A deep convolutional neural network-based automatic delineation strategy for multiple brain metastases stereotactic radiosurgery.

Authors:
Strahinja Stojadinovic, Ph.D.
Strahinja Stojadinovic, Ph.D.
UT Southwestern Medical Center
Associate Professor
Medical Physics
Dallas, TX | United States

PLoS One 2017 6;12(10):e0185844. Epub 2017 Oct 6.

Department of Radiation Oncology, The University of Texas Southwestern Medical Center, Dallas, TX, United States of America.

Accurate and automatic brain metastases target delineation is a key step for efficient and effective stereotactic radiosurgery (SRS) treatment planning. In this work, we developed a deep learning convolutional neural network (CNN) algorithm for segmenting brain metastases on contrast-enhanced T1-weighted magnetic resonance imaging (MRI) datasets. We integrated the CNN-based algorithm into an automatic brain metastases segmentation workflow and validated on both Multimodal Brain Tumor Image Segmentation challenge (BRATS) data and clinical patients' data. Validation on BRATS data yielded average DICE coefficients (DCs) of 0.75±0.07 in the tumor core and 0.81±0.04 in the enhancing tumor, which outperformed most techniques in the 2015 BRATS challenge. Segmentation results of patient cases showed an average of DCs 0.67±0.03 and achieved an area under the receiver operating characteristic curve of 0.98±0.01. The developed automatic segmentation strategy surpasses current benchmark levels and offers a promising tool for SRS treatment planning for multiple brain metastases.

Download full-text PDF

Source
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0185844PLOS
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5630188PMC
October 2017
49 Reads
1 Citation
3.234 Impact Factor

Publication Analysis

Top Keywords

brain metastases
20
stereotactic radiosurgery
8
multiple brain
8
treatment planning
8
automatic brain
8
brats data
8
convolutional neural
8
srs treatment
8
brain
6
metastases
5
data validation
4
validation brats
4
patients' data
4
yielded average
4
075±007 tumor
4
tumor core
4
core 081±004
4
dcs 075±007
4
coefficients dcs
4
clinical patients'
4

Similar Publications