Explainable Feature-Injected Diffusion Model for Medical Image Translation
The integration of computed tomography (CT) and magnetic resonance (MR) imaging is crucial for accurate medical diagnosis and treatment planning. However, translating images between CT and MR remains challenging due to significant differences in imaging modalities. To address this problem, we propos...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10945355/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850271861873573888 |
|---|---|
| author | Jung Su Ahn Ki Hoon Kwak Young-Rae Cho |
| author_facet | Jung Su Ahn Ki Hoon Kwak Young-Rae Cho |
| author_sort | Jung Su Ahn |
| collection | DOAJ |
| description | The integration of computed tomography (CT) and magnetic resonance (MR) imaging is crucial for accurate medical diagnosis and treatment planning. However, translating images between CT and MR remains challenging due to significant differences in imaging modalities. To address this problem, we propose an Explainable Feature-Injected Diffusion Model (EIDM) for unsupervised CT-to-MR image translation. EIDM comprises a feature synthesis module and a diffusion-based latent space learning framework. This model captures frequency representations of the original CT images using the Fast Fourier Transform and applies high-pass filters to restore anatomical structures lost during diffusion. It also integrates weighted heatmaps generated by explainable AI models and utilizes a cross-attention mechanism to achieve unbiased image synthesis. We quantitatively evaluated EIDM and recent approaches using four metrics for comparison. Experimental results demonstrate that EIDM outperforms latest Generative Adversarial Networks (GANs) and diffusion models, generating realistic MR images that preserve anatomical integrity, as evidenced by enhanced scores across evaluation metrics. This work highlights the effectiveness of jointly learning explainable features and contour regions in achieving the goal of translating CT to MR images. |
| format | Article |
| id | doaj-art-ca755c6a89b14eaeab0f45cf7ff47ace |
| institution | OA Journals |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-ca755c6a89b14eaeab0f45cf7ff47ace2025-08-20T01:52:03ZengIEEEIEEE Access2169-35362025-01-0113572555726510.1109/ACCESS.2025.355558510945355Explainable Feature-Injected Diffusion Model for Medical Image TranslationJung Su Ahn0https://orcid.org/0009-0006-5791-3136Ki Hoon Kwak1Young-Rae Cho2https://orcid.org/0000-0002-4645-2542Division of Software, Yonsei University, Mirae Campus, Wonju-si, Gangwon-do, Republic of KoreaDivision of Software, Yonsei University, Mirae Campus, Wonju-si, Gangwon-do, Republic of KoreaDivision of Software, Yonsei University, Mirae Campus, Wonju-si, Gangwon-do, Republic of KoreaThe integration of computed tomography (CT) and magnetic resonance (MR) imaging is crucial for accurate medical diagnosis and treatment planning. However, translating images between CT and MR remains challenging due to significant differences in imaging modalities. To address this problem, we propose an Explainable Feature-Injected Diffusion Model (EIDM) for unsupervised CT-to-MR image translation. EIDM comprises a feature synthesis module and a diffusion-based latent space learning framework. This model captures frequency representations of the original CT images using the Fast Fourier Transform and applies high-pass filters to restore anatomical structures lost during diffusion. It also integrates weighted heatmaps generated by explainable AI models and utilizes a cross-attention mechanism to achieve unbiased image synthesis. We quantitatively evaluated EIDM and recent approaches using four metrics for comparison. Experimental results demonstrate that EIDM outperforms latest Generative Adversarial Networks (GANs) and diffusion models, generating realistic MR images that preserve anatomical integrity, as evidenced by enhanced scores across evaluation metrics. This work highlights the effectiveness of jointly learning explainable features and contour regions in achieving the goal of translating CT to MR images.https://ieeexplore.ieee.org/document/10945355/Medical imagesimage translationdiffusioncross-attentionfeature synthesis |
| spellingShingle | Jung Su Ahn Ki Hoon Kwak Young-Rae Cho Explainable Feature-Injected Diffusion Model for Medical Image Translation IEEE Access Medical images image translation diffusion cross-attention feature synthesis |
| title | Explainable Feature-Injected Diffusion Model for Medical Image Translation |
| title_full | Explainable Feature-Injected Diffusion Model for Medical Image Translation |
| title_fullStr | Explainable Feature-Injected Diffusion Model for Medical Image Translation |
| title_full_unstemmed | Explainable Feature-Injected Diffusion Model for Medical Image Translation |
| title_short | Explainable Feature-Injected Diffusion Model for Medical Image Translation |
| title_sort | explainable feature injected diffusion model for medical image translation |
| topic | Medical images image translation diffusion cross-attention feature synthesis |
| url | https://ieeexplore.ieee.org/document/10945355/ |
| work_keys_str_mv | AT jungsuahn explainablefeatureinjecteddiffusionmodelformedicalimagetranslation AT kihoonkwak explainablefeatureinjecteddiffusionmodelformedicalimagetranslation AT youngraecho explainablefeatureinjecteddiffusionmodelformedicalimagetranslation |