Transfer Learning for Domain Adaptation in MRI: Application in Brain Lesion Segmentation

Abstract

Magnetic Resonance Imaging (MRI) is widely used in routine clinical diagnosis and treatment. However, variations in MRI acquisition protocols result in different appearances of normal and diseased tissue in the images. Convolutional neural networks (CNNs), which have shown to be successful in many medical image analysis tasks, are typically sensitive to the variations in imaging protocols. Therefore, in many cases, networks trained on data acquired with one MRI protocol, do not perform satisfactorily on data acquired with different protocols. This limits the use of models trained with large annotated legacy datasets on a new dataset with a different domain which is often a recurring situation in clinical settings. In this study, we aim to answer the following central questions regarding domain adaptation in medical image analysis: Given a fitted legacy model, 1) How much data from the new domain is required for a decent adaptation of the original network?; and, 2) What portion of the pre-trained model parameters should be retrained given a certain number of the new domain training samples? To address these questions, we conducted extensive experiments in white matter hyperintensity segmentation task. We trained a CNN on legacy MR images of brain and evaluated the performance of the domain-adapted network on the same task with images from a different domain. We then compared the performance of the model to the surrogate scenarios where either the same trained network is used or a new network is trained from scratch on the new dataset.The domain-adapted network tuned only by two training examples achieved a Dice score of 0.63 substantially outperforming a similar network trained on the same set of examples from scratch.

8 pages, 3 figures

References in corpus (4)

• A Survey on Deep Learning in Medical Image Analysis
• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?
• Deep Multi-scale Location-aware 3D Convolutional Neural Networks for Automated Detection of Lacunes of Presumed Vascular Origin

Cited by in corpus (16)

• Domain Adaptation for Medical Image Analysis: A Survey
• Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentation
• Patch-based Output Space Adversarial Learning for Joint Optic Disc and Cup Segmentation
• Machine Learning Techniques for Biomedical Image Segmentation: An Overview of Technical Aspects and Introduction to State-of-Art Applications
• Robust machine learning segmentation for large-scale analysis of heterogeneous clinical brain MRI datasets
• Boundary-weighted Domain Adaptive Neural Network for Prostate MR Image Segmentation
• Transfer Learning in Magnetic Resonance Brain Imaging: a Systematic Review
• LE-UDA: Label-efficient unsupervised domain adaptation for medical image segmentation
• Leveraging Regular Fundus Images for Training UWF Fundus Diagnosis Models via Adversarial Learning and Pseudo-Labeling
• Scribble-based Domain Adaptation via Co-segmentation
• Brain MRI Tumor Segmentation with Adversarial Networks
• An Inductive Transfer Learning Approach using Cycle-consistent Adversarial Domain Adaptation with Application to Brain Tumor Segmentation
• Targeted Gradient Descent: A Novel Method for Convolutional Neural Networks Fine-tuning and Online-learning
• Improved inter-scanner MS lesion segmentation by adversarial training on longitudinal data
• Towards Ultrafast MRI via Extreme k-Space Undersampling and Superresolution
• RootPainter3D: Interactive-machine-learning enables rapid and accurate contouring for radiotherapy