Diffusing the Blind Spot: Uterine MRI Synthesis with Diffusion Models

Müller J, Knupfer A, Blöss Braga P, Vittur EB, Kainz B, Hutter J (2025)

Publication Language: English

Publication Type: Conference contribution

Publication year: 2025

Journal

Lecture Notes in Computer Science Springer Verlag

Publisher: Springer

Series: Lecture Notes in Computer Science

City/Town: Cham

Book Volume: 16149

Pages Range: 93-102

Conference Proceedings Title: Skin Image Analysis, and Computer-Aided Pelvic Imaging for Female Health. 10th International Workshop, ISIC 2025, and First International Workshop, CAPI 2025, Held in Conjunction with MICCAI 2025, Daejeon, South Korea, September 23, 2025, Proceedings

Event location: Daejeon KR

ISBN: 9783032058249

DOI: 10.1007/978-3-032-05825-6_9

Abstract

Despite significant progress in generative modelling, existing diffusion models often struggle to produce anatomically precise female pelvic images, limiting their application in gynaecological imaging, where data scarcity and patient privacy concerns are critical. To overcome these barriers, we introduce a novel diffusion-based framework for uterine MRI synthesis, integrating both unconditional and conditioned Denoising Diffusion Probabilistic Models (DDPMs) and Latent Diffusion Models (LDMs) in 2D and 3D. Our approach generates anatomically coherent, high fidelity synthetic images that closely mimic real scans and provide valuable resources for training robust diagnostic models. We evaluate generative quality using advanced perceptual and distributional metrics, benchmarking against standard reconstruction methods, and demonstrate substantial gains in diagnostic accuracy on a key classification task. A blinded expert evaluation further validates the clinical realism of our synthetic images. We release our models with privacy safeguards and a comprehensive synthetic uterine MRI dataset to support reproducible research and advance equitable AI in gynaecology. The code and data are available at https://github.com/ividja/SynthUterus.

Authors with CRIS profile

Johanna Müller Professur für Image Data Exploration and Analysis Pedro Blöss Braga Lehrstuhl für Dynamics, Control, Machine Learning and Numerics (Alexander von Humboldt-Professur) Bernhard Kainz Professur für Image Data Exploration and Analysis Jana Hutter Professur für Smart Imaging and Data Profiling (Heisenberg-Professur)

How to cite

APA:

Müller, J., Knupfer, A., Blöss Braga, P., Vittur, E.B., Kainz, B., & Hutter, J. (2025). Diffusing the Blind Spot: Uterine MRI Synthesis with Diffusion Models. In M. Emre Celebi, Johanna Paula Müller, Catarina Barata, Allan Halpern, Philipp Tschandl, Marc Combalia, Yuan Liu, Kumar Abhishek, Joanna Jaworek-Korjakowska, Moi Hoon Yap, Katharina Breininger, Maximilian Lindholz, Jana Hutter, Richard Ruppel, Smiti Tripathy, Franziska Mathis-Ullrich, Stefanie Burghaus, Matthias May (Eds.), Skin Image Analysis, and Computer-Aided Pelvic Imaging for Female Health. 10th International Workshop, ISIC 2025, and First International Workshop, CAPI 2025, Held in Conjunction with MICCAI 2025, Daejeon, South Korea, September 23, 2025, Proceedings (pp. 93-102). Daejeon, KR: Cham: Springer.

MLA:

Müller, Johanna, et al. "Diffusing the Blind Spot: Uterine MRI Synthesis with Diffusion Models." Proceedings of the 10th International Workshop on Skin Image Analysis, ISIC 2025 and 1st International Workshop on Computer-Aided Pelvic Imaging for Female Health, CAPI 2025, Held in Conjunction with 28th International Conference on Medical Imaging and Computer Assisted Intervention, MICCAI 2025, Daejeon Ed. M. Emre Celebi, Johanna Paula Müller, Catarina Barata, Allan Halpern, Philipp Tschandl, Marc Combalia, Yuan Liu, Kumar Abhishek, Joanna Jaworek-Korjakowska, Moi Hoon Yap, Katharina Breininger, Maximilian Lindholz, Jana Hutter, Richard Ruppel, Smiti Tripathy, Franziska Mathis-Ullrich, Stefanie Burghaus, Matthias May, Cham: Springer, 2025. 93-102.

BibTeX: Download