PSO Aided Neuro Fuzzy Inference System for Ultrasound Image Segmentation

Abstract

Individual micro calcifications are difficult to be detected as they are variable in shape and size and may be embedded in areas of dense parenchymal tissues. One of the most important problems of medical diagnosis, in general, is the subjectivity of the pattern recognition by diagnosis experts. This is due to the fact that the results are depended on the interpretation of the input from the patients but not on systematic procedure. In this paper, an adaptive neuro-fuzzy model optimized by PSO algorithms has been proposed. The symptoms and signs are gathered and the fuzzy membership values are defined. Feed forward multilayer networks are used to accept the fuzzy input values and is trained using back-propagation algorithm. The system is tested for detecting the micro-calcifications in breast sonograms. Later the results are compared for its performance.

Assessment of Joint Space in Knee Osteoarthritis using Particle Swarm Optimization Technique

“…PSO segmentation is one of the advanced and efficient algorithms which is been used in image processing where a large amount of data need to be analyzed. Earlier, in [9] Yi et al demonstrated a WBC image segmentation including an online trained neural network. Firstly, a mean shift algorithm [10] has been implemented to search the cluster center and uniform sampling is applied to reduce the size of the training set.…”

Prediction of nonmass breast cancer based on ultrasound and molybdenum target characteristics

“…However, some breast cancer ultrasonograms lack conventional mass characteristics, and thus the lesions have a nonmass-type presentation with hazy boundaries and no discernible spatial occupancy impact in two separate vertical views 5 .According to the fth ACR BI-RADS guideline 6 , structural disorders, ductal alterations, and other breast ultrasound-related signs may be the only ultrasound characteristics of nonmass breast cancer 7,8 . However, ultrasound images that demonstrate these signs are not easily recognizable, frequently challenging to recognize correctly and have low diagnostic sensitivity, which can result in a missed diagnosis and a misdiagnosis [9][10][11] .Therefore, their ultrasonographic manifestations are still challenging to recognize clinically. To increase the ultrasound diagnostic conformity rate of nonmass breast cancer and provide an imaging basis for identifying the lesions, we compared the clinical, ultrasound and mammography features of malignant nonmass breast cancer and compared them with those of benign nonmass breast lesions.…”

Review of medical image classification using the adaptive neuro-fuzzy inference system

“…The Authors in[20–22] make use of ANFIS for removing different types of noise from images, such as Gaussian noise,[20] speckle noise[21] and impulse noise. [22] Hence, denoised and quality-enhanced images are obtained.…”

“…Most of the images are affected through noises and artifacts caused by the various acquisition techniques and, hence, an effective technique for denoising is necessary for medical images, particularly in computed tomography, which is a significant and most general modality in medical imaging. The Authors in[ 20 – 22 ] make use of ANFIS for removing different types of noise from images, such as Gaussian noise,[ 20 ] speckle noise[ 21 ] and impulse noise. [ 22 ] Hence, denoised and quality-enhanced images are obtained.…”