Lossless medical image compression based on anatomical information and deep neural networks

Min, Qiusha; Wang, Xin; Huang, Bo; Zhao, Zhengping

doi:10.1016/j.bspc.2022.103499

Cited by 8 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The effectiveness of the presented compression technique is assessed based on PSNR [23], CR, mean structural similarity index (SSIM) [24] and SSS [25]. In summary, higher PSNR and SSIM indicate that the recovered images, R are identical to the original images, O.…”

Section: Performance Metricsmentioning

confidence: 99%

A novel compression methodology for medical images using deep learning for high-speed transmission

Navaneethakrishnan,

Shanmugam

2024

IJRES

View full text Add to dashboard Cite

Medical imaging is a rapidly growing field having a high impact on the early detection, diagnosis and surgical planning of diseases. Several imaging techniques such as computed tomography (CT), magnetic resonance imaging (MRI) and ultrasound (US) imaging generate a higher volume of data, necessitating additional storage and communication requirements. Hence, image compression is utilized in medical field to reduce redundancy and alleviate memory and bandwidth issues. This paper presents a novel deep learning-based compression method to reduce the size of medical images. This method employs a deep convolutional neural network for learning compact representations of medical images, then coded by a Huffman encoder. The compression process is reversed to reconstruct the original image. Several tests are conducted to compare the results with other wellknown compression methods. The proposed model achieved a mean peak signal-to-noise ratio (PSNR) of 42.82 dB with storage space saving (SSS) of 96.15% for CT, 43.88 dB with SSS of 96.25% for MRI, 46.29 dB with SSS of 96.07% for US and 43.51 dB with SSS of 96.95% for X-ray images. The findings showed that the proposed compression technique could greatly compress the image size, saving storage space, facilitating better transmission and preserving critical diagnostic information.

show abstract

Section: Performance Metricsmentioning

confidence: 99%

A novel compression methodology for medical images using deep learning for high-speed transmission

Navaneethakrishnan,

Shanmugam

2024

IJRES

View full text Add to dashboard Cite

show abstract

“…Q. Min et al [21] have proposed a lossless medical image compression technique based on anatomical information and deep neural networks. This work aims to enhance the compression of medical images by utilizing a combination of anatomical knowledge and deep neural network (DNN) technology.…”

Section: Related Workmentioning

confidence: 99%

A State Table SPHIT Approach for Modified Curvelet-based Medical Image Compression

Ja'afar,

Ahmad,

Safie

2024

Int. J. Onl. Eng.

View full text Add to dashboard Cite

Medical imaging plays a significant role in clinical practice. Storing and transferring a large volume of images can be complex and inefficient. This paper presents the development of a new compression technique that combines the fast discrete curvelet transform (FDCvT) with state table set partitioning in the hierarchical trees (STS) encoding scheme. The curvelet transform is an extension of the wavelet transform algorithm that represents data based on scale and position. Initially, the medical image was decomposed using the FDCvT algorithm. The FDCvT algorithm creates symmetrical values for the detail coefficients, and these coefficients are modified to improve the efficiency of the algorithm. The curvelet coefficients are then encoded using the STS and differential pulse-code modulation (DPCM). The greatest amount of energy is contained in the coarse coefficients, which are encoded using the DPCM method. The finest and modified detail coefficients are encoded using the STS method. A variety of medical modalities, including computed tomography (CT), positron emission tomography (PET), and magnetic resonance imaging (MRI), are used to verify the performance of the proposed technique. Various quality metrics, including peak signal-to-noise ratio (PSNR), compression ratio (CR), and structural similarity index (SSIM), are used to evaluate the compression results. Additionally, the computation time for the encoding (ET) and decoding (DT) processes is measured. The experimental results showed that the PET image obtained higher values of the PSNR and CR. The CT image provides high quality for the reconstructed image, with an SSIM value of 0.96 and the fastest ET of 0.13 seconds. The MRI image has the shortest DT, which is 0.23 seconds.

show abstract

“…A significant number of approaches utilize artificial neural networks (ANNs) for specific tasks to increase the compression ratio. Min et al [28] created a hybrid approach to compress three-dimensional (3D) medical images. The hybrid algorithm utilizes the medical images' anatomical features to divide the medical data into specific areas.…”

Section: Related Workmentioning

confidence: 99%

An Improved Medical Image Compression Method Based on Wavelet Difference Reduction

et al. 2023

View full text Add to dashboard Cite

Advanced microscopic techniques such as high-throughput, high-content, multispectral, and 3D imaging could include many images per experiment requiring hundreds of gigabytes (GBs) of memory. Efficient lossy image-compression methods such as joint photographic experts group (JPEG) and JPEG 2000 are crucial to managing these large amounts of data. However, these methods can get visual quality with high compression ratios but do not necessarily maintain the medical data and information integrity. This paper proposes a novel and improved medical image compression method based on color wavelet difference reduction. Specifically, the proposed method is an extension of the standard wavelet difference reduction (WDR) method using mean co-located pixel difference to select the optimum quantity of color images that present the highest similarity in the spatial and temporal domain. The images with large spatiotemporal coherence are encoded as one volume and evaluated regarding the peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). The proposed method is evaluated in the challenging histopathological microscopy image analysis field using 31 slides of colorectal cancer. It is found that the perceptual quality of the medical image is remarkably high. The results indicate that the PSNR improvement over existing schemes may reach up to 22.65 dB compared to JPEG 2000. Also, it can reach up to 10.33dB compared to a method utilizing discrete wavelet transform (DWT), leading us to implement a mobile and web platform that can be used for compressing and transmitting microscopic medical images in real time.

show abstract

Lossless medical image compression based on anatomical information and deep neural networks

Cited by 8 publications

References 22 publications

A novel compression methodology for medical images using deep learning for high-speed transmission

A novel compression methodology for medical images using deep learning for high-speed transmission

A State Table SPHIT Approach for Modified Curvelet-based Medical Image Compression

An Improved Medical Image Compression Method Based on Wavelet Difference Reduction

Contact Info

Product

Resources

About