Dual Skip Connections Minimize the False Positive Rate of Lung Nodule Detection in CT images
This work addresses the challenge of reducing false positives in lung nodule detection for medical imaging, which is incremental as it builds on existing U-Net and Dual Path network architectures.
The paper tackled the problem of automated lung nodule detection in CT images by proposing a dual skip connection upsampling strategy within a U-Net structure, achieving 85.3% sensitivity at 4 false positives per image, an improvement over baseline methods.
Pulmonary cancer is one of the most commonly diagnosed and fatal cancers and is often diagnosed by incidental findings on computed tomography. Automated pulmonary nodule detection is an essential part of computer-aided diagnosis, which is still facing great challenges and difficulties to quickly and accurately locate the exact nodules' positions. This paper proposes a dual skip connection upsampling strategy based on Dual Path network in a U-Net structure generating multiscale feature maps, which aims to minimize the ratio of false positives and maximize the sensitivity for lesion detection of nodules. The results show that our new upsampling strategy improves the performance by having 85.3% sensitivity at 4 FROC per image compared to 84.2% for the regular upsampling strategy or 81.2% for VGG16-based Faster-R-CNN.