Lung Image Database Consortium Dataset Research Articles

An Efficient Sinogram Domain Fully Convolutional Interpolation Network for Sparse-View Computed Tomography Reconstruction

Recently, deep learning techniques have been used for low-dose CT (LDCT) reconstruction to reduce the radiation risk for patients. Despite the improvement in performance, the network models used for LDCT reconstruction are becoming increasingly complex and computationally expensive under the mantra of “deeper is better”. However, in clinical settings, lightweight models with a low computational cost and short reconstruction times are more popular. For this reason, this paper proposes a computationally efficient CNN model with a simple structure for sparse-view LDCT reconstruction. Inspired by super-resolution networks for natural images, the proposed model interpolates projection data directly in the sinogram domain with a fully convolutional neural network that consists of only four convolution layers. The proposed model can be used directly for sparse-view CT reconstruction by concatenating the classic filtered back-projection (FBP) module, or it can be incorporated into existing dual-domain reconstruction frameworks as a generic sinogram domain module. The proposed model is validated on both the 2016 NIH-AAPM-Mayo Clinic LDCT Grand Challenge dataset and The Lung Image Database Consortium dataset. It is shown that despite the computational simplicity of the proposed model, its reconstruction performance at lower sparsity levels (1/2 and 1/4 radiation dose) is comparable to that of the sophisticated baseline models and shows some advantages at higher sparsity levels (1/8 and 1/15 radiation dose). Compared to existing sinogram domain baseline models, the proposed model is computationally efficient and easy to train on small training datasets, and is thus well suited for clinical real-time reconstruction tasks.

Segmentation of ground glass pulmonary nodules using full convolution residual network based on atrous spatial pyramid pooling structure and attention mechanism

Accurate segmentation of ground glass nodule (GGN) is important in clinical. But it is a tough work to segment the GGN, as the GGN in the computed tomography images show blur boundary, irregular shape, and uneven intensity. This paper aims to segment GGN by proposing a fully convolutional residual network, i.e., residual network based on atrous spatial pyramid pooling structure and attention mechanism (ResAANet). The network uses atrous spatial pyramid pooling (ASPP) structure to expand the feature map receptive field and extract more sufficient features, and utilizes attention mechanism, residual connection, long skip connection to fully retain sensitive features, which is extracted by the convolutional layer. First, we employ 565 GGN provided by Shanghai Chest Hospital to train and validate ResAANet, so as to obtain a stable model. Then, two groups of data selected from clinical examinations (84 GGN) and lung image database consortium (LIDC) dataset (145 GGN) were employed to validate and evaluate the performance of the proposed method. Finally, we apply the best threshold method to remove false positive regions and obtain optimized results. The average dice similarity coefficient (DSC) of the proposed algorithm on the clinical dataset and LIDC dataset reached 83.46%, 83.26% respectively, the average Jaccard index (IoU) reached 72.39%, 71.56% respectively, and the speed of segmentation reached 0.1 seconds per image. Comparing with other reported methods, our new method could segment GGN accurately, quickly and robustly. It could provide doctors with important information such as nodule size or density, which assist doctors in subsequent diagnosis and treatment.

Triple novelty block detection and classification approach for lung tumor analysis

AbstractRecently the increased utilization of computer‐aided detection is more helpful to assist the radiologist, recognize the minute lung lesion. In this research article, we propose three novel block detection methods for lung lesion segmentation. First, an automatic algorithm for lung lesion detection and segmentation by using histogram‐based affine‐invariant detection (HAID) is proposed. HAID is a novel segmentation technique that applies enhanced maximally stable extremal region algorithm results to segment the lung lesion. The lung lesions are segmented with an accuracy of 91.5% and false positives per scan is 5.52. To reduce the false positives per scan of lung tumor segmentation, a spatial constraint‐based new fuzzy clustering (SCNFC) approach is then proposed. The experimental results proved the efficiency of the SCNFC technique in the successful segmentation of lung tumor tissues with high accuracy and reduced the false positive per scan (95.21% and 3.69 for a database of simulated computed tomography images). Finally, firefly search‐based Macqueen's K‐means clustering algorithm (FSMKC) is proposed. The performance of the FSMKC method is evaluated on series assessments using the Lung Image Database Consortium dataset (1505 images) and it achieved the accuracy of 97.18% and 96.28% of sensitivity with only 2.27 false positives per scan.

Convolutional Neural Network for Lung Cancer

Lung cancer is the deadliest cancer of the recent decade.75% of the cases are diagnosed in latter stage of cancer, thus the survivalist decreases. With invent of AlexNet in the year 2012 which can train millions of images accurately classified, the role of computer diagnosis increased. This represents a holistic view in reviewing the papers on Lung image database consortium dataset with use of CNN in variant ways to increase sensitivity and accuracy. Small, unvalidated and superficial methods obstruct the usage of CNN.

ResNet based Lung Nodules Detection from Computed Tomography Images

Lung cancer have become one of the major threat to human kind over few years. The survival rate of the patient depends mainly on the stage of cancer when it was detected with early stage detection increases survival rate significantly. Many computer aided detection systems were proposed to assist radiologist in detecting lung nodules efficiently. After the success of deep learning neural network in object classification problem, researchers started adopting it for different tasks in medical image processing and hence in lung nodule detection systems. Hence, a lung nodule detection method using ResNet in CT images is proposed. The proposed method consists of two stages, the pre-processing stage and nodule detection stage. The proposed technique uses morphological operations for segmentation of lungs and convolutional neural network for detection of lung nodules. This method is developed with an aim to provide second opinion to radiologists and reduce their workload. LIDC (Lung Image Database Consortium) dataset which contains 1010 CT patients images of chest regions are taken for experimentation. The model was able to achieve top-5 accuracy of 95.24% on test dataset.

The effects of physics-based data augmentation on the generalizability of deep neural networks: Demonstration on nodule false-positive reduction.

An important challenge for deep learning models is generalizing to new datasets that may be acquired with acquisition protocols different from the training set. It is not always feasible to expand training data to the range encountered in clinical practice. We introduce a new technique, physics-based data augmentation (PBDA), that can emulate new computed tomography (CT) data acquisition protocols. We demonstrate two forms of PBDA, emulating increases in slice thickness and reductions of dose, on the specific problem of false-positive reduction in the automatic detection of lung nodules. We worked with CT images from the lung image database consortium (LIDC) collection. We employed a hybrid ensemble convolutional neural network (CNN), which consists of multiple CNN modules (VGG, DenseNet, ResNet), for a classification task of determining whether an image patch was a suspicious nodule or a false positive. To emulate a reduction in tube current, we injected noise by simulating forward projection, noise addition, and backprojection corresponding to 1.5mAs (a "chest x-ray" dose). To simulate thick slice CT scans from thin slice CT scans, we grouped and averaged spatially contiguous CT within thin slice data. The neural network was trained with 10% of the LIDC dataset that was selected to have either the highest tube current or the thinnest slices. The network was tested on the remaining data. We compared PBDA to a baseline with standard geometric augmentations (such as shifts and rotations) and Gaussian noise addition. PBDA improved the performance of the networks when generalizing to the test dataset in a limited number of cases. We found that the best performance was obtained by applying augmentation at very low doses (1.5mAs), about an order of magnitude less than most screening protocols. In the baseline augmentation, a comparable level of Gaussian noise was injected. For dose reduction PBDA, the average sensitivity of 0.931 for the hybrid ensemble network was not statistically different from the average sensitivity of 0.935 without PBDA. Similarly for slice thickness PBDA, the average sensitivity of 0.900 when augmenting with doubled simulated slice thicknesses was not statistically different from the average sensitivity of 0.895 without PBDA. While there were cases detailed in this paper in which we observed improvements, the overall picture was one that suggests PBDA may not be an effective data enrichment tool. PBDA is a newly proposed strategy for mitigating the performance loss of neural networks related to the variation of acquisition protocol between the training dataset and the data that is encountered in deployment or testing. We found that PBDA does not provide robust improvements with the four neural networks (three modules and the ensemble) tested and for the specific task of false-positive reduction in nodule detection.

Artificial neural network based classification of lung nodules in CT images using intensity, shape and texture features

The cancer of lung has been one of the major threats to human life for decades in developed and developing countries. The Computer Aided Detection CAD could be a powerful tool for initial lung nodule detection and preventing the deaths caused by the lung tumor. In this paper, an advanced technique for lung-nodule detection by using a hybrid feature set and artificial neural network is proposed. Initially, the lung volume is segmented from the input Computed Tomography image using optimal thresholding which is followed by image enhancement using with multi scale dot augmentation filtering. Next, lung nodule candidates have been detected from enhanced image and certain features are extracted. The set feature consists of the texture features, shape 2D and 3D and intensity. Finally, lung nodule’s classification is attained using two-layer feed forward neural network. The Lung Image Database Consortium dataset has been used to evaluate the novel system which achieved a sensitivity of 95.5% with only 5.72 FP per scan.

Multi-scale pulmonary nodule classification with deep feature fusion via residual network

The early stage detection of benign and malignant pulmonary nodules plays an important role in clinical diagnosis. The malignancy risk assessment is usually used to guide the doctor in identifying the cancer stage and making follow-up prognosis plan. However, due to the variance of nodules on size, shape, and location, it has been a big challenge to classify the nodules in computer aided diagnosis system. In this paper, we design a novel model based on convolution neural network to achieve automatic pulmonary nodule malignancy classification. By using our model, the multi-scale features are extracted through the multi-convolution process, and the structure of residual blocks allows the network to capture more high-level and semantic information. Moreover, a strategy is proposed to fuse the features from the last avg-pooling layer and the ones from the last residual block to further enhance the performance of our model. Experimental results on the public Lung Image Database Consortium dataset demonstrate that our model can achieve a lung nodule classification accuracy of $$87.5\%$$ which outperforms state-of-the-art methods.

Lung nodule malignancy classification using only radiologist-quantified image features as inputs to statistical learning algorithms: probing the Lung Image Database Consortium dataset with two statistical learning methods.

In the assessment of nodules in CT scans of the lungs, a number of image-derived features are diagnostically relevant. Currently, many of these features are defined only qualitatively, so they are difficult to quantify from first principles. Nevertheless, these features (through their qualitative definitions and interpretations thereof) are often quantified via a variety of mathematical methods for the purpose of computer-aided diagnosis (CAD). To determine the potential usefulness of quantified diagnostic image features as inputs to a CAD system, we investigate the predictive capability of statistical learning methods for classifying nodule malignancy. We utilize the Lung Image Database Consortium dataset and only employ the radiologist-assigned diagnostic feature values for the lung nodules therein, as well as our derived estimates of the diameter and volume of the nodules from the radiologists' annotations. We calculate theoretical upper bounds on the classification accuracy that are achievable by an ideal classifier that only uses the radiologist-assigned feature values, and we obtain an accuracy of 85.74 [Formula: see text], which is, on average, 4.43% below the theoretical maximum of 90.17%. The corresponding area-under-the-curve (AUC) score is 0.932 ([Formula: see text]), which increases to 0.949 ([Formula: see text]) when diameter and volume features are included and has an accuracy of 88.08 [Formula: see text]. Our results are comparable to those in the literature that use algorithmically derived image-based features, which supports our hypothesis that lung nodules can be classified as malignant or benign using only quantified, diagnostic image features, and indicates the competitiveness of this approach. We also analyze how the classification accuracy depends on specific features and feature subsets, and we rank the features according to their predictive power, statistically demonstrating the top four to be spiculation, lobulation, subtlety, and calcification.

Automatic Scoring of Multiple Semantic Attributes With Multi-Task Feature Leverage: A Study on Pulmonary Nodules in CT Images

The gap between the computational and semantic features is the one of major factors that bottlenecks the computer-aided diagnosis (CAD) performance from clinical usage. To bridge this gap, we exploit three multi-task learning (MTL) schemes to leverage heterogeneous computational features derived from deep learning models of stacked denoising autoencoder (SDAE) and convolutional neural network (CNN), as well as hand-crafted Haar-like and HoG features, for the description of 9 semantic features for lung nodules in CT images. We regard that there may exist relations among the semantic features of "spiculation", "texture", "margin", etc., that can be explored with the MTL. The Lung Image Database Consortium (LIDC) data is adopted in this study for the rich annotation resources. The LIDC nodules were quantitatively scored w.r.t. 9 semantic features from 12 radiologists of several institutes in U.S.A. By treating each semantic feature as an individual task, the MTL schemes select and map the heterogeneous computational features toward the radiologists' ratings with cross validation evaluation schemes on the randomly selected 2400 nodules from the LIDC dataset. The experimental results suggest that the predicted semantic scores from the three MTL schemes are closer to the radiologists' ratings than the scores from single-task LASSO and elastic net regression methods. The proposed semantic attribute scoring scheme may provide richer quantitative assessments of nodules for better support of diagnostic decision and management. Meanwhile, the capability of the automatic association of medical image contents with the clinical semantic terms by our method may also assist the development of medical search engine.

Segmentation of lung lesions on CT scans using watershed, active contours, and Markov random field

Lung lesions vary considerably in size, density, and shape, and can attach to surrounding anatomic structures such as chest wall or mediastinum. Automatic segmentation of the lesions poses a challenge. This work communicates a new three-dimensional algorithm for the segmentation of a wide variety of lesions, ranging from tumors found in patients with advanced lung cancer to small nodules detected in lung cancer screening programs. The authors' algorithm uniquely combines the image processing techniques of marker-controlled watershed, geometric active contours as well as Markov random field (MRF). The user of the algorithm manually selects a region of interest encompassing the lesion on a single slice and then the watershed method generates an initial surface of the lesion in three dimensions, which is refined by the active geometric contours. MRF improves the segmentation of ground glass opacity portions of part-solid lesions. The algorithm was tested on an anthropomorphic thorax phantom dataset and two publicly accessible clinical lung datasets. These clinical studies included a same-day repeat CT (prewalk and postwalk scans were performed within 15 min) dataset containing 32 lung lesions with one radiologist's delineated contours, and the first release of the Lung Image Database Consortium (LIDC) dataset containing 23 lung nodules with 6 radiologists' delineated contours. The phantom dataset contained 22 phantom nodules of known volumes that were inserted in a phantom thorax. For the prewalk scans of the same-day repeat CT dataset and the LIDC dataset, the mean overlap ratios of lesion volumes generated by the computer algorithm and the radiologist(s) were 69% and 65%, respectively. For the two repeat CT scans, the intra-class correlation coefficient (ICC) was 0.998, indicating high reliability of the algorithm. The mean relative difference was -3% for the phantom dataset. The performance of this new segmentation algorithm in delineating tumor contour and measuring tumor size illustrates its potential clinical value for assisting in noninvasive diagnosis of pulmonary nodules, therapy response assessment, and radiation treatment planning.

A novel multithreshold method for nodule detection in lung CT

Multislice computed tomography (MSCT) is a valuable tool for lung cancer detection, thanks to its ability to identify noncalcified nodules of small size (from about 3 mm). Due to the large number of images generated by MSCT, there is much interest in developing computer-aided detection (CAD) systems that could assist radiologists in the lung nodule detection task. A complete multistage CAD system, including lung boundary segmentation, regions of interest (ROIs) selection, feature extraction, and false positive reduction is presented. The selection of ROIs is based on a multithreshold surface-triangulation approach. Surface triangulation is performed at different threshold values, varying from a minimum to a maximum value in a wide range. At a given threshold value, a ROI is defined as the volume inside a connected component of the triangulated isosurface. The evolution of a ROI as a function of the threshold can be represented by a treelike structure. A multithreshold ROI is defined as a path on this tree, which starts from a terminal ROI and ends on the root ROI. For each ROI, the volume, surface area, roundness, density, and moments of inertia are computed as functions of the threshold and used as input to a classification system based on artificial neural networks. The method is suitable to detect different types of nodules, including juxta-pleural nodules and nodules connected to blood vessels. A training set of 109 low-dose MSCT scans made available by the Pisa center of the Italung-CT trial and annotated by expert radiologists was used for the algorithm design and optimization. The system performance was tested on an independent set of 23 low-dose MSCT scans coming from the Pisa Italung-CT center and on 83 scans made available by the Lung Image Database Consortium (LIDC) annotated by four expert radiologists. On the Italung-CT test set, for nodules having a diameter greater than or equal to 3 mm, the system achieved 84% and 71% sensitivity at false positive/scan rates of 10 and 4, respectively. For nodules having a diameter greater than or equal to 4 mm, the sensitivities were 97% and 80% at false positive/scan rates of 10 and 4, respectively. On the LIDC data set, the system achieved a 79% sensitivity at a false positive/scan rate of 4 in the detection of nodules with a diameter greater than or equal to 3 mm that have been annotated by all four radiologists.