International Journal of Electrical and Computer Engineering (IJECE) Vol. 12, No. 2, April 2022, pp. 1437~1448 ISSN: 2088-8708, DOI: 10.11591/ijece.v12i2.pp1437-1448  1437 Journal homepage: http://ijece.iaescore.com A hybrid method for traumatic brain injury lesion segmentation Ahmad Yahya Dawod 1 , Aniwat Phaphuangwittayakul 1 , Salita Angkurawaranon 2 1 International College of Digital Innovation, Chiang Mai University, Chiang Mai, Thailand 2 Faculty of Medicine, Chiang Mai University, Chiang Mai, Thailand Article Info ABSTRACT Article history: Received Mar 24, 2021 Revised Aug 13, 2021 Accepted Sep 4, 2021 Traumatic brain injuries are significant effects of disability and loss of life. Physicians employ computed tomography (CT) images to observe the trauma and measure its severity for diagnosis and treatment. Due to the overlap of hemorrhage and normal brain tissues, segmentation methods sometimes lead to false results. The study is more challenging to unitize the AI field to collect brain hemorrhage by involving patient datasets employing CT scans images. We propose a novel technique free-form object model for brain injury CT image segmentation based on superpixel image processing that uses CT to analyzing brain injuries, quite challenging to create a high outstanding simple linear iterative clustering (SLIC) method. The maintains a strategic distance of the segmentation image to reduced intensity boundaries. The segmentation image contains marked red hemorrhage to modify the free-form object model. The contour labelled by the red mark is the output from our free-form object model. We proposed a hybrid image segmentation approach based on the combined edge detection and dilation technique features. The approach diminishes computational costs, and the show accomplished 96.68% accuracy. The segmenting brain hemorrhage images are achieved in the clustered region to construct a free-form object model. The study also presents further directions on future research in this domain. Keywords: Edge detection Free-form object model Hybrid method Image segmentation Simple linear iterative clustering algorithm This is an open access article under the CC BY-SA license. Corresponding Author: Ahmad Yahya Dawod International College of Digital Innovation, Chiang Mai University 239 Nimmanahaeminda Road, Suthep, Muang, Chiang Mai 50200, Thailand Email: ahmadyahyadawod.a@cmu.ac.th 1. INTRODUCTION Traumatic brain injuries (TBI) are generally affected by external forces on the brain in accidents or head strikes and are considered a significant cause of disabilities and death. TBI can range from an intracerebral hemorrhage, subdural hematoma, epidural hematoma, cerebral contusion, and cerebellar hemorrhage. Medical imaging modalities such as computed tomography (CT) scans are wide to establish severity and diagnosis and decide targeted therapy within early hours of injuries. An accurate and appropriate decision is necessary for physicians to manage the patient more precisely and ensure better diagnosis and outcomes. The segmentation of images is one of the most essential image processing and computer vision procedures. Picture segmentation is the way an image is separated into segments. It is most helpful for image detection purposes for these applications; it is inefficient to process the whole image. Segmentation of the image is utilized to segment from the image for further processing. Image segmentation techniques in computer vision partition the image into several parts based on specific image features like pixel intensity value, color, and texture [1]. Numerous approaches for brain image segmentation [2] have been proposed. Around these approaches work on the values of the clustering model and intensity threshold procedures. However, this conventional segmentation fails to classify subdural successfully as they are hard to define by