发表机构
Institute of Information Processing, Leibniz University Hannover; CAIMED, L3S; Department of Radiology, Charité Universitätsmedizin Berlin; Image Data Exploration and Analysis Lab, Friedrich-Alexander University Erlangen-Nürnberg; Institute for Radiology, University Hospital Erlangen（莱布尼茨汉诺威大学信息处理研究所; CAIMED，L3S; 柏林夏里特大学医学中心放射科; 埃尔朗根-纽伦堡弗里德里希-亚历山大大学图像数据探索与分析实验室; 埃尔朗根大学医院放射研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对女性盆腔疾病实时异常检测难题，提出基于Dinomaly的无监督框架，利用冻结的DINOv3视觉Transformer编码器等，在子宫肌瘤数据集上评估，实现高像素级AUROC和帧级特异性，满足实时临床需求，为医生决策和协议调整提供支持。
AI 中文摘要
女性盆腔疾病研究不足，诊断常延迟。盆腔MRI虽能提供软组织对比，但实时异常检测因生理运动、组织变形和仪器伪影而具挑战性。现有监督方法不实用。本文提出基于Dinomaly的无监督异常检测框架，从健康病例学习规范表示，无需标签标记偏差。利用冻结的DINOv3视觉Transformer编码器等，通过编码器和解码器表示间的逐令牌余弦距离定位异常，生成空间异常图。在子宫肌瘤数据集上评估，框架实现了88.06%的像素级AUROC和95.45%的帧级高特异性，每秒40.5切片，满足实时临床部署要求，能为放射科医生决策和自适应协议调整提供支持。
英文摘要
Female pelvic diseases remain an under researched area characterized by often delayed diagnosis. While pelvic MRI offers superior soft-tissue contrast for diagnosis and image-guided procedures, real-time anomaly detection remains challenging due to physiological motion, tissue deformation, and instrument artifacts. Existing supervised approaches are impractical, as adverse events are rare, heterogeneous, and difficult to annotate. We present a Dinomaly-based unsupervised anomaly detection framework adapted for pelvic MRI that learns normative representations from healthy cases and flags deviations without requiring labels. Our approach leverages a frozen DINOv3 Vision Transformer encoder combined with a noisy MLP bottleneck and Linear Attention decoder to prevent identity mapping while maintaining computational efficiency. Anomalies are localized via per-token cosine distance between encoder and decoder representations, yielding spatial anomaly maps that provide immediate feedback at the scanner to support radiologist decision-making and adaptive protocol adjustment. Evaluated on a curated subset of the Uterine Myoma Dataset, the framework achieves a pixel-level AUROC of 88.06% and high specificity (95.45%) at frame level at 40.5 slices/s, meeting real-time clinical deployment requirements. The spatial anomaly maps and frame-level scores provide immediate, localized feedback at the scanner to support radiologist decision-making and adaptive protocol adjustment during active procedures.
Comments10 pages, 5 figures
