肺结节自动检测的深度学习分析。

Xiaohua Liu
{"title":"肺结节自动检测的深度学习分析。","authors":"Xiaohua Liu","doi":"10.1200/jgo.2019.5.suppl.27","DOIUrl":null,"url":null,"abstract":"27 Background: The prevalence of lung cancer has been increased markedly in worldwide range with growing clinical significance, the quantitative and qualitative analysis on lung nodules has proven to be important for the early-detection of lung cancer as well as its treatment in clinical practice. However, lung lesion screening performed by radiologists can be very time-consuming and its accuracy varies depending on doctor’s individual experiences. In this study, we aim to build up a robust CAD system that automatically detects the lesion locations and quantitatively characterizes the detected lesions on CT images. Methods: Specifically, we employed the deep learning analysis for lesion detection in patients and performed image processing techniques to generate quantitative morphology features for assisting lesion diagnosis . The data collected includes 3956 lung CT series (slice thickness≤3mm) with multiple lung nodules from 15 Class-A hospitals in China , 1155 lung CT scan from Luna16 dataset as well as CT scans from Kaggle dataset (Data Science Bowl 2017). Lung nodule annotation was then performed by two experienced radiologists and further assessed by four senior associate chief physicians. The obtained CT images were randomly selected and split to construct training, validation and test dataset. After preprocessing, a pre-trained ResNet18 framework is transferred to develop a robust detection system to detect the possible lung lesion locations with corresponding probabilities. Results: The resulting detection system yields FROC of 0.4663, recall of 82.46%, precision of 36.06% for 5~30mm nodules. Each detected lesion was labeled by its bounding box and was then analyzed through image processing algorithm to generate diagnostic assisting features, including longest diameter, shortest diameter, volume, largest cross section area as well as its density type (calcify, solid, partial solid, and ground-glass opacity). Conclusions: The proposed CAD system offers a fast and convenient approach for assisting the diagnosis of lung nodule pathologies, and it is beneficial to relate our research to the current framework of lung cancer diagnosis.","PeriodicalId":15862,"journal":{"name":"Journal of global oncology","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2019-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Deep learning analysis for automatic lung nodule detection.\",\"authors\":\"Xiaohua Liu\",\"doi\":\"10.1200/jgo.2019.5.suppl.27\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"27 Background: The prevalence of lung cancer has been increased markedly in worldwide range with growing clinical significance, the quantitative and qualitative analysis on lung nodules has proven to be important for the early-detection of lung cancer as well as its treatment in clinical practice. However, lung lesion screening performed by radiologists can be very time-consuming and its accuracy varies depending on doctor’s individual experiences. In this study, we aim to build up a robust CAD system that automatically detects the lesion locations and quantitatively characterizes the detected lesions on CT images. Methods: Specifically, we employed the deep learning analysis for lesion detection in patients and performed image processing techniques to generate quantitative morphology features for assisting lesion diagnosis . The data collected includes 3956 lung CT series (slice thickness≤3mm) with multiple lung nodules from 15 Class-A hospitals in China , 1155 lung CT scan from Luna16 dataset as well as CT scans from Kaggle dataset (Data Science Bowl 2017). Lung nodule annotation was then performed by two experienced radiologists and further assessed by four senior associate chief physicians. The obtained CT images were randomly selected and split to construct training, validation and test dataset. After preprocessing, a pre-trained ResNet18 framework is transferred to develop a robust detection system to detect the possible lung lesion locations with corresponding probabilities. Results: The resulting detection system yields FROC of 0.4663, recall of 82.46%, precision of 36.06% for 5~30mm nodules. Each detected lesion was labeled by its bounding box and was then analyzed through image processing algorithm to generate diagnostic assisting features, including longest diameter, shortest diameter, volume, largest cross section area as well as its density type (calcify, solid, partial solid, and ground-glass opacity). Conclusions: The proposed CAD system offers a fast and convenient approach for assisting the diagnosis of lung nodule pathologies, and it is beneficial to relate our research to the current framework of lung cancer diagnosis.\",\"PeriodicalId\":15862,\"journal\":{\"name\":\"Journal of global oncology\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-10-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of global oncology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1200/jgo.2019.5.suppl.27\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of global oncology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1200/jgo.2019.5.suppl.27","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

摘要

27背景:肺癌的患病率在世界范围内显著增加,临床意义日益重要,肺结节的定量和定性分析在临床实践中对肺癌的早期发现和治疗具有重要意义。然而,由放射科医生进行的肺病变筛查非常耗时,其准确性取决于医生的个人经验。在本研究中,我们的目标是建立一个强大的CAD系统,自动检测病变的位置,并定量表征检测到的病变在CT图像上。方法:具体而言,我们采用深度学习分析对患者进行病变检测,并使用图像处理技术生成定量形态学特征以辅助病变诊断。收集的数据包括来自中国15家甲级医院的3956个肺CT系列(切片厚度≤3mm),来自Luna16数据集的1155个肺CT扫描以及来自Kaggle数据集的CT扫描(2017年数据科学碗)。然后由两名经验丰富的放射科医生进行肺结节注释,并由四名高级副主任医师进一步评估。随机选取并分割得到的CT图像,构建训练、验证和测试数据集。预处理后,转移预训练的ResNet18框架,开发鲁棒检测系统,以相应概率检测可能的肺病变位置。结果:所建立的检测系统对5~30mm结节的检出率为0.4663,召回率为82.46%,精密度为36.06%。对检测到的病灶进行边界框标记,然后通过图像处理算法进行分析,生成诊断辅助特征,包括最长直径、最短直径、体积、最大横截面积及其密度类型(钙化、实性、部分实性、毛玻璃不透明)。结论:所建立的CAD系统为辅助肺结节病理诊断提供了一种快速便捷的方法,有利于将我们的研究与当前肺癌诊断框架联系起来。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Deep learning analysis for automatic lung nodule detection.
27 Background: The prevalence of lung cancer has been increased markedly in worldwide range with growing clinical significance, the quantitative and qualitative analysis on lung nodules has proven to be important for the early-detection of lung cancer as well as its treatment in clinical practice. However, lung lesion screening performed by radiologists can be very time-consuming and its accuracy varies depending on doctor’s individual experiences. In this study, we aim to build up a robust CAD system that automatically detects the lesion locations and quantitatively characterizes the detected lesions on CT images. Methods: Specifically, we employed the deep learning analysis for lesion detection in patients and performed image processing techniques to generate quantitative morphology features for assisting lesion diagnosis . The data collected includes 3956 lung CT series (slice thickness≤3mm) with multiple lung nodules from 15 Class-A hospitals in China , 1155 lung CT scan from Luna16 dataset as well as CT scans from Kaggle dataset (Data Science Bowl 2017). Lung nodule annotation was then performed by two experienced radiologists and further assessed by four senior associate chief physicians. The obtained CT images were randomly selected and split to construct training, validation and test dataset. After preprocessing, a pre-trained ResNet18 framework is transferred to develop a robust detection system to detect the possible lung lesion locations with corresponding probabilities. Results: The resulting detection system yields FROC of 0.4663, recall of 82.46%, precision of 36.06% for 5~30mm nodules. Each detected lesion was labeled by its bounding box and was then analyzed through image processing algorithm to generate diagnostic assisting features, including longest diameter, shortest diameter, volume, largest cross section area as well as its density type (calcify, solid, partial solid, and ground-glass opacity). Conclusions: The proposed CAD system offers a fast and convenient approach for assisting the diagnosis of lung nodule pathologies, and it is beneficial to relate our research to the current framework of lung cancer diagnosis.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
审稿时长
20 weeks
期刊介绍: The Journal of Global Oncology (JGO) is an online only, open access journal focused on cancer care, research and care delivery issues unique to countries and settings with limited healthcare resources. JGO aims to provide a home for high-quality literature that fulfills a growing need for content describing the array of challenges health care professionals in resource-constrained settings face. Article types include original reports, review articles, commentaries, correspondence/replies, special articles and editorials.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信