TY - GEN
T1 - Classification of Colorectal Cancer Polyps via Transfer Learning and Vision-Based Tactile Sensing
AU - Venkatayogi, Nethra
AU - Kara, Ozdemir Can
AU - Bonyun, Jeff
AU - Ikoma, Naruhiko
AU - Alambeigi, Farshid
N1 - Funding Information:
*Research reported in this publication was supported by the University of Texas at Austin and MD Anderson Cancer Center Pilot Seed Grant.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - In this study, to address the current high early-detection miss rate of colorectal cancer (CRC) polyps, we explore the potentials of utilizing transfer learning and machine learning (ML) classifiers to precisely and sensitively classify the type of CRC polyps. Instead of using the common colonoscopic images, we applied three different ML algorithms on the 3D textural image outputs of a unique vision-based surface tactile sensor (VS-TS). To collect realistic textural images of CRC polyps for training the utilized ML classifiers and evaluating their performance, we first designed and additively manufactured 48 types of realistic polyp phantoms with different hardness, type, and textures. Next, the performance of the used three ML algorithms in classifying the type of fabricated polyps was quantitatively evaluated using various statistical metrics.
AB - In this study, to address the current high early-detection miss rate of colorectal cancer (CRC) polyps, we explore the potentials of utilizing transfer learning and machine learning (ML) classifiers to precisely and sensitively classify the type of CRC polyps. Instead of using the common colonoscopic images, we applied three different ML algorithms on the 3D textural image outputs of a unique vision-based surface tactile sensor (VS-TS). To collect realistic textural images of CRC polyps for training the utilized ML classifiers and evaluating their performance, we first designed and additively manufactured 48 types of realistic polyp phantoms with different hardness, type, and textures. Next, the performance of the used three ML algorithms in classifying the type of fabricated polyps was quantitatively evaluated using various statistical metrics.
KW - colorectal cancer
KW - deep residual networks
KW - machine learning
KW - support vector machine
KW - transfer learning
KW - vision-based surface tactile sensor
UR - http://www.scopus.com/inward/record.url?scp=85144056843&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85144056843&partnerID=8YFLogxK
U2 - 10.1109/SENSORS52175.2022.9967308
DO - 10.1109/SENSORS52175.2022.9967308
M3 - Conference contribution
AN - SCOPUS:85144056843
T3 - Proceedings of IEEE Sensors
BT - 2022 IEEE Sensors, SENSORS 2022 - Conference Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE Sensors Conference, SENSORS 2022
Y2 - 30 October 2022 through 2 November 2022
ER -