秦品乐 李启 曾建潮 张娜 宋宇龙

摘 要：现有基于内容的医学图像检索（CBMIR）算法存在特征提取的不足，导致图像的语义信息表达不完善、图像检索性能较差，为此提出一种多尺度密集网络算法以提高检索精度。首先，将512×512的肺结节图像降维到64×64，同时加入密集模块（dense block）以解决提取的低层特征和高层语义特征之间的差距;其次，由于网络的不同层提取的肺结节图像信息不同，为了提高检索精度和效率，采用多尺度方法结合图像的全局特征和结节局部特征生成检索哈希码。实验结果分析表明，与自适应比特位的检索（ABR）算法相比，提出的算法在64位哈希码编码长度下的肺结节图像检索查准率可以达到91.17%，提高了3.5个百分点;检索一张肺切片需要平均时间为48μs。所提算法的检索结果在表达图像丰富的语义特征和检索效率方面，优于其他对比的网络结构，适用于为医生临床辅助诊断提供依据、帮助患者有效治疗。

关键词：肺结节;医学图像检索;多尺度;密集块;哈希函数

中图分类号： TP391.3

文献标志码：A

Abstract： Aiming at the insufficiency of feature extraction in the existing Content-Based Medical Image Retrieval （CBMIR） algorithms， which resulted in imperfect semantic information representation and poor image retrieval performance， an algorithm based on multi-scale dense network was proposed. Firstly， the size of pulmonary nodule image was reduced from 512×512 to 64×64， and the dense block was added to solve the gap between the extracted low-level features and high-level semantic features. Secondly， as the information of pulmonary nodule images extracted by different layers in the network was varied， in order to improve the retrieval accuracy and efficiency， the multi-scale method was used to combine the global features of the image and the local features of the nodules， so as to generate the retrieval hash code. Finally， the experimental results show that compared with the Adaptive Bit Retrieval （ABR） algorithm， the average retrieval accuracy for pulmonary nodule images based on the proposed algorithm under 64-bit hash code length can reach 91.17%， which is increased by 3.5 percentage points; and the average time required to retrieve a lung slice is 48μs. The retrieval results of the proposed algorithm are superior to other comparative network structures in expressing rich semantic features and retrieval efficiency of images. it is suitable for providing a basis for doctors clinical auxiliary diagnosis and helping patients to treat effectively.The proposed algorithm can contribute to doctor diagnosis and patient treament.

Key words： pulmonary nodule; medical image retrieval; multi-scale; dense block; hash function

0 引言

随着大数据时代的不断发展和图像数据的快速增长，全国医院每年产生约2PB以上的影像数据，怎样把大量的图像数据利用起来达到诊断报告信息共享，帮助医生辅助诊断是本课题的研究目的。基于内容的医学图像检索（Content-Based Medical Image Retrieval， CBMIR）是通过提取图像的语义特征，然后从数据库中检索类似图像的技术，所以正确全面地表达图像的语义信息成了图像检索的关键。……