改进Retinanet检测小病灶，提升多尺度病变识别准确率
PDSE: A Multiple Lesion Detector for CT Images using PANet and Deformable Squeeze-and-Excitation Block
- 用PANet增强特征融合，加入低层特征图提升定位精度
- 引入可变形SE模块，增强通道注意力，使小病灶更易被识别
- 在DeepLesion数据集上达到0.20以上mAP，适合医疗影像分析场景
CT图像中病灶检测因病灶类型、大小和位置多样而极具挑战。本文提出一种一阶段检测框架PDSE，通过重构Retinanet，在多模态CT图像中实现更高精度与效率。具体地，通过引入低层特征图增强路径聚合流程；同时采用自适应Squeeze-and-Excitation（SE）块并集成通道特征注意力机制以提升模型表征能力。该方法显著改善了对小尺寸及多尺度病灶的检测性能。在公开的DeepLesion基准测试中，本方法的平均精度均值（mAP）超过0.20，达到当前最优水平。
原文摘要 · Abstract (English)
Detecting lesions in Computed Tomography (CT) scans is a challenging task in medical image processing due to the diverse types, sizes, and locations of lesions. Recently, various one-stage and two-stage framework networks have been developed to focus on lesion localization. We introduce a one-stage lesion detection framework, PDSE, by redesigning Retinanet to achieve higher accuracy and efficiency for detecting lesions in multimodal CT images. Specifically, we enhance the path aggregation flow by incorporating a low-level feature map. Additionally, to improve model representation, we utilize the adaptive Squeeze-and-Excitation (SE) block and integrate channel feature map attention. This approach has resulted in achieving new state-of-the-art performance. Our method significantly improves the detection of small and multiscaled objects. When evaluated against other advanced algorithms on the public DeepLesion benchmark, our algorithm achieved an mAP of over 0.20.
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。