Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities

TL;DR

This paper introduces location-sensitive deep CNN architectures for brain MRI segmentation of white matter hyperintensities, demonstrating improved accuracy by integrating anatomical location information into the models.

Contribution

The authors propose novel CNN architectures that incorporate anatomical location data, significantly enhancing segmentation performance over traditional methods.

Findings

Location-aware CNNs outperform conventional segmentation methods.

Best model achieves a Dice score close to human performance.

Performance difference between machine and human not statistically significant.

Abstract

The anatomical location of imaging features is of crucial importance for accurate diagnosis in many medical tasks. Convolutional neural networks (CNN) have had huge successes in computer vision, but they lack the natural ability to incorporate the anatomical location in their decision making process, hindering success in some medical image analysis tasks. In this paper, to integrate the anatomical location information into the network, we propose several deep CNN architectures that consider multi-scale patches or take explicit location features while training. We apply and compare the proposed architectures for segmentation of white matter hyperintensities in brain MR images on a large dataset. As a result, we observe that the CNNs that incorporate location information substantially outperform a conventional segmentation method with hand-crafted features as well as CNNs that do not integrate location information. On a test set of 46 scans, the best configuration of our networks obtained a Dice score of 0.791, compared to 0.797 for an independent human observer. Performance levels of the machine and the independent human observer were not statistically significantly different (p-value=0.17).