UteroVAE: A Shape-Informed Variational Autoencoder for Uterine MRI Encoding in Adenomyosis, Fibroids, and Healthy Uteri
Ruppel R, Lindholz M, Schmidt R, El-Nahry Y, Mechsner S, Schulze-Weddige SEE, Baumgärtner GL, Arlt T, Hamm CA, Arndt S, Siegler L, Stepansky L, Hutter J, May M, Penzkofer T (2025)
Publication Language: English
Publication Type: Conference contribution
Publication year: 2025
Journal
Publisher: Springer
Series: Lecture Notes in Computer Science
City/Town: Cham
Book Volume: 16149
Pages Range: 71-81
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
ISBN: 9783032058249
DOI: 10.1007/978-3-032-05825-6_7
Abstract
Uterine disorders, such as adenomyosis and fibroids, are major contributors to pelvic pain, abnormal uterine bleeding, and infertility. Morphologic configurations and geometric alterations of the uterine cavity serve as critical imaging biomarkers in clinical diagnosis. One well established example is the question mark sign, a highly specific indicator of adenomyosis, characterized by distinctive uterine contour distortions. However, beyond this singular marker, a broader range of shape variations may hold diagnostic significance. To systematically capture these morphologic and geometric patterns, we adapted a Variational Autoencoder (VAE) pre-trained on fastMRI datasets. Instead of encoding MRI images alone, we designed the model to jointly incorporate both the segmented uterine cavity and MRI scans. By embedding an anatomy-informed prior, the model is better equipped to characterize structural anatomy relevant to uterine pathology. Our results indicate that both fine-tuning the VAE and using the hybrid encoding approach produce embeddings that align more closely with clinically relevant disease patterns and improve downstream clustering performance. By refining the joint representation of segmentation and MRI data, our method could enhance the potential of latent diffusion models for extracting imaging biomarkers in female pelvic disorders.
Authors with CRIS profile
Lisa Siegler
Institute of Radiology
Leonard Stepansky
Institute of Radiology
Jana Hutter
Professur für Smart Imaging and Data Profiling (Heisenberg-Professur)
Matthias May
Institute of Radiology
Involved external institutions
Germany (DE)How to cite
APA:
Ruppel, R., Lindholz, M., Schmidt, R., El-Nahry, Y., Mechsner, S., Schulze-Weddige, S.E.E.,... Penzkofer, T. (2025). UteroVAE: A Shape-Informed Variational Autoencoder for Uterine MRI Encoding in Adenomyosis, Fibroids, and Healthy Uteri. 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. 71-81). Daejeon, KR: Cham: Springer.
MLA:
Ruppel, Richard, et al. "UteroVAE: A Shape-Informed Variational Autoencoder for Uterine MRI Encoding in Adenomyosis, Fibroids, and Healthy Uteri." 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. 71-81.
BibTeX: Download