An Efficient Lossless ROI Image Compression Using Wavelet-Based Modified Region Growing Algorithm

• Published in: Journal of intelligent systems Vol. 29; no. 1; pp. 1063 - 1078
• Main Authors: Sreenivasulu, P., Varadarajan, S.
• Format: Journal Article
• Language: English
• Published: Berlin De Gruyter 01.01.2020; Walter de Gruyter GmbH
• Subjects: Algorithms; DCT; Discrete cosine transform; Discrete Wavelet Transform; DWT; Experimentation; Image compression; Image quality; Image segmentation; Image transmission; Lossless equipment; Medical image; Medical imaging; merging-based Huffman encoding; modified region growing; non-ROI; region of interest; SPIHT; Storage; Telemedicine; Wavelet transforms
• ISSN: 0334-1860; 2191-026X; 2191-026X
• DOI: 10.1515/jisys-2018-0180

Nowadays, medical imaging and telemedicine are increasingly being utilized on a huge scale. The expanding interest in storing and sending medical images brings a lack of adequate memory spaces and transmission bandwidth. To resolve these issues, compression was introduced. The main aim of lossless image compression is to improve accuracy, reduce the bit rate, and improve the compression efficiency for the storage and transmission of medical images while maintaining an acceptable image quality for diagnosis purposes. In this paper, we propose lossless medical image compression using wavelet transform and encoding method. Basically, the proposed image compression system comprises three modules: (i) segmentation, (ii) image compression, and (iii) image decompression. First, the input medical image is segmented into region of interest (ROI) and non-ROI using a modified region growing algorithm. Subsequently, the ROI is compressed by discrete cosine transform and set partitioning in hierarchical tree encoding method, and the non-ROI is compressed by discrete wavelet transform and merging-based Huffman encoding method. Finally, the compressed image combination of the compressed ROI and non-ROI is obtained. Then, in the decompression stage, the original medical image is extracted using the reverse procedure. The experimentation was carried out using different medical images, and the proposed method obtained better results compared to different other methods.