Optimized active contor segmentation model for medical image compression. (February 2023)

• Record Type: Journal Article
• Authors: Shabbir Tamboli, Shabanam; Butta, Rajasekhar; Sharad Jadhav, T.; Bhatt, Abhishek
• Is Part Of: Biomedical signal processing and control. Volume 80(2023)Part 1
• Publication Date: 2023-02
• Subjects: Medical Image Compression -- Lossy Model -- OACM -- ISPHIHT -- MMBO; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.104244
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: At first, the collected input image is subjected to the image compression phase, which includes the 2 major phases: (a) segmentation and (b) encoding. In the image compression phase, input image is initially segmented by a new OACM. The weighting factor λ and maximal iteration MA X it of ACM is fine-tuned by a new M−MBO model, which is the conceptual improvement of standard MBO. At the end of OACM, the original image is split into ROI region and Non-ROI region. The ROI marked field is encoded using ISPIHT, where as the non-ROI area is encoded using DCT. In terms of bit-stream combination, the outcomes from both the ISPIHT algorithm and the DCT model are merged and the compressed image is its output. Following that, the compressed image is decompressed that will counteract the compression mechanism. It encompasses bit-stream segmentation, which will be processed separately for the non-ROI and ROI regions using both ISPIHT decoded and DCT based decomposition. Finally, the original image is acquired in a more precise manner. Abstract: Nowadays, medical imaging systems tend to have greatest impact on disease identification, diagnosis, and surgical preparation. To save hardware space and transmission bandwidth, it is important to reduce data redundancy in the image. Compressing images is very important for storage and transmitting purposes as it decreases the amount of bits required while retaining the critical information content encapsulated in the image document. This makes the system more peculiar in this field. The proposed paradigm image segmentation is the first step attained by the Optimized Active Contour Model (OACM). Using a new Modified marriage in honey bees optimization model (MMBO), ACM's weighting factor and maximum iteration are fine-tuned. Thereby, the collected input image is segmented into N -ROI and ROI. The ROI marked field will indeed be encoded using ISPIHT-based lossy compression model, whereas the non-ROI area is encoded using DCT based lossy compression model. In terms of BSC, the outcomes from both ISPIHT algorithm and DCT model are merged and the compressed image is its output. Then, the compressed image will then be subjected to image decompression. This will include bit-stream segregation, which will be processed separately for the ROI and non-ROI regions using ISPIHT decoder and DCT-based decomposition. This process results in the original image. A comparative evaluation is undergone between the proposed and the existing techniques under PSNR, SSIM, and CR. Accordingly, the PSNR of the Proposed model is (∼)0.22, which is 26 %, 50 %, 60 %, and 55 % superior to the conventional methods like the MFO, LA, MBO, and JCF-LA.