Repository logo
 

Multi-scale segmentation in GBM treatment using diffusion tensor imaging.

Accepted version
Peer-reviewed

Type

Article

Change log

Authors

Rahmat, Roushanak 
Saednia, Khadijeh 
Haji Hosseini Khani, Mohammad Reza 
Rahmati, Mohamad 

Abstract

Glioblastoma (GBM) is the commonest primary malignant brain tumor in adults, and despite advances in multi-modality therapy, the outlook for patients has changed little in the last 10 years. Local recurrence is the predominant pattern of treatment failure, hence improved local therapies (surgery and radiotherapy) are needed to improve patient outcomes. Currently segmentation of GBM for surgery or radiotherapy (RT) planning is labor intensive, especially for high-dimensional MR imaging methods that may provide more sensitive indicators of tumor phenotype. Automating processing and segmentation of these images will aid treatment planning. Diffusion tensor magnetic resonance imaging is a recently developed technique (DTI) that is exquisitely sensitive to the ordered diffusion of water in white matter tracts. Our group has shown that decomposition of the tensor information into the isotropic component (p - shown to represent tumor invasion) and the anisotropic component (q - shown to represent the tumor bulk) can provide valuable prognostic information regarding tumor infiltration and patient survival. However, tensor decomposition of DTI data is not commonly used for neurosurgery or radiotherapy treatment planning due to difficulties in segmenting the resultant image maps. For this reason, automated techniques for segmentation of tensor decomposition maps would have significant clinical utility. In this paper, we modified a well-established convolutional neural network architecture (CNN) for medical image segmentation and used it as an automatic multi-sequence GBM segmentation based on both DTI image maps (p and q maps) and conventional MRI sequences (T2-FLAIR and T1 weighted post contrast (T1c)). In this proof-of-concept work, we have used multiple MRI sequences, each with individually defined ground truths for better understanding of the contribution of each image sequence to the segmentation performance. The high accuracy and efficiency of our proposed model demonstrates the potential of utilizing diffusion MR images for target definition in precision radiation treatment planning and surgery in routine clinical practice.

Description

Keywords

DTI-MRI, Deep learning, GBM, Image segmentation, Adult, Brain Neoplasms, Diffusion Tensor Imaging, Glioblastoma, Humans, Image Processing, Computer-Assisted, Magnetic Resonance Imaging, Neural Networks, Computer

Journal Title

Comput Biol Med

Conference Name

Journal ISSN

0010-4825
1879-0534

Volume Title

123

Publisher

Elsevier BV
Sponsorship
Cancer Research UK (19732)
Department of Health (via National Institute for Health Research (NIHR)) (CDF-2018-11-ST2-003)
NIHR Academy (CDF-2018-11-ST2-003)
National Institute for Health and Care Research (NIHR/CS/009/011)
CRUK Project grant - PRaM-GBM study (C9216/A19732) NIHR Clinician Scientist Fellowship (project reference NIHR/CS/009/011) and an NIHR Career Development Fellowship (project reference CDF-2018-11-ST2-003) for SJP.