Composite fuzzy-wavelet-based active contour for medical image segmentation

Abstract

Purpose In clinical analysis, medical image segmentation is an important step to study the anatomical structure. This helps to diagnose and classify abnormality in the image. The wide variations in the image modality and limitations in the acquisition process of instruments make this segmentation challenging. This paper aims to propose a semi-automatic model to tackle these challenges and to segment medical images. Design/methodology/approach The authors propose Legendre polynomial-based active contour to segment region of interest (ROI) from the noisy, low-resolution and inhomogeneous medical images using the soft computing and multi-resolution framework. In the first phase, initial segmentation (i.e. prior clustering) is obtained from low-resolution medical images using fuzzy C-mean (FCM) clustering and noise is suppressed using wavelet energy-based multi-resolution approach. In the second phase, resultant segmentation is obtained using the Legendre polynomial-based level set approach. Findings The proposed model is tested on different medical images such as x-ray images for brain tumor identification, magnetic resonance imaging (MRI), spine images, blood cells and blood vessels. The rigorous analysis of the model is carried out by calculating the improvement against noise, required processing time and accuracy of the segmentation. The comparative analysis concludes that the proposed model withstands the noise and succeeds to segment any type of medical modality achieving an average accuracy of 99.57%. Originality/value The proposed design is an improvement to the Legendre level set (L2S) model. The integration of FCM and wavelet transform in L2S makes model insensitive to noise and intensity inhomogeneity and hence it succeeds to segment ROI from a wide variety of medical images even for the images where L2S failed to segment them.

A target region extraction method for ultrasound medical images based on improved PRIDNet and UCTransNet

“…MIoU (%) (3,6,12) 96.14 (6,12,18) 96.13 (12,18,24) 96.14 (3,6,12,18) 96.34 respectively, in comparison with the circumstances where only the original or improved UCTransNet is applied. Consequently, the addition of the enhancement network (Improved PRIDNet) can effectively improve the detail and global information within the target region of the input image, further improving the performance of the segmentation network.…”

“…Traditional machine learning methods encompass techniques such as threshold segmentation, edge detection, and region growing. [9][10][11][12][13] Additionally, they extend to include methods based on texture features and shape-based for segmentation. 14,15 Nevertheless, these approaches exhibit certain limitations in handling ultrasound images, particularly with sensitivity to their complexity, noise, and other issues related to image quality.…”

Steel surface defect classification approach using an All-optical Neuron-based SNN with attention mechanism

“…We employ the wavelet transform (Suthar et al , 2023; Mewada et al , 2020) approach to denoise the images during the image preprocessing stage in order to lessen the impact of the original image noise on the test outcomes. Wavelet characteristics can enhance image quality by reducing noise and inhomogeneous effects.…”

A fast region-based active contour for non-rigid object tracking and its shape retrieval

“…Active contour has played a significant role in non-rigid image segmentation and it has been widely used in medical image segmentation ( Beaupré, Bilodeau & Saunier, 2018 ; Mewada et al, 2020 ) e.g. tissue shape extraction, tumor detection, aerial, and natural image segmentation ( Patel, Mewada & Patnaik, 2012 ), and texture image segmentation ( Mewada, Patel & Patnaik, 2015 ).…”