High performance lung nodule detection schemes in CT using local and global information

Towards Automation in Radiotherapy Planning: A Deep Learning Approach for the Delineation of Parotid Glands in Head and Neck Cancer

The delineation of parotid glands in head and neck (HN) carcinoma is critical to assess radiotherapy (RT) planning. Segmentation processes ensure precise target position and treatment precision, facilitate monitoring of anatomical changes, enable plan adaptation, and enhance overall patient safety. In this context, artificial intelligence (AI) and deep learning (DL) have proven exceedingly effective in precisely outlining tumor tissues and, by extension, the organs at risk. This paper introduces a DL framework using the AttentionUNet neural network for automatic parotid gland segmentation in HN cancer. Extensive evaluation of the model is performed in two public and one private dataset, while segmentation accuracy is compared with other state-of-the-art DL segmentation schemas. To assess replanning necessity during treatment, an additional registration method is implemented on the segmentation output, aligning images of different modalities (Computed Tomography (CT) and Cone Beam CT (CBCT)). AttentionUNet outperforms similar DL methods (Dice Similarity Coefficient: 82.65% ± 1.03, Hausdorff Distance: 6.24 mm ± 2.47), confirming its effectiveness. Moreover, the subsequent registration procedure displays increased similarity, providing insights into the effects of RT procedures for treatment planning adaptations. The implementation of the proposed methods indicates the effectiveness of DL not only for automatic delineation of the anatomical structures, but also for the provision of information for adaptive RT support.

Semi-supervised training using cooperative labeling of weakly annotated data for nodule detection in chest CT

PURPOSE

Machine learning algorithms are best trained with large quantities of accurately annotated samples. While natural scene images can often be labeled relatively cheaply and at large scale, obtaining accurate annotations for medical images is both time consuming and expensive. In this study, we propose a cooperative labeling method that allows us to make use of weakly annotated medical imaging data for the training of a machine learning algorithm. As most clinically produced data are weakly-annotated - produced for use by humans rather than machines and lacking information machine learning depends upon - this approach allows us to incorporate a wider range of clinical data and thereby increase the training set size.

METHODS

Our pseudo-labeling method consists of multiple stages. In the first stage, a previously established network is trained using a limited number of samples with high-quality expert-produced annotations. This network is used to generate annotations for a separate larger dataset that contains only weakly annotated scans. In the second stage, by cross-checking the two types of annotations against each other, we obtain higher-fidelity annotations. In the third stage, we extract training data from the weakly annotated scans, and combine it with the fully annotated data, producing a larger training dataset. We use this larger dataset to develop a computer-aided detection (CADe) system for nodule detection in chest CT.

RESULTS

We evaluated the proposed approach by presenting the network with different numbers of expert-annotated scans in training and then testing the CADe using an independent expert-annotated dataset. We demonstrate that when availability of expert annotations is severely limited, the inclusion of weakly-labeled data leads to a 5% improvement in the competitive performance metric (CPM), defined as the average of sensitivities at different false-positive rates.

CONCLUSIONS

Our proposed approach can effectively merge a weakly-annotated dataset with a small, well-annotated dataset for algorithm training. This approach can help enlarge limited training data by leveraging the large amount of weakly labeled data typically generated in clinical image interpretation.

Building and evaluating an artificial intelligence algorithm: A practical guide for practicing oncologists

The use of machine learning and deep learning has enabled many applications, previously thought of as being impossible. Among all medical fields, cancer care is arguably the most significantly impacted, with precision medicine now truly being a possibility. The effect of these technologies, loosely known as artificial intelligence, is particularly striking in fields involving images (such as radiology and pathology) and fields involving large amounts of data (such as genomics). Practicing oncologists are often confronted with new technologies claiming to predict response to therapy or predict the genomic make-up of patients. Underst-anding these new claims and technologies requires a deep understanding of the field. In this review, we provide an overview of the basis of deep learning. We describe various common tasks and their data requirements so that oncologists could be equipped to start such projects, as well as evaluate algorithms presented to them.

A Computer-Aided Detection System for the Detection of Lung Nodules Based on 3D-ResNet

In recent years, the research into automatic aided detection systems for pulmonary nodules has been extremely active. Most of the existing studies are based on 2D convolution neural networks, which cannot make full use of computed tomography’s (CT) 3D spatial information. To address this problem, a computer-aided detection (CAD) system for lung nodules based on a 3D residual network (3D-ResNet) inspired by cognitive science is proposed in this paper. In this system, we feed the slice information extracted from three different axis planes into the U-NET network set, and make the joint decision to generate a candidate nodule set, which is the input of the proposed 3D residual network after extraction. We extracted 3D samples with 40, 44, 48, 52, and 56 mm sides from each candidate nodule in the candidate set and feed them into the trained residual network to get the probability of positive nodule after re-sampling the 3D sample to 48 × 48 × 48 mm 3 . Finally, a joint judgment is made based on the probabilities of five 3D samples of different sizes to obtain the final result. Random rotation and translation and data amplification technology are used to prevent overfitting during network training. The detection intensity on the largest public data set (i.e., the Lung Image Database Consortium and Image Database Resource Initiative—LIDC-IDRI) reached 86.5% and 92.3% at 1 frame per second (FPs) and 4 FPs respectively using our algorithm, which is better than most CAD systems using 2D convolutional neural networks. In addition, a 3D residual network and a multi-section 2D convolution neural network were tested on the unrelated Tianchi dataset. The results indicate that 3D-ResNet has better feature extraction ability than multi-section 2D-ConvNet and is more suitable for reduction of false positive nodules.

Computerized detection of lung nodules through radiomics

PURPOSE

Lung cancer is a major cause of cancer deaths, and the 5-year survival rate of stage IV lung cancer patients is only 2%. However, the 5-year survival rate of stage I lung cancer patients significantly increases to 50%. As such, spiral computed tomography (CT) scans are necessary to diagnose high-risk lung cancer patients in early stages. In this study, a computer-aided detection (CAD) system with radiomics was proposed. This system could automatically detect pulmonary nodules and reduce radiologists' workloads and human errors.

METHODS

In the proposed scheme, a nodular enhancement filter was used to segment nodule candidates and extract radiomic features. A synthetic minority over-sampling technique was also applied to balance the samples, and a random forest method was utilized to distinguish between real nodules and false positive detections. The radiomics approach quantified intratumor heterogeneity and multifrequency information, which are highly correlated with lung nodules.

RESULTS

The proposed method was used to evaluate 1004 CT cases from the well-known Lung Image Database Consortium, and 88.9% sensitivity with four false positive detections per CT scan was obtained by randomly selecting 502 cases for training and 502 other cases for testing.

CONCLUSIONS

The proposed scheme yielded a high performance on the LIDC database. Therefore, the proposed scheme is possibly effective for various CT configurations used in routine diagnosis and lung cancer screening.

3D Convolutional Neural Network for Automatic Detection of Lung Nodules in Chest CT

Deep convolutional neural networks (CNNs) form the backbone of many state-of-the-art computer vision systems for classification and segmentation of 2D images. The same principles and architectures can be extended to three dimensions to obtain 3D CNNs that are suitable for volumetric data such as CT scans. In this work, we train a 3D CNN for automatic detection of pulmonary nodules in chest CT images using volumes of interest extracted from the LIDC dataset. We then convert the 3D CNN which has a fixed field of view to a 3D fully convolutional network (FCN) which can generate the score map for the entire volume efficiently in a single pass. Compared to the sliding window approach for applying a CNN across the entire input volume, the FCN leads to a nearly 800-fold speed-up, and thereby fast generation of output scores for a single case. This screening FCN is used to generate difficult negative examples that are used to train a new discriminant CNN. The overall system consists of the screening FCN for fast generation of candidate regions of interest, followed by the discrimination CNN.

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

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.

Automatic detection of large pulmonary solid nodules in thoracic CT images

PURPOSE

Current computer-aided detection (CAD) systems for pulmonary nodules in computed tomography (CT) scans have a good performance for relatively small nodules, but often fail to detect the much rarer larger nodules, which are more likely to be cancerous. We present a novel CAD system specifically designed to detect solid nodules larger than 10 mm.

METHODS

The proposed detection pipeline is initiated by a three-dimensional lung segmentation algorithm optimized to include large nodules attached to the pleural wall via morphological processing. An additional preprocessing is used to mask out structures outside the pleural space to ensure that pleural and parenchymal nodules have a similar appearance. Next, nodule candidates are obtained via a multistage process of thresholding and morphological operations, to detect both larger and smaller candidates. After segmenting each candidate, a set of 24 features based on intensity, shape, blobness, and spatial context are computed. A radial basis support vector machine (SVM) classifier was used to classify nodule candidates, and performance was evaluated using ten-fold cross-validation on the full publicly available lung image database consortium database.

RESULTS

The proposed CAD system reaches a sensitivity of 98.3% (234/238) and 94.1% (224/238) large nodules at an average of 4.0 and 1.0 false positives/scan, respectively.

CONCLUSIONS

The authors conclude that the proposed dedicated CAD system for large pulmonary nodules can identify the vast majority of highly suspicious lesions in thoracic CT scans with a small number of false positives.

Hybrid detection of lung nodules on CT scan images

PURPOSE

The diversity of lung nodules poses difficulty for the current computer-aided diagnostic (CAD) schemes for lung nodule detection on computed tomography (CT) scan images, especially in large-scale CT screening studies. We proposed a novel CAD scheme based on a hybrid method to address the challenges of detection in diverse lung nodules.

METHODS

The hybrid method proposed in this paper integrates several existing and widely used algorithms in the field of nodule detection, including morphological operation, dot-enhancement based on Hessian matrix, fuzzy connectedness segmentation, local density maximum algorithm, geodesic distance map, and regression tree classification. All of the adopted algorithms were organized into tree structures with multi-nodes. Each node in the tree structure aimed to deal with one type of lung nodule.

RESULTS

The method has been evaluated on 294 CT scans from the Lung Image Database Consortium (LIDC) dataset. The CT scans were randomly divided into two independent subsets: a training set (196 scans) and a test set (98 scans). In total, the 294 CT scans contained 631 lung nodules, which were annotated by at least two radiologists participating in the LIDC project. The sensitivity and false positive per scan for the training set were 87% and 2.61%. The sensitivity and false positive per scan for the testing set were 85.2% and 3.13%.

CONCLUSIONS

The proposed hybrid method yielded high performance on the evaluation dataset and exhibits advantages over existing CAD schemes. We believe that the present method would be useful for a wide variety of CT imaging protocols used in both routine diagnosis and screening studies.

Pulmonary Nodule Detection in CT Images: False Positive Reduction Using Multi-View Convolutional Networks

We propose a novel Computer-Aided Detection (CAD) system for pulmonary nodules using multi-view convolutional networks (ConvNets), for which discriminative features are automatically learnt from the training data. The network is fed with nodule candidates obtained by combining three candidate detectors specifically designed for solid, subsolid, and large nodules. For each candidate, a set of 2-D patches from differently oriented planes is extracted. The proposed architecture comprises multiple streams of 2-D ConvNets, for which the outputs are combined using a dedicated fusion method to get the final classification. Data augmentation and dropout are applied to avoid overfitting. On 888 scans of the publicly available LIDC-IDRI dataset, our method reaches high detection sensitivities of 85.4% and 90.1% at 1 and 4 false positives per scan, respectively. An additional evaluation on independent datasets from the ANODE09 challenge and DLCST is performed. We showed that the proposed multi-view ConvNets is highly suited to be used for false positive reduction of a CAD system.

Advanced imaging tools in pulmonary nodule detection and surveillance

Lung cancer is a leading cause of death worldwide. The National Lung Screening Trial has demonstrated that lung cancer screening can reduce lung cancer specific and all cause mortality. With approval of national coverage for lung cancer screening, it is expected that an increase in exams related to pulmonary nodule detection and surveillance will ensue. Advanced imaging technologies for nodule detection and surveillance will be more important than ever. While computed tomography (CT) remains the modality of choice, other emerging modalities such as magnetic resonance imaging provides viable alternatives to CT.

Large scale validation of the M5L lung CAD on heterogeneous CT datasets

PURPOSE

M5L, a fully automated computer-aided detection (CAD) system for the detection and segmentation of lung nodules in thoracic computed tomography (CT), is presented and validated on several image datasets.

METHODS

M5L is the combination of two independent subsystems, based on the Channeler Ant Model as a segmentation tool [lung channeler ant model (lungCAM)] and on the voxel-based neural approach. The lungCAM was upgraded with a scan equalization module and a new procedure to recover the nodules connected to other lung structures; its classification module, which makes use of a feed-forward neural network, is based of a small number of features (13), so as to minimize the risk of lacking generalization, which could be possible given the large difference between the size of the training and testing datasets, which contain 94 and 1019 CTs, respectively. The lungCAM (standalone) and M5L (combined) performance was extensively tested on 1043 CT scans from three independent datasets, including a detailed analysis of the full Lung Image Database Consortium/Image Database Resource Initiative database, which is not yet found in literature.

RESULTS

The lungCAM and M5L performance is consistent across the databases, with a sensitivity of about 70% and 80%, respectively, at eight false positive findings per scan, despite the variable annotation criteria and acquisition and reconstruction conditions. A reduced sensitivity is found for subtle nodules and ground glass opacities (GGO) structures. A comparison with other CAD systems is also presented.

CONCLUSIONS

The M5L performance on a large and heterogeneous dataset is stable and satisfactory, although the development of a dedicated module for GGOs detection could further improve it, as well as an iterative optimization of the training procedure. The main aim of the present study was accomplished: M5L results do not deteriorate when increasing the dataset size, making it a candidate for supporting radiologists on large scale screenings and clinical programs.

Effect of segmentation algorithms on the performance of computerized detection of lung nodules in CT

PURPOSE

The purpose of this study is to reveal how the performance of lung nodule segmentation algorithm impacts the performance of lung nodule detection, and to provide guidelines for choosing an appropriate segmentation algorithm with appropriate parameters in a computer-aided detection (CAD) scheme.

METHODS

The database consisted of 85 CT scans with 111 nodules of 3 mm or larger in diameter from the standard CT lung nodule database created by the Lung Image Database Consortium. The initial nodule candidates were identified as those with strong response to a selective nodule enhancement filter. A uniform viewpoint reformation technique was applied to a three-dimensional nodule candidate to generate 24 two-dimensional (2D) reformatted images, which would be used to effectively distinguish between true nodules and false positives. Six different algorithms were employed to segment the initial nodule candidates in the 2D reformatted images. Finally, 2D features from the segmented areas in the 24 reformatted images were determined, selected, and classified for removal of false positives. Therefore, there were six similar CAD schemes, in which only the segmentation algorithms were different. The six segmentation algorithms included the fixed thresholding (FT), Otsu thresholding (OTSU), fuzzy C-means (FCM), Gaussian mixture model (GMM), Chan and Vese model (CV), and local binary fitting (LBF). The mean Jaccard index and the mean absolute distance (Dmean) were employed to evaluate the performance of segmentation algorithms, and the number of false positives at a fixed sensitivity was employed to evaluate the performance of the CAD schemes.

RESULTS

For the segmentation algorithms of FT, OTSU, FCM, GMM, CV, and LBF, the highest mean Jaccard index between the segmented nodule and the ground truth were 0.601, 0.586, 0.588, 0.563, 0.543, and 0.553, respectively, and the corresponding Dmean were 1.74, 1.80, 2.32, 2.80, 3.48, and 3.18 pixels, respectively. With these segmentation results of the six segmentation algorithms, the six CAD schemes reported 4.4, 8.8, 3.4, 9.2, 13.6, and 10.4 false positives per CT scan at a sensitivity of 80%.

CONCLUSIONS

When multiple algorithms are available for segmenting nodule candidates in a CAD scheme, the "optimal" segmentation algorithm did not necessarily lead to the "optimal" CAD detection performance.