TY - GEN
T1 - Towards Reliable Colorectal Cancer Polyps Classification via Vision Based Tactile Sensing and Confidence-Calibrated Neural Networks
AU - Kapuria, Siddhartha
AU - Mohanraj, Tarunraj G.
AU - Venkatayogi, Nethra
AU - Kara, Ozdemir Can
AU - Hirata, Yuki
AU - Minot, Patrick
AU - Kapusta, Ariel
AU - Ikoma, Naruhiko
AU - Alambeigi, Farshid
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - In this study, toward addressing the over-confident outputs of existing artificial intelligence-based colorectal cancer (CRC) polyp classification techniques, we propose a confidence-calibrated residual neural network. Utilizing a novel vision-based tactile sensing (VS-TS) system and unique CRC polyp phantoms, we demonstrate that traditional metrics such as accuracy and precision are not sufficient to encapsulate model performance for handling a sensitive CRC polyp diagnosis. To this end, we develop a residual neural network classifier and address its over-confident outputs for CRC polyps classification via the post-processing method of temperature scaling. To evaluate the proposed method, we introduce noise and blur to the obtained textural images of the VSTS and test the model's reliability for non-ideal inputs through reliability diagrams and other statistical metrics.
AB - In this study, toward addressing the over-confident outputs of existing artificial intelligence-based colorectal cancer (CRC) polyp classification techniques, we propose a confidence-calibrated residual neural network. Utilizing a novel vision-based tactile sensing (VS-TS) system and unique CRC polyp phantoms, we demonstrate that traditional metrics such as accuracy and precision are not sufficient to encapsulate model performance for handling a sensitive CRC polyp diagnosis. To this end, we develop a residual neural network classifier and address its over-confident outputs for CRC polyps classification via the post-processing method of temperature scaling. To evaluate the proposed method, we introduce noise and blur to the obtained textural images of the VSTS and test the model's reliability for non-ideal inputs through reliability diagrams and other statistical metrics.
UR - http://www.scopus.com/inward/record.url?scp=85161852550&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85161852550&partnerID=8YFLogxK
U2 - 10.1109/ISMR57123.2023.10130197
DO - 10.1109/ISMR57123.2023.10130197
M3 - Conference contribution
AN - SCOPUS:85161852550
T3 - 2023 International Symposium on Medical Robotics, ISMR 2023
BT - 2023 International Symposium on Medical Robotics, ISMR 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 International Symposium on Medical Robotics, ISMR 2023
Y2 - 19 April 2023 through 21 April 2023
ER -