MENU

Click here to

×

Are you sure ?

Yes, do it No, cancel

Deep Learning for Automatic Real-Time Pulmonary Nodule Detection and Quantitative Analysis

C Liu1*, S Hu2 , F Yin3 , (1) Duke Kunshan University, Suzhou, Jiangsu, (2) Duke Kunshan University, Suzhou, Jiangsu, (3) Duke University Medical Center, Durham, NC

Presentations

(Wednesday, 7/17/2019) 10:30 AM - 11:00 AM

Room: Exhibit Hall | Forum 2

Purpose: To develop a novel computer-aided diagnosis (CAD) pulmonary nodule detection system that can not only perform real-time detection but also characterize quantitative nodule information based on deep learning methods.

Methods: We constructed a convolutional neural network (CNN) for automated pulmonary nodule detection and characterization. Nodule detection was accomplished by customizing a detection algorithm (YOLO v3), which comprised of a feature extractor and a bounding box generator. The feature extractor had 19 convolutional layers with 7 residual shortcut connections to extract features on input images at three different down-sampling scales (i.e. 4, 8, and 16). The bounding box generator had 7 convolutional layers to determine the location and size of each detected nodule. A python-based characterization system was then developed to characterize size, diameter, and central coordinates of each detected nodule within the generated bounding box. This characterization system applied non-maximum suppression algorithm to exclude nodules below true positive probability threshold. The system was trained and validated using ten-fold cross-validation with 330 XCAT simulated CT scans and 888 patient CT scans from LIDC–IDRI public database, separately. System performance was evaluated using Free-Response Receiver Operating Characteristic (FROC) analysis, competition performance metric (CPM) score, as well as precision analysis of central coordinates and diameters.

Results: The developed CAD system achieved CPM scores of 1 in the simulation image study and 0.869 in the public database study. The average performance time per image was less than 0.1 second. Compared with ground truth data, the average errors of diameter were 0.2 mm using simulated images and 1.1 mm using public database, while the average errors of central coordinate were 0.8 mm and 1.4 mm, respectively.

Conclusion: Preliminary evaluation shown that our proposed CAD system using deep learning methods was robust and achieved real-time nodule detection with high accuracy and characterization with high precision.

Keywords

Pulmonary Nodules , Computer Vision

Taxonomy

IM- CT: CAD

Contact Email