An end-to-end implicit neural representation architecture for medical volume data

Authors: Sheibanifard, A., Yu, H., Ruan, Z. and Zhang, J.J.

Journal: PLoS ONE

Volume: 20

Issue: 1 January

eISSN: 1932-6203

DOI: 10.1371/journal.pone.0314944

Abstract:

Medical volume data are rapidly increasing, growing from gigabytes to petabytes, which presents significant challenges in organisation, storage, transmission, manipulation, and rendering. To address the challenges, we propose an end-to-end architecture for data compression, leveraging advanced deep learning technologies. This architecture consists of three key modules: downsampling, implicit neural representation (INR), and super-resolution (SR). We employ a trade-off point method to optimise each module’s performance and achieve the best balance between high compression rates and reconstruction quality. Experimental results on multi-parametric MRI data demonstrate that our method achieves a high compression rate of up to 97.5% while maintaining superior reconstruction accuracy, with a Peak Signal-to-Noise Ratio (PSNR) of 40.05 dB and Structural Similarity Index (SSIM) of 0.96. This approach significantly reduces GPU memory requirements and processing time, making it a practical solution for handling large medical datasets.

https://eprints.bournemouth.ac.uk/40676/

Source: Scopus

An end-to-end implicit neural representation architecture for medical volume data.

Authors: Sheibanifard, A., Yu, H., Ruan, Z. and Zhang, J.J.

Journal: PLoS One

Volume: 20

Issue: 1

Pages: e0314944

eISSN: 1932-6203

DOI: 10.1371/journal.pone.0314944

Abstract:

Medical volume data are rapidly increasing, growing from gigabytes to petabytes, which presents significant challenges in organisation, storage, transmission, manipulation, and rendering. To address the challenges, we propose an end-to-end architecture for data compression, leveraging advanced deep learning technologies. This architecture consists of three key modules: downsampling, implicit neural representation (INR), and super-resolution (SR). We employ a trade-off point method to optimise each module's performance and achieve the best balance between high compression rates and reconstruction quality. Experimental results on multi-parametric MRI data demonstrate that our method achieves a high compression rate of up to 97.5% while maintaining superior reconstruction accuracy, with a Peak Signal-to-Noise Ratio (PSNR) of 40.05 dB and Structural Similarity Index (SSIM) of 0.96. This approach significantly reduces GPU memory requirements and processing time, making it a practical solution for handling large medical datasets.

https://eprints.bournemouth.ac.uk/40676/

Source: PubMed

An end-to-end implicit neural representation architecture for medical volume data.

Authors: Sheibanifard, A., Yu, H., Ruan, Z. and Zhang, J.J.

Journal: PloS one

Volume: 20

Issue: 1

Pages: e0314944

eISSN: 1932-6203

ISSN: 1932-6203

DOI: 10.1371/journal.pone.0314944

Abstract:

Medical volume data are rapidly increasing, growing from gigabytes to petabytes, which presents significant challenges in organisation, storage, transmission, manipulation, and rendering. To address the challenges, we propose an end-to-end architecture for data compression, leveraging advanced deep learning technologies. This architecture consists of three key modules: downsampling, implicit neural representation (INR), and super-resolution (SR). We employ a trade-off point method to optimise each module's performance and achieve the best balance between high compression rates and reconstruction quality. Experimental results on multi-parametric MRI data demonstrate that our method achieves a high compression rate of up to 97.5% while maintaining superior reconstruction accuracy, with a Peak Signal-to-Noise Ratio (PSNR) of 40.05 dB and Structural Similarity Index (SSIM) of 0.96. This approach significantly reduces GPU memory requirements and processing time, making it a practical solution for handling large medical datasets.

https://eprints.bournemouth.ac.uk/40676/

Source: Europe PubMed Central

An end-to-end implicit neural representation architecture for medical volume data.

Authors: Sheibanifard, A., Yu, H., Ruan, Z. and Zhang, J.J.

Journal: PLoS ONE

Volume: 20

Issue: 1

ISSN: 1932-6203

Abstract:

Medical volume data are rapidly increasing, growing from gigabytes to petabytes, which presents significant challenges in organisation, storage, transmission, manipulation, and rendering. To address the challenges, we propose an end-to-end architecture for data compression, leveraging advanced deep learning technologies. This architecture consists of three key modules: downsampling, implicit neural representation (INR), and super-resolution (SR). We employ a trade-off point method to optimise each module's performance and achieve the best balance between high compression rates and reconstruction quality. Experimental results on multi-parametric MRI data demonstrate that our method achieves a high compression rate of up to 97.5% while maintaining superior reconstruction accuracy, with a Peak Signal-to-Noise Ratio (PSNR) of 40.05 dB and Structural Similarity Index (SSIM) of 0.96. This approach significantly reduces GPU memory requirements and processing time, making it a practical solution for handling large medical datasets.

https://eprints.bournemouth.ac.uk/40676/

Source: BURO EPrints