparable to it (CADxBL/CADxWL; OR 0.886 [0.612–1.282]). The proposed intelligent device shows the potential to support non-expert endoscopists in systematically reaching the performances of expert endoscopists in optical characterization. |
| first_indexed | 2024-03-09T08:55:39Z |
| format | Article |
| id | doaj.art-ed4d822ebac94c70a6dbb4e626ff3565 |
| institution | Directory Open Access Journal |
| issn | 2398-6352 |
| language | English |
| last_indexed | 2024-03-09T08:55:39Z |
| publishDate | 2022-06-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj.art-ed4d822ebac94c70a6dbb4e626ff35652023-12-02T13:23:36ZengNature Portfolionpj Digital Medicine2398-63522022-06-01511810.1038/s41746-022-00633-6A novel AI device for real-time optical characterization of colorectal polypsCarlo Biffi0Pietro Salvagnini1Nhan Ngo Dinh2Cesare Hassan3Prateek Sharma4GI Genius CADx Study GroupAndrea Cherubini5Artificial Intelligence Group, Cosmo AI/LinkverseArtificial Intelligence Group, Cosmo AI/LinkverseArtificial Intelligence Group, Cosmo AI/LinkverseGastroenterology Unit, Nuovo Regina Margherita HospitalVA Medical CenterArtificial Intelligence Group, Cosmo AI/LinkverseAbstract Accurate in-vivo optical characterization of colorectal polyps is key to select the optimal treatment regimen during colonoscopy. However, reported accuracies vary widely among endoscopists. We developed a novel intelligent medical device able to seamlessly operate in real-time using conventional white light (WL) endoscopy video stream without virtual chromoendoscopy (blue light, BL). In this work, we evaluated the standalone performance of this computer-aided diagnosis device (CADx) on a prospectively acquired dataset of unaltered colonoscopy videos. An international group of endoscopists performed optical characterization of each polyp acquired in a prospective study, blinded to both histology and CADx result, by means of an online platform enabling careful video assessment. Colorectal polyps were categorized by reviewers, subdivided into 10 experts and 11 non-experts endoscopists, and by the CADx as either “adenoma” or “non-adenoma”. A total of 513 polyps from 165 patients were assessed. CADx accuracy in WL was found comparable to the accuracy of expert endoscopists (CADxWL/Exp; OR 1.211 [0.766–1.915]) using histopathology as the reference standard. Moreover, CADx accuracy in WL was found superior to the accuracy of non-expert endoscopists (CADxWL/NonExp; OR 1.875 [1.191–2.953]), and CADx accuracy in BL was found comparable to it (CADxBL/CADxWL; OR 0.886 [0.612–1.282]). The proposed intelligent device shows the potential to support non-expert endoscopists in systematically reaching the performances of expert endoscopists in optical characterization.https://doi.org/10.1038/s41746-022-00633-6 |
| spellingShingle | Carlo Biffi Pietro Salvagnini Nhan Ngo Dinh Cesare Hassan Prateek Sharma GI Genius CADx Study Group Andrea Cherubini A novel AI device for real-time optical characterization of colorectal polyps npj Digital Medicine |
| title | A novel AI device for real-time optical characterization of colorectal polyps |
| title_full | A novel AI device for real-time optical characterization of colorectal polyps |
| title_fullStr | A novel AI device for real-time optical characterization of colorectal polyps |
| title_full_unstemmed | A novel AI device for real-time optical characterization of colorectal polyps |
| title_short | A novel AI device for real-time optical characterization of colorectal polyps |
| title_sort | novel ai device for real time optical characterization of colorectal polyps |
| url | https://doi.org/10.1038/s41746-022-00633-6 |
| work_keys_str_mv | AT carlobiffi anovelaideviceforrealtimeopticalcharacterizationofcolorectalpolyps AT pietrosalvagnini anovelaideviceforrealtimeopticalcharacterizationofcolorectalpolyps AT nhanngodinh anovelaideviceforrealtimeopticalcharacterizationofcolorectalpolyps AT cesarehassan anovelaideviceforrealtimeopticalcharacterizationofcolorectalpolyps AT prateeksharma anovelaideviceforrealtimeopticalcharacterizationofcolorectalpolyps AT gigeniuscadxstudygroup anovelaideviceforrealtimeopticalcharacterizationofcolorectalpolyps AT andreacherubini anovelaideviceforrealtimeopticalcharacterizationofcolorectalpolyps AT carlobiffi novelaideviceforrealtimeopticalcharacterizationofcolorectalpolyps AT pietrosalvagnini novelaideviceforrealtimeopticalcharacterizationofcolorectalpolyps AT nhanngodinh novelaideviceforrealtimeopticalcharacterizationofcolorectalpolyps AT cesarehassan novelaideviceforrealtimeopticalcharacterizationofcolorectalpolyps AT prateeksharma novelaideviceforrealtimeopticalcharacterizationofcolorectalpolyps AT gigeniuscadxstudygroup novelaideviceforrealtimeopticalcharacterizationofcolorectalpolyps AT andreacherubini novelaideviceforrealtimeopticalcharacterizationofcolorectalpolyps |