2019/07/18 by Jakub Nalepa, Pablo Ribalta Lorenzo, Nalepa, Jakub +19
Computer Science · Medicine · Neuroscience · #Brain Tumor Detection and Classification #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Medical Image Segmentation Techniques #Radiomics and Machine Learning in Medical Imaging #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1907.08303
openalex publication_date 2019/07/18 · openalex created_date 2022/07/28 · openalex updated_date 2026/07/28
Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) plays an\nimportant role in diagnosis and grading of brain tumor. Although manual DCE\nbiomarker extraction algorithms boost the diagnostic yield of DCE-MRI by\nproviding quantitative information on tumor prognosis and prediction, they are\ntime-consuming and prone to human error. In this paper, we propose a\nfully-automated, end-to-end system for DCE-MRI analysis of brain tumors. Our\ndeep learning-powered technique does not require any user interaction, it\nyields reproducible results, and it is rigorously validated against benchmark\n(BraTS'17 for tumor segmentation, and a test dataset released by the\nQuantitative Imaging Biomarkers Alliance for the contrast-concentration\nfitting) and clinical (44 low-grade glioma patients) data. Also, we introduce a\ncubic model of the vascular input function used for pharmacokinetic modeling\nwhich significantly decreases the fitting error when compared with the state of\nthe art, alongside a real-time algorithm for determination of the vascular\ninput region. An extensive experimental study, backed up with statistical\ntests, showed that our system delivers state-of-the-art results (in terms of\nsegmentation accuracy and contrast-concentration fitting) while requiring less\nthan 3 minutes to process an entire input DCE-MRI study using a single GPU.\n