CADrx for GBM Brain Tumors: Predicting Treatment Response from Changes in Diffusion-Weighted MRI
Open Access
- 15 November 2009
- journal article
- research article
- Published by MDPI AG in Algorithms
- Vol. 2 (4), 1350-1367
- https://doi.org/10.3390/a2041350
Abstract
The goal of this study was to develop a computer-aided therapeutic response (CADrx) system for early prediction of drug treatment response for glioblastoma multiforme (GBM) brain tumors with diffusion weighted (DW) MR images. In conventional Macdonald assessment, tumor response is assessed nine weeks or more post-treatment. However, we will investigate the ability of DW-MRI to assess response earlier, at five weeks post treatment. The apparent diffusion coefficient (ADC) map, calculated from DW images, has been shown to reveal changes in the tumor’s microenvironment preceding morphologic tumor changes. ADC values in treated brain tumors could theoretically both increase due to the cell kill (and thus reduced cell density) and decrease due to inhibition of edema. In this study, we investigated the effectiveness of features that quantify changes from pre- and post-treatment tumor ADC histograms to detect treatment response. There are three parts to this study: first, tumor regions were segmented on T1w contrast enhanced images by Otsu’s thresholding method, and mapped from T1w images onto ADC images by a 3D region of interest (ROI) mapping tool using DICOM header information; second, ADC histograms of the tumor region were extracted from both pre- and five weeks post-treatment scans, and fitted by a two-component Gaussian mixture model (GMM). The GMM features as well as standard histogram-based features were extracted. Finally, supervised machine learning techniques were applied for classification of responders or non-responders. The approach was evaluated with a dataset of 85 patients with GBM under chemotherapy, in which 39 responded and 46 did not, based on tumor volume reduction. We compared adaBoost, random forest and support vector machine classification algorithms, using ten-fold cross validation, resulting in the best accuracy of 69.41% and the corresponding area under the curve (Az) of 0.70.Keywords
This publication has 28 references indexed in Scilit:
- Automated brain tumor segmentation using spatial accuracy-weighted hidden Markov Random FieldComputerized Medical Imaging and Graphics, 2009
- Efficient Multilevel Brain Tumor Segmentation With Integrated Bayesian Model ClassificationIEEE Transactions on Medical Imaging, 2008
- Hierarchical segmentation of malignant gliomas via integrated contextual filter responsePublished by SPIE-Intl Soc Optical Eng ,2008
- A system for brain tumor volume estimation via MR imaging and fuzzy connectednessComputerized Medical Imaging and Graphics, 2005
- Early Detection of Response to Radiation Therapy in Patients With Brain Malignancies Using Conventional and High b-Value Diffusion-Weighted Magnetic Resonance ImagingJournal of Clinical Oncology, 2003
- Automated Segmentation of MR Images of Brain TumorsRadiology, 2001
- Fast tissue segmentation based on a 4D feature map in characterization of intracranial lesionsJournal of Magnetic Resonance Imaging, 1999
- Automatic tumor segmentation using knowledge-based techniquesIEEE Transactions on Medical Imaging, 1998
- Computerized tumor boundary detection using a Hopfield neural networkIEEE Transactions on Medical Imaging, 1997
- Application of fuzzy c-means segmentation technique for tissue differentiation in MR images of a hemorrhagic glioblastoma multiformeMagnetic Resonance Imaging, 1995