What do Deep Neural Networks Learn in Medical Images?

08/01/2022
by   Beentherize, et al.
98

Deep learning is increasingly gaining rapid adoption in healthcare to help improve patient outcomes. This is more so in medical image analysis which requires extensive training to gain the requisite expertise to become a trusted practitioner. However, while deep learning techniques have continued to provide state-of-the-art predictive performance, one of the primary challenges that stands to hinder this progress in healthcare is the opaque nature of the inference mechanism of these models. So, attribution has a vital role in building confidence in stakeholders for the predictions made by deep learning models to inform clinical decisions. This work seeks to answer the question: what do deep neural network models learn in medical images? In that light, we present a novel attribution framework using adaptive path-based gradient integration techniques. Results show a promising direction of building trust in domain experts to improve healthcare outcomes by allowing them to understand the input-prediction correlative structures, discover new bio-markers, and reveal potential model biases.

READ FULL TEXT

page 14

page 15

page 18

page 19

page 20

research
01/19/2021

Using StyleGAN for Visual Interpretability of Deep Learning Models on Medical Images

As AI-based medical devices are becoming more common in imaging fields l...
research
05/12/2023

Unlocking the Potential of Medical Imaging with ChatGPT's Intelligent Diagnostics

Medical imaging is an essential tool for diagnosing various healthcare d...
research
12/19/2018

A Tour of Unsupervised Deep Learning for Medical Image Analysis

Interpretation of medical images for diagnosis and treatment of complex ...
research
11/27/2018

Using Attribution to Decode Dataset Bias in Neural Network Models for Chemistry

Deep neural networks have achieved state of the art accuracy at classify...
research
09/30/2020

Where Does Trust Break Down? A Quantitative Trust Analysis of Deep Neural Networks via Trust Matrix and Conditional Trust Densities

The advances and successes in deep learning in recent years have led to ...
research
04/05/2021

Jekyll: Attacking Medical Image Diagnostics using Deep Generative Models

Advances in deep neural networks (DNNs) have shown tremendous promise in...
research
11/26/2017

An Introduction to Deep Visual Explanation

The practical impact of deep learning on complex supervised learning pro...

Please sign up or login with your details

Forgot password? Click here to reset