Volumetric Segmentation of Brain Regions From MRI Scans Using 3D Convolutional Neural Networks

Abstract

Automated brain segmentation is an active research domain due to the association of various neurological disorders with different regions of the brain, to help medical professionals in prognostics and diagnostics. Traditional techniques like atlas-based and pattern recognition-based methods led to the development of various tools for automated brain segmentation. Recently, deep learning techniques are outperforming classical state-of-the-art methods and gradually becoming more mature. Consequently, deep learning has been extensively employed as a tool for precise segmentation of brain regions because of its capability to learn the intricate features of the high-dimensional data. In this work, a network for the segmentation of multiple brain regions has been proposed that is based on 3D convolutional neural networks and utilizes residual learning and dilated convolution operations to efficiently learn the end-to-end mapping from MRI volumes to the voxel-level brain segments. This research is focused on the segmentation of up to nine brain regions including cerebrospinal fluid, white matter and gray matter as well as their sub-regions. Mean dice scores of 0.879 and 0.914 have been achieved for three and nine brain regions, respectively by using the data from three different sources. Comparative analysis shows that our network gives better dice scores for most of the brain regions than state-of-the-artwork. Moreover, the mean dice score of 0.903, obtained for eight brain regions segmentation with MRBrains18 dataset, is better than 0.876 which was achieved in the previous work.

Light microscopic iris classification using ensemble multi‐class support vector machine

“…The benchmark data sets play an important role in conducting experiments and results comparisons in state of art (Nazir, Khan, Saba, & Rehman, 2019; Ramzan et al, 2020; Ramzan, Khan, Iqbal, Saba, & Rehman, 2020; Rehman et al, 2020; Saba et al, 2019; Saba, Bokhari, et al, 2018; Saba, Khan, et al, 2019; Saba, Rehman, Mehmood, Kolivand, & Sharif, 2018; Saba, Sameh, Khan, et al, 2019).…”

Computer vision for microscopic skin cancer diagnosis using handcrafted and non‐handcrafted features

“…Convolution neural networks are frequently employed in biomedical image analysis and cancer detection. Moreover, Convolutional Neural Networks (CNN)'s based approaches exhibited an excellent skin cancer detection process (Mittal et al, 2020; Ramzan et al, 2020,b). The main merit of CNN based approaches is automatic features extraction and training from automatic feedback.…”

Microscopic brain tumor detection and classification using 3D CNN and feature selection architecture

“…For the treatment of tumors, physicians use several options such as chemotherapy, radiotherapy, and surgery, however; it always depends on the size, shape, and nature of a tumor (Ejaz et al, 2018; Rehman et al, 2020). The clinical technology like MRI yields detailed information of healthy and tumor regions in the forms of their slices (Amin et al, 2019; Amin, Sharif, Yasmin, & Raza, 2019; Ramzan, Khan, Iqbal, Saba, & Rehman, 2020; Tahir et al, 2019). However, due to many slices, it is still a challenging problem to check the tumor abnormality.…”