Johanna P. Müller
Portrait of Johanna P. Müller
Johanna P. Müller

Postdoctoral Research Associate · School of Biomedical Engineering and Imaging Sciences, Department of Cardiovascular Imaging

King's College London, London, UK

See you at ESC Digital & AI Summit 2026!

I build self-supervised and supervised AI that finds rare diseases and under-represented anatomies without labelled examples, working closely with clinicians to make it trustworthy enough for the clinic.

Email
Get in touch
Publications
36 papers

01 News

Recent updates

Nov 2026

Invited Talk at ESC Digital & AI Summit 2026 in Basel, Switzerland

Nov 13 - 10:40 AM "Children are not small adults: AI for fetal cardiology and pediatric care."

Oct 2026

Invited Talk at MIA-NORMAL/CHARMS/ORACLE Symposium at ICL

Yearly symposium organised by IDEA Lab @FAU with talks from PhDs and invited researchers/professors from the Universities of Bamberg, Birmingham and Aalborg.

Sep 2026

Beyond Normals wins MICCAI VLM3D Challenge Tasks (3x 1st, 1x 2nd Place)

Our team wins the Report Generation and Abnormality Classification tasks in CT and MR imaging analysis.

Aug 2026

Five Papers Accepted @ MICCAI 2026

Two main conference papers and three workshop papers accepted at UNSURE, CAPI and AgenticMed.

Aug 2026

Dr.-Ing. completed with distinction

Doctoral thesis, Learning Normative Anatomy under Limited Supervision, at Friedrich-Alexander-Universität Erlangen-Nürnberg.

Jul 2026

MICCAI Outstanding Reviewer Award

Recognised for reviewing at MICCAI 2026.

Jun 2026

Accepted @ MICCAI 2026: Fibers of Asymmetric Similarity

A framework for clinical and imaging data, accepted at MICCAI 2026.

Apr 2026

New Dataset @ISBI 2026: SynthUterus ROI (1.0)

A synthetic dataset of the uterus in four anatomical orientations.

Nov 2025

Best Poster Award

at the Bavarian Conference on AI in Medicine.

Oct 2025

Women in MICCAI Award

Best AI Democratization Paper award at MICCAI 2025.

Jul 2025

Four Papers Accepted @ MICCAI 2025

Main conference and Workshops

PAST

...

02 Research

Areas of active work

Working without or rare labels

I hold a doctoral degree from the IDEA Lab at Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), earned within the joint Borderless research group between Imperial College London and FAU, where my doctoral work focused on machine learning for quality control and diagnostic support at the front line of care. Since September 2026, I am a Postdoctoral Research Associate at King's College London in...

  • Anomaly & out-of-distribution detection
  • Uncertainty quantification
  • Generative modelling for medical imaging
  • Data- and resource-efficient learning
  • Fetal & cardiovascular imaging analysis

03 Selected work

36 total

MICCAI ’26

Fibers of Asymmetric Similarity: A Framework for Clinical and Imaging Data

Müller JP, Baugh M, Wright R, Day T, Razavi R, Kainz B

MICCAI · 2026

@inproceedings{muller2026fibers,
  title     = {Fibers of Asymmetric Similarity: A Framework for
               Clinical and Imaging Data},
  author    = {M{\"u}ller, Johanna P. and Baugh, M. and Wright, R.
               and Day, T. and Razavi, R. and Kainz, B.},
  booktitle = {MICCAI},
  year      = {2026}
}
ASMUS ’25

L-FUSION: Laplacian Fetal Ultrasound Segmentation and Uncertainty Estimation

Müller JP, Wright R, Day T, Venturini L, Budd S, Reynaud H, Hajnal J, Razavi R, Kainz B

Simplifying Medical Ultrasound, ASMUS 2025, eds. Ni D, Noble A, Huang R, Xue W, Springer LNCS vol. 16165, Cham

@inproceedings{muller2026lfusion,
  title     = {L-FUSION: Laplacian Fetal Ultrasound Segmentation and
               Uncertainty Estimation},
  author    = {M{\"u}ller, Johanna P. and Wright, Robert and Day, Thomas G. and Venturini, Lorenzo and Budd, Samuel F. and Reynaud, Hadrien and Hajnal, Joseph V. and Razavi, Reza and Kainz, Bernhard},
  editor    = {Ni, D. and Noble, A. and Huang, R. and Xue, W.},
  booktitle = {Simplifying Medical Ultrasound},
  series    = {Springer LNCS},
  volume    = {16165},
  address   = {Cham},
  year      = {2026},
  note      = {ASMUS 2025}
}
CAPI ’25

Diffusing the Blind Spot: Uterine MRI Synthesis with Diffusion Models

Müller JP, Knupfer A, Blöss P, Vittur EB, Kainz B, Hutter J

MICCAI CAPI Workshop · 2025

@inproceedings{muller2026diffusing,
  title     = {Diffusing the Blind Spot: Uterine MRI Synthesis with
               Diffusion Models},
  author    = {M{\"u}ller, Johanna P. and Knupfer, A. and Bl{\"o}ss, P.
               and Vittur, E. B. and Kainz, B. and Hutter, J.},
  editor    = {Celebi, M. E. and others},
  booktitle = {Skin Image Analysis, and Computer-Aided Pelvic Imaging
               for Female Health},
  series    = {Springer LNCS},
  volume    = {16149},
  address   = {Cham},
  year      = {2025},
  note      = {CAPI 2025}
}
AAAI ’24

Trade-offs in Fine-Tuned Diffusion Models Between Accuracy and Interpretability

Dombrowski M, Reynaud H, Müller JP, Baugh M, Kainz B

Proceedings of the AAAI Conference on Artificial Intelligence, 38(19):21037–21045 · 2024

@inproceedings{dombrowski2024tradeoffs,
  title     = {Trade-offs in Fine-Tuned Diffusion Models Between
               Accuracy and Interpretability},
  author    = {Dombrowski, M. and Reynaud, H. and M{\"u}ller,
               Johanna P. and Baugh, M. and Kainz, B.},
  booktitle = {Proceedings of the AAAI Conference on Artificial
               Intelligence},
  volume    = {38},
  number    = {19},
  pages     = {21037--21045},
  year      = {2024},
  month     = mar
}
UNSURE ’23

Confidence-Aware and Self-supervised Image Anomaly Localisation

Müller JP, Baugh M, Tan J, Dombrowski M, Kainz B

International Workshop on Uncertainty for Safe Utilization of Machine Learning in Medical Imaging, pp. 177–187, Cham: Springer Nature Switzerland · 2023

Introduces confidence-aware self-supervised localisation for detecting rare or unexpected findings in medical images without labelled abnormal examples. Part of the line of work that won the MICCAI Medical Out-of-Distribution (MOOD) Challenge in 2023 and 2024.
@inproceedings{muller2023confidenceaware,
  title     = {Confidence-Aware and Self-supervised Image Anomaly
               Localisation},
  author    = {M{\"u}ller, Johanna P. and Baugh, M. and Tan, J.
               and Dombrowski, M. and Kainz, B.},
  booktitle = {International Workshop on Uncertainty for Safe
               Utilization of Machine Learning in Medical Imaging},
  publisher = {Springer Nature Switzerland},
  address   = {Cham},
  pages     = {177--187},
  year      = {2023},
  month     = oct
}
MICCAI ’23

Many Tasks Make Light Work: Learning to Localise Medical Anomalies from Multiple Synthetic Tasks

Baugh M, Tan J, Müller JP, Dombrowski M, Batten J, Kainz B

International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 162–172, Cham: Springer Nature Switzerland · 2023

@inproceedings{baugh2023many,
  title     = {Many Tasks Make Light Work: Learning to Localise
               Medical Anomalies from Multiple Synthetic Tasks},
  author    = {Baugh, M. and Tan, J. and M{\"u}ller, Johanna P.
               and Dombrowski, M. and Batten, J. and Kainz, B.},
  booktitle = {International Conference on Medical Image Computing
               and Computer-Assisted Intervention},
  publisher = {Springer Nature Switzerland},
  address   = {Cham},
  pages     = {162--172},
  year      = {2023},
  month     = oct
}

04 Blog

Notes, not papers

28 Aug 2026

The Forward-Forward Algorithm: Learning Without Going (Fully) Backward

→ 11 min

Geoffrey Hinton's 2022 proposal to train neural networks with two forward passes instead of one forward and one backward. What goodness means, why it needs no backward pass at all, and a from-scratch NumPy implementation that gets a small digit classifier working on it.

25 Aug 2026

Great Websites Series - #2: Orphanet

→ 2 min

Second in the series on websites worth a permanent bookmark. This time, Orphanet - the reference portal that gave rare diseases a shared vocabulary long before anyone was building models for them.

13 Aug 2026

Great Websites Series - #1: OEIS

→ 2 min

First in an occasional series on websites that have earned a permanent bookmark. Starting with the On-Line Encyclopedia of Integer Sequences.