Computer-aided Detection Of Lung Nodules Research Articles

Editorial Comment: Computer-Aided Detection of Lung Nodules on Low-Dose Pediatric Chest CT-A Cautionary Tale.

Editorial Comment: Computer-Aided Detection of Lung Nodules on Low-Dose Pediatric Chest CT-A Cautionary Tale.

Performance of Lung-Nodule Computer-Aided Detection Systems on Standard-Dose and Low-Dose Pediatric CT Scans: An Intraindividual Comparison.

Background: When applying lung-nodule computer-aided detection (CAD) systems for pediatric CT, performance may be degraded on low-dose scans due to increased image noise. Objective: To conduct an intraindividual comparison of the performance for lung nodule detection of two CAD systems trained using adult data between low-dose and standard-dose pediatric chest CT scans. Methods: This retrospective study included 73 patients (32 female, 41 male; mean age, 14.7 years; age range, 4-20 years) who underwent both clinical standard-dose and investigational low-dose chest CT examinations within the same encounter from November 30, 2018 to August 31, 2020 as part of an earlier prospective study. Fellowship-trained pediatric radiologists annotated lung nodules to serve as the reference standard. Both CT scans were processed using two publicly available lung-nodule CAD systems previously trained using adult data: FlyerScan and Medical Open Network for Artificial Intelligence (MONAI). The systems' sensitivities for nodules measuring 3-30 mm (n=247) were calculated when operating at a fixed frequency of two false-positives per scan. Results: FlyerScan exhibited detection sensitivities of 76.9% (190/247; 95% CI: 73.3-80.8%) on standard-dose scans and 66.8% (165/247; 95% CI: 62.6-71.5) on low-dose scans. MONAI exhibited detection sensitivities of 67.6% (167/247, 95% CI: 61.5-72.1) on standard-dose scans and 62.3% (154/247, 95% CI: 56.1-66.5%) on low-dose scans. The number of detected nodules for standard-dose versus low-dose scans for 3-mm nodules was 33 versus 24 (FlyerScan) and 16 versus 13 (MONAI), 4-mm nodules was 46 versus 42 (FlyerScan) and 39 versus 30 (MONAI), 5-mm nodules was 38 versus 33 (FlyerScan) and 32 versus 31 (MONAI), and 6-mm nodules was 27 versus 20 (FlyerScan) and 24 versus 24 (MONAI). For nodules measuring ≥7 mm, detection did not show a consistent pattern between standard-dose and low-dose scans for either system. Conclusions: Two lung-nodule CAD systems demonstrated decreased sensitivity on low-dose versus standard-dose pediatric CT scans performed in the same patients. The reduced detection at low dose was overall more pronounced for nodules measuring less than 5 mm. Clinical Impact: Caution is needed when using low-dose CT protocols in combination with CAD systems to help detect small lung nodules in pediatric patients.

Performance Analysis in Children of Traditional and Deep Learning CT Lung Nodule Computer-Aided Detection Systems Trained on Adults.

BACKGROUND. Although primary lung cancer is rare in children, chest CT is commonly performed to assess for lung metastases in children with cancer. Lung nodule computer-aided detection (CAD) systems have been designed and studied primarily using adult training data, and the efficacy of such systems when applied to pediatric patients is poorly understood. OBJECTIVE. The purpose of this study was to evaluate in children the diagnostic performance of traditional and deep learning CAD systems trained with adult data for the detection of lung nodules on chest CT scans and to compare the ability of such systems to generalize to children versus to other adults. METHODS. This retrospective study included pediatric and adult chest CT test sets. The pediatric test set comprised 59 CT scans in 59 patients (30 boys, 29 girls; mean age, 13.1 years; age range, 4-17 years), which were obtained from November 30, 2018, to August 31, 2020; lung nodules were annotated by fellowship-trained pediatric radiologists as the reference standard. The adult test set was the publicly available adult Lung Nodule Analysis (LUNA) 2016 subset 0, which contained 89 deidentified scans with previously annotated nodules. The test sets were processed through the traditional FlyerScan (github.com/rhardie1/FlyerScanCT) and deep learning Medical Open Network for Artificial Intelligence (MONAI; github.com/Project-MONAI/model-zoo/releases) lung nodule CAD systems, which had been trained on separate sets of CT scans in adults. Sensitivity and false-positive (FP) frequency were calculated for nodules measuring 3-30 mm; nonoverlapping 95% CIs indicated significant differences. RESULTS. Operating at two FPs per scan, on pediatric testing data FlyerScan and MONAI showed significantly lower detection sensitivities of 68.4% (197/288; 95% CI, 65.1-73.0%) and 53.1% (153/288; 95% CI, 46.7-58.4%), respectively, than on adult LUNA 2016 subset 0 testing data (83.9% [94/112; 95% CI, 79.1-88.0%] and 95.5% [107/112; 95% CI, 90.0-98.4%], respectively). Mean nodule size was smaller (p < .001) in the pediatric testing data (5.4 ± 3.1 [SD] mm) than in the adult LUNA 2016 subset 0 testing data (11.0 ± 6.2 mm). CONCLUSION. Adult-trained traditional and deep learning-based lung nodule CAD systems had significantly lower sensitivity for detection on pediatric data than on adult data at a matching FP frequency. The performance difference may relate to the smaller size of pediatric lung nodules. CLINICAL IMPACT. The results indicate a need for pediatric-specific lung nodule CAD systems trained on data specific to pediatric patients.

Pricing and cost-saving potential for deep-learning computer-aided lung nodule detection software in CT lung cancer screening

ObjectiveAn increasing number of commercial deep learning computer-aided detection (DL-CAD) systems are available but their cost-saving potential is largely unknown. This study aimed to gain insight into appropriate pricing for DL-CAD in different reading modes to be cost-saving and to determine the potentially most cost-effective reading mode for lung cancer screening.MethodsIn three representative settings, DL-CAD was evaluated as a concurrent, pre-screening, and second reader. Scoping review was performed to estimate radiologist reading time with and without DL-CAD. Hourly cost of radiologist time was collected for the USA (€196), UK (€127), and Poland (€45), and monetary equivalence of saved time was calculated. The minimum number of screening CTs to reach break-even was calculated for one-time investment of €51,616 for DL-CAD.ResultsMean reading time was 162 (95% CI: 111–212) seconds per case without DL-CAD, which decreased by 77 (95% CI: 47–107) and 104 (95% CI: 71–136) seconds for DL-CAD as concurrent and pre-screening reader, respectively, and increased by 33–41 s for DL-CAD as second reader. This translates into €1.0–4.3 per-case cost for concurrent reading and €0.8–5.7 for pre-screening reading in the USA, UK, and Poland. To achieve break-even with a one-time investment, the minimum number of CT scans was 12,300–53,600 for concurrent reader, and 9400–65,000 for pre-screening reader in the three countries.ConclusionsGiven current pricing, DL-CAD must be priced substantially below €6 in a pay-per-case setting or used in a high-workload environment to reach break-even in lung cancer screening. DL-CAD as pre-screening reader shows the largest potential to be cost-saving.Critical relevance statementDeep-learning computer-aided lung nodule detection (DL-CAD) software must be priced substantially below 6 euro in a pay-per-case setting or must be used in high-workload environments with one-time investment in order to achieve break-even. DL-CAD as a pre-screening reader has the greatest cost savings potential.Key points• DL-CAD must be substantially below €6 in a pay-per-case setting to reach break-even.• DL-CAD must be used in a high-workload screening environment to achieve break-even.• DL-CAD as a pre-screening reader shows the largest potential to be cost-saving.Graphical

A review of convolutional neural network-based computer-aided lung nodule detection system

Worldwide, lung cancer is the leading cause of mortality and rapidly spreads. Lung tissue that is benign does not grow significantly, but lung tissue that is malignant grows rapidly and attacks the body, posing a grave threat to one's health. This paper provides a literature review of computer-aided detection (CAD) systems for lung cancer diagnosis. Preprocessing, segmentation, detection, and classification are the stages of the CAD system. This review divides the preprocessing into three stages: image smoothing, edge sharpening, and noise removal. Additionally, lung segmentation is divided into three stages: histogram-based thresholding, linked component analysis, and lung extraction. The detecting phase aids in decreasing the workload. Several techniques are briefly described, including random forest, support vector machine (SVM), naive bayes, K-nearest neighbor (KNN), and convolutional neural network (CNN). Classification is the final stage; the image is then identified as containing or not possessing nodules. The prospect of incorporating CNN-based deep learning techniques into the CAD system is discussed. This paper is superior to other review studies on this topic due to its comprehensive examination of pertinent literature and structured presentation. We anticipate that our study may aid professional researchers and radiologists in developing more effective CAD systems for detecting lung cancer.

Artificial Intelligence in Lung Cancer Imaging: Unfolding the Future.

Lung cancer is one of the malignancies with higher morbidity and mortality. Imaging plays an essential role in each phase of lung cancer management, from detection to assessment of response to treatment. The development of imaging-based artificial intelligence (AI) models has the potential to play a key role in early detection and customized treatment planning. Computer-aided detection of lung nodules in screening programs has revolutionized the early detection of the disease. Moreover, the possibility to use AI approaches to identify patients at risk of developing lung cancer during their life can help a more targeted screening program. The combination of imaging features and clinical and laboratory data through AI models is giving promising results in the prediction of patients' outcomes, response to specific therapies, and risk for toxic reaction development. In this review, we provide an overview of the main imaging AI-based tools in lung cancer imaging, including automated lesion detection, characterization, segmentation, prediction of outcome, and treatment response to provide radiologists and clinicians with the foundation for these applications in a clinical scenario.

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

This study aimed to explore the possibility and clinical utility of existing artificial intelligence (AI)-based computer-aided detection (CAD) of lung nodules to identify pulmonary oligometastases. The chest computed tomography (CT) scans of patients with lung metastasis from colorectal cancer between March 2006 and November 2018 were analyzed. The patients were selected from a database of 1395 patients and studied in 2 cohorts. The first cohort included 50 patients, and the CT scans of these patients were independently evaluated for lung-nodule (≥3 mm) detection by a CAD-assisted radiation oncologist (CAD-RO) as well as by an expert radiologist. Interobserver variability by 2 additional radiation oncologists and 2 thoracic surgeons were also measured. In the second cohort of 305 patients, survival outcomes were evaluated based on the number of CAD-RO-detected nodules. In the first cohort, the sensitivity and specificity of the CAD-RO for identifying oligometastatic disease (OMD) from varying criteria by ≤2 nodules, ≤3 nodules, ≤4 nodules, and ≤5 nodules were 71.9% and 88.9%, 82.9% and 93.3%, 97.1% and 73.3%, and 97.5% and 90.0%, respectively. The sensitivity of the CAD-RO in the nodule detection compared with the radiologist was 81.6%. The average (standard deviation) sensitivity in interobserver variability analysis was 80.0% (3.7%). In the second cohort, the 5-year survival rates of patients with 1, 2, 3, 4, or ≥5 metastatic nodules were 75.2%, 52.9%, 45.7%, 29.1%, and 22.7%, respectively. Proper identification of the pulmonary OMD and the correlation between the number of CAD-RO-detected nodules and survival suggest the potential practicality of AI in OMD recognition. Developing a deep learning-based model specific to the metastatic setting, which enables a quick estimation of disease burden and identification of OMD, is underway.

An improved capuchin search algorithm optimized hybrid CNN-LSTM architecture for malignant lung nodule detection

For the early diagnosis of lung cancer, radiologists assisted computer-aided detection (CAD) systems are used. The false-positive reduction (FPR) is important in feature representation and classification based on lung nodule CAD. The region of interest (ROI) in lung computer-aided detection comprises an extra imbalance between negative and positive samples, as well as false positives. To tackle image recognition challenges, specific machine learning or deep learning models are utilized in the existing research. This study presents novel and effective methods for classifying lung nodule abnormalities. In the original computed tomography (CT) image, the binary operation is done first for pre-processing. The lung nodules are then located using an entropy-based K-means clustering approach, and these nodules are segmented using an automated active contour level set. Finally, the Improved Capuchin Search Algorithm (ICSA) optimized hybrid convolutional neural network (CNN) based long and short term memory (LSTM) is used to classify abnormalities of lung nodules into Juxtapleural pulmonary nodules, Juxtavascular pulmonary nodules, Ground-glass opaque (GGO) pulmonary nodules, and Small pulmonary nodules categories. The Opposition based learning and chaotic local search strategy are used in the ICSA algorithm to minimize the complexity of the hybrid CNN-LSTM architecture by optimizing the hyperparameters. The overall pulmonary nodule identification accuracy is improved and it is measured using different metrics such as accuracy, sensitivity, and precision. F1-score, dice, Jaccard, and Hausdorff. The simulation results show that the proposed method outperforms the existing state-of-the-art methods.

Automatic detection of pulmonary nodules on CT images with YOLOv3: development and evaluation using simulated and patient data.

To develop a high-efficiency pulmonary nodule computer-aided detection (CAD) method for localization and diameter estimation. The developed CAD method centralizes a novel convolutional neural network (CNN) algorithm, You Only Look Once (YOLO) v3, as a deep learning approach. This method is featured by two distinct properties: (I) an automatic multi-scale feature extractor for nodule feature screening, and (II) a feature-based bounding box generator for nodule localization and diameter estimation. Two independent studies were performed to train and evaluate this CAD method. One study comprised of a computer simulation that utilized computer-based ground truth. In this study, 300 CT scans were simulated by Cardiac-torso (XCAT) digital phantom. Spherical nodules of various sizes (i.e., 3-10 mm in diameter) were randomly implanted within the lung region of the simulated images-the second study utilized human-based ground truth in patients. The CAD method was developed by CT scans sourced from the LIDC-IDRI database. CT scans with slice thickness above 2.5 mm were excluded, leaving 888 CT images for analysis. A 10-fold cross-validation procedure was implemented in both studies to evaluate network hyper-parameterization and generalization. The overall accuracy of the CAD method was evaluated by the detection sensitivities, in response to average false positives (FPs) per image. In the patient study, the detection accuracy was further compared against 9 recently published CAD studies using free-receiver response operating characteristic (FROC) curve analysis. Localization and diameter estimation accuracies were quantified by the mean and standard error between the predicted value and ground truth. The average results among the 10 cross-validation folds in both studies demonstrated the CAD method achieved high detection accuracy. The sensitivity was 99.3% (FPs =1), and improved to 100% (FPs =4) in the simulation study. The corresponding sensitivities were 90.0% and 95.4% in the patient study, displaying superiority over several conventional and CNN-based lung nodule CAD methods in the FROC curve analysis. Nodule localization and diameter estimation errors were less than 1 mm in both studies. The developed CAD method achieved high computational efficiency: it yields nodule-specific quantitative values (i.e., number, existence confidence, central coordinates, and diameter) within 0.1 s for 2D CT slice inputs. The reported results suggest that the developed lung pulmonary nodule CAD method possesses high accuracies of nodule localization and diameter estimation. The high computational efficiency enables its potential clinical application in the future.

Computer-aided detection of lung nodules: a review

We present an in-depth review and analysis of salient methods for computer-aided detection of lung nodules. We evaluate the current methods for detecting lung nodules using literature searches with selection criteria based on validation dataset types, nodule sizes, numbers of cases, types of nodules, extracted features in traditional feature-based classifiers, sensitivity, and false positives (FP)/scans. Our review shows that current detection systems are often optimized for particular datasets and can detect only one or two types of nodules. We conclude that, in addition to achieving high sensitivity and reduced FP/scans, strategies for detecting lung nodules must detect a variety of nodules with high precision to improve the performances of the radiologists. To the best of our knowledge, ours is the first review of the effectiveness of feature extraction using traditional feature-based classifiers. Moreover, we discuss deep-learning methods in detail and conclude that features must be appropriately selected to improve the overall accuracy of the system. We present an analysis of current schemes and highlight constraints and future research areas.

Automatic Detection of Lung Nodules Using 3D Deep Convolutional Neural Networks

Lung cancer is the leading cause of cancer deaths worldwide. Accurate early diagnosis is critical in increasing the 5-year survival rate of lung cancer, so the efficient and accurate detection of lung nodules, the potential precursors to lung cancer, is paramount. In this paper, a computer-aided lung nodule detection system using 3D deep convolutional neural networks (CNNs) is developed. The first multi-scale 11-layer 3D fully convolutional neural network (FCN) is used for screening all lung nodule candidates. Considering relative small sizes of lung nodules and limited memory, the input of the FCN consists of 3D image patches rather than of whole images. The candidates are further classified in the second CNN to get the final result. The proposed method achieves high performance in the LUNA16 challenge and demonstrates the effectiveness of using 3D deep CNNs for lung nodule detection.

Optimized feature selection-based clustering approach for computer-aided detection of lung nodules in different modalities

Early detection of pulmonary lung nodules plays a significant role in the diagnosis of lung cancer. Computed tomography (CT) and chest radiographs (CRs) are currently being used by radiologists to detect such nodules. In this paper, we present a novel cluster-based classifier architecture for lung nodule computer-aided detection systems in both modalities. We propose a novel optimized method of feature selection for both cluster and classifier components. For CRs, we make use of an independent database comprising of 160 cases with a total of 173 nodules for training purposes. Testing is implemented on a publicly available database created by the Standard Digital Image Database Project Team of the Scientific Committee of the Japanese Society of Radiological Technology (JRST). The JRST database comprises 154 CRs containing one radiologist-confirmed nodule in each. In this research, we exclude 14 cases from the JRST database that contain lung nodules in the retrocardiac and subdiaphragmatic regions of the lung. For CT scans, the analysis is based on threefold cross-validation performance on 107 cases from publicly available dataset created by Lung Image Database Consortium comprised of 280 nodules. Overall, with a specificity of 3 false positives per case/patient on average, we show a classifier performance boost of 7.7% for CRs and 5.0% for CT scans when compared to a single aggregate classifier architecture.

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

Objective: The aim of this paper is to describe a novel algorithm for False Positive Reduction in lung nodule Computer Aided Detection(CAD).Methods: In this paper, we describes a new CT lung CAD method which aims to detect solid nodules. Specially, we proposed a multi-kernel classifier with a ℓ2, 1 norm regularizer for heterogeneous feature fusion and selection from the feature subset level, and designed two efficient strategies to optimize the parameters of kernel weights in non-smooth ℓ2, 1 regularized multiple kernel learning algorithm. The first optimization algorithm adapts a proximal gradient method for solving the ℓ2, 1 norm of kernel weights, and use an accelerated method based on FISTA; the second one employs an iterative scheme based on an approximate gradient descent method.Results: The results demonstrates that the FISTA-style accelerated proximal descent method is efficient for the ℓ2, 1 norm formulation of multiple kernel learning with the theoretical guarantee of the convergence rate. Moreover, the experimental results demonstrate the effectiveness of the proposed methods in terms of Geometric mean (G-mean) and Area under the ROC curve (AUC), and significantly outperforms the competing methods.Conclusions: The proposed approach exhibits some remarkable advantages both in heterogeneous feature subsets fusion and classification phases. Compared with the fusion strategies of feature-level and decision level, the proposed ℓ2, 1 norm multi-kernel learning algorithm is able to accurately fuse the complementary and heterogeneous feature sets, and automatically prune the irrelevant and redundant feature subsets to form a more discriminative feature set, leading a promising classification performance. Moreover, the proposed algorithm consistently outperforms the comparable classification approaches in the literature.

A multi-kernel based framework for heterogeneous feature selection and over-sampling for computer-aided detection of pulmonary nodules

Classification plays a critical role in False Positive Reduction (FPR) in lung nodule Computer Aided Detection (CAD). To achieve effective recognition of nodule, many machine learning methods have been proposed. However, multiple heterogeneous feature subsets, high dimensional irrelevant features, as well as imbalanced distribution between the nodule and non-nodule classes typically makes this problem challenging. To solve these challenges, we proposed a multi-kernel based framework for feature selection and imbalanced data learning in Lung nodule CAD, involving multiple kernel learning with a ℓ2,1 norm regularizer for heterogeneous feature fusion and selection from the feature subset level, a multi-kernel feature selection based on pairwise similarities from the feature level, and a multi-kernel over-sampling for the imbalanced data learning. Experimental results demonstrate the effectiveness of the proposed method in terms of Geometric mean (G-mean) and Area under the ROC curve (AUC), and consistently outperform the competing methods.

Pulmonary Nodule Classification with Deep Convolutional Neural Networks on Computed Tomography Images.

Computer aided detection (CAD) systems can assist radiologists by offering a second opinion on early diagnosis of lung cancer. Classification and feature representation play critical roles in false-positive reduction (FPR) in lung nodule CAD. We design a deep convolutional neural networks method for nodule classification, which has an advantage of autolearning representation and strong generalization ability. A specified network structure for nodule images is proposed to solve the recognition of three types of nodules, that is, solid, semisolid, and ground glass opacity (GGO). Deep convolutional neural networks are trained by 62,492 regions-of-interest (ROIs) samples including 40,772 nodules and 21,720 nonnodules from the Lung Image Database Consortium (LIDC) database. Experimental results demonstrate the effectiveness of the proposed method in terms of sensitivity and overall accuracy and that it consistently outperforms the competing methods.

A joint ROI extraction filter for computer aided lung nodule detection.

Extraction of regions of interest plays an important rule in computer aided lung nodules detection. However, because of the complex background and structure, accurate and robust extraction of ROIs in medical image still remains a problem. Aim at this problem, a two-stage operations joint filter: Hessian-LoB, is proposed. The first stage is blobs (which being taken as candidate ROIs) detection and the second stage is ROIs extraction. In the first stage, the derivatives of a Hessian matrix at multiple scales are convolved with input images to localize blobs. Then in the second stage, Laplacian of bilateral filter (LoB) is convolved with the detected blobs to extract the final ROIs. Experiments show that the proposed filter can deal with images with noise and low brightness contrast, and is effectively in ROI extraction for lung nodule detection.

Computer-aided detection of lung nodules using outer surface features.

In this study, a computer-aided detection (CAD) system was developed for the detection of lung nodules in computed tomography images. The CAD system consists of four phases, including two-dimensional and three-dimensional preprocessing phases. In the feature extraction phase, four different groups of features are extracted from volume of interests: morphological features, statistical and histogram features, statistical and histogram features of outer surface, and texture features of outer surface. The support vector machine algorithm is optimized using particle swarm optimization for classification. The CAD system provides 97.37% sensitivity, 86.38% selectivity, 88.97% accuracy and 2.7 false positive per scan using three groups of classification features. After the inclusion of outer surface texture features, classification results of the CAD system reaches 98.03% sensitivity, 87.71% selectivity, 90.12% accuracy and 2.45 false positive per scan. Experimental results demonstrate that outer surface texture features of nodule candidates are useful to increase sensitivity and decrease the number of false positives in the detection of lung nodules in computed tomography images.

Toward clinically usable CAD for lung cancer screening with computed tomography.

The purpose of this study was to define clinically appropriate, computer-aided lung nodule detection (CAD) requirements and protocols based on recent screening trials. In the following paper, we describe a CAD evaluation methodology based on a publically available, annotated computed tomography (CT) image data set, and demonstrate the evaluation of a new CAD system with the functionality and performance required for adoption in clinical practice. A new automated lung nodule detection and measurement system was developed that incorporates intensity thresholding, a Euclidean Distance Transformation, and segmentation based on watersheds. System performance was evaluated against the Lung Imaging Database Consortium (LIDC) CT reference data set. The test set comprised thin-section CT scans from 108 LIDC subjects. The median (±IQR) sensitivity per subject was 100 (±37.5) for nodules ≥ 4mm and 100 (±8.33) for nodules ≥ 8mm. The corresponding false positive rates were 0 (±2.0) and 0 (±1.0), respectively. The concordance correlation coefficient between the CAD nodule diameter and the LIDC reference was 0.91, and for volume it was 0.90. The new CAD system shows high nodule sensitivity with a low false positive rate. Automated volume measurements have strong agreement with the reference standard. Thus, it provides comprehensive, clinically-usable lung nodule detection and assessment functionality. • CAD requirements can be based on lung cancer screening trial results. • CAD systems can be evaluated using publically available annotated CT image databases. • A new CAD system was developed with a low false positive rate. • The CAD system has reliable measurement tools needed for clinical use.

A novel lung nodules detection scheme based on vessel segmentation on CT images

Lung vessels often interfere with the detection of lung nodules. In this paper, a novel computer-aided lung nodule detection scheme on vessel segmentation is proposed. This paper describes an active contour model which can combine image region mean gray value and image edge energy. It is used to segment and remove lung vessels. A selective shape filter based on Hessian Matrix is used to detect suspicious nodules and remove omitted lung vessels. This paper extracts density, shape and position features of suspicious nodules, and uses a Rule-Based Classification (RBC) method to identify true positive nodules. In the experiment results, the detection sensitivity is about 90% and FP is 1/scan.

Ensemble-based hybrid probabilistic sampling for imbalanced data learning in lung nodule CAD

Classification plays a critical role in false positive reduction (FPR) in lung nodule computer aided detection (CAD). The difficulty of FPR lies in the variation of the appearances of the nodules, and the imbalance distribution between the nodule and non-nodule class. Moreover, the presence of inherent complex structures in data distribution, such as within-class imbalance and high-dimensionality are other critical factors of decreasing classification performance. To solve these challenges, we proposed a hybrid probabilistic sampling combined with diverse random subspace ensemble. Experimental results demonstrate the effectiveness of the proposed method in terms of geometric mean (G-mean) and area under the ROC curve (AUC) compared with commonly used methods.