Orchestral fully convolutional networks for small lesion segmentation in brain MRI

White matter (WM) lesion identification and segmentation has proved of clinical importance for diagnosis, treatment and neurological outcomes. Convolutional neural networks (CNN) have demonstrated their success for large lesion load segmentation, but are not sensitive to small deep WM and sub-cortic...

Full description

Saved in:
Bibliographic Details
Published in:2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) 2018-04, Vol.2018, p.889-892
Main Authors: Xu, Botian, Chai, Yaqiong, Galarza, Cristina M., Vu, Chau Q., Tamrazi, Benita, Gaonkar, Bilwaj, Macyszyn, Luke, Coates, Thomas D., Lepore, Natasha, Wood, John C.
Format: Article
Language:English
Subjects:
anemia
Convolution
convolutional neural networks
deep learning
Image segmentation
Lesions
Magnetic resonance imaging
segmentation
Three-dimensional displays
Training
White matter
white matter hyperintensities
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:White matter (WM) lesion identification and segmentation has proved of clinical importance for diagnosis, treatment and neurological outcomes. Convolutional neural networks (CNN) have demonstrated their success for large lesion load segmentation, but are not sensitive to small deep WM and sub-cortical lesion segmentation. We propose to use multi-scale and supervised fully convolutional networks (FCN) to segment small WM lesions in 22 anemic patients. The multiple scales enable us to identify the small lesions while reducing many false alarms, and the multi-supervised scheme allows a better management of the unbalanced data. Compared to a single FCN (Dice score ∼ 0.31), the performance on the testing dataset of our proposed networks achieved a Dice score of 0.78.
ISSN:1945-7928
1945-8452
DOI:10.1109/ISBI.2018.8363714