用轻量版Swin Transformer高效检测肺结节，小结节识别更准。
An Efficient Approach to Detecting Lung Nodules Using Swin Transformer
- 用小型Swin Transformer+特征金字塔网络，兼顾精度与效率。
- 小结节检测的mAP和mAR分别提升1.3%和1.6%，整体mAP达94.7%。
- 适合医疗影像快速筛查，尤其对小结节检测有优势。
肺癌是致死率最高的癌症，早期诊断可显著提升生存率。肺结节是肺癌的常见征兆，其检测至关重要。现有检测模型多存在效率不足问题。本文提出一种新方法，基于2D CT切片，降低训练与推理的计算负担。采用Swin Transformer的微型版本，兼顾视觉变换器（ViT）的优势与低计算成本。引入特征金字塔网络以增强小结节检测能力。同时使用迁移学习加速训练过程。实验结果表明，所提模型在小结节检测上达到更高的平均精度（mAP）和平均召回率（mAR），分别比当前最优方法提升1.3%和1.6%。总体实现mAP 94.7%、mAR 94.9%，优于现有方法。
原文摘要 · Abstract (English)
Lung cancer has the highest rate of cancer-caused deaths, and early-stage diagnosis could increase the survival rate. Lung nodules are common indicators of lung cancer, making their detection crucial. Various lung nodule detection models exist, but many lack efficiency. Hence, we propose a more efficient approach by leveraging 2D CT slices, reducing computational load and complexity in training and inference. We employ the tiny version of Swin Transformer to benefit from Vision Transformers (ViT) while maintaining low computational cost. A Feature Pyramid Network is added to enhance detection, particularly for small nodules. Additionally, Transfer Learning is used to accelerate training. Our experimental results show that the proposed model outperforms state-of-the-art methods, achieving higher mAP and mAR for small nodules by 1.3% and 1.6%, respectively. Overall, our model achieves the highest mAP of 94.7% and mAR of 94.9%.
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。