Dual Skip Connections Minimize the False Positive Rate of Lung Nodule Detection in CT images

TL;DR

This paper introduces a dual skip connection upsampling method within a U-Net architecture to improve lung nodule detection in CT images, significantly reducing false positives and increasing sensitivity.

Contribution

It proposes a novel dual skip connection upsampling strategy based on a Dual Path network in U-Net, enhancing multiscale feature extraction for better nodule detection.

Findings

Achieved 85.3% sensitivity at 4 FROC per image.

Outperformed regular upsampling and VGG16-based Faster R-CNN.

Reduced false positive rate in lung nodule detection.

Abstract

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.