用注意力机制修正误检，提升癌症病理图像中分裂细胞检测准确率。
MIDOG 2025: Mitotic Figure Detection with Attention-Guided False Positive Correction
- 引入反馈注意力网络，区分正常与异常分裂细胞
- 融合网络修正原始检测框，使F1得分达0.655
- 适合医学图像检测、病理诊断辅助系统开发者
我们提出一种新方法，扩展现有的全卷积单阶段目标检测器（FCOS）用于分裂细胞检测。复合模型加入反馈注意力级联网络（FAL-CNN），用于分类正常与异常分裂细胞，并通过融合网络对FCOS预测的边界框进行调整。该方法旨在降低FCOS的误检率，提升检测精度并增强模型泛化能力。在初步评估数据集上，模型的分裂细胞检测F1得分为0.655。
原文摘要 · Abstract (English)
We present a novel approach which extends the existing Fully Convolutional One-Stage Object Detector (FCOS) for mitotic figure detection. Our composite model adds a Feedback Attention Ladder CNN (FAL-CNN) model for classification of normal versus abnormal mitotic figures, feeding into a fusion network that is trained to generate adjustments to bounding boxes predicted by FCOS. Our network aims to reduce the false positive rate of the FCOS object detector, to improve the accuracy of object detection and enhance the generalisability of the network. Our model achieved an F1 score of 0.655 for mitosis detection on the preliminary evaluation dataset.
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。