Toward an Expert Level of Lung Cancer Detection and Classification Using a Deep Convolutional Neural Network
| Autor: | Zai‐yi Liu, Zhu Liang, Yu Zongqiao, Chao Zhang, Shao-hong Huang, Yi-Long Wu, Xing Sun, Jie Qin, Feiyue Huang, Wen-Zhao Zhong, Yan‐bin Zhang, Wei-Neng Feng, Xue-Ning Yang, Xiaowei Guo, Qing Zhou, Chang Jia, Xing‐lin Gao, Tao Zhou, Yun‐sheng Wu, Xuegong Zhang, Ming‐fang Zhao, Ke Li, Kang Dang, Wei‐jun Fang |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Male
Cancer Research medicine.medical_specialty Lung Neoplasms Cancer Diagnostics and Molecular Pathology Databases Factual Subgroup analysis Convolutional neural network 030218 nuclear medicine & medical imaging Model validation 03 medical and health sciences Deep Learning 0302 clinical medicine Pulmonary nodule medicine Humans Lung cancer Lung Retrospective Studies business.industry Deep learning Middle Aged medicine.disease Confidence interval Clinical Practice ROC Curve Oncology 030220 oncology & carcinogenesis Radiographic Image Interpretation Computer-Assisted Female Neural Networks Computer Artificial intelligence Radiology Tomography X-Ray Computed business Algorithms |
| Zdroj: | The Oncologist. 24:1159-1165 |
| ISSN: | 1549-490X 1083-7159 |
| DOI: | 10.1634/theoncologist.2018-0908 |
| Popis: | Background Computed tomography (CT) is essential for pulmonary nodule detection in diagnosing lung cancer. As deep learning algorithms have recently been regarded as a promising technique in medical fields, we attempt to integrate a well-trained deep learning algorithm to detect and classify pulmonary nodules derived from clinical CT images. Materials and Methods Open-source data sets and multicenter data sets have been used in this study. A three-dimensional convolutional neural network (CNN) was designed to detect pulmonary nodules and classify them into malignant or benign diseases based on pathologically and laboratory proven results. Results The sensitivity and specificity of this well-trained model were found to be 84.4% (95% confidence interval [CI], 80.5%–88.3%) and 83.0% (95% CI, 79.5%–86.5%), respectively. Subgroup analysis of smaller nodules ( Conclusion Under the companion diagnostics, the three-dimensional CNN with a deep learning algorithm may assist radiologists in the future by providing accurate and timely information for diagnosing pulmonary nodules in regular clinical practices. Implications for Practice The three-dimensional convolutional neural network described in this article demonstrated both high sensitivity and high specificity in classifying pulmonary nodules regardless of diameters as well as superiority compared with manual assessment. Although it still warrants further improvement and validation in larger screening cohorts, its clinical application could definitely facilitate and assist doctors in clinical practice. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text