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.

Highlights

  • Between 2007-2011, 10,743 new cases of glioblastoma were diagnosed in the United Kingdom (UK) giving an annual incidence of 4.64/100,000/year (Brodbelt et al (2015))

  • Several novel MR imaging techniques have been assessed for improved mapping of tumour infiltration (Bauer et al (2013)) and comparative studies suggest that diffusion tensor MRI (DTI), a method sensitive to the directional diffusion of water molecules, may provide the best estimate of the invasive mar20 gin (Sternberg et al (2014))

  • 40 The aim of this study was to develop a tool to automate the segmentation of p and q maps, both calculated from low-resolution DTI data, together with additional contextual information from conventional MRI and perfusion MRI (or perfusion-weighted imaging (PWI))

Read more

Summary

Introduction

Between 2007-2011, 10,743 new cases of glioblastoma were diagnosed in the United Kingdom (UK) giving an annual incidence of 4.64/100,000/year (Brodbelt et al (2015)). Several novel MR imaging techniques have been assessed for improved mapping of tumour infiltration (Bauer et al (2013)) and comparative studies suggest that diffusion tensor MRI (DTI), a method sensitive to the directional diffusion of water molecules, may provide the best estimate of the invasive mar gin (Sternberg et al (2014)). By decomposing the tensor into its isotropic component (p) and anisotropic component (q), it is possible to differentiate white matter tracts invaded by a tumor from those that have been displaced or destroyed by tumor (Price et al (2004)) This has been confirmed in prospective image-guided biopsy studies (Price et al (2006)). Uptake of the technique into routine clinical practice is hampered by the fact that segmentation of the p and q maps is time consuming and requires a degree of operator expertise

Objectives
Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call