Cargando…
The intersection of video capsule endoscopy and artificial intelligence: addressing unique challenges using machine learning
INTRODUCTION: Technical burdens and time-intensive review processes limit the practical utility of video capsule endoscopy (VCE). Artificial intelligence (AI) is poised to address these limitations, but the intersection of AI and VCE reveals challenges that must first be overcome. We identified five...
Autores principales: | , , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Cornell University
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10473821/ https://www.ncbi.nlm.nih.gov/pubmed/37664408 |
_version_ | 1785100342365519872 |
---|---|
author | Guleria, Shan Schwartz, Benjamin Sharma, Yash Fernandes, Philip Jablonski, James Adewole, Sodiq Srivastava, Sanjana Rhoads, Fisher Porter, Michael Yeghyayan, Michelle Hyatt, Dylan Copland, Andrew Ehsan, Lubaina Brown, Donald Syed, Sana |
author_facet | Guleria, Shan Schwartz, Benjamin Sharma, Yash Fernandes, Philip Jablonski, James Adewole, Sodiq Srivastava, Sanjana Rhoads, Fisher Porter, Michael Yeghyayan, Michelle Hyatt, Dylan Copland, Andrew Ehsan, Lubaina Brown, Donald Syed, Sana |
author_sort | Guleria, Shan |
collection | PubMed |
description | INTRODUCTION: Technical burdens and time-intensive review processes limit the practical utility of video capsule endoscopy (VCE). Artificial intelligence (AI) is poised to address these limitations, but the intersection of AI and VCE reveals challenges that must first be overcome. We identified five challenges to address. Challenge #1: VCE data are stochastic and contains significant artifact. Challenge #2: VCE interpretation is cost-intensive. Challenge #3: VCE data are inherently imbalanced. Challenge #4: Existing VCE AIMLT are computationally cumbersome. Challenge #5: Clinicians are hesitant to accept AIMLT that cannot explain their process. METHODS: An anatomic landmark detection model was used to test the application of convolutional neural networks (CNNs) to the task of classifying VCE data. We also created a tool that assists in expert annotation of VCE data. We then created more elaborate models using different approaches including a multi-frame approach, a CNN based on graph representation, and a few-shot approach based on meta-learning. RESULTS: When used on full-length VCE footage, CNNs accurately identified anatomic landmarks (99.1%), with gradient weighted-class activation mapping showing the parts of each frame that the CNN used to make its decision. The graph CNN with weakly supervised learning (accuracy 89.9%, sensitivity of 91.1%), the few-shot model (accuracy 90.8%, precision 91.4%, sensitivity 90.9%), and the multi-frame model (accuracy 97.5%, precision 91.5%, sensitivity 94.8%) performed well. DISCUSSION: Each of these five challenges is addressed, in part, by one of our AI-based models. Our goal of producing high performance using lightweight models that aim to improve clinician confidence was achieved. |
format | Online Article Text |
id | pubmed-10473821 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Cornell University |
record_format | MEDLINE/PubMed |
spelling | pubmed-104738212023-09-02 The intersection of video capsule endoscopy and artificial intelligence: addressing unique challenges using machine learning Guleria, Shan Schwartz, Benjamin Sharma, Yash Fernandes, Philip Jablonski, James Adewole, Sodiq Srivastava, Sanjana Rhoads, Fisher Porter, Michael Yeghyayan, Michelle Hyatt, Dylan Copland, Andrew Ehsan, Lubaina Brown, Donald Syed, Sana ArXiv Article INTRODUCTION: Technical burdens and time-intensive review processes limit the practical utility of video capsule endoscopy (VCE). Artificial intelligence (AI) is poised to address these limitations, but the intersection of AI and VCE reveals challenges that must first be overcome. We identified five challenges to address. Challenge #1: VCE data are stochastic and contains significant artifact. Challenge #2: VCE interpretation is cost-intensive. Challenge #3: VCE data are inherently imbalanced. Challenge #4: Existing VCE AIMLT are computationally cumbersome. Challenge #5: Clinicians are hesitant to accept AIMLT that cannot explain their process. METHODS: An anatomic landmark detection model was used to test the application of convolutional neural networks (CNNs) to the task of classifying VCE data. We also created a tool that assists in expert annotation of VCE data. We then created more elaborate models using different approaches including a multi-frame approach, a CNN based on graph representation, and a few-shot approach based on meta-learning. RESULTS: When used on full-length VCE footage, CNNs accurately identified anatomic landmarks (99.1%), with gradient weighted-class activation mapping showing the parts of each frame that the CNN used to make its decision. The graph CNN with weakly supervised learning (accuracy 89.9%, sensitivity of 91.1%), the few-shot model (accuracy 90.8%, precision 91.4%, sensitivity 90.9%), and the multi-frame model (accuracy 97.5%, precision 91.5%, sensitivity 94.8%) performed well. DISCUSSION: Each of these five challenges is addressed, in part, by one of our AI-based models. Our goal of producing high performance using lightweight models that aim to improve clinician confidence was achieved. Cornell University 2023-08-24 /pmc/articles/PMC10473821/ /pubmed/37664408 Text en https://creativecommons.org/licenses/by/4.0/This work is licensed under a Creative Commons Attribution 4.0 International License (https://creativecommons.org/licenses/by/4.0/) , which allows reusers to distribute, remix, adapt, and build upon the material in any medium or format, so long as attribution is given to the creator. The license allows for commercial use. |
spellingShingle | Article Guleria, Shan Schwartz, Benjamin Sharma, Yash Fernandes, Philip Jablonski, James Adewole, Sodiq Srivastava, Sanjana Rhoads, Fisher Porter, Michael Yeghyayan, Michelle Hyatt, Dylan Copland, Andrew Ehsan, Lubaina Brown, Donald Syed, Sana The intersection of video capsule endoscopy and artificial intelligence: addressing unique challenges using machine learning |
title | The intersection of video capsule endoscopy and artificial intelligence: addressing unique challenges using machine learning |
title_full | The intersection of video capsule endoscopy and artificial intelligence: addressing unique challenges using machine learning |
title_fullStr | The intersection of video capsule endoscopy and artificial intelligence: addressing unique challenges using machine learning |
title_full_unstemmed | The intersection of video capsule endoscopy and artificial intelligence: addressing unique challenges using machine learning |
title_short | The intersection of video capsule endoscopy and artificial intelligence: addressing unique challenges using machine learning |
title_sort | intersection of video capsule endoscopy and artificial intelligence: addressing unique challenges using machine learning |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10473821/ https://www.ncbi.nlm.nih.gov/pubmed/37664408 |
work_keys_str_mv | AT guleriashan theintersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT schwartzbenjamin theintersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT sharmayash theintersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT fernandesphilip theintersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT jablonskijames theintersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT adewolesodiq theintersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT srivastavasanjana theintersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT rhoadsfisher theintersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT portermichael theintersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT yeghyayanmichelle theintersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT hyattdylan theintersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT coplandandrew theintersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT ehsanlubaina theintersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT browndonald theintersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT syedsana theintersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT guleriashan intersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT schwartzbenjamin intersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT sharmayash intersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT fernandesphilip intersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT jablonskijames intersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT adewolesodiq intersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT srivastavasanjana intersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT rhoadsfisher intersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT portermichael intersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT yeghyayanmichelle intersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT hyattdylan intersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT coplandandrew intersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT ehsanlubaina intersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT browndonald intersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning AT syedsana intersectionofvideocapsuleendoscopyandartificialintelligenceaddressinguniquechallengesusingmachinelearning |