# Challenging DINOv3 Foundation Model under Low Inter-Class Variability: A Case Study on Fetal Brain Ultrasound

arXiv: https://arxiv.org/abs/2511.01915 · HTML: https://mlsanity.com/paper/2511.01915/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 46 references that are in the map.
- First posted on arXiv 1 Nov 2025.

## Builds on (most cited first, 15 of 15)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [Medical SAM 2: Segment medical images as video via Segment Anything Model 2](https://mlsanity.com/paper/2408.00874/) (2024)
- [On the Challenges and Perspectives of Foundation Models for Medical Image Analysis](https://mlsanity.com/paper/2306.05705/) (2023)
- [SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasound](https://mlsanity.com/paper/1612.05601/) (2016)
- [USFM: A Universal Ultrasound Foundation Model Generalized to Tasks and Organs towards Label Efficient Image Analysis](https://mlsanity.com/paper/2401.00153/) (2023)
- [A Review on Deep-Learning Algorithms for Fetal Ultrasound-Image Analysis](https://mlsanity.com/paper/2201.12260/) (2022)
- [Generalisability of fetal ultrasound deep learning models to low-resource imaging settings in five African countries](https://mlsanity.com/paper/2209.09610/) (2022)
- [AutoFB: Automating Fetal Biometry Estimation from Standard Ultrasound Planes](https://mlsanity.com/paper/2107.05255/) (2021)
- [Towards Foundation Models Learned from Anatomy in Medical Imaging via Self-Supervision](https://mlsanity.com/paper/2309.15358/) (2023)
- [PSFHS Challenge Report: Pubic Symphysis and Fetal Head Segmentation from Intrapartum Ultrasound Images](https://mlsanity.com/paper/2409.10980/) (2024)
- [General Methods Make Great Domain-specific Foundation Models: A Case-study on Fetal Ultrasound](https://mlsanity.com/paper/2506.19552/) (2025)

## Built on by (most cited first, 1 of 1)

- [FedCC: A Low-Resource Federated Adaptation of Foundation Models for Robust Corpus Callosum localization in Fetal Ultrasound Images](https://mlsanity.com/paper/2607.18283/) (2026)

## Abstract (arXiv)

Purpose: This study provides the first comprehensive evaluation of foundation models in fetal ultrasound (US) imaging under low inter-class variability conditions. While recent vision foundation models such as DINOv3 have shown remarkable transferability across medical domains, their ability to discriminate anatomically similar structures has not been systematically investigated. We address this gap by focusing on fetal brain standard planes--transthalamic (TT), transventricular (TV), and transcerebellar (TC)--which exhibit highly overlapping anatomical features and pose a critical challenge for reliable biometric assessment. Methods: To ensure a fair and reproducible evaluation, all publicly available fetal ultrasound datasets were curated and aggregated into a unified multicenter benchmark, FetalUS-188K, comprising more than 188,000 annotated images from heterogeneous acquisition settings. DINOv3 was pretrained in a self-supervised manner to learn ultrasound-aware representations. The learned features were then evaluated through standardized adaptation protocols, including linear probing with frozen backbone and full fine-tuning, under two initialization schemes: (i) pretraining on FetalUS-188K and (ii) initialization from natural-image DINOv3 weights. Results: Models pretrained on fetal ultrasound data consistently outperformed those initialized on natural images, with weighted F1-score improvements of up to 20 percent. Domain-adaptive pretraining enabled the network to preserve subtle echogenic and structural cues crucial for distinguishing intermediate planes such as TV. Conclusion: Results demonstrate that generic foundation models fail to generalize under low inter-class variability, whereas domain-specific pretraining is essential to achieve robust and clinically reliable representations in fetal brain ultrasound imaging.