College of Electronic Information Engineering, Hebei University of Technology, Tianjin 300401, China.
Comput Intell Neurosci. 2022 Mar 31;2022:9465646. doi: 10.1155/2022/9465646. eCollection 2022.
The characteristics of pulmonary are complex, and the cost of manual screening is high. The detection model based on convolutional neural network is an essential method for assisted diagnosis with artificial intelligence. However, it also has the disadvantages of complex structure and a large number of parameters, and the detection accuracy needs to be further improved. Therefore, an improved lightweight YOLOv4 pulmonary detection model named MIP-MY is proposed. Firstly, over 300 actual cases are selected to make a common dataset by professional physicians, which is used to evaluate the performance of the model. Subsequently, by introducing the inverted residual channel attention and the pyramid pooling module, a new structure of MIP is created and used as the backbone extractor of MIP-MY, which could further decrease the number of parameters and fuse context information. Then the multiple receptive field module is added after the three effective feature layers of the backbone extractor, which effectively enhances the information extraction ability of the deep feature layer and reduces the miss detection rate of small pulmonary lesions. Finally, the pulmonary detection model MIP-MY with lightweight and multiple receptive field characteristics is constructed by combining each improved modules with multiscale structure. Compared to the original YOLOv4, the model parameters of MIP-MY is reduced by 47%, while the mAP value is raised to 95.32% and the miss detection rate is decreased to 6%. It is verified that the model can effectively assist radiologists in the diagnosis of pulmonary .
肺部 的特征复杂，手动筛查成本高。基于卷积神经网络的检测模型是人工智能辅助诊断的重要方法。但是，它也存在结构复杂、参数多的缺点，检测精度有待进一步提高。因此，提出了一种改进的轻量级 YOLOv4 肺部 检测模型，命名为 MIP-MY。首先，由专业医生选择 300 多个实际病例制作通用数据集，用于评估模型的性能。随后，通过引入倒置残差通道注意力和金字塔池化模块，创建了新的 MIP 结构，并将其用作 MIP-MY 的骨干提取器，进一步减少了参数数量并融合了上下文信息。然后在骨干提取器的三个有效特征层后添加了多感受野模块，有效增强了深层特征层的信息提取能力，降低了小肺部 病变的漏检率。最后，通过将每个改进的模块与多尺度结构相结合，构建了具有轻量化和多感受野特征的肺部 检测模型 MIP-MY。与原始的 YOLOv4 相比，MIP-MY 的模型参数减少了 47%，而 mAP 值提高到 95.32%，漏检率降低到 6%。验证了该模型可以有效辅助放射科医生进行肺部 诊断。
