PuSH - Publikationsserver des Helmholtz Zentrums München

Alaya, M.B.* ; Lang, D.M. ; Wiestler, B.* ; Schnabel, J.A. ; Bercea, C.-I.

MedEdit: Counterfactual diffusion-based image editing on brain MRI.

In: (Simulation and Synthesis in Medical Imaging). Berlin [u.a.]: Springer, 2025. 167-176 (Lect. Notes Comput. Sc. ; 15187 LNCS)
DOI
Denoising diffusion probabilistic models enable high-fidelity image synthesis and editing. In biomedicine, these models facilitate counterfactual image editing, producing pairs of images where one is edited to simulate hypothetical conditions. For example, they can model the progression of specific diseases, such as stroke lesions. However, current image editing techniques often fail to generate realistic biomedical counterfactuals, either by inadequately modeling indirect pathological effects like brain atrophy or by excessively altering the scan, which disrupts correspondence to the original images. Here, we propose MedEdit, a conditional diffusion model for medical image editing. MedEdit induces pathology in specific areas while balancing the modeling of disease effects and preserving the original scan’s integrity. We evaluated MedEdit on the Atlas v2.0 stroke dataset using Frechet Inception Distance and Dice scores, outperforming state-of-the-art diffusion-based methods such as Palette (by 45%) and SDEdit (by 61%). Additionally, clinical evaluations by a board-certified neuroradiologist confirmed that MedEdit generated realistic stroke scans indistinguishable from real ones. We believe this work will enable counterfactual image editing research to further advance the development of realistic and clinically useful imaging tools.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Konferenzbeitrag
Korrespondenzautor
Schlagwörter Biomedical Imaging ; Conditional Multimodal Learning
ISSN (print) / ISBN 0302-9743
e-ISSN 1611-3349
Konferenztitel Simulation and Synthesis in Medical Imaging
Zeitschrift Lecture Notes in Computer Science
Quellenangaben Band: 15187 LNCS, Heft: , Seiten: 167-176 Artikelnummer: , Supplement: ,
Verlag Springer
Verlagsort Berlin [u.a.]
Nichtpatentliteratur Publikationen
Institut(e) Helmholtz Artifical Intelligence Cooperation Unit (HAICU)
Institute for Machine Learning in Biomed Imaging (IML)