Journal of Computer Applications ›› 2018, Vol. 38 ›› Issue (11): 3225-3230.DOI: 10.11772/j.issn.1001-9081.2018041244

Previous Articles     Next Articles

Lung tumor image recognition algorithm based on cuckoo search and deep belief network

YANG Jian1, ZHOU Tao1,2, GUO Lifang2, ZHANG Feifei1, LIANG Mengmeng1   

  1. 1. Public Administration Research Center, Ningxia Medical University, Yinchuan Ningxia 750000, China;
    2. College of Science, Ningxia Medical University, Yinchuan Ningxia 750000, China
  • Received:2018-04-30 Revised:2018-06-20 Online:2018-11-10 Published:2018-11-10
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61561040).

基于布谷鸟搜索和深度信念网络的肺部肿瘤图像识别算法

杨健1, 周涛1,2, 郭丽芳2, 张飞飞1, 梁蒙蒙1   

  1. 1. 宁夏医科大学 公共管理研究中心, 银川 750000;
    2. 宁夏医科大学 理学院, 银川 750000
  • 通讯作者: 周涛
  • 作者简介:杨健(1993-),女,山东诸城人,硕士研究生,主要研究方向:深度学习、医学图像分析处理;周涛(1977-),男,宁夏同心人,教授,博士,主要研究方向:粗糙集、医学图像分析处理;郭丽芳(1973-),女,宁夏银川人,副教授,博士,主要研究方向:医学图像分析处理;张飞飞(1991-),女,甘肃宁县人,硕士研究生,主要研究方向:粗糙集、医学图像分析处理;梁蒙蒙(1992-),女,安徽临泉人,硕士研究生,主要研究方向:深度学习、医学图像分析处理。
  • 基金资助:
    国家自然科学基金资助项目(61561040)。

Abstract: Due to random initialization of the weights, Deep Belief Network (DBN) easily falls into a local optimum, the Cuckoo Search (CS) algorithm was introduced into the traditional DBN model and a lung cancer image recognition algorithm based on CS-DBN was proposed. Firstly, the global optimization ability of CS was used to optimize initial weights of DBN, and on this basis, the layer-by-layer pre-training of DBN was performed. Secondly, the whole network was fine-tuned by using Back Propagation (BP) algorithm, so that the network weights were optimized. Finally, the CS-DBN was applied to the identification of lung tumor images, and CS-DBN was compared with traditional DBN from the four perspectives of Restricted Boltzmann Machine (RBM) training times, training batch sizes, DBN hidden layers numbers, and hidden layer nodes to verify the feasibility and effectiveness of the algorithm. The experimental results show that the recognition accuracy of CS-DBN is obviously higher than that of traditional DBN. Under the conditions of different RBM training times, training batch sizes, DBN hidden layer numbers, and hidden layer nodes, the increase range of CS-DBN identification accuracy over traditional DBN are 1.13 to 4.33, 2 to 3.34, 1.07 to 3.34 and 1.4 to 3.34 percentage points respectively. CS-DBN can improve the accuracy of lung tumor recognition to a certain extent, thereby improving the performance of computer-aided diagnosis of lung tumors.

Key words: Cuckoo Search (CS) algorithm, Deep Belief Network (DBN), Restricted Boltzmann Machine (RBM), lung tumor, image recognition

摘要: 针对深度信念网络(DBN)权值随机初始化易使网络陷入局部最优的问题,在传统DBN模型中引入布谷鸟搜索(CS)算法,提出一种基于CS-DBN的肺部肿瘤图像识别算法。首先,利用CS的全局寻优能力对DBN的初始权值进行优化,并在此基础上进行DBN的逐层预训练;然后,利用反向传播(BP)算法对整个网络进行微调,从而使网络权值达到最优;最后,将CS-DBN应用于肺部肿瘤图像的识别,实验从受限玻尔兹曼机(RBM)训练次数、训练批次大小、DBN隐层层数和隐层节点数四个角度将CS-DBN与传统DBN进行比较,以验证该算法的可行性和有效性。实验结果表明,CS-DBN的识别精度明显高于传统DBN,在不同RBM训练次数、训练批次大小、DBN隐层层数和隐层节点数条件下,CS-DBN较传统DBN识别率提高百分点的范围分别是1.13~4.33、2.00~3.34、1.07~3.34和1.40~3.34。CS-DBN能够在一定程度上提高肺部肿瘤的识别精度,从而提高肺部肿瘤计算机辅助诊断性能。

关键词: 布谷鸟搜索算法, 深度信念网络, 受限玻尔兹曼机, 肺部肿瘤, 图像识别

CLC Number: