Е-Публикации
Технически университет - София

Abstract: Medical image quality is very important. High quality ensures the standard of medical diagnosis, treatment, and patient life through health care or automated intelligence systems for medical diagnosis, monitoring, and treatment. The computing difficulties in processing medical images are discussed in the study. Proposing parallel computational models and program implementations based on medical image filtering techniques is one of the main issues. A filter-based parallel computational model is designed. Implementing a multithreaded parallel program verifies the suggested parallel model. An analysis of the effectiveness of medical image filters using a parallel multithreaded computer implementation that generates output images for each type of applied filter and applies filters on a list of compressed medical images. The BlackAndWhiteFilter, UVFilter, BinaryThresholdFilter, and RobertFilter have been applied. Experimental estimates have been analysed for the parallel performance metrics execution time and speedup. The performance estimation and scalability analyses demonstrate the strong scalability of the proposed solution.

References

1. M. Viceconti, P. Hunter and R. Hose, “Big data, big knowledge: big data for personalized healthcare,” IEEE J Biomed Health Inform 19, 1209–1215, 2015, doi: 10.1109/JBHI.2015.2406883.
2. O. Sandali, J. Tahiri, A. Armia Balamoun, C. Duliere, M. El Sanharawi, V. Borderie, Use of Black-and-White Digital Filters to Optimize Visualization in Cataract Surgery. Journal of Clinical Medicine. 2022; 11(14):4056. https://doi.org/10.3390/jcm11144056.
3. S. Petrò, G. Moroni, Effect of filters on segmentation-free geometric verification by X-ray CT, Procedia CIRP, Volume 114, 2022, pp. 73-78.
4. B. Karthicsonia, M. Vanitha, Edge Based Segmentation in Medical ImagesInternational Journal of Engineering and Advanced Technology (IJEAT), ISSN: 2249 – 8958, Volume-9 Issue-1, October 2019.
5. P. Simangunsong, P. Hasugian, Pattern Recognition in Medical Images Through Innovative Edge Detection with Robert's Method, Informatika dan Sains, Volume 14, Number 01, 2024, DOI 10.58471/JIS.v14i01.4080.
6. J. Tetreault, R. Choudhury, B. Genereaux, K. Kersten, J. Guan, Scalable and Modular AI Deployment Powered by NVIDIA Clara Deploy, White Paper, https://developer.download.nvidia.com/whitepapers/2020/claradeploy-whitepaper.pdf
7. Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, et all. Caffe: Convolutional Architecture for Fast Feature Embedding, arXiv:1408.5093, 2014.
8. K. KsiąĪek, Z. Marszaáek, G. Capizzi, et all. The impact of parallel programming on faster image filtering, 2018 Federated Conference on Computer Science and Information Systems, DOI: 10.15439/2018F71.
9. D. Akgün, Performance Evaluations for Parallel Image Filter on Multi - Core Computer using Java Threads, International Journal of Computer Applications (0975 – 8887), Volume 74– No.11, July 2013.
10. A. Kika, S. Greca, Multithreading Image Processing in Single-core and Multi-core CPU using Java, (IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 4, No. 9, 2013.

Issue