Texture descriptors to distinguish radiation necrosis from recurrent brain tumors on multi-parametric MRI

Di erentiating radiation necrosis (a radiation induced treatment e ect) from recurrent brain tumors (rBT) is currently one of the most clinically challenging problems in care and management of brain tumor (BT) patients. Both radiation necrosis (RN), and rBT exhibit similar morphological appearance on standard MRI making non-invasive diagnosis extremely challenging for clinicians, with surgical intervention being the only course for obtaining de nitive ground truth". Recent studies have reported that the underlying biological pathways de n- ing RN and rBT are fundamentally di erent. This strongly suggests that there might be phenotypic di erences and hence cues on multi-parametric MRI, that can distinguish between the two pathologies. One challenge is that these di erences, if they exist, might be too subtle to distinguish by the human observer. In this work, we explore the utility of computer extracted texture descriptors on multi-parametric MRI (MP-MRI) to provide alternate representations of MRI that may be capable of accentuating subtle micro-architectural di erences between RN and rBT for primary and metastatic (MET) BT patients. We further explore the utility of texture descriptors in identifying the MRI protocol (from amongst T1-w, T2-w and FLAIR) that best distinguishes RN and rBT across two independent cohorts of primary and MET patients. A set of 119 texture descriptors (co-occurrence matrix homogeneity, neighboring gray-level dependence matrix, multi-scale Gaussian derivatives, Law features, and histogram of gradient orientations (HoG)) for modeling di erent macro and micro-scale morphologic changes within the treated lesion area for each MRI protocol were extracted. Principal component analysis based variable importance projection (PCA-VIP), a feature selection method previously developed in our group, was employed to identify the importance of every texture descriptor in distinguishing RN and rBT on MP-MRI. PCA-VIP employs regression analysis to provide an importance score to each feature based on their ability to distinguish the two classes (RN/rBT). The top performing features identi ed via PCA-VIP were employed within a random- forest classi er to di erentiate RN from rBT across two cohorts of 20 primary and 22 MET patients. Our results revealed that, (a) HoG features at di erent orientations were the most important image features for both cohorts, suggesting inherent orientation di erences between RN, and rBT, (b) inverse di erence moment (capturing local intensity homogeneity), and Laws features (capturing local edges and gradients) were identi ed as important for both cohorts, and (c) Gd-C T1-w MRI was identi ed, across the two cohorts, as the best MRI protocol in distinguishing RN/rBT.

[1]  O. Belohlávek,et al.  Brain metastases after stereotactic radiosurgery using the Leksell gamma knife: can FDG PET help to differentiate radionecrosis from tumour progression? , 2002, European Journal of Nuclear Medicine and Molecular Imaging.

[2]  Prateek Prasanna,et al.  Decision support system for detection of diabetic retinopathy using smartphones , 2013, 2013 7th International Conference on Pervasive Computing Technologies for Healthcare and Workshops.

[3]  Mark E Mullins,et al.  Radiation necrosis versus glioma recurrence: conventional MR imaging clues to diagnosis. , 2005, AJNR. American journal of neuroradiology.

[4]  A. King,et al.  Late radiation injury to the temporal lobes: morphologic evaluation at MR imaging. , 1999, Radiology.

[5]  Anant Madabhushi,et al.  Variable Ranking with PCA: Finding Multiparametric MR Imaging Markers for Prostate Cancer Diagnosis and Grading , 2011, Prostate Cancer Imaging.

[6]  I. Marshall,et al.  Reproducibility of metabolite peak areas in 1H MRS of brain. , 1996, Magnetic resonance imaging.

[7]  P Van Tassel,et al.  Malignant gliomas: MR imaging spectrum of radiation therapy- and chemotherapy-induced necrosis of the brain after treatment. , 2000, Radiology.

[8]  K. Ohata,et al.  Methionine positron emission tomography of recurrent metastatic brain tumor and radiation necrosis after stereotactic radiosurgery: is a differential diagnosis possible? , 2003, Journal of neurosurgery.

[9]  K. Laws Textured Image Segmentation , 1980 .

[10]  M. Gilbert,et al.  Cerebral Radiation Necrosis , 2003, The neurologist.

[11]  W P Dillon,et al.  Preoperative proton MR spectroscopic imaging of brain tumors: correlation with histopathologic analysis of resection specimens. , 2001, AJNR. American journal of neuroradiology.

[12]  T. Cascino,et al.  Response criteria for phase II studies of supratentorial malignant glioma. , 1990, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[13]  Edward H. Adelson,et al.  The Laplacian Pyramid as a Compact Image Code , 1983, IEEE Trans. Commun..

[14]  Jayaram K. Udupa,et al.  New methods of MR image intensity standardization via generalized scale. , 2006 .

[15]  Miguel Ángel Guevara-López,et al.  An evaluation of image descriptors combined with clinical data for breast cancer diagnosis , 2013, International Journal of Computer Assisted Radiology and Surgery.

[16]  H. Hricak,et al.  Prostate cancer imaging , 2008, Acta radiologica.

[17]  Emanuele Menegatti,et al.  Different Approaches for Extracting Information from the Co-Occurrence Matrix , 2013, PloS one.

[18]  M. Markey,et al.  Differentiating tumor recurrence from treatment necrosis: a review of neuro-oncologic imaging strategies. , 2013, Neuro-oncology.

[19]  Y. Yamada,et al.  Radiation necrosis following treatment of high grade glioma—a review of the literature and current understanding , 2012, Acta Neurochirurgica.

[20]  Alan C. Evans,et al.  A nonparametric method for automatic correction of intensity nonuniformity in MRI data , 1998, IEEE Transactions on Medical Imaging.

[21]  Dean C. Barratt,et al.  Prostate Cancer Imaging. Image Analysis and Image-Guided Interventions - International Workshop, Held in Conjunction with MICCAI 2011, Toronto, Canada, September 22, 2011. Proceedings , 2011, Prostate Cancer Imaging.

[22]  R. Lenkinski,et al.  Central gland and peripheral zone prostate tumors have significantly different quantitative imaging signatures on 3 tesla endorectal, in vivo T2‐weighted MR imagery , 2012, Journal of magnetic resonance imaging : JMRI.

[23]  P. Wen,et al.  Novel anti-angiogenic therapies for malignant gliomas , 2008, The Lancet Neurology.

[24]  W. Reddick,et al.  Clinical value of proton magnetic resonance spectroscopy for differentiating recurrent or residual brain tumor from delayed cerebral necrosis. , 1996, International journal of radiation oncology, biology, physics.

[25]  J. Fike,et al.  The Radioresponse of the Central Nervous System: A Dynamic Process , 2000, Radiation research.

[26]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).