In vivo computer-aided diagnosis of colorectal polyps using white light endoscopy
Background and study aims Artificial intelligence is currently able to accurately predict the histology of colorectal polyps. However, systems developed to date use complex optical technologies and have not been tested in vivo. The objective of this study was to evaluate the efficacy of a new deep l...
Main Authors: | , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Georg Thieme Verlag KG
2022-09-01
|
Series: | Endoscopy International Open |
Online Access: | http://www.thieme-connect.de/DOI/DOI?10.1055/a-1881-3178 |
_version_ | 1811268188792422400 |
---|---|
author | Ana García-Rodríguez Yael Tudela Henry Córdova Sabela Carballal Ingrid Ordás Leticia Moreira Eva Vaquero Oswaldo Ortiz Liseth Rivero F. Javier Sánchez Miriam Cuatrecasas Maria Pellisé Jorge Bernal Glòria Fernández-Esparrach |
author_facet | Ana García-Rodríguez Yael Tudela Henry Córdova Sabela Carballal Ingrid Ordás Leticia Moreira Eva Vaquero Oswaldo Ortiz Liseth Rivero F. Javier Sánchez Miriam Cuatrecasas Maria Pellisé Jorge Bernal Glòria Fernández-Esparrach |
author_sort | Ana García-Rodríguez |
collection | DOAJ |
description | Background and study aims Artificial intelligence is currently able to accurately predict the histology of colorectal polyps. However, systems developed to date use complex optical technologies and have not been tested in vivo. The objective of this study was to evaluate the efficacy of a new deep learning-based optical diagnosis system, ATENEA, in a real clinical setting using only high-definition white light endoscopy (WLE) and to compare its performance with endoscopists.
Methods ATENEA was prospectively tested in real life on consecutive polyps detected in colorectal cancer screening colonoscopies at Hospital Clínic. No images were discarded, and only WLE was used. The in vivo ATENEA’s prediction (adenoma vs non-adenoma) was compared with the prediction of four staff endoscopists without specific training in optical diagnosis for the study purposes. Endoscopists were blind to the ATENEA output. Histology was the gold standard.
Results Ninety polyps (median size: 5 mm, range: 2–25) from 31 patients were included of which 69 (76.7 %) were adenomas. ATENEA correctly predicted the histology in 63 of 69 (91.3 %, 95 % CI: 82 %–97 %) adenomas and 12 of 21 (57.1 %, 95 % CI: 34 %–78 %) non-adenomas while endoscopists made correct predictions in 52 of 69 (75.4 %, 95 % CI: 60 %–85 %) and 20 of 21 (95.2 %, 95 % CI: 76 %–100 %), respectively. The global accuracy was 83.3 % (95 % CI: 74%–90 %) and 80 % (95 % CI: 70 %–88 %) for ATENEA and endoscopists, respectively.
Conclusion ATENEA can accurately be used for in vivo characterization of colorectal polyps, enabling the endoscopist to make direct decisions. ATENEA showed a global accuracy similar to that of endoscopists despite an unsatisfactory performance for non-adenomatous lesions. |
first_indexed | 2024-04-12T21:17:21Z |
format | Article |
id | doaj.art-a56f9f13fef54de2acd35a3e9993011a |
institution | Directory Open Access Journal |
issn | 2364-3722 2196-9736 |
language | English |
last_indexed | 2024-04-12T21:17:21Z |
publishDate | 2022-09-01 |
publisher | Georg Thieme Verlag KG |
record_format | Article |
series | Endoscopy International Open |
spelling | doaj.art-a56f9f13fef54de2acd35a3e9993011a2022-12-22T03:16:24ZengGeorg Thieme Verlag KGEndoscopy International Open2364-37222196-97362022-09-011009E1201E120710.1055/a-1881-3178In vivo computer-aided diagnosis of colorectal polyps using white light endoscopyAna García-Rodríguez0Yael Tudela1Henry Córdova2Sabela Carballal3Ingrid Ordás4Leticia Moreira5Eva Vaquero6Oswaldo Ortiz7Liseth Rivero8F. Javier Sánchez9Miriam Cuatrecasas10Maria Pellisé11Jorge Bernal12Glòria Fernández-Esparrach13Endoscopy Unit. Gastroenterology Department. ICMDiM. Hospital Clínic of Barcelona. University of Barcelona, Barcelona, Catalonia, SpainComputer Science Department. Autonomous University of Barcelona and Computer Vision Center, Barcelona, Catalonia, SpainEndoscopy Unit. Gastroenterology Department. ICMDiM. Hospital Clínic of Barcelona. University of Barcelona, Barcelona, Catalonia, SpainEndoscopy Unit. Gastroenterology Department. ICMDiM. Hospital Clínic of Barcelona. University of Barcelona, Barcelona, Catalonia, SpainEndoscopy Unit. Gastroenterology Department. ICMDiM. Hospital Clínic of Barcelona. University of Barcelona, Barcelona, Catalonia, SpainEndoscopy Unit. Gastroenterology Department. ICMDiM. Hospital Clínic of Barcelona. University of Barcelona, Barcelona, Catalonia, SpainEndoscopy Unit. Gastroenterology Department. ICMDiM. Hospital Clínic of Barcelona. University of Barcelona, Barcelona, Catalonia, SpainEndoscopy Unit. Gastroenterology Department. ICMDiM. Hospital Clínic of Barcelona. University of Barcelona, Barcelona, Catalonia, SpainEndoscopy Unit. Gastroenterology Department. ICMDiM. Hospital Clínic of Barcelona. University of Barcelona, Barcelona, Catalonia, SpainComputer Science Department. Autonomous University of Barcelona and Computer Vision Center, Barcelona, Catalonia, SpainIDIBAPS, Barcelona, Catalonia, SpainEndoscopy Unit. Gastroenterology Department. ICMDiM. Hospital Clínic of Barcelona. University of Barcelona, Barcelona, Catalonia, SpainComputer Science Department. Autonomous University of Barcelona and Computer Vision Center, Barcelona, Catalonia, SpainEndoscopy Unit. Gastroenterology Department. ICMDiM. Hospital Clínic of Barcelona. University of Barcelona, Barcelona, Catalonia, SpainBackground and study aims Artificial intelligence is currently able to accurately predict the histology of colorectal polyps. However, systems developed to date use complex optical technologies and have not been tested in vivo. The objective of this study was to evaluate the efficacy of a new deep learning-based optical diagnosis system, ATENEA, in a real clinical setting using only high-definition white light endoscopy (WLE) and to compare its performance with endoscopists. Methods ATENEA was prospectively tested in real life on consecutive polyps detected in colorectal cancer screening colonoscopies at Hospital Clínic. No images were discarded, and only WLE was used. The in vivo ATENEA’s prediction (adenoma vs non-adenoma) was compared with the prediction of four staff endoscopists without specific training in optical diagnosis for the study purposes. Endoscopists were blind to the ATENEA output. Histology was the gold standard. Results Ninety polyps (median size: 5 mm, range: 2–25) from 31 patients were included of which 69 (76.7 %) were adenomas. ATENEA correctly predicted the histology in 63 of 69 (91.3 %, 95 % CI: 82 %–97 %) adenomas and 12 of 21 (57.1 %, 95 % CI: 34 %–78 %) non-adenomas while endoscopists made correct predictions in 52 of 69 (75.4 %, 95 % CI: 60 %–85 %) and 20 of 21 (95.2 %, 95 % CI: 76 %–100 %), respectively. The global accuracy was 83.3 % (95 % CI: 74%–90 %) and 80 % (95 % CI: 70 %–88 %) for ATENEA and endoscopists, respectively. Conclusion ATENEA can accurately be used for in vivo characterization of colorectal polyps, enabling the endoscopist to make direct decisions. ATENEA showed a global accuracy similar to that of endoscopists despite an unsatisfactory performance for non-adenomatous lesions.http://www.thieme-connect.de/DOI/DOI?10.1055/a-1881-3178 |
spellingShingle | Ana García-Rodríguez Yael Tudela Henry Córdova Sabela Carballal Ingrid Ordás Leticia Moreira Eva Vaquero Oswaldo Ortiz Liseth Rivero F. Javier Sánchez Miriam Cuatrecasas Maria Pellisé Jorge Bernal Glòria Fernández-Esparrach In vivo computer-aided diagnosis of colorectal polyps using white light endoscopy Endoscopy International Open |
title | In vivo computer-aided diagnosis of colorectal polyps using white light endoscopy |
title_full | In vivo computer-aided diagnosis of colorectal polyps using white light endoscopy |
title_fullStr | In vivo computer-aided diagnosis of colorectal polyps using white light endoscopy |
title_full_unstemmed | In vivo computer-aided diagnosis of colorectal polyps using white light endoscopy |
title_short | In vivo computer-aided diagnosis of colorectal polyps using white light endoscopy |
title_sort | in vivo computer aided diagnosis of colorectal polyps using white light endoscopy |
url | http://www.thieme-connect.de/DOI/DOI?10.1055/a-1881-3178 |
work_keys_str_mv | AT anagarciarodriguez invivocomputeraideddiagnosisofcolorectalpolypsusingwhitelightendoscopy AT yaeltudela invivocomputeraideddiagnosisofcolorectalpolypsusingwhitelightendoscopy AT henrycordova invivocomputeraideddiagnosisofcolorectalpolypsusingwhitelightendoscopy AT sabelacarballal invivocomputeraideddiagnosisofcolorectalpolypsusingwhitelightendoscopy AT ingridordas invivocomputeraideddiagnosisofcolorectalpolypsusingwhitelightendoscopy AT leticiamoreira invivocomputeraideddiagnosisofcolorectalpolypsusingwhitelightendoscopy AT evavaquero invivocomputeraideddiagnosisofcolorectalpolypsusingwhitelightendoscopy AT oswaldoortiz invivocomputeraideddiagnosisofcolorectalpolypsusingwhitelightendoscopy AT lisethrivero invivocomputeraideddiagnosisofcolorectalpolypsusingwhitelightendoscopy AT fjaviersanchez invivocomputeraideddiagnosisofcolorectalpolypsusingwhitelightendoscopy AT miriamcuatrecasas invivocomputeraideddiagnosisofcolorectalpolypsusingwhitelightendoscopy AT mariapellise invivocomputeraideddiagnosisofcolorectalpolypsusingwhitelightendoscopy AT jorgebernal invivocomputeraideddiagnosisofcolorectalpolypsusingwhitelightendoscopy AT gloriafernandezesparrach invivocomputeraideddiagnosisofcolorectalpolypsusingwhitelightendoscopy |