Wang Xing, Wu Houde, Wang Longshuang, Chen Jingxu, Li Yi, He Xinliu, Chen Ting, Wang Minghui, Guo Li
Department of Cardiology, Tianjin Chest Hospital, Tianjin, 300000, China.
School of Medical Imaging, Tianjin Medical University, No. 1 Guangdong Road, Tianjin, 300203, China.
BMC Med Imaging. 2025 Jul 1;25(1):247. doi: 10.1186/s12880-025-01784-0.
Lung cancer remains the leading cause of cancer-related mortality worldwide, emphasizing the critical need for early pulmonary nodule detection to improve patient outcomes. Current methods encounter challenges in detecting small nodules and exhibit high false positive rates, placing an additional diagnostic burden on radiologists. This study aimed to develop a two-stage deep learning model integrating U-Net, Yolov8s, and the Swin transformer to enhance pulmonary nodule detection in computer tomography (CT) images, particularly for small nodules, with the goal of improving detection accuracy and reducing false positives.
We utilized the LUNA16 dataset (888 CT scans) and an additional 308 CT scans from Tianjin Chest Hospital. Images were preprocessed for consistency. The proposed model first employs U-Net for precise lung segmentation, followed by Yolov8s augmented with the Swin transformer for nodule detection. The Shape-aware IoU (SIoU) loss function was implemented to improve bounding box predictions.
For the LUNA16 dataset, the model achieved a precision of 0.898, a recall of 0.851, and a mean average precision at 50% IoU (mAP50) of 0.879, outperforming state-of-the-art models. The Tianjin Chest Hospital dataset has a precision of 0.855, a recall of 0.872, and an mAP50 of 0.862.
This study presents a two-stage deep learning model that leverages U-Net, Yolov8s, and the Swin transformer for enhanced pulmonary nodule detection in CT images. The model demonstrates high accuracy and a reduced false positive rate, suggesting its potential as a useful tool for early lung cancer diagnosis and treatment.
肺癌仍是全球癌症相关死亡的主要原因，这凸显了早期肺结节检测对于改善患者预后的迫切需求。当前的检测方法在检测小结节时面临挑战，且假阳性率较高，给放射科医生带来了额外的诊断负担。本研究旨在开发一种集成U-Net、Yolov8s和Swin变换器的两阶段深度学习模型，以提高计算机断层扫描（CT）图像中肺结节的检测能力，特别是对于小结节，目标是提高检测准确性并减少假阳性。
我们使用了LUNA16数据集（888例CT扫描）以及来自天津胸科医院的另外308例CT扫描。对图像进行预处理以确保一致性。所提出的模型首先使用U-Net进行精确的肺部分割，然后使用增强了Swin变换器的Yolov8s进行结节检测。采用形状感知交并比（SIoU）损失函数来改进边界框预测。
对于LUNA16数据集，该模型的精度为0.898，召回率为0.851，在50%交并比（IoU）下的平均精度均值（mAP50）为0.879，优于现有最先进的模型。天津胸科医院数据集的精度为0.855，召回率为0.872，mAP50为0.862。
本研究提出了一种两阶段深度学习模型，该模型利用U-Net、Yolov8s和Swin变换器来增强CT图像中肺结节的检测。该模型显示出高准确性和降低的假阳性率，表明其作为早期肺癌诊断和治疗有用工具的潜力。
