基于YOLOv8m的改进腕部X光片骨折检测算法  

Fracture detection in wrist X-ray image using an improved algorithm based on YOLOv8m

在线阅读下载全文

作  者:彭志博 陈勇[1] 崔艳荣[1] PENG Zhibo;CHEN Yong;CUI Yanrong(School of Computer Science,Yangtze University,Jingzhou 434000,China)

机构地区:[1]长江大学计算机科学学院,湖北荆州434000

出  处:《中国医学物理学杂志》2025年第4期542-549,共8页Chinese Journal of Medical Physics

基  金:国家自然科学基金(62077018)。

摘  要:目前腕部X光片的骨折检测存在误诊率高、医疗资源不足等问题。为了辅助医生进行骨折诊断,提出了一种基于YOLOv8m的X光片骨折检测方法。首先引入可分离大核注意力机制来提取重要特征信息,抑制不显著特征信息;然后将残差块融入注意力机制,增强注意力机制的作用,增加模型的泛化能力;最后将可切换空洞卷积与C2f模块结合,增加模型的感受野,捕捉不同尺寸的特征信息。实验结果表明,与先进的YOLOv8l改进模型相比,本文模型mAP50提高了1.3%,由于使用了规格更小的YOLOv8m为基础模型,参数量降低了14.3%,浮点运算次数降低了42.7%。此模型能够辅助放射科医生进行腕部X光片的骨折诊断。Currently,the fracture detection in wrist X-ray image has high misdiagnosis rates and faces the challenge of inadequate medical resources.To assist doctors in fracture diagnosis,an improved approach based on YOLOv8m for fracture detection in wrist X-ray image is proposed:(1)a large separable kernel attention mechanism is introduced to extract crucial feature information while suppressing insignificant ones;(2)residual block is integrated into the attention mechanism to enhance its effectiveness and the model's generalization ability;(3)switchable atrous convolution is combined with the C2f module to expand the model's receptive field,enabling it to capture multi-scale feature information.Experimental results demonstrate that compared with the improved model based on the advanced YOLOv8l,the proposed approach achieves a 1.3%increase in mAP50.Notably,by adopting the more compact YOLOv8m model as the basic model,parameter count is reduced by 14.3%,and the floating-point operations per second is lowered by 42.7%.The proposed model can effectively aid radiologists in detecting fractures in wrist X-ray image.

关 键 词:X射线 骨折检测 深度学习 YOLOv8 

分 类 号:R318[医药卫生—生物医学工程] TP391[医药卫生—基础医学]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象