RESEARCH ARTICLE Brain tumor segmentation using a deep Shuffled-YOLO network Angamuthu Rajasekaran Kavitha | Karthikeyan Palaniappan Department of Computer Science and Engineering, Chennai Institute of Technology, Anna University, Chennai, Tamil Nadu, India Correspondence Angamuthu Rajasekaran Kavitha, Department of Computer Science and Engineering, Chennai Institute of Technology, Anna University, Chennai, Tamil Nadu, India. Email: kavithaar@citchennai.net Abstract Brain tumor is an anomalous proliferation of cells in the brain that can evolve to malignant and benign tumors. Currently, segmentation of brain tumor is the most important surgical and pharmaceutical procedures. However, manu- ally segmenting brain tumors is hard because it is hard to find erratically shaped tumors with only one modality; the MRI modalities are integrated to provide multi-modal images with data that can be utilized to segment tumors. The recent developments in machine learning and the accessibility of medical diagnostic imaging have made it possible to tackle the challenges of segment- ing brain tumors with deep neural networks. In this work, a novel Shuffled- YOLO network has been proposed for segmenting brain tumors from multi- modal MRI images. Initially, the scalable range-based adaptive bilateral filer (SCRAB) pre-processing technique was used to eliminate the noise artifacts from MRI while preserving the edges. In the segmentation phase, we propose a novel deep Shuffled-YOLO architecture for segmenting the internal tumor structures that include non-enhancing, edema, necrosis, and enhancing tumors from the multi-modality MRI sequences. The experimental fallouts reveal that the proposed Shuffled-YOLO network achieves a better accuracy range of 98.07% for BraTS 2020 and 97.04% for BraTS 2019 with very minimal computational complexity compared to the state-of-the-art models. KEYWORDS brain tumor, multi-modalities, scalable range-based adaptive bilateral filter, segmentation, Shuffled-YOLO network 1 | INTRODUCTION A brain tumor is an anomalous development of cells in the brain. The segmentation of brain tumors is critical for cancer diagnosis and therapy planning. 1 Glioma is the normal kind of brain cancer. Low-grade glioma (LGG) and High-grade glioma (HGG) are two different types of gliomas. 2 HGG tumors are malignant, proliferating, and quickly infiltrating neighboring tissues, whereas LGG tumors are less invasive. 3 Brain cancer is the 10th most familiar cause of morality among both men and women. In current statistics, approximately, 18 600 people are expected to die from primary malignant brain tumors. Brain tumors can be caused only by major exposure to radiation from X-rays and some brain tumors are heredi- tary. 4 As a brain tumor develops and suppresses on con- tiguous nerves or blood vessels, it may cause symptoms such as headache, nausea and vomiting, confusion and unusual sleepiness. 5 The complication of brain tumor can be limited if it is diagnosed and treated at an early stage. 6 In order to plan treatment and involve medical personnel, brain tumors must be segmented correctly. Received: 5 July 2022 Revised: 19 October 2022 Accepted: 18 November 2022 DOI: 10.1002/ima.22832 Int J Imaging Syst Technol. 2022;1–12. wileyonlinelibrary.com/journal/ima © 2022 Wiley Periodicals LLC. 1