SM-SegNet: A Lightweight Squeeze M-SegNet for Tissue Segmentation in Brain MRI Scans

Title

SM-SegNet: A Lightweight Squeeze M-SegNet for Tissue Segmentation in Brain MRI Scans

Creator

Yamanakkanavar N.; Choi J.Y.; Lee B.

Description

In this paper, we propose a novel squeeze M-SegNet (SM-SegNet) architecture featuring a fire module to perform accurate as well as fast segmentation of the brain on magnetic resonance imaging (MRI) scans. The proposed model utilizes uniform input patches, combined-connections, long skip connections, and squeezeexpand convolutional layers from the fire module to segment brain MRI data. The proposed SM-SegNet architecture involves a multi-scale deep network on the encoder side and deep supervision on the decoder side, which uses combined-connections (skip connections and pooling indices) from the encoder to the decoder layer. The multi-scale side input layers support the deep network layers extraction of discriminative feature information, and the decoder side provides deep supervision to reduce the gradient problem. By using combined-connections, extracted features can be transferred from the encoder to the decoder resulting in recovering spatial information, which makes the model converge faster. Long skip connections were used to stabilize the gradient updates in the network. Owing to the adoption of the fire module, the proposed model was significantly faster to train and offered a more efficient memory usage with 83% fewer parameters than previously developed methods, owing to the adoption of the fire module. The proposed method was evaluated using the open-access series of imaging studies (OASIS) and the internet brain segmentation registry (IBSR) datasets. The experimental results demonstrate that the proposed SM-SegNet architecture achieves segmentation accuracies of 95% for cerebrospinal fluid, 95% for gray matter, and 96% for white matter, which outperforms the existing methods in both subjective and objective metrics in brain MRI segmentation. 2022 by the authors. Licensee MDPI, Basel, Switzerland.

Source

Sensors, Vol-22, No. 14

Date

2022-01-01

Publisher

MDPI

Subject

brain MRI; combined-connection; convolutional neural network; fire module; tissue segmentation

Coverage

Yamanakkanavar N., Department of Electronics and Communications Engineering, CHRIST University, Bangalore, 560029, India; Choi J.Y., Division of Computer Engineering, Hankuk University of Foreign Studies, Yongin, 17035, South Korea; Lee B., Department of Information and Communications Engineering, Chosun University, Gwangju, 61452, South Korea

Rights

All Open Access; Gold Open Access; Green Open Access

Relation

ISSN: 14248220; PubMed ID: 35890829

Format

Online

Language

English

Type

Article

Identifier

https://doi.org/10.3390/s22145148

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85133677653&doi=10.3390%2fs22145148&partnerID=40&md5=91a977568dbe83e92d2169dc21b4e73c