# The autoPET3 Challenge: Automated Lesion Segmentation in Whole-Body PET/CT unicodex2013 Multitracer Multicenter Generalization

arXiv: https://arxiv.org/abs/2605.05775 · HTML: https://mlsanity.com/paper/2605.05775/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 59 references that are in the map.
- First posted on arXiv 7 May 2026.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [DataComp: In search of the next generation of multimodal datasets](https://mlsanity.com/paper/2304.14108/) (2023)
- [3D MRI brain tumor segmentation using autoencoder regularization](https://mlsanity.com/paper/1810.11654/) (2018)
- [nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation](https://mlsanity.com/paper/2404.09556/) (2024)
- [nnU-Net for Brain Tumor Segmentation](https://mlsanity.com/paper/2011.00848/) (2020)
- [Towards Generalizable Tumor Synthesis](https://mlsanity.com/paper/2402.19470/) (2024)
- [Methods and open-source toolkit for analyzing and visualizing challenge results](https://mlsanity.com/paper/1910.05121/) (2019)
- [MultiTalent: A Multi-Dataset Approach to Medical Image Segmentation](https://mlsanity.com/paper/2303.14444/) (2023)
- [From FDG to PSMA: A Hitchhiker's Guide to Multitracer, Multicenter Lesion Segmentation in PET/CT Imaging](https://mlsanity.com/paper/2409.09478/) (2024)
- [Every Component Counts: Rethinking the Measure of Success for Medical Semantic Segmentation in Multi-Instance Segmentation Tasks](https://mlsanity.com/paper/2410.18684/) (2024)
- [Autopet III challenge: Incorporating anatomical knowledge into nnUNet for lesion segmentation in PET/CT](https://mlsanity.com/paper/2409.12155/) (2024)
- [Advanced Tumor Segmentation in PET/CT Imaging: A Training Strategy Study with nnU-Net for AutoPET III](https://mlsanity.com/paper/2605.08161/) (2026)

## Built on by (most cited first, 3 of 3)

- [Foundation Model-Enabled Efficient Data Sampling (FEEDS): A label-efficient training strategy for pan-cancer, multi-tracer PET/CT datasets](https://mlsanity.com/paper/2608.11076/) (2026)
- [Improving PET/CT-Based Whole-Body Lesion Segmentation Using Prediction Uncertainty-Augmented Models](https://mlsanity.com/paper/2606.10115/) (2026)
- [Three-Phase Scribble-Adaptive Curriculum Learning for autoPETV Grand Challenge](https://mlsanity.com/paper/2608.22096/) (2026)

## Abstract (arXiv)

We report the design and results of the third autoPET challenge (MICCAI 2024), which benchmarked automated lesion segmentation in whole-body PET/CT under a compositional generalization setting. Training data comprised 1,014 [18F]-FDG PET/CT studies from the University Hospital T"ubingen and 597 [18F]/[68Ga]-PSMA PET/CT studies from the LMU University Hospital Munich, constituting the largest publicly available annotated PSMA PET/CT dataset to date. The held-out test set of 200 studies covered four tracer-center combinations, two of which represented unseen compositional pairings. A complementary data-centric award category isolated the contribution of data handling strategies by restricting participants to a fixed baseline model. Seventeen teams submitted 27 algorithms, predominantly nnU-Net-based 3D networks with PET/CT channel concatenation. The top-ranked algorithm achieved a mean DSC of 0.66, FNV of 3.18 mL, and FPV of 2.78 mL across all four test conditions, improving DSC by 8% and reducing the false-negative volume by 5 mL relative to the provided baseline. Ranking was stable across bootstrap resampling and alternative ranking schemes for the top tier. Beyond the benchmark, we provide an in-depth analysis of segmentation performance at the patient and lesion level. Three main conclusions can be drawn: (1) in-domain multitracer PET/CT segmentation is sufficient and probably approaching reader agreement; (2) compositional generalization to unseen tracer-center combinations remains an open problem mainly driven by systematic volume overestimation; (3) heterogeneity and case difficulty drive performance variation substantially more than the choice of algorithm among top-ranked teams.