基于多尺度密集网络的肺结节图像检索算法

doi:10.11772/j.issn.1001-9081.2018071451

计算机应用 ›› 2019, Vol. 39 ›› Issue (2): 392-397.DOI: 10.11772/j.issn.1001-9081.2018071451

基于多尺度密集网络的肺结节图像检索算法

秦品乐, 李启, 曾建潮, 张娜, 宋宇龙

中北大学大数据学院, 太原 030051

收稿日期:2018-07-13 修回日期:2018-09-13 出版日期:2019-02-10 发布日期:2019-02-15
通讯作者: 秦品乐
作者简介:秦品乐(1978-),男,山西长治人,副教授,博士,CCF会员,主要研究方向:大数据、机器视觉、三维重建;李启(1991-),男,山西大同人,硕士研究生,主要研究方向:机器学习、计算机视觉、数字图像处理;曾建潮(1963-),男,山西太原人,教授,博士生导师,博士,主要研究方向:复杂系统的维护决策和健康管理;张娜(1995-),女,山西临汾人,硕士研究生,主要研究方向:机器学习、计算机视觉、数字图像处理;宋宇龙(1978-),男,山西长治人,硕士研究生,主要研究方向:大数据、机器视觉。
基金资助:
山西省自然科学基金资助项目（2015011045）。

Image retrieval algorithm for pulmonary nodules based on multi-scale dense network

QIN Pingle, LI Qi, ZENG Jianchao, ZHANG Na, SONG Yulong

Data Science and Technology, North University of China, Taiyuan Shanxi 030051, China

Received:2018-07-13 Revised:2018-09-13 Online:2019-02-10 Published:2019-02-15
Supported by:
This work is partially supported by the Natural Science Foundation of Shanxi Province (2015011045).

摘要/Abstract

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48 μs。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

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 48 μs. The retrieval results of the proposed algorithm are superior to other comparative network structures in expressing rich semantic features and retrieval efficiency of images. The proposed algorithm can contribute to doctor diagnosis and patient treament.

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

中图分类号:

TP391.3

秦品乐, 李启, 曾建潮, 张娜, 宋宇龙. 基于多尺度密集网络的肺结节图像检索算法[J]. 计算机应用, 2019, 39(2): 392-397.

QIN Pingle, LI Qi, ZENG Jianchao, ZHANG Na, SONG Yulong. Image retrieval algorithm for pulmonary nodules based on multi-scale dense network[J]. Journal of Computer Applications, 2019, 39(2): 392-397.

参考文献

[1] QAYYUM A, ANWAR S M, MAJID M, et al. Medical image retrieval using deep convolutional neural networks:a review[EB/OL].[2018-04-12]. https://arxiv.org/ftp/arxiv/papers/1709/1709.02250.pdf.
[2] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe, Nevada:Curran Associates Inc., 2012:1097-1105.
[3] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL].[2018-04-12]. https://arxiv.org/pdf/1409.1556.pdf.
[4] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2016:770-778.
[5] KIM J, LEE J K, LEE K M. Accurate image super-resolution using very deep convolutional networks[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2016:1646-1654.
[6] HUANG G, LIU Z, KILIAN Q W, et al. Densely connected convolutional networks[EB/OL].[2018-04-12]. https://arxiv.org/pdf/1608.06993.pdf.
[7] HE K, ZHANG X, REN S, et al. Identity mappings in deep residual networks[C]//Proceedings of the 14th European Conference on Computer Vision, LNCS 9908. Cham:Springer, 2016:630-645.
[8] CHEN Y, JIN X, KANG B, et al. Sharing residual units through collective tensor factorization in deep neural networks[EB/OL]. (2017-03-15)[2018-04-02]. http://cn.arxiv.org/abs/1703.02180.pdf.
[9] 李净,郭洪禹.图像检索中结合文本信息的多示例原型选择及主动学习策略[J],计算机应用,2012,32(10):2899-2903. (LI J, GUO H Y. Multi-instance prototype selection and active learning combined with textual information in image retrieval[J]. Journal of Computer Applications, 2012, 32(10):2899-2903.)
[10] KRIZHEVSKY A. Learning multiple layers of features from tiny images[EB/OL].[2018-04-08]. http://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf
[11] DENG J, DONG W, SOCHER R, et al, ImageNet:a large-scale hierarchical image database[C]//Proceeding of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2009:248-255.
[12] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//Proceeding of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2005:886-893.
[13] LOWE D G,. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[14] LU X, SONG L, XIE R, et al, Deep hash learning for efficient image retrieval[C]//Proceedings of the 2017 IEEE International Conference on Multimedia and Expo Workshops. Washington, DC:IEEE Computer Society, 2017:579-584.
[15] CONJETI S, ROY A G, KATOUZIAN A, et al, Deep residual hashing[EB/OL].[2018-05-04]. http://cn.arxiv.org/abs/1612.05400.pdf.
[16] DUAN L, ZHAO C, MIAO J, et al. Deep hashing based fusing index method for large-scale image retrieval[J]. Applied Computational Intelligence and Soft Computing, 2017, 2017:Article ID 9635348.
[17] RAZAVIAN A S, AZIZPOUR H, SULLIVAN J,et al, CNN features off-the-shelf:an astounding baseline for recognition[C]//Proceeding of the 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Washington, DC:IEEE Computer Society, 2014:512-519.
[18] HUANG G, SUN Y, LIU Z, et al. Deep networks with stochastic depth[C]//Proceedings of the 2016 European Conference on Computer Vision, LNCS 9908. Cham:Springer, 2016:646-661.
[19] GIRSHICK R, DONAHUE J, DARRELL T, et al. Region-based convolutional networks for accurate object detection and semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(1):142-158.
[20] IOFFE S, SZEGEDY C, Batch normalization:accelerating deep network training by reducing internal covariate shift[C]//Proceedings of the 32nd International Conference on Machine Learning.[S.l.]:PMLR, 2015:448-156.
[21] 杨晓兰,强彦,赵娟娟,等.基于医学征象和卷积神经网络的肺结节CT图像哈希检索[J].智能系统学报,2017,12(6):857-864. (YANG X L, QIANG Y, ZHAO J J, et al. Hashing retrieval for CT images of pulmonary nodules based on medical signs and convolutional neural networks[J]. CAAI Transactions on Intelligent Systems, 2017, 12(6):857-864.)

基于多尺度密集网络的肺结节图像检索算法

Image retrieval algorithm for pulmonary nodules based on multi-scale dense network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	牛康力, 谌雨章, 沈君凤, 曾张帆, 潘永才, 王绎冲. 基于深度学习的双通道夜视图像复原方法[J]. 计算机应用, 2021, 41(6): 1775-1784.
[2]	曹建芳, 田晓东, 贾一鸣, 闫敏敏. 改进DeepLabV3+模型在壁画分割中的应用[J]. 计算机应用, 2021, 41(5): 1471-1476.
[3]	蒋丽, 黄仕建, 严文娟. 基于低秩行为信息和多尺度卷积神经网络的人体行为识别方法[J]. 计算机应用, 2021, 41(3): 721-726.
[4]	杜培德, 严华. 基于多尺度空间注意力特征融合的人群计数网络[J]. 计算机应用, 2021, 41(2): 537-543.
[5]	韩建栋, 李晓宇. 基于多尺度特征融合的行人重识别方法[J]. 计算机应用, 2021, 41(10): 2991-2996.
[6]	肖勇, 郑楷洪, 郑镇境, 钱斌, 李森, 马千里. 基于多尺度跳跃深度长短期记忆网络的短期多变量负荷预测[J]. 计算机应用, 2021, 41(1): 231-236.
[7]	温静, 宋建伟. 基于多级全局信息传递模型的视觉显著性检测[J]. 计算机应用, 2021, 41(1): 208-214.
[8]	张永宏, 刘昊, 田伟, 王剑庚. 基于DeepLab v3的西藏地区降雨云团分割方法[J]. 计算机应用, 2020, 40(9): 2781-2788.
[9]	高智勇, 黄金镇, 杜程刚. 基于特征金字塔网络的肺结节检测[J]. 计算机应用, 2020, 40(9): 2571-2576.
[10]	马金林, 魏萌, 马自萍. 基于深度迁移学习的肺结节分割方法[J]. 计算机应用, 2020, 40(7): 2117-2125.
[11]	石陆魁, 马红祺, 张朝宗, 樊世燕. 基于改进残差结构的肺结节检测方法[J]. 计算机应用, 2020, 40(7): 2110-2116.
[12]	朱兴动, 田少兵, 黄葵, 范加利, 王正, 陈化成. 基于深度卷积神经网络的舰载机目标检测[J]. 计算机应用, 2020, 40(5): 1529-1533.
[13]	张战成, 张大龙, 罗晓清. 带有语义特征得分的肺结节检测方法[J]. 计算机应用, 2020, 40(3): 925-930.
[14]	边小勇, 费雄君, 穆楠. 基于尺度注意力网络的遥感图像场景分类[J]. 计算机应用, 2020, 40(3): 872-877.
[15]	顾军华, 王锋, 戚永军, 孙哲然, 田泽培, 张亚娟. 基于多尺度卷积特征融合的肺结节图像检索方法[J]. 计算机应用, 2020, 40(2): 561-565.