# Benchmarking Self-Supervised 3D Medical Vision Foundation Models and Transferability Estimation

arXiv: https://arxiv.org/abs/2610.17573 · HTML: https://mlsanity.com/paper/2610.17573/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 44 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 27 of 27)

- [nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation](https://mlsanity.com/paper/2404.09556/) (2024)
- [Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography](https://mlsanity.com/paper/2403.17834/) (2024)
- [The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 Challenge](https://mlsanity.com/paper/1912.01054/) (2019)
- [LEEP: A New Measure to Evaluate Transferability of Learned Representations](https://mlsanity.com/paper/2002.12462/) (2020)
- [LogME: Practical Assessment of Pre-trained Models for Transfer Learning](https://mlsanity.com/paper/2102.11005/) (2021)
- [RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank](https://mlsanity.com/paper/2210.02885/) (2022)
- [Transferability and Hardness of Supervised Classification Tasks](https://mlsanity.com/paper/1908.08142/) (2019)
- [SAM-Med3D: Towards General-purpose Segmentation Models for Volumetric Medical Images](https://mlsanity.com/paper/2310.15161/) (2023)
- [ISLES 2022: A multi-center magnetic resonance imaging stroke lesion segmentation dataset](https://mlsanity.com/paper/2206.06694/) (2022)
- [Merlin: A Computed Tomography Vision-Language Foundation Model and Dataset](https://mlsanity.com/paper/2406.06512/) (2024)
- [An Information-Theoretic Approach to Transferability in Task Transfer Learning](https://mlsanity.com/paper/2212.10082/) (2022)
- [VoCo: A Simple-yet-Effective Volume Contrastive Learning Framework for 3D Medical Image Analysis](https://mlsanity.com/paper/2402.17300/) (2024)
- [Transferability Estimation using Bhattacharyya Class Separability](https://mlsanity.com/paper/2111.12780/) (2021)
- [Ranking Neural Checkpoints](https://mlsanity.com/paper/2011.11200/) (2020)
- [The University of California San Francisco Preoperative Diffuse Glioma MRI (UCSF-PDGM) Dataset](https://mlsanity.com/paper/2109.00356/) (2021)
- [BrainSegFounder: Towards 3D Foundation Models for Neuroimage Segmentation](https://mlsanity.com/paper/2406.10395/) (2024)
- [A generalizable 3D framework and model for self-supervised learning in medical imaging](https://mlsanity.com/paper/2501.11755/) (2025)
- [An OpenMind for 3D medical vision self-supervised learning](https://mlsanity.com/paper/2412.17041/) (2024)
- [Primus: Enforcing Attention Usage for 3D Medical Image Segmentation](https://mlsanity.com/paper/2503.01835/) (2025)
- [Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance](https://mlsanity.com/paper/2110.06893/) (2021)
- [3D Foundation Model for Generalizable Disease Detection in Head Computed Tomography](https://mlsanity.com/paper/2502.02779/) (2025)
- [Pick the Best Pre-trained Model: Towards Transferability Estimation for Medical Image Segmentation](https://mlsanity.com/paper/2307.11958/) (2023)
- [The Performance of Transferability Metrics does not Translate to Medical Tasks](https://mlsanity.com/paper/2308.07444/) (2023)
- [Decipher-MR: A Vision-Language Foundation Model for 3D MRI Representations](https://mlsanity.com/paper/2509.21249/) (2025)
- [Large-scale Multi-sequence Pretraining for Generalizable MRI Analysis in Versatile Clinical Applications](https://mlsanity.com/paper/2508.07165/) (2025)
- [Topology-Driven Transferability Estimation of Medical Foundation Models for Segmentation](https://mlsanity.com/paper/2602.23916/) (2026)
- [Topology-Driven Transferability Estimation for 3D Medical Vision Foundation Models](https://mlsanity.com/paper/2607.04199/) (2026)

## Abstract (arXiv)

Self-supervised pretraining has expanded the pool of 3D medical foundation models, but published evaluations use different datasets, endpoints and fine-tuning protocols. Models also differ in architecture, pretraining objective and data, while downstream targets range from voxel-level masks to patient-level diagnoses and outcomes. As a result, published findings provide little directly comparable evidence for choosing a model for a new task. Direct comparison of adaptation performance requires fine-tuning candidates on labelled target data, at substantial computational cost. We benchmark 23 candidates across the same 14 segmentation, classification and regression tasks spanning multiple anatomies and modalities. No candidate ranked among the top three across all segmentation tasks or across all classification and regression tasks; a convolutional encoder could outperform a transformer trained with the same objective on one task but underperform it on another. We benchmark transferability estimators against the fine-tuned rankings and find that their agreement varies across dense segmentation, classification and regression. InsightRank uses task-appropriate frozen-feature statistics and architecture-aware pairwise comparisons to rank candidates before fine-tuning. Across the 23-model pool, mean Kendall tau-b was 0.431 for segmentation and 0.352 for classification and regression. The segmentation Top 3 contained a task winner on four of nine tasks; the image-level Top 3 contained none on the five tasks, despite better full-ranking agreement than the matched conventional estimators. A three-model shortlist reduced recorded extraction-plus-training job time by 85.8% across seven segmentation tasks. Together, the benchmark provides a common reference for model selection and InsightRank offers a lower-cost way to prioritize fine-tuning, with shortlist performance that differs by target type.