ResDCE-diff : Dynamic contrast enhanced MRI translation in prostate cancer using residual denoising diffusion models

Kishore Kumar, Sriprabha Ramanarayanan, Keerthi Ram, Harsh Agarwal, Ramesh Venkatesan, Mohanasankar Sivaprakasam
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:2427-2446, 2026.

Abstract

Dynamic contrast enhanced MRI (DCE-MRI) identifies early perfusion patterns of aggressive prostate tumors, but its reliance on gadolinium contrast agents limits wider clinical adoption due to safety concerns. Recently, diffusion models offer a potential solution to synthesize contrast-enhanced images directly from non-contrast MRI. Previous diffusion models for prostate DCE-MRI require long inference times as they need hundreds or thousands of sampling steps limiting practical use. Moreover, the reverse generation process for DCE-MRI synthesis starts from pure noise without explicitly utilizing the prior information present in the non-contrast inputs in the diffusion process. We propose ResDCE-diff, a residual denoising diffusion model to synthesize early and late phase DCE-MRI images from non-contrast multi-modal inputs (T2-w, Apparent diffusion coefficient, and pre-contrast MRI). The diffusion process shifts anatomical, micro-structurally relevant and physics-informed residual features between the non-contrast inputs and DCE-MRI targets. Extensive experiments using PROSTATEx dataset show that ResDCE-diff, (i) consistently outperforms previous methods across early and late DCE-MRI phases with improvement margins of +1.29 db and +1.17 dB in PSNR, +0.04 and +0.03 in SSIM respectively, (ii) requires significantly lesser diffusion steps ($\approx$ 15) compared to the baseline diffusion model, and (iii) exhibits relatively higher diagnostically relevant synthesis quality.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-kumar26a, title = {ResDCE-diff : Dynamic contrast enhanced MRI translation in prostate cancer using residual denoising diffusion models}, author = {Kumar, Kishore and Ramanarayanan, Sriprabha and Ram, Keerthi and Agarwal, Harsh and Venkatesan, Ramesh and Sivaprakasam, Mohanasankar}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {2427--2446}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/kumar26a/kumar26a.pdf}, url = {https://proceedings.mlr.press/v315/kumar26a.html}, abstract = {Dynamic contrast enhanced MRI (DCE-MRI) identifies early perfusion patterns of aggressive prostate tumors, but its reliance on gadolinium contrast agents limits wider clinical adoption due to safety concerns. Recently, diffusion models offer a potential solution to synthesize contrast-enhanced images directly from non-contrast MRI. Previous diffusion models for prostate DCE-MRI require long inference times as they need hundreds or thousands of sampling steps limiting practical use. Moreover, the reverse generation process for DCE-MRI synthesis starts from pure noise without explicitly utilizing the prior information present in the non-contrast inputs in the diffusion process. We propose ResDCE-diff, a residual denoising diffusion model to synthesize early and late phase DCE-MRI images from non-contrast multi-modal inputs (T2-w, Apparent diffusion coefficient, and pre-contrast MRI). The diffusion process shifts anatomical, micro-structurally relevant and physics-informed residual features between the non-contrast inputs and DCE-MRI targets. Extensive experiments using PROSTATEx dataset show that ResDCE-diff, (i) consistently outperforms previous methods across early and late DCE-MRI phases with improvement margins of +1.29 db and +1.17 dB in PSNR, +0.04 and +0.03 in SSIM respectively, (ii) requires significantly lesser diffusion steps ($\approx$ 15) compared to the baseline diffusion model, and (iii) exhibits relatively higher diagnostically relevant synthesis quality.} }
Endnote
%0 Conference Paper %T ResDCE-diff : Dynamic contrast enhanced MRI translation in prostate cancer using residual denoising diffusion models %A Kishore Kumar %A Sriprabha Ramanarayanan %A Keerthi Ram %A Harsh Agarwal %A Ramesh Venkatesan %A Mohanasankar Sivaprakasam %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-kumar26a %I PMLR %P 2427--2446 %U https://proceedings.mlr.press/v315/kumar26a.html %V 315 %X Dynamic contrast enhanced MRI (DCE-MRI) identifies early perfusion patterns of aggressive prostate tumors, but its reliance on gadolinium contrast agents limits wider clinical adoption due to safety concerns. Recently, diffusion models offer a potential solution to synthesize contrast-enhanced images directly from non-contrast MRI. Previous diffusion models for prostate DCE-MRI require long inference times as they need hundreds or thousands of sampling steps limiting practical use. Moreover, the reverse generation process for DCE-MRI synthesis starts from pure noise without explicitly utilizing the prior information present in the non-contrast inputs in the diffusion process. We propose ResDCE-diff, a residual denoising diffusion model to synthesize early and late phase DCE-MRI images from non-contrast multi-modal inputs (T2-w, Apparent diffusion coefficient, and pre-contrast MRI). The diffusion process shifts anatomical, micro-structurally relevant and physics-informed residual features between the non-contrast inputs and DCE-MRI targets. Extensive experiments using PROSTATEx dataset show that ResDCE-diff, (i) consistently outperforms previous methods across early and late DCE-MRI phases with improvement margins of +1.29 db and +1.17 dB in PSNR, +0.04 and +0.03 in SSIM respectively, (ii) requires significantly lesser diffusion steps ($\approx$ 15) compared to the baseline diffusion model, and (iii) exhibits relatively higher diagnostically relevant synthesis quality.
APA
Kumar, K., Ramanarayanan, S., Ram, K., Agarwal, H., Venkatesan, R. & Sivaprakasam, M.. (2026). ResDCE-diff : Dynamic contrast enhanced MRI translation in prostate cancer using residual denoising diffusion models. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:2427-2446 Available from https://proceedings.mlr.press/v315/kumar26a.html.

Related Material