RUN:Residual U-Net for Computer-Aided Detection of Pulmonary Nodules without Candidate Selection

TL;DR

This paper introduces RUN, a residual U-Net-based network that detects pulmonary nodules in a single step, significantly improving detection sensitivity and surpassing current state-of-the-art methods in lung cancer early diagnosis.

Contribution

The paper presents a novel residual U-Net architecture that enhances nodule detection by eliminating candidate selection, improving depth, and achieving superior performance on LUNA16 dataset.

Findings

Achieved 90.90% sensitivity at 2 false positives per scan.

Outperformed existing methods on LUNA16 challenge.

Validated effectiveness of residual U-Net in medical image detection.

Abstract

The early detection and early diagnosis of lung cancer are crucial to improve the survival rate of lung cancer patients. Pulmonary nodules detection results have a significant impact on the later diagnosis. In this work, we propose a new network named RUN to complete nodule detection in a single step by bypassing the candidate selection. The system introduces the shortcut of the residual network to improve the traditional U-Net, thereby solving the disadvantage of poor results due to its lack of depth. Furthermore, we compare the experimental results with the traditional U-Net. We validate our method in LUng Nodule Analysis 2016 (LUNA16) Nodule Detection Challenge. We acquire a sensitivity of 90.90% at 2 false positives per scan and therefore achieve better performance than the current state-of-the-art approaches.