Authors: Sadanand L. Shelgaonkar; Anil B. Nandgaonkar
Addresses: Department of Information Technology, A.P. Shah Institute of Technology, Thane (Mumbai), India ' Dr. Babasaheb Ambedkar Technological University, Lonere Dist. Raigad 402 103, Maharashtra, India
Abstract: Nowadays, the ultrasound modality is the current research areas for lesion analysis. Hence, this paper adopts an optimised deep belief neural (ODBN) network for enhancing the US image of pelvic portions. It considers the higher order and lower order statistical characteristics of the image to define the appropriate filter band for image enhancement. To optimise the lower order features, an advanced optimisation search algorithm named grey wolf optimiser algorithm (GWO) is exploited. The ODBN learns the optimised features and the noise characteristics for precise prediction of the filter bands, which enhance the image substantially over the conventional filter bands. The performance of the proposed method is compared with the conventional methods using the benchmark and real-time US images of pelvic lesions. The quality of enhancement is ensured using renowned measures namely PSNR and ESSIM that exhibit the performance of the proposed approach.
Keywords: ultrasound; reference-based quality metric; PSNR; edge-based structural similarity; ESSIM; grey wolf optimiser; GWO; DBN.
International Journal of Medical Engineering and Informatics, 2019 Vol.11 No.3, pp.226 - 251
Available online: 14 Aug 2019 *Full-text access for editors Access for subscribers Purchase this article Comment on this article