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 ((Formula presented.)), structural similarity ((Formula presented.)), and compression ratio ((Formula presented.)) 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 (Formula presented.) of most well-known compression methods. DLAD combined with HEVC-visually lossless achieves the highest average (Formula presented.) 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 (Formula presented.) and (Formula presented.) 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.
Bibliographical noteFunding Information:
This research is funded by Vietnam National Foundation for Science and Technology Development (NAFOSTED) under grant number 102.01‐2018.316. We would like to thank NVIDIA Company for the GPU hardware aid and Mayo Clinic for the CT images. We also would like to thank Mr. Le Quoc Anh for his technical support in this project.
This research is funded by Vietnam National Foundation for Science and Technology Development (NAFOSTED) under grant number 102.01-2018.316. We would like to thank NVIDIA Company for the GPU hardware aid and Mayo Clinic for the CT images. We also would like to thank Mr. Le Quoc Anh for his technical support in this project.
© 2021 American Association of Physicists in Medicine