eprintid: 4671
rev_number: 6
eprint_status: archive
userid: 311
dir: disk0/00/00/46/71
datestamp: 2021-12-13 03:55:52
lastmod: 2021-12-13 03:55:52
status_changed: 2021-12-13 03:55:52
type: article
metadata_visibility: show
creators_name: Luu, Manh Ha
creators_name: Xiem, HoangVan
creators_id: halm@vnu.edu.vn
creators_id: xiemhoang@vnu.edu.vn
title: Efficiently compressing 3D medical images for teleinterventions via CNNs and anisotropic diffusion
ispublished: pub
subjects: ElectronicsandComputerEngineering
divisions: fac_fet
abstract: Purpose: Efficient compression of images while preserving image quality has the potential to be a major enabler of effective remote clinical diagnosis and treatment, since poor Internet connection conditions are often the primary constraint in such services. This paper presents a framework for organ-specific image compression for teleinterventions based on a deep learning approach and anisotropic diffusion filter.
Methods: The proposed method, deep learning and anisotropic diffusion (DLAD), uses a convolutional neural network architecture to extract a probability map for the organ of interest; this probability map guides an anisotropic diffusion filter that smooths the image except at the location of the organ of interest. Subsequently, a compression method, such as BZ2 and HEVC-visually lossless, is applied to compress the image. We demonstrate the proposed method on three-dimensional (3D) CT images acquired for radio frequency ablation (RFA) of liver lesions. We quantitatively evaluate the proposed method on 151 CT images using peak-signal-to-noise ratio (PSNR ), structural similarity ( SSIM ), and compression ratio ( CRCR ) metrics. Finally, we compare the assessments of two radiologists on the liver lesion detection and the liver lesion center annotation using 33 sets of the original images and the compressed images.
Results: The results show that the method can significantly improve CRCR of most well-known compression methods. DLAD combined with HEVC-visually lossless achieves the highest average CRCR of 6.45, which is 36% higher than that of the original HEVC and outperforms other state-of-the-art lossless medical image compression methods. The means of PSNRPSNR and SSIMSSIM are 70 dB and 0.95, respectively. In addition, the compression effects do not statistically significantly affect the assessments of the radiologists on the liver lesion detection and the lesion center annotation.
Conclusions: We thus conclude that the method has a high potential to be applied in teleintervention applications.
date: 2021-06
date_type: published
publisher: Epub 2021
official_url: 10.1002/mp.14814. Epub 2021 Apr 5. PMID: 33656213.
full_text_status: none
publication: Med Phys . 2021
volume: 48
number: 6
pagerange: 2877-2890
refereed: TRUE
issn: 2473-4209
citation:   Luu, Manh Ha and Xiem, HoangVan  (2021) Efficiently compressing 3D medical images for teleinterventions via CNNs and anisotropic diffusion.  Med Phys . 2021, 48  (6).   pp. 2877-2890.  ISSN 2473-4209