J Shanghai Jiaotong Univ Sci

Journal of Shanghai Jiao Tong University (Science) ›› 2019, Vol. 24 ›› Issue (4): 517-523.doi: 10.1007/s12204-019-2084-4

Previous Articles     Next Articles

Automatic Detection of Lung Nodules Using 3D Deep Convolutional Neural Networks

Automatic Detection of Lung Nodules Using 3D Deep Convolutional Neural Networks

FU Ling (傅玲), MA Jingchen (马璟琛), CHEN Yizhi (琛奕志), LARSSON Rasmus, ZHAO Jun *(赵俊)   

  1. (1. School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China; 2. SJTU-UIH Institute for Medical Imaging Technology, Shanghai Jiao Tong University, Shanghai 200240, China; 3. MED-X Research Institute, Shanghai Jiao Tong University, Shanghai 200030, China; 4. School of Technology and Health, KTH Royal Institute of Technology, SE-100 44, Stockholm, Sweden)
  2. (1. School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China; 2. SJTU-UIH Institute for Medical Imaging Technology, Shanghai Jiao Tong University, Shanghai 200240, China; 3. MED-X Research Institute, Shanghai Jiao Tong University, Shanghai 200030, China; 4. School of Technology and Health, KTH Royal Institute of Technology, SE-100 44, Stockholm, Sweden)
  • Online:2019-08-01 Published:2019-07-29
  • Contact: ZHAO Jun *(赵俊) E-mail: junzhao@sjtu.edu.cn

PDF (PC)

136

Abstract: Lung cancer is the leading cause of cancer deaths worldwide. Accurate early diagnosis is critical in increasing the 5-year survival rate of lung cancer, so the efficient and accurate detection of lung nodules, the potential precursors to lung cancer, is paramount. In this paper, a computer-aided lung nodule detection system using 3D deep convolutional neural networks (CNNs) is developed. The first multi-scale 11-layer 3D fully convolutional neural network (FCN) is used for screening all lung nodule candidates. Considering relative small sizes of lung nodules and limited memory, the input of the FCN consists of 3D image patches rather than of whole images. The candidates are further classified in the second CNN to get the final result. The proposed method achieves high performance in the LUNA16 challenge and demonstrates the effectiveness of using 3D deep CNNs for lung nodule detection.

Key words: lung nodule detection| computer-aided detection (CAD)| convolutional neural network (CNN)| fully convolutional neural network (FCN)

摘要： Lung cancer is the leading cause of cancer deaths worldwide. Accurate early diagnosis is critical in increasing the 5-year survival rate of lung cancer, so the efficient and accurate detection of lung nodules, the potential precursors to lung cancer, is paramount. In this paper, a computer-aided lung nodule detection system using 3D deep convolutional neural networks (CNNs) is developed. The first multi-scale 11-layer 3D fully convolutional neural network (FCN) is used for screening all lung nodule candidates. Considering relative small sizes of lung nodules and limited memory, the input of the FCN consists of 3D image patches rather than of whole images. The candidates are further classified in the second CNN to get the final result. The proposed method achieves high performance in the LUNA16 challenge and demonstrates the effectiveness of using 3D deep CNNs for lung nodule detection.

关键词: lung nodule detection| computer-aided detection (CAD)| convolutional neural network (CNN)| fully convolutional neural network (FCN)

CLC Number: