Adaptive comprehensive particle swarm optimisation‐based functional‐link neural network filtre model for denoising ultrasound images

IET Image Processing

Dinesh Goyal¹  Sunil Kumar Jangir²  Justin Joseph³  Sudhansu Kumar Mishra⁴  Manish Kumar⁵ 

[1] Department of Computer Science & Engineering Poornima Institute of Engineering & Technology Jaipur India;Department of Computer Science and Engineering Mody University of Science and Technology Sikar Rajasthan 332311 India;Department of Electrical Engineering Indian Institute of Technology Gandhinagar India;Department of Electrical and Electronics Engineering Birla Institute of Technology Ranchi India;Department of Electronics & Biomedical Engineering Mody University of Science & Technology Sikar India;

关键词: Sonic and ultrasonic radiation (medical uses);    Patient diagnostic methods and instrumentation;    Other topics in statistics;    Optimisation techniques;    Optical, image and video signal processing;    Filtering methods in signal processing;   

DOI  :  10.1049/ipr2.12100

来源: DOAJ

【 摘 要 】

Abstract Multiplicative speckle is a dominant type of noise that spoils the inherent features of the medical ultrasound (US) images. Apart from the speckle, impulse and Gaussian noises also appear in the US image due to the error encountered during the data transmission and transition of switching circuits and sensors. The noise not only deteriorates the visual quality of the US but also creates complications in the diagnosis. In this study, an adaptive comprehensive particle swarm optimisation‐based functional‐link neural network (ACPSO‐FLNN) filtre has been proposed and implemented in filtering noisy US images in different noise conditions. The proposed filtre is compared with some state‐of‐the‐art filtering techniques. Quantitative and qualitative measures such as training time, time complexity, convergence rate, and statistical test are included to study the performance of the proposed filtre. Furthermore, sensitivity, computational complexity, and order of the proposed filtre are also investigated. Friedman's test with 50 images is performed for statistical validation. The lower rank, that is, 6 and critical value of 21 × 10–4 of the proposed ACPSO‐FLNN filtre validates its dominance over other filtres.

【 授权许可】

Unknown