AI-assisted dynamic tissue evaluation for early bowel cancer diagnosis using a vibrational capsule

Abstract

With early sign of bowel cancer being changes in affected lesions biomechanical properties, an AI-assisted dynamic tissue evaluation is proposed for early bowel cancer diagnosis. Dynamic signals from a self-propelled vibrational capsule in contact with in-situ bowel lesions were processed and analysed for features that may be indicative of biomechanical changes in the lesions. Different combinations of the features were used to develop different lesion characterisation models. Supervised classification using Multi-Layer Perceptron (MLP) and Stacking Ensemble networks (SE) was carried out alongside unsupervised classification using K-means clustering. The SE base-learners comprised Support Vector Machine (SVM), Decision Tree, Na¨ıve Bayes and Random Forest. Cross-validation on simulated test data showed that the SEs outperformed their composite base-learners, however, SVM as a base-learner showed tendency to yield greater than 90% accuracy. The MLPs outperformed the SEs in accuracies and in numbers of high-performance models, hence, were the only supervised network used during experimental validation and they yielded an average accuracy of 96.5%. For unsupervised classification, both simulation and experimental data showed that the lesions are best clustered into two categories representing benign and malignant lesions.