# UltraAD: Fine-Grained Ultrasound Anomaly Classification via Few-Shot CLIP Adaptation

arXiv: https://arxiv.org/abs/2506.19694 · HTML: https://mlsanity.com/paper/2506.19694/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 24 Jun 2025.

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling](https://mlsanity.com/paper/2111.03930/) (2021)
- [WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation](https://mlsanity.com/paper/2303.14814/) (2023)
- [Visual-Language Prompt Tuning with Knowledge-guided Context Optimization](https://mlsanity.com/paper/2303.13283/) (2023)
- [AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection](https://mlsanity.com/paper/2310.18961/) (2023)
- [AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection](https://mlsanity.com/paper/2407.15795/) (2024)
- [Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images](https://mlsanity.com/paper/2403.12570/) (2024)
- [Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures](https://mlsanity.com/paper/2307.15220/) (2023)
- [LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP](https://mlsanity.com/paper/2404.02285/) (2024)
- [VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation](https://mlsanity.com/paper/2407.12276/) (2024)
- [MediCLIP: Adapting CLIP for Few-shot Medical Image Anomaly Detection](https://mlsanity.com/paper/2405.11315/) (2024)
- [Class-Aware Adversarial Transformers for Medical Image Segmentation](https://mlsanity.com/paper/2201.10737/) (2022)
- [Robotic Ultrasound Imaging: State-of-the-Art and Future Perspectives](https://mlsanity.com/paper/2307.05545/) (2023)
- [CMU-Net: A Strong ConvMixer-based Medical Ultrasound Image Segmentation Network](https://mlsanity.com/paper/2210.13012/) (2022)
- [Diffusion Models with Implicit Guidance for Medical Anomaly Detection](https://mlsanity.com/paper/2403.08464/) (2024)
- [Machine Learning in Robotic Ultrasound Imaging: Challenges and Perspectives](https://mlsanity.com/paper/2401.02376/) (2024)
- [Intelligent Robotic Sonographer: Mutual Information-based Disentangled Reward Learning from Few Demonstrations](https://mlsanity.com/paper/2307.03705/) (2023)
- [Motion Magnification in Robotic Sonography: Enabling Pulsation-Aware Artery Segmentation](https://mlsanity.com/paper/2307.03698/) (2023)
- [VibNet: Vibration-Boosted Needle Detection in Ultrasound Images](https://mlsanity.com/paper/2403.14523/) (2024)
- [Class-Aware Cartilage Segmentation for Autonomous US-CT Registration in Robotic Intercostal Ultrasound Imaging](https://mlsanity.com/paper/2406.04100/) (2024)
- [Text-driven Adaptation of Foundation Models for Few-shot Surgical Workflow Analysis](https://mlsanity.com/paper/2501.09555/) (2025)

## Built on by (most cited first, 5 of 5)

- [Speckle2Self: Self-Supervised Ultrasound Speckle Reduction Without Clean Data](https://mlsanity.com/paper/2507.06828/) (2025)
- [Recognizing Surgical Phases Anywhere: Few-Shot Test-time Adaptation and Task-graph Guided Refinement](https://mlsanity.com/paper/2506.20254/) (2025)
- [MTL-MAD: Multi-Task Learners are Effective Medical Anomaly Detectors](https://mlsanity.com/paper/2605.05891/) (2026)
- [Beyond Static Anchors: Bounded Prototype Conditioning for Language-Free Medical Anomaly Detection](https://mlsanity.com/paper/2608.00442/) (2026)
- [Bridging Vision Foundation Model Priors with CLIP for Spatial-aware Few-shot Anomaly Detection in Medical Images](https://mlsanity.com/paper/2609.12454/) (2026)

## Abstract (arXiv)

Precise anomaly detection in medical images is critical for clinical decision-making. While recent unsupervised or semi-supervised anomaly detection methods trained on large-scale normal data show promising results, they lack fine-grained differentiation, such as benign vs. malignant tumors. Additionally, ultrasound (US) imaging is highly sensitive to devices and acquisition parameter variations, creating significant domain gaps in the resulting US images. To address these challenges, we propose UltraAD, a vision-language model (VLM)-based approach that leverages few-shot US examples for generalized anomaly localization and fine-grained classification. To enhance localization performance, the image-level token of query visual prototypes is first fused with learnable text embeddings. This image-informed prompt feature is then further integrated with patch-level tokens, refining local representations for improved accuracy. For fine-grained classification, a memory bank is constructed from few-shot image samples and corresponding text descriptions that capture anatomical and abnormality-specific features. During training, the stored text embeddings remain frozen, while image features are adapted to better align with medical data. UltraAD has been extensively evaluated on three breast US datasets, outperforming state-of-the-art methods in both lesion localization and fine-grained medical classification. The code will be released upon acceptance.