首页|期刊导航|郑州大学学报(理学版)|基于X光影像的肺炎分类与定位方法研究

基于X光影像的肺炎分类与定位方法研究OA

Research on Pneumonia Classification and Localization Methods Based on X-ray Imaging

中文摘要英文摘要

肺炎是一种高致死率的疾病,针对肺炎治疗与早期筛查工具的研究受到了广泛关注.然而,胸部影像的复杂性、标注的困难性,以及肺炎类间相似性、类内差异性均为研究带来了挑战.首先,采用基于孪生网络的自监督学习方法提取胸部 X 光影像的自监督视觉特征表示,并通过多层感知机(multilayer perceptron,MLP)检测头完成肺炎的分类任务.其次,在 YOLOv10 的骨干网络中引入空间通道注意力机制,利用通道内的空间信息增强肺炎病灶特征,从而提升 YOLOv10 网络对肺炎病灶的识别能力.最后,在 COVID-19 Radiography Database 和 RSNA Pneumonia Detection 数据集上对所提出的方法进行了评估,实验结果表明所提出的算法在基于 X 光影像的肺炎分类与定位任务中的有效性.

Pneumonia is a disease characterized by high mortality,and research on its treatment and ear-ly screening tools has garnered significant attention.However,the complexity of chest images,annotation difficulty,and the inter-class similarities and intra-class variations of pneumonia all pose challenges to pneumonia classification and localization tasks based on X-ray images.To address these challenges,a new method was proposed in this study.Firstly,a self-supervised learning approach utilizing a siamese network was applied to extract self-supervised visual feature representation of chest X-ray images,and a multi-layer perceptron(MLP)detection head was used to perform pneumonia classification task.Second-ly,a spatial-channel attention module was designed in the backbone network of YOLOv10.By utilizing the spatial information across channels to enhance pneumonia features,the ability of the YOLOv10 net-work to identify pneumonia lesions was enhanced.Finally,the proposed algorithm was evaluated using the COVID-19 Radiography Database and RSNA Pneumonia Detection dataset.The results demonstrated its effectiveness of the proposed algorithm in pneumonia classification and localization tasks based on X-ray images.

温亚雪;李玉琴;蒋振刚;师为礼;代博璠

长春理工大学 计算机科学技术学院 吉林 长春 130022长春理工大学 计算机科学技术学院 吉林 长春 130022长春理工大学 计算机科学技术学院 吉林 长春 130022长春理工大学 计算机科学技术学院 吉林 长春 130022长春理工大学 计算机科学技术学院 吉林 长春 130022

信息技术与安全科学

肺炎分类病灶定位自监督学习注意力机制

pneumonia classificationlesion localizationself-supervised learningattention mechanism

《郑州大学学报(理学版)》 2026 (6)

55-60,6

吉林省教育厅科学技术研究项目(JJKH20240948KJ)

10.13705/j.issn.1671-6841.2025016

评论