Full Text:  <122>

Suppl. Mater.: 

Summary:  <4>

CLC number: 

On-line Access: 2022-11-15

Received: 2021-12-13

Revision Accepted: 2022-05-03

Crosschecked: 2022-11-16

Cited: 0

Clicked: 194

Citations:  Bibtex RefMan EndNote GB/T7714

 ORCID:

Shengdong NIE

https://orcid.org/0000-0001-7825-4455

Dachuan GAO

https://orcid.org/0000-0002-6399-1708

Yuanzhong XIE

https://orcid.org/0000-0003-2593-4806

-   Go to

Article info.
Open peer comments

Journal of Zhejiang University SCIENCE B

Accepted manuscript available online (unedited version)


A method for distinguishing benign and malignant pulmonary nodules based on 3D dual path network aided by K-means clustering analysis


Author(s):  Dachuan GAO, Xiaodan YE, Xuewen HOU, Yang CHEN, Xue KONG, Yuanzhong XIE, Shengdong NIE

Affiliation(s):  School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China; more

Corresponding email(s):  xie01088@126.com, nsd4647@163.com

Key Words:  CT images, Pulmonary nodule, Computer-aided diagnosis, Dual Path Network, Clustering analysis


Share this article to: More <<< Previous Paper|Next Paper >>>

Dachuan GAO, Xiaodan YE, Xuewen HOU, Yang CHEN, Xue KONG, Yuanzhong XIE, Shengdong NIE. A method for distinguishing benign and malignant pulmonary nodules based on 3D dual path network aided by K-means clustering analysis[J]. Journal of Zhejiang University Science B, 2022, 23(6): 957-967.

@article{title="A method for distinguishing benign and malignant pulmonary nodules based on 3D dual path network aided by K-means clustering analysis",
author="Dachuan GAO, Xiaodan YE, Xuewen HOU, Yang CHEN, Xue KONG, Yuanzhong XIE, Shengdong NIE",
journal="Journal of Zhejiang University Science B",
volume="23",
number="11",
pages="957-967",
year="2022",
publisher="Zhejiang University Press & Springer",
doi="10.1631/jzus.B2101009"
}

%0 Journal Article
%T A method for distinguishing benign and malignant pulmonary nodules based on 3D dual path network aided by K-means clustering analysis
%A Dachuan GAO
%A Xiaodan YE
%A Xuewen HOU
%A Yang CHEN
%A Xue KONG
%A Yuanzhong XIE
%A Shengdong NIE
%J Journal of Zhejiang University SCIENCE B
%V 23
%N 11
%P 957-967
%@ 1673-1581
%D 2022
%I Zhejiang University Press & Springer

TY - JOUR
T1 - A method for distinguishing benign and malignant pulmonary nodules based on 3D dual path network aided by K-means clustering analysis
A1 - Dachuan GAO
A1 - Xiaodan YE
A1 - Xuewen HOU
A1 - Yang CHEN
A1 - Xue KONG
A1 - Yuanzhong XIE
A1 - Shengdong NIE
J0 - Journal of Zhejiang University Science B
VL - 23
IS - 11
SP - 957
EP - 967
%@ 1673-1581
Y1 - 2022
PB - Zhejiang University Press & Springer
ER -


Abstract: 
In the USA, there were about 1 ‍806 ‍590 new cancer cases in 2020, and 606 520 cancer deaths are expected to have occurred in 2021. Lung cancer has become the leading cause of death from cancer in both men and women (Siegel et al., 2020). Clinical studies show that the five-year survival rate of lung cancer patients after early diagnosis and treatment intervention can reach 80%, compared with that of patients having advanced lung cancer. Thus, the early diagnosis of lung cancer is a key factor to reduce mortality.

基于三维双路径网络与K均值聚类算法的肺结节良恶性鉴别方法

高大川1,叶晓丹2,侯学文1,陈阳1,孔雪3,谢元忠3,聂生东1
1上海理工大学健康科学与工程学院,中国上海市,200093
2上海市胸科医院放射科,中国上海市,200030
3泰安中心医院医学影像中心,中国泰安市,271000
目的:为了提高肺癌早期诊断的准确性,本文使用机器学习,可以有效地帮助放射科医生区分肺结节的良恶性。
创新点:基于三维双路径网络(3DDPN)辅助K均值聚类分析区分良恶性肺结节,类别分析可以有效地表示良恶性肺结节的多种潜在亚型。
方法:在这项研究中,我们提出了一种基于3DDPN并辅以聚类分析来识别良恶性肺结节的新分类方案。首先,根据四位放射科医生的标注结果,从计算机断层扫描(CT)图像中截取以肺结节为中心,尺寸为64×64×64的像素单元;并训练pre-3D DPN模型提取卷积神经网络(CNN)特征。随后,采用随机森林特征选择算法滤除不相关的特征,并采用K均值聚类算法生成聚类标签。最后,使用具有新聚类标签的数据训练3D DPN对肺结节进行良恶性分类。
结果:使用肺影像数据联盟-影像数据库资源计划(LIDC-IDRI)数据库中的966个肺结节进行实验验证,最终所提方法的分类准确率、敏感度、特异度及接受者操作特性曲线(ROC)下面积(AUC)分别达92.86%、94.44%、91.94%及96.43%。此外,从上海胸科医院(SCH)收集了67个结节进行临床验证,获得的准确率为86.57%。
结论:本文所提出的方法可以准确地区分良恶性结节,可作为肺结节良恶性诊断的计算机辅助方法。

关键词组:计算机断层扫描(CT)图像;肺结节;计算机辅助诊断;双路径网络(DPN);聚类分析

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1]AlbertRH, RussellJJ, 2009. Evaluation of the solitary pulmonary nodule. Am Fam Physician, 80(8):827-831.

[2]ArmatoSG III, McLennanG, BidautL, et al., 2011. The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans. Med Phys, 38(2):915-931.

[3]BergstraJ, BengioY, 2012. Random search for hyper-parameter optimization. J Mach Learn Res, 13:281-305.

[4]CaoP, LiuXL, YangJZ, et al., 2017. A multi-kernel based framework for heterogeneous feature selection and over-sampling for computer-aided detection of pulmonary nodules. Pattern Recogn, 64:327-346.

[5]CauseyJL, ZhangJY, MaSQ, et al., 2018. Highly accurate model for prediction of lung nodule malignancy with CT scans. Sci Rep, 8:9286.

[6]ChenYP, LiJN, XiaoHX, et al., 2017. Dual path networks. Proceedings of the 31st International Conference on Neural Information Processing Systems. Curran Associates Inc., Red Hook, NY, USA, p.4470-4478.

[7]DeyR, LuZJ, HongY, 2018. Diagnostic classification of lung nodules using 3D neural networks. 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington, DC, USA. IEEE, p.774-778.

[8]DharaAK, MukhopadhyayS, DuttaA, et al., 2016. A combination of shape and texture features for classification of pulmonary nodules in lung CT images. J Digit Imaging, 29(4):466-475.

[9]Díaz-UriarteR, de AndrésSA, 2006. Gene selection and classification of microarray data using random forest. BMC Bioinformatics, 7:3.

[10]GongJ, LiuJY, SunXW, et al., 2018. Computer-aided diagnosis of lung cancer: the effect of training data sets on classification accuracy of lung nodules. Phys Med Biol, 63(3):035036.

[11]GouldMK, DoningtonJ, LynchWR, et al., 2013. Evaluation of individuals with pulmonary nodules: when is it lung cancer? Diagnosis and management of lung cancer, 3rd ed: American College of Chest Physicians Evidence-Based Clinical Practice Guidelines. CHEST, 143(5 Suppl):e93S-e120S.

[12]HeKM, ZhangXY, RenSQ, et al., 2016. Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA. IEEE, p.770-778.

[13]HuangG, LiuZ, van der MaatenL, et al., 2017. Densely connected convolutional networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA. IEEE, p.2261-2269.

[14]KingmaDP, BaJ, 2015. Adam: a method for stochastic optimization. Proceedings of the 3rd International Conference on Learning Representations, San Diego.

[15]KrizhevskyA, SutskeverI, HintonGE, 2017. ImageNet classification with deep convolutional neural networks. Commun ACM, 60(6):84-90.

[16]LuD, WengQ, 2007. A survey of image classification methods and techniques for improving classification performance. Int J Remote Sens, 28(5):823-870.

[17]LyuJ, BiXJ, LingSH, 2020. Multi-level cross residual network for lung nodule classification. Sensors, 20(10):2837.

[18]MastouriR, KhlifaN, NejiH, et al., 2021. A bilinear convolutional neural network for lung nodules classification on CT images. Int J Comput Assist Radiol Surg, 16(1):91-101.

[19]McHughML, 2012. Interrater reliability: the kappa statistic. Biochem Med, 22(3):276-282.

[20]ShenDG, WuGR, SukHI, 2017. Deep learning in medical image analysis. Annu Rev Biomed Eng, 19:221-248.

[21]ShenW, ZhouM, YangF, et al., 2017. Multi-crop convolutional neural networks for lung nodule malignancy suspiciousness classification. Pattern Recogn, 61:663-673.

[22]SiegelRL, MillerKD, Goding SauerA, et al., 2020. Colorectal cancer statistics, 2020. CA Cancer J Clin, 70(3):‍145-164.

[23]SnoeckxA, ReyntiensP, DesbuquoitD, et al., 2018. Evaluation of the solitary pulmonary nodule: size matters, but do not ignore the power of morphology. Insights Imaging, 9(1):73-86.

[24]van ErkelAR, PattynamaPM, 1998. Receiver operating characteristic (ROC) analysis: basic principles and applications in radiology. Eur J Radiol, 27(2):88-94.

[25]WuWH, HuHH, GongJ, et al., 2019. Malignant-benign classification of pulmonary nodules based on random forest aided by clustering analysis. Phys Med Biol, 64(3):035017.

[26]ZhangF, SongY, CaiWD, et al., 2013. Context curves for classification of lung nodule images. 2013 International Conference on Digital Image Computing: Techniques and Applications (DICTA), Hobart, TAS, Australia. IEEE, p.1-7.

[27]ZhuWT, LiuCC, FanW, et al., 2018. DeepLung: deep 3D dual path nets for automated pulmonary nodule detection and classification. 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe, NV, USA. IEEE, p.673-681.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - 2022 Journal of Zhejiang University-SCIENCE