Enhanced Transfer Learning Through Medical Imaging and Patient Demographic Data Fusion

11/29/2021
by   Spencer A. Thomas, et al.
0

In this work we examine the performance enhancement in classification of medical imaging data when image features are combined with associated non-image data. We compare the performance of eight state-of-the-art deep neural networks in classification tasks when using only image features, compared to when these are combined with patient metadata. We utilise transfer learning with networks pretrained on ImageNet used directly as feature extractors and fine tuned on the target domain. Our experiments show that performance can be significantly enhanced with the inclusion of metadata and use interpretability methods to identify which features lead to these enhancements. Furthermore, our results indicate that the performance enhancement for natural medical imaging (e.g. optical images) benefit most from direct use of pre-trained models, whereas non natural images (e.g. representations of non imaging data) benefit most from fine tuning pre-trained networks. These enhancements come at a negligible additional cost in computation time, and therefore is a practical method for other applications.

READ FULL TEXT

page 1

page 4

research
10/08/2021

Combining Image Features and Patient Metadata to Enhance Transfer Learning

In this work, we compare the performance of six state-of-the-art deep ne...
research
10/13/2021

MedNet: Pre-trained Convolutional Neural Network Model for the Medical Imaging Tasks

Deep Learning (DL) requires a large amount of training data to provide q...
research
09/09/2022

Saliency Guided Adversarial Training for Learning Generalizable Features with Applications to Medical Imaging Classification System

This work tackles a central machine learning problem of performance degr...
research
06/13/2021

HistoTransfer: Understanding Transfer Learning for Histopathology

Advancement in digital pathology and artificial intelligence has enabled...
research
10/20/2020

ivadomed: A Medical Imaging Deep Learning Toolbox

ivadomed is an open-source Python package for designing, end-to-end trai...
research
02/03/2018

AFT*: Integrating Active Learning and Transfer Learning to Reduce Annotation Efforts

The splendid success of convolutional neural networks (CNNs) in computer...
research
05/27/2023

FoPro-KD: Fourier Prompted Effective Knowledge Distillation for Long-Tailed Medical Image Recognition

Transfer learning is a promising technique for medical image classificat...

Please sign up or login with your details

Forgot password? Click here to reset