Computer-aided detection of pulmonary nodules based on convolutional neural networks: a review

S-Net: an S-shaped network for nodule detection in 3D CT images

Objective. Accurate and automatic detection of pulmonary nodules is critical for early lung cancer diagnosis, and promising progress has been achieved in developing effective deep models for nodule detection. However, most existing nodule detection methods merely focus on integrating elaborately designed feature extraction modules into the backbone of the detection network to extract rich nodule features while ignore disadvantages of the structure of detection network itself. This study aims to address these disadvantages and develop a deep learning-based algorithm for pulmonary nodule detection to improve the accuracy of early lung cancer diagnosis.Approach. In this paper, an S-shaped network called S-Net is developed with the U-shaped network as backbone, where an information fusion branch is used to propagate lower-level details and positional information critical for nodule detection to higher-level feature maps, head shared scale adaptive detection strategy is utilized to capture information from different scales for better detecting nodules with different shapes and sizes and the feature decoupling detection head is used to allow the classification and regression branches to focus on the information required for their respective tasks. A hybrid loss function is utilized to fully exploit the interplay between the classification and regression branches.Main results. The proposed S-Net network with ResSENet and other three U-shaped backbones from SANet, OSAF-YOLOv3 and MSANet (R+SC+ECA) models achieve average CPM scores of 0.914, 0.915, 0.917 and 0.923 on the LUNA16 dataset, which are significantly higher than those achieved with other existing state-of-the-art models.Significance. The experimental results demonstrate that our proposed method effectively improves nodule detection performance, which implies potential applications of the proposed method in clinical practice.

The International Association for the Study of Lung Cancer Early Lung Imaging Confederation Open-Source Deep Learning and Quantitative Measurement Initiative

INTRODUCTION

With global adoption of computed tomography (CT) lung cancer screening, there is increasing interest to use artificial intelligence (AI) deep learning methods to improve the clinical management process. To enable AI research using an open-source, cloud-based, globally distributed, screening CT imaging data set and computational environment that are compliant with the most stringent international privacy regulations that also protect the intellectual properties of researchers, the International Association for the Study of Lung Cancer sponsored development of the Early Lung Imaging Confederation (ELIC) resource in 2018. The objective of this report is to describe the updated capabilities of ELIC and illustrate how this resource can be used for clinically relevant AI research.

METHODS

In this second phase of the initiative, metadata and screening CT scans from two time points were collected from 100 screening participants in seven countries. An automated deep learning AI lung segmentation algorithm, automated quantitative emphysema metrics, and a quantitative lung nodule volume measurement algorithm were run on these scans.

RESULTS

A total of 1394 CTs were collected from 697 participants. The LAV950 quantitative emphysema metric was found to be potentially useful in distinguishing lung cancer from benign cases using a combined slice thickness more than or equal to 2.5 mm. Lung nodule volume change measurements had better sensitivity and specificity for classifying malignant from benign lung nodules when applied to solid lung nodules from high-quality CT scans.

CONCLUSIONS

These initial experiments revealed that ELIC can support deep learning AI and quantitative imaging analyses on diverse and globally distributed cloud-based data sets.

Expanding Role of Advanced Image Analysis in CT-detected Indeterminate Pulmonary Nodules and Early Lung Cancer Characterization

The implementation of low-dose chest CT for lung screening presents a crucial opportunity to advance lung cancer care through early detection and interception. In addition, millions of pulmonary nodules are incidentally detected annually in the United States, increasing the opportunity for early lung cancer diagnosis. Yet, realization of the full potential of these opportunities is dependent on the ability to accurately analyze image data for purposes of nodule classification and early lung cancer characterization. This review presents an overview of traditional image analysis approaches in chest CT using semantic characterization as well as more recent advances in the technology and application of machine learning models using CT-derived radiomic features and deep learning architectures to characterize lung nodules and early cancers. Methodological challenges currently faced in translating these decision aids to clinical practice, as well as the technical obstacles of heterogeneous imaging parameters, optimal feature selection, choice of model, and the need for well-annotated image data sets for the purposes of training and validation, will be reviewed, with a view toward the ultimate incorporation of these potentially powerful decision aids into routine clinical practice.

Development of a computer-aided quality assurance support system for identifying hand X-ray image direction using deep convolutional neural network

The convenience of imaging has improved with digitization; however, there has been no progress in the methods used to prevent human error. Therefore, radiographic incidents and accidents are not prevented. In Japan, image interpretation is conducted for incident prevention; nevertheless, in some cases, incidents are overlooked. Thus, assistance from a computer-aided quality assurance support system is important. This study developed a method to identify hand image direction, which is an elementary technology of a computer-aided quality assurance support system. In total, 14,236 hand X-ray images were used to classify hand directions (upward, downward, rightward, and leftward) commonly evaluated in clinical settings. The accuracy of the conventional classification method using original images, classification method with histogram equation images, and a novel classification method using binarization images for background removal via U-Net segmentation was evaluated. The following classification accuracy rates were achieved: 89.20% if the original image was input, 99.10% if the histogram equation image was input, and 99.70% if binarization images for background removal via U-Net segmentation was input. Our computer-aided quality assurance support system can be used to identify hand direction with high accuracy.