PUNDIT: Pulmonary nodule detection with image category transformation
Related Experiment Video
Updated: Aug 16, 2025
Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
Published on: May 19, 2023
Wangyuan Zhao1, Jingchen Ma2, Lu Zhao1
1School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China.
Background:
Convolutional neural networks (CNNs) have achieved great success in pulmonary nodules detection, which plays an important role in lung cancer screening.
Purpose:
In this paper, we proposed a novel strategy for pulmonary nodule detection by learning it from a harder task, which was to transform nodule images into normal images. We named this strategy as pulmonary nodule detection with image category transformation (PUNDIT).
Methods:
There were two steps for nodules detection, nodule candidate detection and false positive (FP) reduction. In nodule candidate detection step, a segmentation-based framework was built for detection. We designed an image category transformation (ICT) task to translate nodule images into pixel-to-pixel normal images and share the information of detection and transformation tasks by multitask learning. As for references of transformation tasks, we proposed background consistency losses into standard cycle-consistent adversarial networks, which can solve the problem of background uncontrolled changing. A three-dimensional network was used in FP reduction step.
Results:
PUNDIT was evaluated in two datasets, cancer screening dataset (CSD) with 1186 nodules for cross-validation and (CTD) with 3668 nodules for external test. Results were mainly evaluated by competition performance metric (CPM), the average sensitivity at seven predefined FP rates. The CPM was improved from 0.906 to 0.931 in CSD, and from 0.835 to 0.848 in CTD.
Conclusions:
Experimental results showed that PUNDIT can improve the performance of pulmonary nodules detection effectively.
