FD-AA：一种用于胸部CT偶然腹部异常检测的轻量级焦点-弥散与衰减感知头部
FD-AA: A Lightweight Focal-Diffuse And Attenuation-Aware Head for Incidental Abdominal Abnormality Detection in Chest CT
浏览论文内容
中文总结 AI 辅助
FD-AA是一种轻量级器官感知分类头部，通过衰减感知模块和掩蔽广义均值池化结合焦点与弥散证据，在胸部CT偶然腹部异常检测中超越直接分类，并在多个编码器上取得SOTA性能。
中文摘要 AI 辅助
常规胸部CT扫描会捕获上腹部结构，其中可能包含临床上相关的偶然异常。检测这些发现需要从具有不同空间范围和衰减模式的器官中提取特征。我们提出了FD-AA，一种轻量级的器官感知分类头部，可适配冻结的3D CT编码器。在每个器官内，衰减感知模块保留稀疏的焦点证据，而掩蔽广义均值池化捕获弥散性异常模式。在七个腹部器官中，FD-AA与Pillar-0结合在CT-RATE测试集（AUC = 0.798）和外部RAD-ChestCT数据集（AUC = 0.713）上均达到了最先进（SOTA）性能。具体而言，与仅使用冻结Pillar-0的直接分类相比，FD-AA将宏观AUC/AP从0.763/0.346提升至0.798/0.405（p = 0.034/0.016）。这种性能提升在多个冻结编码器上具有泛化性（MedicalNet上AUC提升+9.8%，CT-CLIP上+14.7%，ResNet上+3.7%），证明了FD-AA在不同特征表示上的有效性。这些结果支持将焦点-弥散聚合与显式HU证据相结合用于偶然腹部异常检测的有效性。
英文摘要
Routine chest CT captures upper-abdominal structures that may contain clinically relevant incidental abnormalities. Detecting these findings requires feature extraction from organs with different spatial extents and attenuation patterns. We propose FD-AA, a lightweight organ-aware classification head adaptable for frozen 3-D CT encoders. Within each organ, an attenuation-aware module preserves sparse focal evidence, while masked generalized-mean pooling captures diffuse anomaly patterns. In seven abdominal organs, FD-AA with Pillar-0 achieved state-of-the-art (SOTA) performance in both the CT-RATE test set (AUC = 0.798) and the external RAD-ChestCT dataset (AUC = 0.713). More specifically, FD-AA improved macro AUC/AP from 0.763/0.346 to 0.798/0.405 over direct classification using frozen Pillar-0 only (p = 0.034/0.016). Such performance gain generalizes across multiple frozen encoders (AUC improvement on MedicalNet +9.8%, CT-CLIP +14.7%, ResNet +3.7%), demonstrating the effectiveness of FD-AA across different feature representations. These results support the effectiveness of integrating focal-diffuse aggregation with explicit HU evidence for incidental abdominal abnormality detection.
发表机构
- Siemens Medical Solutions USA, Inc.（西门子医疗美国有限公司）
- University of California, Los Angeles（加州大学洛杉矶分校）
机构由 AI 辅助整理，请以论文原文为准。
