Please wait a minute...
高校应用数学学报
Applied Mathematics A Journal of Chinese Universities  2018, Vol. 33 Issue (2): 127-139    DOI:
    
A kind of deep learning acceleration method for pulmonary nodule detection
LI Zheng,    HU Xiang-liang ,  LIANG Ke-wei ,  YU Ding-ding
Download:   PDF(1070KB)
Export: BibTeX | EndNote (RIS)      

Abstract  The deep learning method for pulmonary nodule detection is generally divided into
two stages: candidate nodule detection and false positive nodule elimination. Based on the two-stage
method, an incremental learning acceleration scheme is proposed that integrates new data to improve
the accuracy of the system. The training model of historical data screens new data and selects the
data with poor performance as an input for the continuous training of the two-stage model. The above
methods are tested on LUNA16 and TIANCHI17 two classic data sets. Using only half of the new
ones, the new model can achieve the same e?ect as the traditional two-stage method.

Key words： pulmonary nodule detection              deep learning              two-stage method        false positives        incre-mental learning     
Published: 24 July 2018
CLC:  TP391  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Cite this article:

. A kind of deep learning acceleration method for pulmonary nodule detection. Applied Mathematics A Journal of Chinese Universities, 2018, 33(2): 127-139.

URL:

http://www.zjujournals.com/amjcua/     OR     http://www.zjujournals.com/amjcua/Y2018/V33/I2/127


一类用于肺结节检测的深度学习加速方法

肺结节检测的深度学习方法一般分为候选结节检测和假阳性结节消除两个阶
段. 基于两阶段方法, 提出了一种整合新数据以提升系统准确性的增量学习加速方案.
利用历史数据的训练模型对新数据进行筛选, 把表现性能不好的数据作为继续训练两
阶段模型的输入. 在LUNA16 和TIANCHI17两个经典数据集上对上述方法进行测试,
只需利用一半以下的新训练数据就能取得与传统两阶段方法相同的效果.

关键词： 肺结节检测 ,   深度学习 ,   ,  两阶段方法 ,   ,  假阳性 ,   ,  增量学习 
[1] LIU Wei-qi, LIANG Shan-shan. A new kind of location invariant extreme value index estimator[J]. Applied Mathematics A Journal of Chinese Universities, 2018, 33(2): 179-190.
[2] ZHAO Yuan-ying, XU Deng-ke, PANG Yi-cheng. Bayesian analysis for joint mean and variance models[J]. Applied Mathematics A Journal of Chinese Universities, 2018, 33(2): 157-166.
[3] . GMM estimation of nonparametric spatial lag model[J]. Applied Mathematics A Journal of Chinese Universities, 2018, 33(2): 140-156.
[4] LIN Cheng-long, LIANG Zong-qi, DU Rui-lian. New multi-stage envelope periodic solutions for a class of nonlinear Schrodinger equation with wave operator[J]. Applied Mathematics A Journal of Chinese Universities, 2018, 33(2): 211-222.
[5] LIU Jiang, ZHANG Long, JIANG Zhong-chuan, LI Yan-qing. Synchronous control on inverter system of grid connected high-power wind generators with nonlinear and pulse disturbance#br#[J]. Applied Mathematics A Journal of Chinese Universities, 2017, 32(4): 388-402.
[6] BAI Yong-xin, TIAN Mao-zai. Confidence interval construction for the risk difference of chronic disease based on saddle-point approximation under poisson distribution[J]. Applied Mathematics A Journal of Chinese Universities, 2017, 32(3): 253-266.
[7] WU Xiu-feng, HUANG Jun-jie, Alatancang. Pertubation of four classes of point spectra for $3\times3$ upper triangular operator matrices[J]. Applied Mathematics A Journal of Chinese Universities, 2017, 32(1): 93-102.
[8] KONG Xiang-shan, LI Hai-tao, ZHAO Hong-xin, LV Xun-jing. Bifurcation of positive solutions for a class of integral boundary value problems of fractional differential equations[J]. Applied Mathematics A Journal of Chinese Universities, 2017, 32(1): 13-22.
[9] CHEN Xiao-li, HU Qiao-zhen. Endpoint estimates for commutators of intrinsic square functions on the weighted weak Hardy spaces[J]. Applied Mathematics A Journal of Chinese Universities, 2017, 32(1): 109-119.
[10] WANG Chun-fa, CHEN Rong-da. Option pricing in Markov regime switching Levy models using Fourier-Cosine expansions[J]. Applied Mathematics A Journal of Chinese Universities, 2016, 31(4): 390-404.