paper-with-me

홈 › Papers

Toward Training-Free Zero-Shot Anomaly Detection in 3D Medical Images: A Batch-Based Approach Using 2D Foundation Models

2026-06-17 · Tai Le-Gia arxiv

Zero-shot anomaly detection (ZSAD) is attractive for medical imaging because clinical systems must handle heterogeneous acquisition protocols, changing patient populations, and pathologies for which annotated training data may be unavailable. Most existing zero-shot anomaly detection methods are designed for 2D images, and their direct extension to 3D medical volumes is limited by the scarcity of large-scale volumetric foundation models or by the difficulty of utilizing volumetric context. We propose CS3F, a training-free batch-based framework for ZSAD in 3D medical images using 2D foundation models. Each volume is decomposed along multiple anatomical axes and encoded slice-wise by a 2D vision transformer. These are then converted into localized volumetric tokens by pooling neighboring slice features. Anomaly scores are obtained from cross-subject mutual similarity: tokens that lack close analogues in other subjects are assigned higher anomaly scores. To reduce the attenuation of focal lesion signals caused by depth pooling, we introduce a coarse-to-fine tokenization strategy that enables fine-resolution volumetric scoring without exhaustive matching. CS3F is evaluated on brain MRI across metastases, glioma, and stroke, as well as validated on lung CT to test generalizability beyond atlas-aligned brain MRI. The results show that frozen 2D foundation models can support anomaly localization in 3D medical images, and that the benefit of fine tokenization depends strongly on lesion contrast and imaging modality.

📄 PDF Abstract BibTeX arXiv:2606.18749

Code (0)

등록된 구현이 없습니다.

Tasks

Anomaly Detection

Similar Papers 제목 키워드 기반

AnomalyAgent: Training-Free Agentic Models for Zero-/Few-Shot Anomaly Detection

2026-05-28 · Yi Zhang, Jiawen Zhu, Lele Fu, Guansong Pang arxiv

Benefiting from generalizability of vision-language models (VLMs) such as CLIP, many zero-/few-shot anomaly detection (AD) approaches have achieved impressive detection performance across various datasets. Nevertheless, …

Anomaly Detection

Training-Free Zero-Shot Anomaly Detection in 3D Brain MRI with 2D Foundation Models

2026-02-17 · Tai Le-Gia, Jaehyun Ahn arxiv

Zero-shot anomaly detection (ZSAD) has gained increasing attention in medical imaging as a way to identify abnormalities without task-specific supervision, but most advances remain limited to 2D datasets. Extending ZSAD …

Anomaly Detection

FADE: Few-shot/zero-shot Anomaly Detection Engine using Large Vision-Language Model

2024-08-31 · Yuanwei Li, Elizaveta Ivanova, Martins Bruveris

Automatic image anomaly detection is important for quality inspection in the manufacturing industry. The usual unsupervised anomaly detection approach is to train a model for each object class using a dataset of normal s…

Anomaly DetectionAnomaly SegmentationLanguage ModelingLanguage Modelling+2

Zero-Shot Anomaly Detection via Batch Normalization

2023-02-15 · NeurIPS 2023 11 · Aodong Li, Chen Qiu, Marius Kloft, Padhraic Smyth 외

Anomaly detection (AD) plays a crucial role in many safety-critical application domains. The challenge of adapting an anomaly detector to drift in the normal data distribution, especially when no training data is availab…

Anomaly DetectionUnsupervised Anomaly Detectionzero-shot anomaly detectionZero-shot Generalization

MRAD: Zero-Shot Anomaly Detection with Memory-Driven Retrieval

2026-01-31 · Chaoran Xu, Chengkan Lv, Qiyu Chen, Feng Zhang 외 arxiv

Zero-shot anomaly detection (ZSAD) often leverages pretrained vision or vision-language models, but many existing methods use prompt learning or complex modeling to fit the data distribution, resulting in high training o…

Anomaly ClassificationAnomaly Detection