Open Access

ARTICLE

Brain Tumor Segmentation in Multimodal MRI Using U-Net Layered Structure

by Muhammad Javaid Iqbal¹, Muhammad Waseem Iqbal², Muhammad Anwar^3,*, Muhammad Murad Khan⁴, Abd Jabar Nazimi⁵, Mohammad Nazir Ahmad⁶

1 Department of Information Technology, The Superior University, Lahore, Pakistan
2 Department of Software Engineering, The Superior University, Lahore, Pakistan
3 Department of Information Sciences, Division of Science and Technology, University of Education, Lahore, Pakistan
4 Department of Computer Science, Government College University, Faisalabad, Pakistan
5 Deptment of Oral and Maxillofacial Surgery, Faculty of Dentistry, Universiti Kebangsaan Malaysia, Kuala Lumpur, Malaysia
6 Institute of IR4.0, Universiti Kebangsaan Malaysia, Bangi, Selangor, Malaysia

* Corresponding Author: Muhammad Anwar. Email:

Computers, Materials & Continua 2023, 74(3), 5267-5281. https://doi.org/10.32604/cmc.2023.033024

Received 05 June 2022; Accepted 22 September 2022; Issue published 28 December 2022

Abstract

The brain tumour is the mass where some tissues become old or damaged, but they do not die or not leave their space. Mainly brain tumour masses occur due to malignant masses. These tissues must die so that new tissues are allowed to be born and take their place. Tumour segmentation is a complex and time-taking problem due to the tumour’s size, shape, and appearance variation. Manually finding such masses in the brain by analyzing Magnetic Resonance Images (MRI) is a crucial task for experts and radiologists. Radiologists could not work for large volume images simultaneously, and many errors occurred due to overwhelming image analysis. The main objective of this research study is the segmentation of tumors in brain MRI images with the help of digital image processing and deep learning approaches. This research study proposed an automatic model for tumor segmentation in MRI images. The proposed model has a few significant steps, which first apply the pre-processing method for the whole dataset to convert Neuroimaging Informatics Technology Initiative (NIFTI) volumes into the 3D NumPy array. In the second step, the proposed model adopts U-Net deep learning segmentation algorithm with an improved layered structure and sets the updated parameters. In the third step, the proposed model uses state-of-the-art Medical Image Computing and Computer-Assisted Intervention (MICCAI) BRATS 2018 dataset with MRI modalities such as T1, T1Gd, T2, and Fluid-attenuated inversion recovery (FLAIR). Tumour types in MRI images are classified according to the tumour masses. Labelling of these masses carried by state-of-the-art approaches such that the first is enhancing tumour (label 4), edema (label 2), necrotic and non-enhancing tumour core (label 1), and the remaining region is label 0 such that edema (whole tumour), necrosis and active. The proposed model is evaluated and gets the Dice Coefficient (DSC) value for High-grade glioma (HGG) volumes for their test set-a, test set-b, and test set-c 0.9795, 0.9855 and 0.9793, respectively. DSC value for the Low-grade glioma (LGG) volumes for the test set is 0.9950, which shows the proposed model has achieved significant results in segmenting the tumour in MRI using deep learning approaches. The proposed model is fully automatic that can implement in clinics where human experts consume maximum time to identify the tumorous region of the brain MRI. The proposed model can help in a way it can proceed rapidly by treating the tumor segmentation in MRI.

---

Keywords

---