Robot-Enabled Machine Learning-Based Diagnosis of Gastric Cancer Polyps Using Partial Surface Tactile Imaging

TL;DR

This paper introduces a robotic tactile sensing system combined with machine learning to improve the diagnosis of gastric cancer polyps, overcoming data scarcity and bias issues in traditional methods.

Contribution

It presents a novel integration of a vision-based tactile sensor with a robotic manipulator and a machine learning algorithm for tumor classification, using synthetic data from custom phantoms.

Findings

Successful evaluation of the ML model with synthetic data

Improved classification accuracy under partial sensor contact

Demonstrated advantages of automated data collection

Abstract

In this paper, to collectively address the existing limitations on endoscopic diagnosis of Advanced Gastric Cancer (AGC) Tumors, for the first time, we propose (i) utilization and evaluation of our recently developed Vision-based Tactile Sensor (VTS), and (ii) a complementary Machine Learning (ML) algorithm for classifying tumors using their textural features. Leveraging a seven DoF robotic manipulator and unique custom-designed and additively-manufactured realistic AGC tumor phantoms, we demonstrated the advantages of automated data collection using the VTS addressing the problem of data scarcity and biases encountered in traditional ML-based approaches. Our synthetic-data-trained ML model was successfully evaluated and compared with traditional ML models utilizing various statistical metrics even under mixed morphological characteristics and partial sensor contact.