nnLandmark: A Self-Configuring Method for 3D Medical Landmark Detection

Alexandra Ertl, Stefan Denner, Robin Peretzke, Shuhan Xiao, David Zimmerer, Maximilian Fischer, Markus Ralf Bujotzek, Xin Yang, Peter Neher, Fabian Isensee, Klaus Maier-Hein

Keywords: 3D Medical Landmark Detection, Self-Configuration, Benchmarking

TL;DR: We present a self-configuring method for 3D landmark detection which demonstrates state-of-the-art performance and can serve as a strong common baseline and standardized framework for developing new methods.

Abstract:

Landmark detection is central to many medical applications, such as identifying critical structures for treatment planning or defining control points for biometric measurements. However, manual annotation is labor-intensive and requires expert anatomical knowledge.
While deep learning shows promise in automating this task, fair evaluation and interpretation of methods in a broader context, are hindered by limited public benchmarking, inconsistent baseline implementations, and non-standardized experimentation.
To overcome these pitfalls, we present nnLandmark, a self-configuring framework for 3D landmark detection that combines tailored heatmap generation, loss design, inference logic, and a robust set of hyperparameters for heatmap regression, while reusing components from nnU-Net’s underlying self-configuration and training engine.
nnLandmark achieves state-of-the-art performance across three public and one private dataset, benchmarked against three recently published methods.
Its out-of-the-box usability enables training strong landmark detection models on new datasets without expert knowledge or dataset-specific hyperparameter tuning.
Beyond accuracy, nnLandmark provides both a strong, common baseline and a flexible, standardized environment for developing and evaluating new methodological contributions. It further streamlines evaluation across multiple datasets by offering data conversion utilities for current public benchmarks. Together, these properties position nnLandmark as a central tool for advancing 3D medical landmark detection through systematic, transparent benchmarking, enabling to genuinely measure methodological progress.
The code will be available upon acceptance.

Primary Subject Area: Segmentation

Secondary Subject Area: Application: Radiology

Registration Requirement: Yes

Reproducibility: https://github.com/MIC-DKFZ/nnLandmark

Visa & Travel: No

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Midl Latex Submission Checklist: Ensure no LaTeX errors during compilation., Replace NNN with your OpenReview submission ID., Includes \documentclass{midl}, \jmlryear{2026}, \jmlrworkshop, \jmlrvolume, \editors, and correct \bibliography command., Did not override options of the hyperref package., Did not use the times package., Use the correct spelling and format, avoid Unicode characters, and use LaTeX equivalents instead., Any math in the title and abstract must be enclosed within $...$., Did not override the bibliography style defined in midl.cls and did not use \begin{thebibliography} directly to insert references., Avoid using \scalebox; use \resizebox when needed., Included all necessary figures and removed *unused* files in the zip archive., Removed special formatting, visual annotations, and highlights used during rebuttal., All special characters in the paper and .bib file use LaTeX commands (e.g., \'e for é)., No separate supplementary PDF uploads., Acknowledgements, references, and appendix must start after the main content.

Submission Number: 74