Predicting the generalization of computer aided detection (CADe) models for colonoscopy

Abstract Generalizability of AI colonoscopy algorithms is important for wider adoption in clinical practice. However, current techniques for evaluating performance on unseen data require expensive and time-intensive labels. We show that a "Masked Siamese Network" (MSN), trained to predict masked out regions of polyp images without labels, can predict the performance of Computer Aided Detection (CADe) of polyps on colonoscopies, without labels. This holds on Japanese colonoscopies even when MSN is only trained on Israeli colonoscopies, which differ in scoping hardware, endoscope software, screening guidelines, bowel preparation, patient demographics, and the use of techniques such as narrow-band imaging (NBI) and chromoendoscopy (CE). Since our technique uses neither colonoscopy-specific information nor labels, it has the potential to apply to more medical imaging domains.

Authors

Institutions

Publication Details

Journal
Discover Artificial Intelligence
Published
2024-11-19
DOI
https://doi.org/10.1007/s44163-024-00187-4
Primary Topic
Colorectal Cancer Screening and Detection
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Predicting the generalization of computer aided detection (CADe) models for colonoscopy

Hiroshi Nakase, Kaho Kobayashi, Yotam Intrator, Masaaki Miyo et al.
Discover Artificial Intelligence
Colorectal Cancer Screening and Detection
article

Predicting the generalization of computer aided detection (CADe) models for colonoscopy

Hiroshi Nakase, Kaho Kobayashi, Yotam Intrator, Masaaki Miyo, Ehud Rivlin, Atsushi Hamabe, Koji Ando, Ichiro Takemasa, Joseph R. Ledsam, Mitsuhiko Ota, Carson McNeil, Eiji Oki, Hiroki Kayama, Joel Shor, Hiro‐o Yamano, Daisuke Tsurumaru, Roman Goldenberg, Haruei Ogino
article en

Abstract

Abstract Generalizability of AI colonoscopy algorithms is important for wider adoption in clinical practice. However, current techniques for evaluating performance on unseen data require expensive and time-intensive labels. We show that a "Masked Siamese Network" (MSN), trained to predict masked out regions of polyp images without labels, can predict the performance of Computer Aided Detection (CADe) of polyps on colonoscopies, without labels. This holds on Japanese colonoscopies even when MSN is only trained on Israeli colonoscopies, which differ in scoping hardware, endoscope software, screening guidelines, bowel preparation, patient demographics, and the use of techniques such as narrow-band imaging (NBI) and chromoendoscopy (CE). Since our technique uses neither colonoscopy-specific information nor labels, it has the potential to apply to more medical imaging domains.

Discover Artificial IntelligenceVol. 4(1)
Kyushu University (JP), Sapporo Medical University (JP), Somerville Hospital (US), Enzo Life Sciences (United States) (US)
Verily Life Sciences
Openalex Percentile: Top 63%
Colorectal Cancer Screening and Detection
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.