GRAPE让医学影像诊断模型更智能、安全且可扩展。
GRAPE: Graph-Augmented Prototype Explanations for Interactive Medical Image Diagnosis
- 用图注意力建模解剖结构共现关系，提升诊断准确性。
- 检测医生标注冲突，误标识别率高达85%且无额外开销。
- 只需一张标注图即可新增病灶类型，无需重训练。
基于原型的医学图像分类器存在三大临床缺陷：将病灶视为独立、隐式放大不安全的医生反馈、新增病灶需全量重训。本文提出GRAPE（图增强原型解释），统一解决上述问题。首先，图注意力任务头建模解剖概念共现，在TBX11K上使宏平均F1提升13.8个百分点；其次，提出首个原型模型中的概念不一致安全检查机制，能在医生绘制区域与模型主导发现冲突时预警，对错误标注的检出率达85%，远超MC-Dropout的51%，且无额外推理开销；第三，开放词汇原型锚定技术将视觉原型与临床文本对齐，仅需单张标注图像即可引入新病灶类型，无需修改其他模块。在NIH ChestX-ray14上，仅用一个积液样本即恢复全监督定位精度；在TBX11K上，原型图谱的病灶定位效果优于端到端基线2.6倍。三项功能均仅增加1~2毫秒延迟，适用于交互式批量处理。项目页面：https://github.com/KurbanIntelligenceLab/GRAPE。
原文摘要 · Abstract (English)
Prototype-based medical image classifiers present three clinical limitations: they treat findings as independent, silently amplify unsafe physician feedback, and require full retraining whenever a new finding is needed. We present GRAPE (Graph-Augmented Prototype Explanations), a unified architecture that addresses all three challenges. First, a Graph Attention Task Head models anatomical concept co-occurrence, boosting macro-F1 by +13.8,pp over the prototype baseline on TBX11K. Second, a Concept-Mismatch Safety Check - the first such mechanism in prototype-based medical classifiers - warns when the model's dominant finding inside a doctor-drawn region conflicts with the claimed label, catching 85% of erroneous annotations versus 51% for MC-Dropout with no extra inference cost. Third, Open-Vocabulary Prototype Anchoring aligns visual prototypes to clinical text, allowing a new finding to be added from a single labeled image without modifying any other component. On NIH ChestX-ray14, one Effusion example recovers full-supervision localization accuracy; on TBX11K, prototype maps achieve 2.6x better lesion localization than end-to-end baselines. All three capabilities add only +1~ms latency at interactive batch size. The project page is https://github.com/KurbanIntelligenceLab/GRAPE.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。