Towards a computer aided diagnosis (CAD) for brain MRI glioblastomas tumor exploration based on a deep convolutional neu
- PDF / 927,471 Bytes
- 21 Pages / 439.37 x 666.142 pts Page_size
- 41 Downloads / 165 Views
Towards a computer aided diagnosis (CAD) for brain MRI glioblastomas tumor exploration based on a deep convolutional neuronal networks (D-CNN) architectures Hiba Mzoughi 1,2 & Ines Njeh 1,3 & Mohamed Ben Slima 1,4 & Ahmed Ben Hamida 1,5 & Chokri Mhiri 6 & Kheireddine Ben Mahfoudh 7 Received: 14 February 2020 / Revised: 16 July 2020 / Accepted: 28 August 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
Manuel brain glioblastomas tumor exploration through MRI modalities is time-consuming. It is considered as a harmful and critical task due to highly inhomogeneous tumor regions composition. For this reason, clinicians recommend the Computer-Aided Diagnosis (CAD) tools to ensure a more accurate diagnostic. Based on convolutional DeepLearning algorithms, this paper investigates a fully automatic CAD for brain Glioblastomas tumors exploration including three steps: pre-processing, segmentation, and finally classification. A denoising and an automatic contrast enhancement method have been applied to preprocess the MRI scans. A Multi-Modal Cascaded U-net architecture, based on Fully Convolutional deep Network (FCN), has been adopted for the Region of Interest (ROI) extraction and finally, Deep Convolutional Neural Network (D-CNN) architecture has been used to classify brain glioblastomas tumor into High-Grade (HG) and LowGrade (LG). Experiments were performed on the Multimodal Brain Tumor Segmentation Challenge BraTS-2018 datasets benchmark. Several validations metric have been adopted to assess the CAD’s performances. The Dice Metric (DM) parameter has been calculated between the obtained segmentation results and the available ground truth data. The accuracy parameter has been computed for classification performance evaluation. The higher DM and accuracy values could attest the performance and the efficiency of the proposed CAD tool. Keywords Magnetic resonance imaging (MR) . Glioblastomas . Preprocessing . Convolutional neural networks (CNNs) . Fully convolutional networks (FCNs) . U-net . Segmentation . Classification
* Hiba Mzoughi [email protected] Extended author information available on the last page of the article
Multimedia Tools and Applications
1 Introduction Glioblastomas, designated as the most frequent brain tumor in adults, is considered as the most dangerous primary Central Nervous System (CNS) tumor [26]. Referring to Clinical Oncology American Society statistics, only 11% of patients diagnosed with gliomas tumors could have a 5-years estimated survival rate. The Magnetic Resonance Imaging (MRI) is considered among the best modalities to explore and to characterize such pathology. The variety and the complexity of the glioblastomas structures could yield several problems in the clinical diagnosis process. In fact, the glioblastomas brain tumors are considered as heterogeneous and the edema‘s presence around the tumor could make the Region Of Interest (ROI) extraction process more crucial, especially, when making manual exploration. Owing to artificial intelligenc
Data Loading...
