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

Abstract

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.

Efficient Pneumonia Detection in Chest Xray Images Using Deep Transfer Learning

“…Saraiva et al [44], Ayan et al [45], and Rahman et al [46] used deep learning based methods for pneumonia classification. Xiao et al [47] proposed a novel multi-scale heterogeneous three-dimensional (3D) convolutional neural network (MSH-CNN) based on chest computed tomography (CT) images. Xu et al [48] used a hierarchical convolutional neural network (CNN) structure and a novel loss function, sin-loss, for pneumonia detection.…”

A Lightweight Deep Learning‐Based Pneumonia Detection Approach for Energy‐Efficient Medical Systems

“…Some researchers, such as Saraiva et al [49], Ayan and Ünver [50], and Rahman et al [51], have applied deep learning techniques to classify types of pneumonia. Furthermore, researchers introduced a three-dimensional (3D) convolutional neural network (MSH-CNN) to develop a diverse multiscale novel that depends on CT images of the chest [52]. On the other hand, another study was focused on detecting pneumonia using the hierarchical structure of CNN and loss function novel, sin-loss [53].…”

A Survey on Pneumonia Detection Methods Using Computer-aided Diagnosis

“…Based on chest computed tomography (CT) images. A novel multi-scale heterogeneous three-dimensional (3D) convolutional neural network (MSH-CNN) was proposed by Xiao et al [25]. For pneumonia detection, a hierarchical CNN structure and a novel loss function, sin loss is used by Xu et al [26].…”