Medical Images Segmentation Based on Unsupervised Algorithms: A Review

Abstract

Medical image segmentation plays an essential role in computer-aided diagnostic systems in various applications. Therefore, researchers are attracted to apply new algorithms for medical image processing because it is a massive investment in developing medical imaging methods such as dermatoscopy, X-rays, microscopy, ultrasound, computed tomography (CT), positron emission tomography, and magnetic resonance imaging. (Magnetic Resonance Imaging), So segmentation of medical images is considered one of the most important medical imaging processes because it extracts the field of interest from the Return on investment (ROI) through an automatic or semi-automatic process. The medical image is divided into regions based on the specific descriptions, such as tissue/organ division in medical applications for border detection, tumor detection/segmentation, and comprehensive and accurate detection. Several methods of segmentation have been proposed in the literature, but their efficacy is difficult to compare. To better address, this issue, a variety of measurement standards have been suggested to decide the consistency of the segmentation outcome. Unsupervised ranking criteria use some of the statistics in the hash score based on the original picture. The key aim of this paper is to study some literature on unsupervised algorithms (K-mean, K-medoids) and to compare the working efficiency of unsupervised algorithms with different types of medical images.

Automated brain tumour segmentation from multi‐modality magnetic resonance imaging data based on new particle swarm optimisation segmentation method

“…At each step, swarms that improve are rewarded (extension of particle life or creation of a new offspring) the swarms that stagnate are punished (reduction of swarm life or deletion of particles) 30 . To analyse the state of the general swarm, the fitness function was evaluated and updated the best position of each particle.…”

“…At each step, swarms that improve are rewarded (extension of particle life or creation of a new offspring) the swarms that stagnate are punished (reduction of swarm life or deletion of particles). 30 To…”

An Integrated Gesture Framework of Smart Entry Based on Arduino and Random Forest Classifier

“…The architecture of machine learning classifiers is diverse, encompassing a range of approaches from supervised learning, where models are trained on labeled data, to unsupervised learning, which involves finding hidden patterns in unlabeled data. Among the most prevalent and powerful classifiers are neural networks, decision trees, support vector machines (SVMs), and random forests, each exhibiting unique strengths suited to specific types of data and analytical requirements [36].…”

Analysis and Improvement of CT-Scan/MRI Medical Image Quality in Stroke Patients with Hybrid Thresholding Method: A Case Study in Padang BMC Hospital

“…The level of segmentation accuracy is not high, the number of medical images in the image collection file is small, and the intensity and resolution are very low. Inaccurate segmentation results cannot meet the clinical requirements medically expected by the medical party [18], [19]. This study improves the quality and analyzes CT-Scan/MRI Medical Images on images of brain stroke patients with the hybrid thresholding method to provide recommendations to the medical community regarding the level of clarity, area, and volume of the brain stroke area.…”