Diminution index: A novel 3D feature for pulmonary nodule detection

Automated Computer-Aided Detection of Lung Nodules in Metastatic Colorectal Cancer Patients for the Identification of Pulmonary Oligometastatic Disease

Computer-aided Lung Nodule Detection in CT: Results of Large-Scale Observer Test 1

Based on Global Cancer 2015 statistics, the lung cancer of all types constitutes 27% of overall cancers while 19.5% of cancer deaths are due to lung cancer. In lieu of this, an effective lung cancer screening test using Computed Tomography (CT) scan is crucial to detect cancer at the early stage. The interpretation of the CT images requires an advanced CAD system of high accuracy for instance, in classifying the lung nodules. Recently, Deep Learning method that is Convolution Neural Network (CNN) shows an outstanding success in lung nodules classification. However, the training of CNN requires a great number of images. Such a requirement is an issue in the case of medical images. Generative adversarial network (GAN) has been introduced to generate new image datasets for CNN training. Thus, the main objective of this study is to compare the performance of CNN architectures with and without the implementation of GAN for lung nodules classification in CT images. Here, the study used Conditional GAN (cGAN) to generate benign nodules images. The classification accuracy of the combined cGAN-CNN architecture was compared among CNN pretraining networks namely GoogleNet, ShuffleNet, DenseNet, and MobileNet based on classification accuracy, specificity, sensitivity, and AUC-ROC values. The experiment was tested on LIDC-IDRI database. The results showed cGAN-CNN architecture improves the overall classification accuracy as compared to CNN alone with the cGAN-ShuffleNet architecture performed the best, achieving 98.38% accuracy, 98.13% specificity, 100% sensitivity and AUC-ROC at 99.90%. Overall, the classification performance of CNN can be improved by integrating GAN architecture to mitigate the constraint of having a large medical image dataset, in this case, CT lung nodules images.

Early detection of pulmonary nodules is crucial for improving prognosis of patients with lung cancer. Computer-aided detection of lung nodules in thoracic computed tomography (CT) scans has a great potential to enhance the performance of the radiologist in detecting nodules. In this paper we present a computer-aided lung nodule detection system for computed tomography (CT) scans that works in three steps. The system first segments the lung using thresholding and hole filling. From this segmentation the system extracts candidate nodules using Laplacian of Gaussian. To reject false positives among the detected candidate nodules, multiple established features are calculated. We propose a novel feature based on a spherical shell filter, which is specifically designed to distinguish between vascular structures and nodular structures. The performance of the proposed CAD system was evaluated by partaking in the ANODE09 challenge, which presents a platform for comparing automatic nodule detection programs. The results from the challenge show that our CAD system ranks third among the submitted works, demonstrating the efficacy of our proposed CAD system. The results also show that our proposed spherical shell filter in combination with conventional features can significantly reduce the number of false positives from the detected candidate nodules.

Lung cancer is a deadly cancer that causes millions of deaths every year around the world. Accurate lung nodule detection and segmentation in computed tomography (CT) images is a vital step for diagnosing lung cancer early. Most existing systems face several challenges, such as the heterogeneity in CT images and variation in nodule size, shape, and location, which limit their accuracy. In an attempt to handle these challenges, this article proposes a fully automated deep learning framework that consists of lung nodule detection and segmentation models. Our proposed system comprises two cascaded stages: (1) nodule detection based on fine-tuned Faster R-CNN to localize the nodules in CT images, and (2) nodule segmentation based on the U-Net architecture with two effective blocks, namely position attention-aware weight excitation (PAWE) and channel attention-aware weight excitation (CAWE), to enhance the ability to discriminate between nodule and non-nodule feature representations. The experimental results demonstrate that the proposed system yields a Dice score of 89.79% and 90.35%, and an intersection over union (IoU) of 82.34% and 83.21% on the publicly available LUNA16 and LIDC-IDRI datasets, respectively.

We are developing a computer-aided detection system to assist radiologists in the detection of lung nodules on thoracic computed tomography (CT) images. The purpose of this study was to improve the false-positive (FP) reduction stage of our algorithm by developing features that extract three-dimensional (3D) shape information from volumes of interest identified in the prescreening stage. We formulated 3D gradient field descriptors, and derived 19 gradient field features from their statistics. Six ellipsoid features were obtained by computing the lengths and the length ratios of the principal axes of an ellipsoid fitted to a segmented object. Both the gradient field features and the ellipsoid features were designed to distinguish spherical objects such as lung nodules from elongated objects such as vessels. The FP reduction performance in this new 25-dimensional feature space was compared to the performance in a 19-dimensional space that consisted of features extracted using previously developed methods. The performance in the 44-dimensional combined feature space was also evaluated. Linear discriminant analysis with stepwise feature selection was used for classification. The parameters used for feature selection were optimized using the simplex algorithm. Training and testing were performed using a leave-one-patient-out scheme. The FP reduction performances in different feature spaces were evaluated by using the area Az under the receiver operating characteristic curve and the number of FPs per CT section at a given sensitivity as accuracy measures. Our data set consisted of 82 CT scans (3551 axial sections) from 56 patients with section thickness ranging from 1.0 to 2.5 mm. Our prescreening algorithm detected 111 of the 116 solid nodules (nodule size: 3.0-30.6 mm) marked by experienced thoracic radiologists. The test Az values were 0.95 +/- 0.01, 0.88 +/- 0.02, and 0.94 +/- 0.01 in the new, previous, and combined feature spaces, respectively. The number of FPs per section at 80% sensitivity in these three feature spaces were 0.37, 1.61, and 0.34, respectively. The improvement in the test Az with the 25 new features was statistically significant (p<0.0001) compared to that with the previous 19 features alone.

A pulmonary nodule is a small round or oval-shaped growth in the lung. Pulmonary nodules are detected in Computed Tomography (CT) lung scans. Early and accurate detection of such nodules could help in successful diagnosis and treatment of lung cancer. In recent years, the demand for CT scans has increased substantially, thus increasing the workload on radiologists who need to spend hours reading through CT-scanned images. Computer-Aided Detection (CAD) systems are designed to assist radiologists in the reading process and thus making the screening more effective. Recently, applying deep learning to medical images has gained attraction due to its high potential. In this paper, inspired by the successful use of deep convolutional neural networks (DCNNs) in natural image recognition, we propose a detection system based on DCNNs which is able to detect pulmonary nodules in CT images. In addition, this system does not use image segmentation or post-classification false-positive r eduction techniques which are commonly used in other detection systems. The system achieved an accuracy of 63.49% on the publicly available Lung Image Database Consortium (LIDC) dataset which contains 1018 thoracic CT scans with pulmonary nodules of different shapes and sizes.

We are developing a computer-aided detection system to aid radiologists in diagnosing lung cancer in thoracic computed tomographic (CT) images. The purpose of this study was to improve the false-positive (FP) reduction stage of our algorithm by developing and incorporating a gradient field technique. This technique extracts 3D shape information from the gray-scale values within a volume of interest. The gradient field feature values are higher for spherical objects, and lower for elongated and irregularly-shaped objects. A data set of 55 thin CT scans from 40 patients was used to evaluate the usefulness of the gradient field technique. After initial nodule candidate detection and rule-based first stage FP reduction, there were 3487 FP and 65 true positive (TP) objects in our data set. Linear discriminant classifiers with and without the gradient field feature were designed for the second stage FP reduction. The accuracy of these classifiers was evaluated using the area Az under the receiver operating characteristic (ROC) curve. The Az values were 0.93 and 0.91 with and without the gradient field feature, respectively. The improvement with the gradient field feature was statistically significant (p=0.01).

Volume quantifications of lung nodules with multidetector computed tomography (CT) images provide useful information for monitoring nodule developments. The accuracy and precision of the volume quantification, however, can be impacted by imaging and reconstruction parameters. This study aimed to investigate the impact of iterative reconstruction algorithms on the accuracy and precision of volume quantification with dose and slice thickness as additional variables. Repeated CT images were acquired from an anthropomorphic chest phantom with synthetic nodules (9.5 and 4.8 mm) at six dose levels, and reconstructed with three reconstruction algorithms [filtered backprojection (FBP), adaptive statistical iterative reconstruction (ASiR), and model based iterative reconstruction (MBIR)] into three slice thicknesses. The nodule volumes were measured with two clinical software (A: Lung VCAR, B: iNtuition), and analyzed for accuracy and precision. Precision was found to be generally comparable between FBP and iterative reconstruction with no statistically significant difference noted for different dose levels, slice thickness, and segmentation software. Accuracy was found to be more variable. For large nodules, the accuracy was significantly different between ASiR and FBP for all slice thicknesses with both software, and significantly different between MBIR and FBP for 0.625 mm slice thickness with Software A and for all slice thicknesses with Software B. For small nodules, the accuracy was more similar between FBP and iterative reconstruction, with the exception of ASIR vs FBP at 1.25 mm with Software A and MBIR vs FBP at 0.625 mm with Software A. The systematic difference between the accuracy of FBP and iterative reconstructions highlights the importance of extending current segmentation software to accommodate the image characteristics of iterative reconstructions. In addition, a calibration process may help reduce the dependency of accuracy on reconstruction algorithms, such that volumes quantified from scans of different reconstruction algorithms can be compared. The little difference found between the precision of FBP and iterative reconstructions could be a result of both iterative reconstruction's diminished noise reduction at the edge of the nodules as well as the loss of resolution at high noise levels with iterative reconstruction. The findings do not rule out potential advantage of IR that might be evident in a study that uses a larger number of nodules or repeated scans.

When assessing the volume of pulmonary nodules on computed tomography (CT) images, there is an inevitable discrepancy between values based on the diameter-based volume calculation and the voxel-counting method, which is derived from the Euclidean distance measurement method on pixel/voxel-based digital image. We aimed to evaluate the ability of a modified diameter measurement method to reduce the discrepancy, and we determined a conversion equation to equate volumes derived from different methods. Two different anthropomorphic phantoms with subsolid and solid nodules were repeatedly scanned under various settings. Nodules in CT images were detected and segmented using a fully automated algorithm and the volume was calculated using three methods: the voxel-counting method (Vvc ), diameter-based volume calculation (Vd ), and a modified diameter-based volume calculation (Vd+ 1), in which one pixel spacing was added to the diameters in the three axes (x-, y-, and z-axis). For each nodule, Vd and Vd +1 were compared to Vvc by computing the absolute percentage error (APE) as follows: APE =100 × (V - Vvc )/Vvc . Comparisons between APEd and APEd+1 according to CT parameter setting were performed using the Wilcoxon signed-rank test. The Jonckheere-Terpstra test was used to evaluate trends across the four different nodule sizes. The deep learning-based computer-aided diagnosis (DL-CAD) successfully detected and segmented all nodules in a fully automatic manner. The APE was significantly less with Vd+1 than with Vd (Wilcoxon signed-rank test, P<0.05) regardless of CT parameters and nodule size. The APE median increased as the size of the nodule decreased. This trend was statistically significant (Jonckheere-Terpstra test, P<0.001) regardless of volume measurement method (diameter-based and modified diameter-based volume calculations). Our modified diameter-based volume calculation significantly reduces the discrepancy between the diameter-based volume calculation and voxel-counting method.

Computer-aided diagnoses programs are developed for alerting the radiologist by indicating potential sites of lesions. One of the important tasks in the development of a computational system for detecting lung nodules is to diminish the number of false positives keeping on high sensitivities. In this work we describe a system for automatic lung nodule detection. The detection is carried out in several stages. First, a knowledge-based segmentation process delimits the lung boundaries. Then, a progressive thresholding of an image in which the conspicuity of nodules has been enhanced by means of filter matching and a set of growth and circularity tests fix the areas suspicious of being nodules into region previously labelled as lungs. Finally, these suspicious regions are confirmed as nodules in a new feature (curvature) space, which gives us an important help in the task of distinguishing true and false nodules from previously extracted suspicious regions. Preliminary results are very promising, achieving high sensitivities with a little ratio of false positives.

Computer-vision techniques based on wavelets are presented with applications to computer-aided diagnosis (CAD) in medical images. CAD is a method for assisting radiologists’ interpretation of medical images. CAD schemes act as a second reader and alert radiologists to suspicious lesions. Development of CAD schemes is an active area of research, motivated by the fact that radiologists tend to misdiagnose cancerous lesions in medical images. In the past several years, we have been extensively developing wavelet-based techniques for CAD schemes. Development of these techniques has led to a new CAD scheme and has yielded significant improvements in the performance of the existing CAD schemes. This chapter describes two wavelet-based, low-level computer vision techniques: simultaneous segmentation and registration, and matching pursuit with optimally weighted wavelet packets. We present their application to the computer-aided detection of lung nodules in chest radiographs and microcalcifications in mammograms.

A ℓ2, 1 norm regularized multi-kernel learning for false positive reduction in Lung nodule CAD

Effect of CAD on Radiologists' Detection of Lung Nodules on Thoracic CT Scans: Analysis of an Observer Performance Study by Nodule Size

Computer Aided Detection (CAD) systems provide a second opinion to radiologists in detecting lung cancer by providing automated analysis of the scans. The proposed CAD system consists of five processing steps: image acquisition, preprocessing, lung segmentation, nodule detection and false positive reduction. First, 400 CT scans are downloaded from the Lung Image Database Consortium (LIDC). Preprocessing is implemented using contrast stretching and enhancing. Lung segmentation and nodule detection stages are performed using a combination of region growing, thresholding and morphological operations. Each 3D structure is then subjected to tabular structure elimination to provide nodule candidates. In the false positive reduction stage, some of the basic nodule features are extracted from the training data to set thresholds for a simple rule-based classifier. The CAD achieved sensitivity of 77.77%, specificity of 69.5% and accuracy 70.53 % with an average 4.1 FPs/scan.