Automatic nodule detection for lung cancer in CT images: A review

In the design of computer-aided diagnosis systems for lung cancer diagnosis, an appropriate and accurate segmentation of the pulmonary nodules in computerized tomography (CT) is one of the most relevant and difficult tasks An accurate segmentation is crucial for the posterior measurement of nodule characteristics and for lung cancer diagnosis This paper proposes different approaches that use Hessian-based strategies for lung nodule segmentation in chest CT scans We propose a multiscale segmentation process that uses the central medialness adaptive principle, a Hessian-based strategy that was originally formulated for tubular extraction but it also provides good segmentation results in blob-like structures as is the case of lung nodules We compared this proposal with a well established Hessian-based strategy that calculates the Shape Index (SI) and Curvedness (CV) We adapted the SI and CV approach for multiscale nodule segmentation Moreover, we propose the combination of both strategies by combining the results, in order to take benefit of the advantages of both strategies Different cases with pulmonary nodules from the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) database were taken and used to analyze and validate the approaches The chest CT images present a large variability in nodule characteristics and image conditions Our proposals provide an accurate lung nodule segmentation, similar to radiologists performance Our Hessian-based approaches were validated with 569 solid and mostly solid nodules demonstrating that these novel strategies have good results when compared with the radiologists segmentations, providing accurate pulmonary nodule volumes for posterior characterization and appropriate diagnosis

Hessian based approaches for 3D lung nodule segmentation

Pulmonary nodule detection has great significance for early treating lung cancer and increasing patient survival. This work presents a novel automated computer-aided detection scheme for pulmonary nodules based on deep convolutional neural networks (DCNNs). The proposed approach employs 3D DCNNs based on squeeze-and-excitation network and residual network (SE-ResNet) for pulmonary nodule candidate detection and false-positive reduction. Specifically, a 3D region proposal network with a U-Net-like structure is designed for detecting pulmonary nodule candidates. For the subsequent false-positive reduction, a 3D SE-ResNet-based classifier is presented to accurately discriminate the true nodules from candidates. The 3D SE-ResNet modules boost the representational power of the network by adaptively recalibrating channel-wise residual feature responses. Both models utilize 3D SE-ResNet modules to learn nodule features effectively and improve nodule detection performance. On the public available lung nodule analysis 2016 dataset with 888 scans included, the proposed method reaches high detection sensitivities of 93.6% and 95.7% at one and four false positives per scan, respectively. Meanwhile, the competition performance metric score of 0.904 is achieved. The proposed method has the capability to detect multi-size nodules, especially the extremely small nodules. In this paper, a 3D DCNNs framework based on 3D SE-ResNet modules is proposed to detect pulmonary nodules in chest CT images accurately. Experimental results demonstrate superior effectiveness of the proposed approach in pulmonary nodule detection task.

Automated pulmonary nodule detection in CT images using 3D deep squeeze-and-excitation networks

Lung cancer is still the most concerned disease around the world. Lung nodule generates in the pulmonary parenchyma which indicates the latent risk of lung cancer. Computer-aided pulmonary nodules detection system is necessary, which can reduce diagnosis time and decrease mortality of patients. In this study, we have proposed a new computer aided diagnosis (CAD) system for detection of early pulmonary nodule, which can help radiologists quickly locate suspected nodules and make judgments. This system consists of four main sections: pulmonary parenchyma segmentation, nodule candidate detection, features extraction (total 22 features) and nodule classification. The publicly available data set created by the Lung Image Database Consortium (LIDC) is used for training and testing. This study selects 6400 slices from 80 CT scans containing totally 978 nodules, which is labeled by four radiologists. Through a fast segmentation method proposed in this paper, pulmonary nodules including 888 true nodules and 11,379 false positive nodules are segmented. By means of an ensemble classifier, Random Forest (RF), this study acquires 93.2, 92.4, 94.8, 97.6% of accuracy, sensitivity, specificity, area under the curve (AUC), respectively. Compared with support vector machine (SVM) classifier, RF can reduce more false positive nodules and acquire larger AUC. With the help of this CAD system, radiologist can be provided with a great reference for pulmonary nodule diagnosis timely.

An Assisted Diagnosis System for Detection of Early Pulmonary Nodule in Computed Tomography Images

This paper presents a systematic review of the literature focused on the lung nodule detection in chest computed tomography (CT) images. Manual detection of lung nodules by the radiologist is a sequential and time-consuming process. The detection is subjective and depends on the radiologist’s experiences. Owing to the variation in shapes and appearances of a lung nodule, it is very difficult to identify the proper location of the nodule from a huge number of slices generated by the CT scanner. Small nodules (< 10 mm in diameter) may be missed by this manual detection process. Therefore, computer-aided diagnosis (CAD) system acts as a “second opinion” for the radiologists, by making final decision quickly with higher accuracy and greater confidence. The goal of this survey work is to present the current state of the artworks and their progress towards lung nodule detection to the researchers and readers in this domain. This review paper has covered the published works from 2009 to April 2018. Different nodule detection approaches are described elaborately in this work. Recently, it is observed that deep learning (DL)-based approaches are applied extensively for nodule detection and characterization. Therefore, emphasis has been given to convolutional neural network (CNN)-based DL approaches by describing different CNN-based networks.

Lung Nodule Detection from Feature Engineering to Deep Learning in Thoracic CT Images: a Comprehensive Review

Refinement of lung nodule candidates based on local geometric shape analysis and Laplacian of Gaussian kernels

This work aims to develop a unified methodology for the false positives reduction in lung nodules computer-aided detection schemes. The 3D region of each detected nodule candidate is first reconstructed using the sparse field method for accurately segmenting the objects. This technique enhances the level set modeling by restricting the computations to a narrow band near the evolving curve. Then, a set of 2D and 3D relevant features are extracted for each segmented candidate. Subsequently, a hybrid undersampling/boosting algorithm called RUSBoost is applied to analyze the features and discriminate real nodules from non-nodules. The performance of the proposed scheme was evaluated by using 70 CT images, randomly selected from the Lung Image Database Consortium and containing 198 nodules. Applying RUSBoost classifier exhibited a better performance than some commonly used classifiers. It effectively reduced the average number of FPs to only 3.9 per scan based on a fivefold cross-validation. The practical implementation, applicability for different nodule types and adaptability in handling the imbalanced data classification insure the improvement in lung nodules detection by utilizing this new approach.

A unified methodology based on sparse field level sets and boosting algorithms for false positives reduction in lung nodules detection

In this paper, a new method is presented for reducing salt and pepper noise in color images. This method consists of three steps: In the first step, Laplacian operators and threshold values are used to identify pixels that are likely to have been corrupted by noise; in the second step, these noise candidates are judged by using the neighborhood of each pixel. After recognizing the noisy pixels, the vector median filter is used for replacing the noisy pixels, in the third step. The proposed algorithm is tested against different color images, and it gives a better peak signal-to-noise ratio and a lower normalized mean square error. These results have also been checked and analyzed visually. The performance of the proposed method is compared with common existing vector filters at different noise densities. Extensive experiments show that the proposed algorithm provides better performance than many of the existing vector filters in terms of noise suppression and preserving thin lines, fine details, and image edges.

A new filter to remove salt and pepper noise in color images

The need for efficient image browsing and searching motivates the use of Content-Based Image Retrieval (CBIR) systems. However, they suffer from a big gap between high-level image semantics and low-level features. So, a learning process to reduce the gap seems quite useful. This paper presents a novel Learning Automata (LA)-based approach to improve the CBIR systems. Distributed Learning Automata (DLA) is used in this work to learn the relevant images from textual query feedbacks of the users. Subsequently, the retrieved images are ranked according to the learning outcome and similarity measure. In this study, the similarity between images is evaluated based on two color descriptors: the global color histogram and local color auto-correlogram. A thorough observation and comparison of these color descriptors performances are performed with different color spaces and also with various similarity measures. Experimental results on two publicly available databases demonstrate that the performance of the proposed CBIR system after each round is improved and the system could retrieve images compatible with the users’ perception.

Soudeh Saien

Papers

Refinement of lung nodule candidates based on local geometric shape analysis and Laplacian of Gaussian kernels

A unified methodology based on sparse field level sets and boosting algorithms for false positives reduction in lung nodules detection

A new filter to remove salt and pepper noise in color images

A learning automata framework based on relevance feedback for content-based image retrieval