Pulmonary Nodule Screening and Qualitative Diagnosis Based on Deep Learning

ZHANG Zhenghua; CAI Yaqian; HAN Dan; ZHOU Xiaojun; HUANG Yilong; LI Junli

doi:10.3971/j.issn.1000-8578.2020.19.1107

Cancer Research on Prevention and Treatment > 2020 > 47(4): 283-287. > DOI: 10.3971/j.issn.1000-8578.2020.19.1107

ZHANG Zhenghua, CAI Yaqian, HAN Dan, ZHOU Xiaojun, HUANG Yilong, LI Junli. Pulmonary Nodule Screening and Qualitative Diagnosis Based on Deep Learning[J]. Cancer Research on Prevention and Treatment, 2020, 47(4): 283-287. DOI: 10.3971/j.issn.1000-8578.2020.19.1107

Citation:

PDF (3720 KB)

Pulmonary Nodule Screening and Qualitative Diagnosis Based on Deep Learning

Department of Medical Imaging, First Affiliated Hospital of Kunming Medical University, Kunming 650032, China

More Information

Corresponding author:
HAN Dan, E-mail: kmhandan@sina.com
Received Date: September 01, 2019
Revised Date: October 14, 2019
Available Online: January 12, 2024

Graphical Abstract

Abstract

Abstract

Objective
To explore the clinical application value of deep learning-based artificial intelligence (AI) in the detection and related quantitative measurement of pulmonary nodules.
Methods
We collected 250 cases of chest CT scan and compared the misdiagnosis rate, missed diagnosis rate, sensitivity, positive predictive value and average diagnosis time of pulmonary nodules among group A (hospitalized), group B (AI) and group C (hospitalized+AI). Meanwhile, AI quantization parameters of solid nodules and ground glass nodules (GGN) were compared, and ROC curve analysis was performed for the parameters with statistical difference.
Results
A total of 2230 nodules were identified. The misdiagnosis rate of group B was significantly higher than those of group A and C, and the positive predictive value was significantly lower than those of group A and C (P < 0.05). The rate of missed diagnosis in group A was significantly higher than those in group B and C, and the sensitivity was significantly lower than those in group B and C (P < 0.05). There were statistically significant differences in the long diameter, maximum area, volume, minimum CT value and malignant probability between solid benign and malignant nodules (P < 0.05). The indexes of area under the ROC curve (AUC) greater than 0.7 were: long diameter, maximum area, volume and malignant probability. There were statistically significant differences in the length, maximum area, volume, average CT value, maximum CT value and malignant probability between GGN benign and malignant nodules (P < 0.05). ROC curve analysis of all parameters showed that AUC was greater than 0.7.
Conclusion
AI-assisted film reading could significantly improve work efficiency and sensitivity of pulmonary nodules detection and reduce the rates of misdiagnosis and missed diagnosis. Meanwhile, it has certain reference value for the prediction of benign and malignant pulmonary nodules.
- AI,
- Pulmonary nodules,
- Lung cancer,
- CT

FullText(HTML)

References (18)

References

[1]	Litjens G, Kooi T, Bejnordi BE, et al. A survey on deep learning in medical image analysis[J]. Med Image Anal, 2017, 42(9): 60-88.
[2]	Qin C, Yao D, Shi Y, et al. Computer-aided detection in chest radiography based on artificial intelligence: a survey[J]. Biomed Eng Online, 2018, 17(1): 113.
[3]	Gong L, Jiang S, Yang Z, et al. Automated pulmonary nodule detection in CT images using 3D deep squeeze-and-excitation networks[J]. Int J Comput Assist Radiol Surg, 2019, 14(11): 1969-1979.
[4]	Valente IR, Cortez PC, Neto EC, et al. Automatic 3D pulmonary nodule detection in CT images: A survey[J]. Comput Methods Programs Biomed, 2016, 124: 91-107.
[5]	中国食品药品检定研究院, 中华医学会放射学分会心胸学组.胸部CT肺结节数据标注与质量控制专家共识(2018)[J].中华放射学杂志, 2019, 53(1): 9-15. China Institute of Food and Drug Control, Chinese Medical Association. Expert consensus on the rule and quality control of pulmonary nodule annotation based on thoracic CT (2018)[J]. Zhonghua Fang She Xue Za Zhi, 2019, 53(1): 9-15.
[6]	Shaffie A, Soliman A, Fraiwan L, et al. A Generalized Deep Learning-Based Diagnostic System for Early Diagnosis of Various Types of Pulmonary Nodules[J]. Technol Cancer Res Treat, 2018, 17: 1533033818798800.
[7]	Zhang G, Yang Z, Gong L, et al. An Appraisal of Nodule Diagnosis for Lung Cancer in CT Images[J]. J Med Syst, 2019, 43(7): 181.
[8]	胡琼洁, 陈冲, 王玉锦, 等.实习医师以共同阅片和第二阅片者模式使用计算机辅助检测系统在低剂量CT中的应用研究[J].放射学实践, 2018, 33(10): 1022-1028. Hu QJ, Chen C, Wang YJ, et al. A computer-aided detection (CAD) system on low-dose chest CT images in concurent-reader and second-reader modes:influence on interns[J]. Fang She Xue Shi Jian, 2018, 33(10): 1022-1028.
[9]	邵亚军, 张荣宝, 郭佑民, 等.计算机辅助工具对肺结节检测效能的研究[J].实用放射学杂志, 2018, 34(9): 1430-1433. Shao YJ, Zhang BR, Guo YM, et al. Effectiveness of computer-aided detection for pulmonary nodules[J]. Shi Yong Fang She Xue Za Zhi, 2018, 34(9): 1430-1433.
[10]	顾亚峰, 李琼, 范丽, 等.不同窗宽窗位下肺亚实性结节及其实性成分大小对病理等级的预测价值[J].中华放射学杂志, 2017, 51(7): 484-488. Gu YF, Li Q, Fan L, et al. Predictive value of whole nodule size and solid component size of pulmonary subsolid nodule with different window setting for the pathologic grade[J]. Zhonghua Fang She Xue Za Zhi, 2017, 51(7): 484-488.
[11]	Du Y, Zhao Y, Sidorenkov G, et al. Methods of computed tomography screening and management of lung cancer in Tianjin: design of a population-based cohort study[J]. Cancer Biol Med, 2019, 16(1): 181-188.
[12]	Shi Z, Deng J, She Y, et al. Quantitative features can predict further growth of persistent pure ground-glass nodule[J]. Quant Imaging Med Surg, 2019, 9(2): 283-291.
[13]	Kitami A, Sano F, Hayashi S, et al. Correlation between histological invasiveness and the computed tomography value in pure ground-glass nodules[J]. Surg Today, 2016, 46(5): 593-598.
[14]	熊廷伟, 李川, 龚明福, 等. MSCT在肺孤立性磨玻璃结节鉴别诊断中的价值[J].中华肺部疾病杂志(电子版), 2018, 11(4): 401-404. Xiong TW, Li C, Gong MF, et al. Value of multi-slice spiral CT in differential diagnosis of solitary ground-glass opacity in lungs[J]. Zhonghua Fei Bu Ji Bing Za Zhi(Dian Zi Ban), 2018, 11(4): 401-404.
[15]	Yang Y, Wang WW, Ren Y, et al. Computerized texture analysis predicts histological invasiveness within lung adenocarcinoma manifesting as pure ground-glass nodules[J]. Acta Radiol, 2019, 60(10): 1258-1264.
[16]	矫娜, 吴明祥, 龚静山, 等.计算机辅助诊断定量分析表现为磨玻璃样结节的肺原位腺癌与非典型腺瘤样增生[J].中国CT和MRI杂志, 2015, 13(6): 29-31. Jiao N, Wu MX, Gong JS, et al. Computer-aided Differential Diagnosis of Adenocarcinoma Insitu and Atypical Adenomatous Hyperplasis Which Appear as Ground Glass Opacity[J]. Zhongguo CT He MRI Za Zhi, 2015, 13(6): 29-31.
[17]	Xiang W, Xing Y, Jiang S, et al. Morphological factors differentiating between early lung adenocarcinomas appearing as pure ground-glass nodules measuring ≤10 mm on thin-section computed tomography[J]. Cancer Imaging, 2014, 14: 33.
[18]	曹恩涛, 于红, 范丽, 等.纯磨玻璃密度结节肺腺癌的CT三维定量分析[J].中华放射学杂志, 2016, 50(12): 940-945. Cao ET, Yu H, Fan L, et al. Quantitative CT analysis of early-stage lung adenocarcinoma with pure ground-glass opacity[J]. Zhonghua Fang She Xue Za Zhi, 2016, 50(12): 940-945.

[1]	WANG Jingya, HE Zhengzhong, LI Yanping, WANG Xiaohong, LIU Yongsheng, TAN Wenyong. Target Volume Variation of Intrapulmonary Lesions Delineated in Four-dimensional CT Imaging[J]. Cancer Research on Prevention and Treatment, 2014, 41(09): 1009-1013. DOI: 10.3971/j.issn.1000-8578.2014.09.012
[2]	LIAO Riqiang, YANG Xuening, ZHONG Wenzhao, NIE Qiang, DONG Song, WANG Siyun, WU Yilong. Role of Mediastinoscopy in PET/CT Positive Mediastinal Involvement in Non-small Cell Lung Cancer[J]. Cancer Research on Prevention and Treatment, 2013, 40(12): 1170-1173. DOI: 10.3971/j.issn.1000-8578.2013.12.014
[3]	LI Jian, QIU Jun, HE Tian-chu. Role of CT Scan,SOD and MDA Expression in Radiation-induced Lung Injury[J]. Cancer Research on Prevention and Treatment, 2011, 38(09): 998-1001. DOI: 10.3971/j.issn.1000-8578.2011.09.007
[4]	WANG Yan-yang, ZHE Hong, FU Xiao-long, XIA Bing. Role of Kilovoltage Cone-beam CT in Determining Individual Internal Target Volume for Lung Cancer Patients[J]. Cancer Research on Prevention and Treatment, 2011, 38(04): 437-439. DOI: 10.3971/j.issn.1000-8578.2011.04.019
[5]	YAN Qing dong. Clinical Application Value and Prevention of Complication about Puncture Biopsy to Lung Disease under CT Direction[J]. Cancer Research on Prevention and Treatment, 2004, 31(11): 700-701. DOI: 10.3971/j.issn.1000-8578.2078
[6]	LI Zhen, HU Dao-yu, ZHANG Yu-qin, HUANG Yan-rong. The Matched Control Analysis of Misdiagnosis Hepatic Schistosomiasis to Hepatocarcinoma by CT and Pathology[J]. Cancer Research on Prevention and Treatment, 2004, 31(10): 639-641. DOI: 10.3971/j.issn.1000-8578.2560
[7]	LUO Cheng-gang, GE Hong-hui, CHENG xian. Diagnosis with CT of Postperative Recurrence of Rectal Carcinoma[J]. Cancer Research on Prevention and Treatment, 2000, 27(05): 387-388. DOI: 10.3971/j.issn.1000-8578.2758
[8]	Li Li, . Value of localization of insulinoma by angiographic CT[J]. Cancer Research on Prevention and Treatment, 1998, 25(6): 473-474.
[9]	Chen Zhaoqiu, . The Analysis of 21 Cases of Intracranial Metastatic Tumor with Clinical Manifestation and without CT Finding[J]. Cancer Research on Prevention and Treatment, 1994, 21(6): 382-383.
[10]	Ge Honghui. CT diagnosis of maxillary cyst with bone destruction[J]. Cancer Research on Prevention and Treatment, 1994, 21(3): 170-171.

Cited By

Cited by

Periodical cited type(12)

1.	崔舒蕾，王建卫. 肺磨玻璃结节干预策略崔舒蕾，王建卫. 中华肿瘤防治杂志. 2024(04): 233-240 .
2.	孙德秀，马隽. 高分辨率CT联合人工智能对肺磨玻璃结节的定性诊断价值. 中国卫生工程学. 2024(05): 656-658 .
3.	杨练，贾强，杨朝辉，孙立风，纪英财，侯岩松. 基于深度学习的SPECT图像左心室心肌感兴趣区自动识别技术. 中国医疗设备. 2023(02): 41-46 .
4.	赵耀，谢玉海，高续，胡东，顾晓艳. 计算机辅助对肺结节良恶性的诊断效能及影响因素分析. 医学影像学杂志. 2023(08): 1486-1489 .
5.	魏周阳，刘政，赵红梅，符桑，周艳红，王锡榜. 湘潭市某单位员工肺结节筛检情况及影响因素研究. 华南预防医学. 2022(02): 147-150+155 .
6.	魏周阳，赵红梅，符桑，王锡榜，刘政. 某市2311名事业单位人员肺结节筛检情况及生活习惯相关性调查. 实用预防医学. 2022(07): 778-781 .
7.	许国安，朱良炎，徐靖，邓武昌，殷波，高栋才，秦伟国，龚攀，沈颖，刘彬. 人工智能肺结节辅助诊断系统在肺磨玻璃结节病理浸润程度评估中的应用价值. 南昌大学学报(医学版). 2022(04): 53-56 .
8.	刘巧林，高胜新，胡天明，刘国忠. 螺旋CT对肺部1 cm以下孤立局限性磨玻璃密度结节的诊断价值. 中国现代医生. 2021(15): 117-120 .
9.	魏宁，蔺瑞江，马敏杰，陈昶，韩彪. 人工智能辅助诊断系统影像学微特征与磨玻璃结节样肺腺癌预后的关系. 肿瘤防治研究. 2021(09): 877-882 . 本站查看
10.	于广浩，李为民，高杨，董默，李彩娟，朱险峰，李莲娣. 人工智能系统在CT肺小结节筛查中的准确率及检出时间分析. 中国医药科学. 2021(21): 193-195+208 .
11.	王晓元，杜美玲，张鹏祥，李飞星，张爱爱，李方江. 基于人工智能心电远程记录构建运动性心脏性猝死三级防治体系. 实用临床医药杂志. 2021(24): 65-68+73 .
12.	南岩东，李玉娟，刘苗苗，金发光，张涛. 人工智能在肺结节良恶性鉴别诊断中的价值分析. 中华肺部疾病杂志(电子版). 2020(06): 760-763 .

Other cited types(6)

Get Citation

PDF

XML

Article views (2167) PDF downloads (1226) Cited by(18)

Turn off MathJax

Article Contents

Abstract

References

Pulmonary Nodule Screening and Qualitative Diagnosis Based on Deep Learning