Study of Manhattan and Region Growing Methods for Brain Tumor Detection

Abstract

This paper investigates the utilization of regiongrowing segmentation and Content-Based Image Retrieval (CBIR) techniques to predict brain cancer, particularly focusing on brain tumors. Recent advancements in medical science have brought about promising diagnostic methods and treatments, offering patients renewed hope for recovery. However, the existing problems in diagnosing brain cancer include time inefficiency, inconsistency, inaccuracy, and costly. Hence, this study aims to find an innovative approach to address the predicaments of cancer diagnosis by harnessing the power of artificial intelligence, specifically within the realm of computer vision. The methods of regiongrowing segmentation and CBIR are particularly employed for this purpose. To predict the presence of brain tumors, these methods are applied to brain CT-scan images. The dataset comprises over 800 images sourced from Kaggle.com and a hospital in Lampung, Indonesia. The effectiveness of the region-growing segmentation method is evaluated using Receiver Operating Characteristics (ROC) analysis, along with an assessment of the quality of affected regions within brain CT-scan images. The study demonstrates that the segmentation methods achieve an accuracy rate of 79% when tested on a dataset consisting of 400 normal brain CT-scan images and 400 brain cancer CT-scan images. Simultaneously, the accuracy of brain image retrieval using CBIR techniques is remarkable, surpassing 96% and 94% with the Manhattan and Euclidean distance metrics, respectively. In conclusion, the findings of this research indicate that the combination of CBIR and segmentation methods can substantially enhance the performance of algorithms designed for brain tumor detection.