# DINO-3DRA: Leveraging 2D Foundation Model Semantics for 3D Cerebral Aneurysm Segmentation

arXiv: https://arxiv.org/abs/2608.07767 · HTML: https://mlsanity.com/paper/2608.07767/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 24 references that are in the map.
- First posted on arXiv 7 Aug 2026.

## Builds on (most cited first, 17 of 17)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation](https://mlsanity.com/paper/1912.05074/) (2019)
- [DeepVesselNet: Vessel Segmentation, Centerline Prediction, and Bifurcation Detection in 3-D Angiographic Volumes](https://mlsanity.com/paper/1803.09340/) (2018)
- [DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation](https://mlsanity.com/paper/2503.18944/) (2025)
- [MedDINOv3: How to adapt vision foundation models for medical image segmentation?](https://mlsanity.com/paper/2509.02379/) (2025)
- [Dino U-Net: Exploiting High-Fidelity Dense Features from Foundation Models for Medical Image Segmentation](https://mlsanity.com/paper/2508.20909/) (2025)
- [Medical Slice Transformer: Improved Diagnosis and Explainability on 3D Medical Images with DINOv2](https://mlsanity.com/paper/2411.15802/) (2024)
- [Does DINOv3 Set a New Medical Vision Standard? Benchmarking 2D and 3D Classification, Segmentation, and Registration](https://mlsanity.com/paper/2509.06467/) (2025)
- [Exploiting DINOv3-Based Self-Supervised Features for Robust Few-Shot Medical Image Segmentation](https://mlsanity.com/paper/2601.08078/) (2026)
- [Adaptive Semi-Supervised Segmentation of Brain Vessels with Ambiguous Labels](https://mlsanity.com/paper/2308.03613/) (2023)
- [Unsupervised Domain Adaptation for Brain Vessel Segmentation through Transwarp Contrastive Learning](https://mlsanity.com/paper/2402.15237/) (2024)
- [GS-EMA: Integrating Gradient Surgery Exponential Moving Average with Boundary-Aware Contrastive Learning for Enhanced Domain Generalization in Aneurysm Segmentation](https://mlsanity.com/paper/2402.15239/) (2024)

## Abstract (arXiv)

Accurate aneurysm segmentation in 3D rotational angiography (3DRA) is hindered by extreme class imbalance, morphological similarity to vessels, and absent large-scale 3D pretraining. 2D vision foundation models encode dense structural priors from 1.7 billion images, yet na"ive slice-wise transfer fragments anatomical continuity and destabilises optimisation. We propose DINO-3DRA, a dual-path framework achieving effective cross-dimensional semantic transfer by injecting frozen DINOv3 features into a 3D U-Net backbone via Room-Lite spatial mixing and calibrated residual fusion. On multi-centre 3DRA data, DINO-3DRA achieves state-of-the-art aneurysm segmentation (Dice: 0.758; HD95: 2.75 mm; +13% over nnU-Net) with only 5.72M trainable parameters. Ablation studies confirm that gains arise from structured cross-dimensional transfer rather than loss design alone, with bridged foundation features improving anatomical continuity between aneurysms and parent vessels. Without fine-tuning on CADA and SHINY-ICARUS, DINO-3DRA eliminates all catastrophic failure cases observed in baseline architectures, demonstrating robust generalisation across heterogeneous imaging protocols.