Classification of Colorectal Cancer Polyps via Transfer Learning and Vision-Based Tactile Sensing
This work addresses colorectal cancer detection for medical applications, but it is incremental as it applies existing methods to new sensor data.
The study tackled the high early-detection miss rate of colorectal cancer polyps by using transfer learning and machine learning classifiers on 3D textural images from a vision-based tactile sensor, achieving quantitative evaluation with various statistical metrics on 48 fabricated polyp phantoms.
In this study, to address the current high earlydetection 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.