从CT图像中检测新型冠状病毒感染导致的肺炎：一种细节上采样和注意力引导的深度学习方法

陈俊任; 陈芮; 邱甲军; 殷晋; 张磊

doi:10.12182/20240360605

从CT图像中检测新型冠状病毒感染导致的肺炎：一种细节上采样和注意力引导的深度学习方法

Identifying Novel Coronavirus Pneumonia With CT Images: A Deep Learning Approach With Detail Upsampling and Attention Guidance

摘要

摘要:
目的通过对细节信息的恢复并结合局部信息的挖掘，构建基于深度学习的目标检测方法以帮助放射科医生快速诊断新型冠状病毒感染导致的肺炎（novel coronavirus pneumonia, NCP）患者CT图像中的病灶。
方法提出一种细节上采样和注意力引导的深度学习方法。该方法使用一种基于三双线插值的线性上采样算法来增强特征图在上采样过程中细节信息的恢复能力，并在特征提取模块中嵌入基于垂直和水平空间的视觉注意力机制以增强目标检测算法对NCP病灶关键信息的表征能力。
结果在NCP数据集上的实验结果显示，使用基于细节上采样算法的检测方法与基线模型相比提升了1.07%的召回率，达到了85.14%的AP50。在特征提取模块中嵌入注意力机制后取得了86.13%的AP50和73.92 %的召回率以及90.37%的精确率，优于流行的目标检测模型。
结论 CT图像中基于深度学习的特征信息挖掘能够进一步提升病灶检测能力，所提出的方法有助于放射科医生快速检测CT图像中的NCP病灶，为NCP患者的早期干预和高强度监测提供重要的临床依据。

Abstract:
Objective To construct a deep learning-based target detection method to help radiologists perform rapid diagnosis of lesions in the CT images of patients with novel coronavirus pneumonia (NCP) by restoring detailed information and mining local information.
Methods We present a deep learning approach that integrates detail upsampling and attention guidance. A linear upsampling algorithm based on bicubic interpolation algorithm was adopted to improve the restoration of detailed information within feature maps during the upsampling phase. Additionally, a visual attention mechanism based on vertical and horizontal spatial dimensions embedded in the feature extraction module to enhance the capability of the object detection algorithm to represent key information related to NCP lesions.
Results Experimental results on the NCP dataset showed that the detection method based on the detail upsampling algorithm improved the recall rate by 1.07% compared with the baseline model, with the AP50 reaching 85.14%. After embedding the attention mechanism in the feature extraction module, 86.13% AP50, 73.92% recall, and 90.37% accuracy were achieved, which were better than those of the popular object detection models.
Conclusion The feature information mining of CT images based on deep learning can further improve the lesion detection ability. The proposed approach helps radiologists rapidly identify NCP lesions on CT images and provides an important clinical basis for early intervention and high-intensity monitoring of NCP patients.

HTML全文

参考文献(28)

🍰 koko体育app相关的文章

施引文献

资源附件(0)

开放获取 本文遵循知识共享署名—非商业性使用4.0国际许可协议（CC BY-NC 4.0），允许第三方对本刊发表的论文自由🎉共享（即在任何媒介以任何形式复制、发行原文）、演绎（即修改、转换或以原文为基础进行创作），必须给出适当的署名，提供指向本文许可协议的链接，同时标明是否对原文作了修改；不得将本文用于商业目的。CC BY-NC 4.0许可协议详情请访问