摘要
目的超声弹性成像技术已逐步应用于支气管淋巴结良恶性的诊断,帮助确定肺癌分期。在支气管超声弹性图像中,淋巴结区域的精确定位对诊断准确度具有重要影响,但通常依赖专业医师的手动分割,费时费力。为此,本文设计了一种注意力上下文编码器网络(attention context encoder network,ACE-Net)。方法本文网络模型包括编码器、上下文提取器和解码器3部分。使用在ImageNet数据集上预训练且去掉平均池化层和全连接层的34层残差网络ResNet-34作为编码器提取特征,上下文提取器从编码器的输出中进一步提取高级语义信息,同时保留尽可能多的空间信息,基于AG(attention gate)的解码器可以抑制输入图像中的不相关区域,同时突出对当前任务更关键的特征。结果实验在本文收集的包含支气管超声弹性图像及对应分割标签的数据集上进行,与6种典型的U-Net结构深度网络模型的分割性能进行对比,数据集中的每幅图像中的淋巴结都由专业医师手动分割标注。基础U-Net网络得到淋巴结分割结果的Dice系数、敏感度和特异度分别为0.8207、85.08%和96.82%,其他改进网络的分割性能在此基础上均有一定提高,本文方法的Dice系数、敏感度和特异度分别为0.8451、87.92%和97.04%,Dice系数和敏感度在所有方法中取得了最优值,特异度取得了次优值。结论以U-Net为代表的深度学习模型在支气管超声弹性图像淋巴结分割问题中具有很大潜力,将上下文提取器和注意力机制融入U-Net网络可以一定程度提升分割精度。本文收集的数据集将有助于推动支气管超声弹性图像淋巴结分割问题的研究。
Objective Lung cancer threatens human health severely.It is one of the malignant tumors with the fastest increase in morbidity and mortality and the greatest threat to the life of the population.In the past 50 years,many countries have addressed that the incidence and mortality of lung cancer have increased significantly.The incidence and mortality of lung cancer rank the first among all the malignant tumors.Recent ultrasound elastography technology has been gradually applied to diagnose the benign and malignant bronchial lymph nodes to aid the degree analysis of lung cancer.Ultrasonic elastography provides more information than conventional two-dimensional ultrasound via the evaluation of lesion toughness.Color Doppler energy imaging superimposes the color coding system on the conventional ultrasound image.In general,the hardness of the diseased lymph node is relatively large,and the degree of deformation is small after being squeezed,which is represented as blue color in the elastic image.The normal lymph node is relatively soft,which is represented as red or green colors in the elastic image.Bronchial ultrasound elastography is generated through the squeezing deformation issues of the lymph nodes in related to the record of heartbeat,breathing movement and the pulsation of blood vessels around the lungs.In bronchial ultrasound elastic images,the precise positioning of the lymph node area is of great significance to the diagnosis accuracy of the disease.However,this kind of task is time-consuming and laborious due to its manual segmentation in clinical.We carried out the deep learning based automatic segmentation method of mediastinal lymph nodes in bronchial ultrasound elastic images via U-Net-type architectures.Method A dataset consisting of 205 bronchial ultrasound elastic images and corresponding segmentation labels is collected.The lymph nodes of each image are manually segmented and labeled.Based on this dataset,six classic deep network models based on U-Net are tested.The U-Net has an encoderdecoder stru
作者
刘羽
吴蓉蓉
唐璐
宋宁宁
Liu Yu;Wu Rongrong;Tang Lu;Song Ningning(Department of Biomedical Engineering,Hefei University of Technology,Hefei 230009,China;School of Medical Imaging,Xuzhou Medical University,Xuzhou 221004,China;Nanjing First Hospital,Nanjing 210006,China)
出处
《中国图象图形学报》
CSCD
北大核心
2022年第10期3082-3091,共10页
Journal of Image and Graphics
基金
国家自然科学基金项目(82001912,62176081,61701160)。
