A Deep Dive into Understanding Tumor Foci Classification using Multiparametric MRI Based on Convolutional Neural Network

TL;DR

This paper develops a specialized workflow for classifying prostate tumor foci using multiparametric MRI with deep learning, addressing data scarcity and interpretability issues in medical imaging.

Contribution

It introduces a novel approach combining deep feature extraction with traditional classifiers for small, imbalanced prostate mpMRI datasets and explores model interpretability.

Findings

Effective feature extraction from deep models for prostate mpMRI

Improved classification performance on small datasets

Insights into deep learning model interpretation for medical images

Abstract

Deep learning models have had a great success in disease classifications using large data pools of skin cancer images or lung X-rays. However, data scarcity has been the roadblock of applying deep learning models directly on prostate multiparametric MRI (mpMRI). Although model interpretation has been heavily studied for natural images for the past few years, there has been a lack of interpretation of deep learning models trained on medical images. This work designs a customized workflow for the small and imbalanced data set of prostate mpMRI where features were extracted from a deep learning model and then analyzed by a traditional machine learning classifier. In addition, this work contributes to revealing how deep learning models interpret mpMRI for prostate cancer patients stratification.