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

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...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports 2017-07, Vol.7 (1), p.5110-12, Article 5110
Main Authors: Ghafoorian, Mohsen, Karssemeijer, Nico, Heskes, Tom, van Uden, Inge W. M., Sanchez, Clara I., Litjens, Geert, de Leeuw, Frank-Erik, van Ginneken, Bram, Marchiori, Elena, Platel, Bram
Format: Article
Language:English
Subjects:
692/53/2421
692/617/375/599
Aged
Aged, 80 and over
Computer vision
Decision Making
Female
Humanities and Social Sciences
Humans
Image processing
Image Processing, Computer-Assisted
Information processing
Magnetic Resonance Imaging
Male
Middle Aged
multidisciplinary
Neural networks
Neural Networks (Computer)
Neuroimaging
Science
Science (multidisciplinary)
Segmentation
Substantia alba
White Matter - diagnostic imaging
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 handcrafted features as well as CNNs that do not integrate location information. On a test set of 50 scans, the best configuration of our networks obtained a Dice score of 0.792, compared to 0.805 for an independent human observer. Performance levels of the machine and the independent human observer were not statistically significantly different (p-value = 0.06).
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-017-05300-5