MhURI:A Supervised Segmentation Approach to Leverage Salient Brain Tissues in Magnetic Resonance Images. (March 2021)

• Record Type: Journal Article
• Authors: Ghosal, Palash; Chowdhury, Tamal; Kumar, Amish; Bhadra, Ashok Kumar; Chakraborty, Jayasree; Nandi, Debashis
• Is Part Of: Computer methods and programs in biomedicine. Volume 200(2021)
• Publication Date: 2021-03
• Subjects: Brain -- Convolutional Neural Network -- Inception module -- MRI -- Morphological gradient -- Segmentation; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2020.105841
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: A deep learning framework is proposed for the task of brain tissue segmentation from MR images and can be extended to other types of segmentation problems. It is shown that how domain knowledge or problem specific information can be incorporated into deep learning methods to push its limitations. Morphological information is introduced to enhance structural details into MR images that in turn helps in better segmentation performance. Novel contributions include a convolutional module named Residual Inception 2 Residual (RI2R) that can be used as the building block of various deep learning architectures and a global feature extractor block used prior to segmentation to liberate the segmenter from extracting global features. Two different datasets are exploited and the results are analysed carefully to prove the generalizability of our method. Abstract: Background and objectives: Accurate segmentation of critical tissues from a brain MRI is pivotal for characterization and quantitative pattern analysis of the human brain and thereby, identifies the earliest signs of various neurodegenerative diseases. To date, in most cases, it is done manually by the radiologists. The overwhelming workload in some of the thickly populated nations may cause exhaustion leading to interruption for the doctors, which may pose a continuing threat to patient safety. A novel fusion method called U-Net inception based on 3D convolutions and transition layers is proposed to address this issue. Methods: A 3D deep learning method called Multi headed U-Net with Residual Inception (MhURI) accompanied by Morphological Gradient channel for brain tissue segmentation is proposed, which incorporates Residual Inception 2-Residual (RI2R) module as the basic building block. The model exploits the benefits of morphological pre-processing for structural enhancement of MR images. A multi-path data encoding pipeline is introduced on top of the U-Net backbone, which encapsulates initial global features and captures the information from each MRI modality. Results: The proposed model has accomplished encouraging outcomes, which appreciates the adequacy in terms of some of the established quality metrices when compared with some of the state-of-the-art methods while evaluating with respect to two popular publicly available data sets. Conclusion: The model is entirely automatic and able to segment gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) from brain MRI effectively with sufficient accuracy. Hence, it may be considered to be a potential computer-aided diagnostic (CAD) tool for radiologists and other medical practitioners in their clinical diagnosis workflow.