|
Journal of Zhejiang University SCIENCE B
ISSN 1673-1581(Print), 1862-1783(Online), Monthly
2022 Vol.23 No.11 P.957-967
A method for distinguishing benign and malignant pulmonary nodules based on 3D dual path network aided by K-means clustering analysis
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.
Key words: CT images, Pulmonary nodule, Computer-aided diagnosis, Dual Path Network, Clustering analysis
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:
References:
Open peer comments: Debate/Discuss/Question/Opinion
<1>
DOI:
10.1631/jzus.B2101009
CLC number:
Download Full Text:
Downloaded:
1183
Download summary:
<Click Here>Downloaded:
542Clicked:
1287
Cited:
0
On-line Access:
2024-08-27
Received:
2023-10-17
Revision Accepted:
2024-05-08
Crosschecked:
2022-11-16