A survey of pulmonary nodule detection, segmentation and classification in computed tomography with deep learning techniques

  title={A survey of pulmonary nodule detection, segmentation and classification in computed tomography with deep learning techniques},
  author={Jianrong Wu and Tianyi Qian},
  journal={Journal of Medical Artificial Intelligence},
  • Jianrong Wu, Tianyi Qian
  • Published 19 April 2019
  • Medicine, Computer Science
  • Journal of Medical Artificial Intelligence
Lung cancer is the top cause for deaths by cancers whose 5-year survival rate is less than 20%. To improve the survival rate of patients with lung cancers, the early detection and early diagnosis is significant. Furthermore, early detection of pulmonary nodules is essential for the detection and diagnosis of lung cancer in early stage. The National Lung Screening Trial (NLST) showed annual screening by low-dose computed tomography (LDCT) could help to reduce the deaths caused by lung cancer of… 

Tables from this paper

Deep Learning Applications in Computed Tomography Images for Pulmonary Nodule Detection and Diagnosis: A Review

A baseline understanding of the topic is provided for interested readers by categorizing segmentation parts based on lung nodule type and network architectures, i.e., general neural network and multiview convolution neural network architecture.

A Two-Stage Framework for Automated Malignant Pulmonary Nodule Detection in CT Scans

A two-stage framework that exploits the ever-growing advances in deep neural network models, and that is comprised of a semantic segmentation stage followed by localization and classification, is proposed that significantly improves the accuracy of nodule detection compared to the classical U-Net model and its most recent variants.

Comparative evaluation of conventional and deep learning methods for semi-automated segmentation of pulmonary nodules on CT.

Deep learning is a viable approach for semi-automated segmentation of pulmonary nodules on CT scans based on deep learning methods based on conventional methods.

Automatic segmentation for pulmonary nodules in CT images based on multifractal analysis

An intelligent method to automatically detect and segment pulmonary nodules from computed tomography (CT) scans is presented and can avoid the problem of selecting seeds when applying region-growing techniques to segmentmonary nodules.

Convolutional Neural Networks for the Automated Segmentation and Recurrence Risk Prediction of Surgically Resected Lung Tumors

This proposed framework is the first fully automated segmentation and recurrence risk prediction system to be implemented and demonstrates that first, automated nodule segmentation methods can generalize to enable pipelines for a wide range of multitask systems and second, that deep learning and image processing have the potential to improve current prognostic tools.

An effective neural network model for lung nodule detection in CT images with optimal fuzzy model

The results demonstrate that ANN with Oppositional based Ant Lion Optimization (OALO) algorithm achieves high accuracy and less execution time compared to existing algorithms.

Lung nodules segmentation from CT with DeepHealth toolkit

The goal of this study was to demonstrate the feasibility of Deephealth toolkit including PyECVL and PyEDDL libraries to precisely segment lung nodules to depict accurate segmentation of lung nodule across a wide diameter range and better accuracy over a traditional detection approach.

Volumetric lung nodule segmentation using adaptive ROI with multi-view residual learning

A novel semi-automated approach for 3-D segmentation of lung nodule in computerized tomography scans, which achieved the average dice score of 87.5%, which is significantly higher than the existing state-of-the-art techniques.

Deep Active Learning for Effective Pulmonary Nodule Detection

This work proposes a novel active learning approach to improve the training efficiency for a deep network-based lung nodule detection framework as well as reduce the annotation cost for the low-dose computed tomography (CT) scans.



Lung nodule detection in CT images using deep convolutional neural networks

This CADe system is validated on a larger number of lung nodules compared to other studies, which increases the variation in their appearance, and therefore, makes their detection by a CADe systems more challenging.


This survey focusses on different techniques used to detect and classify the lung nodules which in turn will assist the domain experts for better diagnosis.

Evaluate the Malignancy of Pulmonary Nodules Using the 3-D Deep Leaky Noisy-OR Network

A 3-D deep neural network for automatic diagnosing lung cancer from computed tomography scans that selects the top five nodules based on the detection confidence, evaluates their cancer probabilities, and combines them with a leaky noisy-OR gate to obtain the probability of lung cancer for the subject.

Accurate Pulmonary Nodule Detection in Computed Tomography Images Using Deep Convolutional Neural Networks

This paper introduces a deconvolutional structure to Faster Region-based Convolutional Neural Network (Faster R-CNN) for candidate detection on axial slices and proposes a novel pulmonary nodule detection approach based on DCNNs.

Automated system for lung nodules classification based on wavelet feature descriptor and support vector machine

The CADx system presented is competitive with other literature systems in terms of sensitivity and reduces the complexity of classification by not performing the typical segmentation stage of most CADx systems.

Lung nodule diagnosis from CT images based on ensemble learning

This paper presents a computer-aided classification method using computed tomography images of the lung based on ensemble of three classifiers including MLP, KNN and SVM, and the results show good improvement in diagnosing of pulmonary nodules.

Joint learning for pulmonary nodule segmentation, attributes and malignancy prediction

An interpretable and multi-task learning CNN — Joint learning for Pulmonary Nodule Segmentation Attributes and Malignancy Prediction (PN-SAMP), able to not only accurately predict the malignancy of lung nodules, but also provide semantic high-level attributes as well as the areas of detected nodules.

An Automatic Detection System of Lung Nodule Based on Multigroup Patch-Based Deep Learning Network

The results demonstrate that the multigroup patch-based learning system is efficient to improve the performance of lung nodule detection and greatly reduce the false positives under a huge amount of image data.