NoduleNet: Decoupled False Positive Reduction for Pulmonary Nodule Detection and Segmentation

2019 ◽  
pp. 266-274 ◽  
Author(s):  
Hao Tang ◽  
Chupeng Zhang ◽  
Xiaohui Xie
Keyword(s):  
Pulmonary Nodule ◽  
False Positive ◽  
False Positive Reduction ◽  
Nodule Detection ◽  
Pulmonary Nodule Detection

Pulmonary Nodule Detection in CT Images: False Positive Reduction Using Multi-View Convolutional Networks

2016 ◽  
Vol 35 (5) ◽  
pp. 1160-1169 ◽  
Author(s):  
Arnaud Arindra Adiyoso Setio ◽  
Francesco Ciompi ◽  
Geert Litjens ◽  
Paul Gerke ◽  
Colin Jacobs ◽  
...  
Keyword(s):  
Pulmonary Nodule ◽  
False Positive ◽  
Ct Images ◽  
Convolutional Networks ◽  
False Positive Reduction ◽  
Nodule Detection ◽  
Pulmonary Nodule Detection

A deep 3D residual CNN for false-positive reduction in pulmonary nodule detection

2018 ◽  
Vol 45 (5) ◽  
pp. 2097-2107 ◽  
Author(s):  
Hongsheng Jin ◽  
Zongyao Li ◽  
Ruofeng Tong ◽  
Lanfen Lin
Keyword(s):  
Pulmonary Nodule ◽  
False Positive ◽  
False Positive Reduction ◽  
Nodule Detection ◽  
Pulmonary Nodule Detection

scholarly journals Multi-Scale Heterogeneous 3D CNN for False-Positive Reduction in Pulmonary Nodule Detection, Based on Chest CT Images

2019 ◽  
Vol 9 (16) ◽  
pp. 3261 ◽  
Author(s):  
Zhitao Xiao ◽  
Naichao Du ◽  
Lei Geng ◽  
Fang Zhang ◽  
Jun Wu ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Pulmonary Nodule ◽  
False Positive ◽  
Multi Scale ◽  
False Positive Reduction ◽  
Nodule Detection ◽  
Computer Aided ◽  
Pulmonary Nodule Detection ◽  
3D Cnn ◽  
Aided Diagnosis

Currently, lung cancer has one of the highest mortality rates because it is often caught too late. Therefore, early detection is essential to reduce the risk of death. Pulmonary nodules are considered key indicators of primary lung cancer. Developing an efficient and accurate computer-aided diagnosis system for pulmonary nodule detection is an important goal. Typically, a computer-aided diagnosis system for pulmonary nodule detection consists of two parts: candidate nodule extraction and false-positive reduction of candidate nodules. The reduction of false positives (FPs) of candidate nodules remains an important challenge due to morphological characteristics of nodule height changes and similar characteristics to other organs. In this study, we propose a novel multi-scale heterogeneous three-dimensional (3D) convolutional neural network (MSH-CNN) based on chest computed tomography (CT) images. There are three main strategies of the design: (1) using multi-scale 3D nodule blocks with different levels of contextual information as inputs; (2) using two different branches of 3D CNN to extract the expression features; (3) using a set of weights which are determined by back propagation to fuse the expression features produced by step 2. In order to test the performance of the algorithm, we trained and tested on the Lung Nodule Analysis 2016 (LUNA16) dataset, achieving an average competitive performance metric (CPM) score of 0.874 and a sensitivity of 91.7% at two FPs/scan. Moreover, our framework is universal and can be easily extended to other candidate false-positive reduction tasks in 3D object detection, as well as 3D object classification.

Sign in / Sign up

Export Citation Format

Share Document