Deep Transfer Learning Strategy for Invasive Lung Adenocarcinoma Classification Appearing as Ground Glass Nodules

Chen Ma, Shihong Yue, Qi Li
{"title":"Deep Transfer Learning Strategy for Invasive Lung Adenocarcinoma Classification Appearing as Ground Glass Nodules","authors":"Chen Ma, Shihong Yue, Qi Li","doi":"10.1109/I2MTC50364.2021.9459841","DOIUrl":null,"url":null,"abstract":"Lung cancer is one of the deadliest diseases in which adenocarcinoma account for nearly 40%. To make an effective treatment and diagnosis, it is vital to accurately discriminate invasive adenocarcinoma (IA) from non-IA by analyzing ground glass nodules (GGNs) from patient's CT images. Compared with solid nodules and normal lung parenchyma, the contours of GGN are blurred and the gray scale is little changed. So far, the problem to accurately discriminate IA and non-IA remains unsolved due to insufficient labeled GGN images. In this paper, considering the generalization of convolutional neural network (CNN) and various flexible transfer strategies, we proposed a lung adenocarcinoma classification method after combining transfer learning and CNN, where the use of transfer learning strategies aims at overcoming the problem of insufficient GGN samples. Firstly, the CT image on IA and non-IA patients were collected which were labeled by surgical pathology. Secondly, two transfer learning strategies that consist of CNN feature extractor and fine-tuning network were applied to classify IA and non-IA. Finally, in the fine-tuning network process, a Progressive Fine-Tuning (PFT) strategy was combined to determine the effective depth of fine-tuning to avoid inaccurate induction of GGNs. In the CNN feature extractor experiment, four comparable models were used including linear discrimination, Support Vector Machines, K-nearest neighbor, and subspace discrimination. The indicators of sensitivity, specificity, accuracy, and AUC (area under curve) were used to quantitatively assess the performance of the two transfer strategies. Experiments show that the strategy of CNN feature extractor based on transfer learning had the highest accuracy, which was significantly higher than fine-tuning network strategy with PFT. In the experiment of CNN feature extractor, the model of linear discrimination to predict the invasiveness of GGNs has 94% accuracy whereas the other three models have 92.9%, 93.1% and 92.9%, respectively.","PeriodicalId":6772,"journal":{"name":"2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)","volume":"28 1","pages":"1-5"},"PeriodicalIF":0.0000,"publicationDate":"2021-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/I2MTC50364.2021.9459841","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

Abstract

Lung cancer is one of the deadliest diseases in which adenocarcinoma account for nearly 40%. To make an effective treatment and diagnosis, it is vital to accurately discriminate invasive adenocarcinoma (IA) from non-IA by analyzing ground glass nodules (GGNs) from patient's CT images. Compared with solid nodules and normal lung parenchyma, the contours of GGN are blurred and the gray scale is little changed. So far, the problem to accurately discriminate IA and non-IA remains unsolved due to insufficient labeled GGN images. In this paper, considering the generalization of convolutional neural network (CNN) and various flexible transfer strategies, we proposed a lung adenocarcinoma classification method after combining transfer learning and CNN, where the use of transfer learning strategies aims at overcoming the problem of insufficient GGN samples. Firstly, the CT image on IA and non-IA patients were collected which were labeled by surgical pathology. Secondly, two transfer learning strategies that consist of CNN feature extractor and fine-tuning network were applied to classify IA and non-IA. Finally, in the fine-tuning network process, a Progressive Fine-Tuning (PFT) strategy was combined to determine the effective depth of fine-tuning to avoid inaccurate induction of GGNs. In the CNN feature extractor experiment, four comparable models were used including linear discrimination, Support Vector Machines, K-nearest neighbor, and subspace discrimination. The indicators of sensitivity, specificity, accuracy, and AUC (area under curve) were used to quantitatively assess the performance of the two transfer strategies. Experiments show that the strategy of CNN feature extractor based on transfer learning had the highest accuracy, which was significantly higher than fine-tuning network strategy with PFT. In the experiment of CNN feature extractor, the model of linear discrimination to predict the invasiveness of GGNs has 94% accuracy whereas the other three models have 92.9%, 93.1% and 92.9%, respectively.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
以磨玻璃结节为表现的浸润性肺腺癌分类的深度迁移学习策略
肺癌是最致命的疾病之一,其中腺癌占近40%。通过分析患者CT图像中的磨砂玻璃结节(ggn),准确鉴别浸润性腺癌(IA)与非浸润性腺癌(IA)是有效治疗和诊断的关键。与实性结节和正常肺实质相比,GGN轮廓模糊,灰度变化不大。到目前为止,由于标记的GGN图像不足,准确区分IA和非IA的问题仍然没有解决。本文考虑到卷积神经网络(convolutional neural network, CNN)的泛化性以及各种灵活的迁移策略,提出了一种将迁移学习与CNN相结合的肺腺癌分类方法,其中迁移学习策略的使用旨在克服GGN样本不足的问题。首先收集IA和非IA患者的CT图像,并进行手术病理标记。其次,采用CNN特征提取器和微调网络两种迁移学习策略对IA和非IA进行分类;最后,在网络微调过程中,结合渐进微调(PFT)策略来确定有效的微调深度,以避免不准确的诱导ggn。在CNN特征提取器实验中,使用了线性判别、支持向量机、k近邻和子空间判别四种可比较的模型。采用敏感性、特异性、准确性和曲线下面积等指标定量评价两种转移策略的效果。实验表明,基于迁移学习的CNN特征提取器策略具有最高的准确率,显著高于基于PFT的微调网络策略。在CNN特征提取器的实验中,线性判别模型预测ggn侵袭性的准确率为94%,而其他三种模型的准确率分别为92.9%、93.1%和92.9%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Microwave Quantification of Porosity Level in 3D Printed Polymers Fast Transient Harmonic Selective Extraction Based on Modulation-CDSC-SDFT A UWB-based localization system: analysis of the effect of anchor positions and robustness enhancement in indoor environments Miniaturised bidirectional acoustic tag to enhance marine animal tracking studies Overload Current Interruption Protection Method based on Tunnel Magnetoresistive Sensor Measurement
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1