Feature selection and performance evaluation of support vector machine (SVM)-based classifier for differentiating benign and malignant pulmonary nodules by computed tomography

PET radiomics in lung cancer: advances and translational challenges

Radiomics is an emerging field of medical imaging that aims at improving the accuracy of diagnosis, prognosis, treatment planning and monitoring non-invasively through the automated or semi-automated quantitative analysis of high-dimensional image features. Specifically in the field of nuclear medicine, radiomics utilizes imaging methods such as positron emission tomography (PET) and single photon emission computed tomography (SPECT) to evaluate biomarkers related to metabolism, blood flow, cellular activity and some biological pathways. Lung cancer ranks among the leading causes of cancer-related deaths globally, and radiomics analysis has shown great potential in guiding individualized therapy, assessing treatment response, and predicting clinical outcomes. In this review, we summarize the current state-of-the-art radiomics progress in lung cancer, highlighting the potential benefits and existing limitations of this approach. The radiomics workflow was introduced first including image acquisition, segmentation, feature extraction, and model building. Then the published literatures were described about radiomics-based prediction models for lung cancer diagnosis, differentiation, prognosis and efficacy evaluation. Finally, we discuss current challenges and provide insights into future directions and potential opportunities for integrating radiomics into routine clinical practice.

Optimizing the Diagnostic Algorithm for Pulmonary Embolism in Acute COPD Exacerbation Using Fuzzy Rough Sets and Support Vector Machine

Aiming to optimize the diagnosis of pulmonary embolism (PE) in patients with acute exacerbation of chronic obstructive pulmonary disease (AECOPD), we conducted a retrospective study enrolling 185 AECOPD patients, of whom 90 were diagnosed with PE based on computed tomography pulmonary angiography (CTPA). Ten characteristic indicators and 27 blood indicators were extracted for each patient. First, we quantified the importance of each indicator for diagnosing PE in AECOPD using fuzzy rough sets (FRS) and selected the more important indicators to construct a support vector machine (SVM) diagnosis model called FRS-SVM. The performance of the proposed diagnosis model on the test sets was compared to that of the logistic regression model. The average accuracy and area under the curve (AUC) of the proposed model for the test sets in 10 independent trials were 94.67% and 0.944, respectively, compared to 80.41% and 0.809 for the logistic regression model. Thus, we validated the higher accuracy and stability of the FRS-SVM for PE diagnosis in patients with AECOPD. This model improved the prediction probability before CTPA and can be used in clinical practice to help doctors make decisions.

Differential disease diagnoses of epistaxis based on dynamic uncertain causality graph

PURPOSE

Epistaxis is a common symptom and can be caused by various diseases, including nasal diseases, systemic diseases, etc. Many misdiagnosis and missed diagnosis of epistaxis are caused by lack of clinical knowledge and experience, especially some interns and the clinicans in primary hospitals. To help inexperienced clinicans improve their diagnostic accuracies of epistaxis, a computer-aided diagnostic system based on Dynamic Uncertain Causality Graph (DUCG) was designed in this study.

METHODS

We build a visual epistaxis knowledge base based on medical experts' knowledge and experience. The knowledge base intuitively expresses the causal relationship among diseases, risk factors, symptoms, signs, laboratory checks, and image examinations. The DUCG inference algorithm well addresses the patients' clinical information with the knowledge base to deduce the currently suspected diseases and calculate the probability of each suspected disease.

RESULT

The model can differentially diagnose 24 diseases with epistaxis as the chief complaint. A third-party verification was performed, and the total diagnostic precision was 97.81%. In addition, the DUCG-based diagnostic model was applied in Jiaozhou city and Zhongxian county, China, covering hundreds of primary hospitals and clinics. So far, the clinicians using the model have all agreed with the diagnostic results. The 432 real-world application cases show that this model is good for the differential diagnoses of epistaxis.

CONCLUSION

The results show that the DUCG-based epistaxis diagnosis model has high diagnostic accuracy. It can assist primary clinicians in completing the differential diagnosis of epistaxis and can be accepted by clinicians.

Toward the determination of sensitive and reliable whole-lung computed tomography features for robust standard radiomics and delta-radiomics analysis in a nonhuman primate model of coronavirus disease 2019

Purpose

We propose a method to identify sensitive and reliable whole-lung radiomic features from computed tomography (CT) images in a nonhuman primate model of coronavirus disease 2019 (COVID-19). Criteria used for feature selection in this method may improve the performance and robustness of predictive models.

Approach

Fourteen crab-eating macaques were assigned to two experimental groups and exposed to either severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) or a mock inoculum. High-resolution CT scans were acquired before exposure and on several post-exposure days. Lung volumes were segmented using a deep-learning methodology, and radiomic features were extracted from the original image. The reliability of each feature was assessed by the intraclass correlation coefficient (ICC) using the mock-exposed group data. The sensitivity of each feature was assessed using the virus-exposed group data by defining a factor R that estimates the excess of variation above the maximum normal variation computed in the mock-exposed group. R and ICC were used to rank features and identify non-sensitive and unstable features.

Results

Out of 111 radiomic features, 43% had excellent reliability ( ICC > 0.90 ), and 55% had either good ( ICC > 0.75 ) or moderate ( ICC > 0.50 ) reliability. Nineteen features were not sensitive to the radiological manifestations of SARS-CoV-2 exposure. The sensitivity of features showed patterns that suggested a correlation with the radiological manifestations.

Conclusions

Features were quantified and ranked based on their sensitivity and reliability. Features to be excluded to create more robust models were identified. Applicability to similar viral pneumonia studies is also possible.

Computed Tomography Features of Lung Structure Have Utility for Differentiating Malignant and Benign Pulmonary Nodules

BACKGROUND

Chronic obstructive pulmonary disease (COPD) is a known comorbidity for lung cancer independent of smoking history. Quantitative computed tomography (qCT) imaging features related to COPD have shown promise in the assessment of lung cancer risk. We hypothesize that qCT features from the lung, lobe, and airway tree related to the location of the pulmonary nodule can be used to provide informative malignancy risk assessment.

METHODS

A total of 183 qCT features were extracted from 278 individuals with a solitary pulmonary nodule of known diagnosis (71 malignant, 207 benign). These included histogram and airway characteristics of the lungs, lobe, and segmental paths. Performances of the least absolute shrinkage and selection operator (LASSO) regression analysis and an ensemble of neural networks (ENN) were compared for feature set selection and classification on a testing cohort of 49 additional individuals (15 malignant, 34 benign).

RESULTS

The LASSO and ENN methods produced different feature sets for classification with LASSO selecting fewer qCT features (7) than the ENN (17). The LASSO model with the highest performing training area under the curve (AUC) (0.80) incorporated automatically extracted features and reader-measured nodule diameter with a testing AUC of 0.62. The ENN model with the highest performing AUC (0.77) also incorporated qCT and reader diameter but maintained higher testing performance AUC (0.79).

CONCLUSIONS

Automatically extracted qCT imaging features of the lung can be informative of the differentiation between individuals with malignant pulmonary nodules and those with benign pulmonary nodules, without requiring nodule segmentation and analysis.

Three-Dimensional Texture Feature Analysis of Pulmonary Nodules in CT Images: Lung Cancer Predictive Models Based on Support Vector Machine Classifier

To extract texture features of pulmonary nodules from three-dimensional views and to assess if predictive models of lung CT images from a three-dimensional texture feature could improve assessments conducted by radiologists. Clinical and CT imaging data for three dimensions (axial, coronal, and sagittal) in pulmonary nodules in 285 patients were collected from multiple centers and the Cancer Imaging Archive after ethics committee approval. Three-dimensional texture feature values (contourlets), and clinical and computed tomography (CT) imaging data were built into support vector machine (SVM) models to predict lung cancer, using four evaluation methods (disjunctive, conjunctive, voting, and synthetic); sensitivity, specificity, the Youden index, discriminant power (DP), and F value were calculated to assess model effectiveness. Additionally, diagnostic accuracy (three-dimensional model, axial model, and radiologist assessment) was assessed using the area under the curves for receiver operating characteristic (ROC) curves. Cross-sectional data from 285 patients (median age, 62 [range, 45-83] years; 115 males [40.4%]) were evaluated. Integrating three-dimensional assessments, the voting method had relatively high effectiveness based on both sensitivity (0.98) and specificity (0.79), which could improve radiologist diagnosis (maximum sensitivity, 0.75; maximum specificity, 0.51) for 23% and 28% respectively. Furthermore, the three-dimensional texture feature model of the voting method has the best diagnosis of precision rate (95.4%). Of all three-dimensional texture feature methods, the result of the voting method was the best, maintaining both high sensitivity and specificity scores. Additionally, the three-dimensional texture feature models were superior to two-dimensional models and radiologist-based assessments.

Three Stream Network Model for Lung Cancer Classification in the CT Images

Lung cancer is considered to be one of the deadly diseases that threaten the survival of human beings. It is a challenging task to identify lung cancer in its early stage from the medical images because of the ambiguity in the lung regions. This paper proposes a new architecture to detect lung cancer obtained from the CT images. The proposed architecture has a three-stream network to extract the manual and automated features from the images. Among these three streams, automated feature extraction as well as the classification is done using residual deep neural network and custom deep neural network. Whereas the manual features are the handcrafted features obtained using high and low-frequency sub-bands in the frequency domain that are classified using a Support Vector Machine Classifier. This makes the architecture robust enough to capture all the important features required to classify lung cancer from the input image. Hence, there is no chance of missing feature information. Finally, all the obtained prediction scores are combined by weighted based fusion. The experimental results show 98.2% classification accuracy which is relatively higher in comparison to other existing methods.

Combining machine learning and texture analysis to differentiate mediastinal lymph nodes in lung cancer patients

Evaluate whether texture analysis associated with machine learning approaches could differentiate between malignant and benign lymph nodes. A total 18 patients with lung cancer were selected, with 39 lymph nodes, being 15 malignant and 24 benign. Retrospective computed tomography scans were utilized both with and without contrast medium. The great differential of this work was the use of 15 textures from mediastinal lymph nodes, with five different physicians as operators. First and second order statistical textures such as gray level run length and co-occurrence matrix were extracted and applied to three different machine learning classifiers. The best machine learning classifier demonstrated a variability of less than 5% among operators. The support vector machine (SVM) classifier presented 95% of the area under the ROC curve (AUC) and 89% of sensitivity for sequences without contrast medium. SVM classifier presented 93% of AUC and 86% of sensitivity for sequences with contrast medium. Texture analysis and machine learning may be helpful in the differentiation between malign and benign lymph nodes. This study can aid the physician in diagnosis and staging of lymph nodes and potentially reduce the number of invasive analysis to histopathological confirmation.

Classification of malignant lung cancer using deep learning

In the automatic detection of suspicious shaded regions on CT images derived from the LIDC-IDRI dataset, the diagnostic system plays a significant role. This paper introduces an automatic recognition method for lung nodules of the regions of concern (ROI). The lung regions are segmented from DICOM image size 512 × 512 by adding a median filter, Gaussian filter, Gabor filter and watershed algorithm. AlexNet uses 227 × 227 × 3 with "fc7" (fully connected) layers and GoogLeNet uses 224 × 224 × 3 with "pool5-drop 7 × 7 s1" layers. Here, the authors explain what is better about AlexNet and GoogLeNet through its performance analysis, feature extraction, classification, sensitivity, specificity, detection and false alarm rate with time complexity. A multi-class SVM classifier with 100% precision and specificity provided the best performance in deep learning neural networks.

Machine learning approach for distinguishing malignant and benign lung nodules utilizing standardized perinodular parenchymal features from CT

PURPOSE

Computed tomography (CT) is an effective method for detecting and characterizing lung nodules in vivo. With the growing use of chest CT, the detection frequency of lung nodules is increasing. Noninvasive methods to distinguish malignant from benign nodules have the potential to decrease the clinical burden, risk, and cost involved in follow-up procedures on the large number of false-positive lesions detected. This study examined the benefit of including perinodular parenchymal features in machine learning (ML) tools for pulmonary nodule assessment.

METHODS

Lung nodule cases with pathology confirmed diagnosis (74 malignant, 289 benign) were used to extract quantitative imaging characteristics from computed tomography scans of the nodule and perinodular parenchyma tissue. A ML tool development pipeline was employed using k-medoids clustering and information theory to determine efficient predictor sets for different amounts of parenchyma inclusion and build an artificial neural network classifier. The resulting ML tool was validated using an independent cohort (50 malignant, 50 benign).

RESULTS

The inclusion of parenchymal imaging features improved the performance of the ML tool over exclusively nodular features (P < 0.01). The best performing ML tool included features derived from nodule diameter-based surrounding parenchyma tissue quartile bands. We demonstrate similar high-performance values on the independent validation cohort (AUC-ROC = 0.965). A comparison using the independent validation cohort with the Fleischner pulmonary nodule follow-up guidelines demonstrated a theoretical reduction in recommended follow-up imaging and procedures.

CONCLUSIONS

Radiomic features extracted from the parenchyma surrounding lung nodules contain valid signals with spatial relevance for the task of lung cancer risk classification. Through standardization of feature extraction regions from the parenchyma, ML tool validation performance of 100% sensitivity and 96% specificity was achieved.

Post-imaging pulmonary nodule mathematical prediction models: are they clinically relevant?

OBJECTIVES

Post-imaging mathematical prediction models (MPMs) provide guidance for the management of solid pulmonary nodules by providing a lung cancer risk score from demographic and radiologists-indicated imaging characteristics. We hypothesized calibrating the MPM risk score threshold to a local study cohort would result in improved performance over the original recommended MPM thresholds. We compared the pre- and post-calibration performance of four MPM models and determined if improvement in MPM prediction occurs as nodules are imaged longitudinally.

MATERIALS AND METHODS

A common cohort of 317 individuals with computed tomography-detected, solid nodules (80 malignant, 237 benign) were used to evaluate the MPM performance. We created a web-based application for this study that allows others to easily calibrate thresholds and analyze the performance of MPMs on their local cohort. Thirty patients with repeated imaging were tested for improved performance longitudinally.

RESULTS

Using calibrated thresholds, Mayo Clinic and Brock University (BU) MPMs performed the best (AUC = 0.63, 0.61) compared to the Veteran's Affairs (0.51) and Peking University (0.55). Only BU had consensus with the original MPM threshold; the other calibrated thresholds improved MPM accuracy. No significant improvements in accuracy were found longitudinally between time points.

CONCLUSIONS

Calibration to a common cohort can select the best-performing MPM for your institution. Without calibration, BU has the most stable performance in solid nodules ≥ 8 mm but has only moderate potential to refine subjects into appropriate workup. Application of MPM is recommended only at initial evaluation as no increase in accuracy was achieved over time.

KEY POINTS

• Post-imaging lung cancer risk mathematical predication models (MPMs) perform poorly on local populations without calibration. • An application is provided to facilitate calibration to new study cohorts: the Mayo Clinic model, the U.S. Department of Veteran's Affairs model, the Brock University model, and the Peking University model. • No significant improvement in risk prediction occurred in nodules with repeated imaging sessions, indicating the potential value of risk prediction application is limited to the initial evaluation.

Convolutional neural network-based PSO for lung nodule false positive reduction on CT images

BACKGROUND AND OBJECTIVE

Detection of lung nodules is critical in CAD systems; this is because of their similar contrast with other structures and low density, which result in the generation of numerous false positives (FPs). Therefore, this study proposes a methodology to reduce the FP number using a deep learning technique in conjunction with an evolutionary technique.

METHOD

The particle swarm optimization (PSO) algorithm was used to optimize the network hyperparameters in the convolutional neural network (CNN) in order to enhance the network performance and eliminate the requirement of manual search.

RESULTS

The methodology was tested on computed tomography (CT) scans from the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) with the highest accuracy of 97.62%, sensitivity of 92.20%, specificity of 98.64%, and area under the receiver operating characteristic (ROC) curve of 0.955.

CONCLUSION

The results demonstrate the high performance-potential of the PSO algorithm in the identification of optimal CNN hyperparameters for lung nodule candidate classification into nodules and non-nodules, increasing the sensitivity rates in the FP reduction step of CAD systems.

Quantitative CT analysis of pulmonary nodules for lung adenocarcinoma risk classification based on an exponential weighted grey scale angular density distribution feature

BACKGROUND AND OBJECTIVES

To improve lung nodule classification efficiency, we propose a lung nodule CT image characterization method. We propose a multi-directional feature extraction method to effectively represent nodules of different risk levels. The proposed feature combined with pattern recognition model to classify lung adenocarcinomas risk to four categories: Atypical Adenomatous Hyperplasia (AAH), Adenocarcinoma In Situ (AIS), Minimally Invasive Adenocarcinoma (MIA), and Invasive Adenocarcinoma (IA).

METHODS

First, we constructed the reference map using an integral image and labelled this map using a K-means approach. The density distribution map of the lung nodule image was generated after scanning all pixels in the nodule image. An exponential function was designed to weight the angular histogram for each component of the distribution map, and the features of the image were described. Then, quantitative measurement was performed using a Random Forest classifier. The evaluation data were obtained from the LIDC-IDRI database and the CT database which provided by Shanghai Zhongshan hospital (ZSDB). In the LIDC-IDRI, the nodules are categorized into three configurations with five ranks of malignancy ("1" to "5"). In the ZSDB, the nodule categories are AAH, AIS, MIA, and IA.

RESULTS

The average of Student's t-test p-values were less than 0.02. The AUCs for the LIDC-IDRI database were 0.9568, 0.9320, and 0.8288 for Configurations 1, 2, and 3, respectively. The AUCs for the ZSDB were 0.9771, 0.9917, 0.9590, and 0.9971 for AAH, AIS, MIA and IA, respectively.

CONCLUSION

The experimental results demonstrate that the proposed method outperforms the state-of-the-art and is robust for different lung CT image datasets.

Feature Selection for Automatic Tuberculosis Screening in Frontal Chest Radiographs

To detect pulmonary abnormalities such as Tuberculosis (TB), an automatic analysis and classification of chest radiographs can be used as a reliable alternative to more sophisticated and technologically demanding methods (e.g. culture or sputum smear analysis). In target areas like Kenya TB is highly prevalent and often co-occurring with HIV combined with low resources and limited medical assistance. In these regions an automatic screening system can provide a cost-effective solution for a large rural population. Our completely automatic TB screening system is processing the incoming CXRs (chest X-ray) by applying image preprocessing techniques to enhance the image quality followed by an adaptive segmentation based on model selection. The delineated lung regions are described by a multitude of image features. These characteristics are than optimized by a feature selection strategy to provide the best description for the classifier, which will later decide if the analyzed image is normal or abnormal. Our goal is to find the optimal feature set from a larger pool of generic image features, -used originally for problems such as object detection, image retrieval, etc. For performance evaluation measures such as under the curve (AUC) and accuracy (ACC) were considered. Using a neural network classifier on two publicly available data collections, -namely the Montgomery and the Shenzhen dataset, we achieved the maximum area under the curve and accuracy of 0.99 and 97.03%, respectively. Further, we compared our results with existing state-of-the-art systems and to radiologists' decision.

MRI features predict p53 status in lower-grade gliomas via a machine-learning approach

Background

P53 mutation status is a pivotal biomarker for gliomas. Here, we developed a machine-learning model to predict p53 status in lower-grade gliomas based on radiomic features extracted from conventional magnetic resonance (MR) images.

Methods

Preoperative MR images were retrospectively obtained from 272 patients with primary grade II/III gliomas. The patients were randomly allocated in a 2:1 ratio to a training (n = 180) or validation (n = 92) set. A total of 431 radiomic features were extracted from each patient. The lest absolute shrinkage and selection operator (LASSO) method was used for feature selection and radiomic signature construction. Subsequently, a machine-learning model to predict p53 status was established using the selected features and a Support Vector Machine classifier. The predictive performance of all individual features and the model was calculated using receiver operating characteristic curves in both the training and validation sets.

Results

The p53-related radiomic signature was built using the LASSO algorithm; this procedure consisted of four first-order statistics or related wavelet features (including Maximum, Median, Minimum, and Uniformity), a shape and size-based feature (Spherical Disproportion), and ten textural features or related wavelet features (including Correlation, Run Percentage, and Sum Entropy). The prediction accuracies based on the area under the curve were 89.6% in the training set and 76.3% in the validation set, which were better than individual features.

Conclusions

These results demonstrate that MR image texture features are predictive of p53 mutation status in lower-grade gliomas. Thus, our procedure can be conveniently used to facilitate presurgical molecular pathological diagnosis.

•

We established a p53-related radiomic signature in lower-grade gliomas based on LASSO algorithm.

•

We developed a machine-learning model using the radiomic signature and a support vector machine.

•

P53 mutation status of lower-grade gliomas was predicted effectively based on our machine-learning model.

Correlation coefficient based supervised locally linear embedding for pulmonary nodule recognition

BACKGROUND AND OBJECTIVE

Dimensionality reduction techniques are developed to suppress the negative effects of high dimensional feature space of lung CT images on classification performance in computer aided detection (CAD) systems for pulmonary nodule detection.

METHODS

An improved supervised locally linear embedding (SLLE) algorithm is proposed based on the concept of correlation coefficient. The Spearman's rank correlation coefficient is introduced to adjust the distance metric in the SLLE algorithm to ensure that more suitable neighborhood points could be identified, and thus to enhance the discriminating power of embedded data. The proposed Spearman's rank correlation coefficient based SLLE (SC(2)SLLE) is implemented and validated in our pilot CAD system using a clinical dataset collected from the publicly available lung image database consortium and image database resource initiative (LICD-IDRI). Particularly, a representative CAD system for solitary pulmonary nodule detection is designed and implemented. After a sequential medical image processing steps, 64 nodules and 140 non-nodules are extracted, and 34 representative features are calculated. The SC(2)SLLE, as well as SLLE and LLE algorithm, are applied to reduce the dimensionality. Several quantitative measurements are also used to evaluate and compare the performances.

RESULTS

Using a 5-fold cross-validation methodology, the proposed algorithm achieves 87.65% accuracy, 79.23% sensitivity, 91.43% specificity, and 8.57% false positive rate, on average. Experimental results indicate that the proposed algorithm outperforms the original locally linear embedding and SLLE coupled with the support vector machine (SVM) classifier.

CONCLUSIONS

Based on the preliminary results from a limited number of nodules in our dataset, this study demonstrates the great potential to improve the performance of a CAD system for nodule detection using the proposed SC(2)SLLE.

LUNGx Challenge for computerized lung nodule classification

The purpose of this work is to describe the LUNGx Challenge for the computerized classification of lung nodules on diagnostic computed tomography (CT) scans as benign or malignant and report the performance of participants' computerized methods along with that of six radiologists who participated in an observer study performing the same Challenge task on the same dataset. The Challenge provided sets of calibration and testing scans, established a performance assessment process, and created an infrastructure for case dissemination and result submission. Ten groups applied their own methods to 73 lung nodules (37 benign and 36 malignant) that were selected to achieve approximate size matching between the two cohorts. Area under the receiver operating characteristic curve (AUC) values for these methods ranged from 0.50 to 0.68; only three methods performed statistically better than random guessing. The radiologists' AUC values ranged from 0.70 to 0.85; three radiologists performed statistically better than the best-performing computer method. The LUNGx Challenge compared the performance of computerized methods in the task of differentiating benign from malignant lung nodules on CT scans, placed in the context of the performance of radiologists on the same task. The continued public availability of the Challenge cases will provide a valuable resource for the medical imaging research community.

Improving malignancy prediction through feature selection informed by nodule size ranges in NLST

Computed tomography (CT) is widely used during diagnosis and treatment of Non-Small Cell Lung Cancer (NSCLC). Current computer-aided diagnosis (CAD) models, designed for the classification of malignant and benign nodules, use image features, selected by feature selectors, for making a decision. In this paper, we investigate automated selection of different image features informed by different nodule size ranges to increase the overall accuracy of the classification. The NLST dataset is one of the largest available datasets on CT screening for NSCLC. We used 261 cases as a training dataset and 237 cases as a test dataset. The nodule size, which may indicate biological variability, can vary substantially. For example, in the training set, there are nodules with a diameter of a couple millimeters up to a couple dozen millimeters. The premise is that benign and malignant nodules have different radiomic quantitative descriptors related to size. After splitting training and testing datasets into three subsets based on the longest nodule diameter (LD) parameter accuracy was improved from 74.68% to 81.01% and the AUC improved from 0.69 to 0.79. We show that if AUC is the main factor in choosing parameters then accuracy improved from 72.57% to 77.5% and AUC improved from 0.78 to 0.82. Additionally, we show the impact of an oversampling technique for the minority cancer class. In some particular cases from 0.82 to 0.87.

Test-retest reproducibility analysis of lung CT image features

Quantitative size, shape, and texture features derived from computed tomographic (CT) images may be useful as predictive, prognostic, or response biomarkers in non-small cell lung cancer (NSCLC). However, to be useful, such features must be reproducible, non-redundant, and have a large dynamic range. We developed a set of quantitative three-dimensional (3D) features to describe segmented tumors and evaluated their reproducibility to select features with high potential to have prognostic utility. Thirty-two patients with NSCLC were subjected to unenhanced thoracic CT scans acquired within 15 min of each other under an approved protocol. Primary lung cancer lesions were segmented using semi-automatic 3D region growing algorithms. Following segmentation, 219 quantitative 3D features were extracted from each lesion, corresponding to size, shape, and texture, including features in transformed spaces (laws, wavelets). The most informative features were selected using the concordance correlation coefficient across test-retest, the biological range and a feature independence measure. There were 66 (30.14%) features with concordance correlation coefficient ≥ 0.90 across test-retest and acceptable dynamic range. Of these, 42 features were non-redundant after grouping features with R (2) Bet ≥ 0.95. These reproducible features were found to be predictive of radiological prognosis. The area under the curve (AUC) was 91% for a size-based feature and 92% for the texture features (runlength, laws). We tested the ability of image features to predict a radiological prognostic score on an independent NSCLC (39 adenocarcinoma) samples, the AUC for texture features (runlength emphasis, energy) was 0.84 while the conventional size-based features (volume, longest diameter) was 0.80. Test-retest and correlation analyses have identified non-redundant CT image features with both high intra-patient reproducibility and inter-patient biological range. Thus making the case that quantitative image features are informative and prognostic biomarkers for NSCLC.

Automated system for lung nodules classification based on wavelet feature descriptor and support vector machine

Background

Lung cancer is a leading cause of death worldwide; it refers to the uncontrolled growth of abnormal cells in the lung. A computed tomography (CT) scan of the thorax is the most sensitive method for detecting cancerous lung nodules. A lung nodule is a round lesion which can be either non-cancerous or cancerous. In the CT, the lung cancer is observed as round white shadow nodules. The possibility to obtain a manually accurate interpretation from CT scans demands a big effort by the radiologist and might be a fatiguing process. Therefore, the design of a computer-aided diagnosis (CADx) system would be helpful as a second opinion tool.

Methods

The stages of the proposed CADx are: a supervised extraction of the region of interest to eliminate the shape differences among CT images. The Daubechies db1, db2, and db4 wavelet transforms are computed with one and two levels of decomposition. After that, 19 features are computed from each wavelet sub-band. Then, the sub-band and attribute selection is performed. As a result, 11 features are selected and combined in pairs as inputs to the support vector machine (SVM), which is used to distinguish CT images containing cancerous nodules from those not containing nodules.

Results

The clinical data set used for experiments consists of 45 CT scans from ELCAP and LIDC. For the training stage 61 CT images were used (36 with cancerous lung nodules and 25 without lung nodules). The system performance was tested with 45 CT scans (23 CT scans with lung nodules and 22 without nodules), different from that used for training. The results obtained show that the methodology successfully classifies cancerous nodules with a diameter from 2 mm to 30 mm. The total preciseness obtained was 82%; the sensitivity was 90.90%, whereas the specificity was 73.91%.

Conclusions

The CADx system presented is competitive with other literature systems in terms of sensitivity. The system reduces the complexity of classification by not performing the typical segmentation stage of most CADx systems. Additionally, the novelty of the algorithm is the use of a wavelet feature descriptor.

Support vector machine model for diagnosing pneumoconiosis based on wavelet texture features of digital chest radiographs

This study aims to explore the classification ability of decision trees (DTs) and support vector machines (SVMs) to discriminate between the digital chest radiographs (DRs) of pneumoconiosis patients and control subjects. Twenty-eight wavelet-based energy texture features were calculated at the lung fields on DRs of 85 healthy controls and 40 patients with stage I and stage II pneumoconiosis. DTs with algorithm C5.0 and SVMs with four different kernels were trained by samples with two combinations of the texture features to classify a DR as of a healthy subject or of a patient with pneumoconiosis. All of the models were developed with fivefold cross-validation, and the final performances of each model were compared by the area under receiver operating characteristic (ROC) curve. For both SVM (with a radial basis function kernel) and DT (with algorithm C5.0), areas under ROC curves (AUCs) were 0.94 ± 0.02 and 0.86 ± 0.04 (P = 0.02) when using the full feature set and 0.95 ± 0.02 and 0.88 ± 0.04 (P = 0.05) when using the selected feature set, respectively. When built on the selected texture features, the SVM with a polynomial kernel showed a higher diagnostic performance with an AUC value of 0.97 ± 0.02 than SVMs with a linear kernel, a radial basis function kernel and a sigmoid kernel with AUC values of 0.96 ± 0.02 (P = 0.37), 0.95 ± 0.02 (P = 0.24), and 0.90 ± 0.03 (P = 0.01), respectively. The SVM model with a polynomial kernel built on the selected feature set showed the highest diagnostic performance among all tested models when using either all the wavelet texture features or the selected ones. The model has a good potential in diagnosing pneumoconiosis based on digital chest radiographs.

Quantification of heterogeneity as a biomarker in tumor imaging: a systematic review

BACKGROUND

Many techniques are proposed for the quantification of tumor heterogeneity as an imaging biomarker for differentiation between tumor types, tumor grading, response monitoring and outcome prediction. However, in clinical practice these methods are barely used. This study evaluates the reported performance of the described methods and identifies barriers to their implementation in clinical practice.

METHODOLOGY

The Ovid, Embase, and Cochrane Central databases were searched up to 20 September 2013. Heterogeneity analysis methods were classified into four categories, i.e., non-spatial methods (NSM), spatial grey level methods (SGLM), fractal analysis (FA) methods, and filters and transforms (F&T). The performance of the different methods was compared.

PRINCIPAL FINDINGS

Of the 7351 potentially relevant publications, 209 were included. Of these studies, 58% reported the use of NSM, 49% SGLM, 10% FA, and 28% F&T. Differentiation between tumor types, tumor grading and/or outcome prediction was the goal in 87% of the studies. Overall, the reported area under the curve (AUC) ranged from 0.5 to 1 (median 0.87). No relation was found between the performance and the quantification methods used, or between the performance and the imaging modality. A negative correlation was found between the tumor-feature ratio and the AUC, which is presumably caused by overfitting in small datasets. Cross-validation was reported in 63% of the classification studies. Retrospective analyses were conducted in 57% of the studies without a clear description.

CONCLUSIONS

In a research setting, heterogeneity quantification methods can differentiate between tumor types, grade tumors, and predict outcome and monitor treatment effects. To translate these methods to clinical practice, more prospective studies are required that use external datasets for validation: these datasets should be made available to the community to facilitate the development of new and improved methods.

The development and evaluation of a computerized diagnosis scheme for pneumoconiosis on digital chest radiographs

Purpose

To diagnose pneumoconiosis using a computer-aided diagnosis system based on digital chest radiographs.

Methods

Lung fields were first extracted by combining the traditional Otsu-threshold method with a morphological reconstruction on digital radiographs (DRs), and then subdivided into six non-overlapping regions (region (a-f)). Twenty-two wavelet-based energy texture features were calculated exclusively from each region and selected using a decision tree algorithm. A support vector machine (SVM) with a linear kernel was trained using samples with texture features to classify an individual region of a healthy subject or a pneumoconiosis patient. The final classification results were obtained by integrating these individual classifiers with the weighted voting method. All models were developed on a dataset of 85 healthy controls and 40 stage I or II pneumoconiosis patients and validated by using the bootstrap resampling with replacement method.

Results

The areas under receiver operating characteristic curves (AUCs) of regions (c) and (f) were 0.688 and 0.563, which were worse than those of the other four regions. Region (c) and (f) were both excluded from the individual classifiers that were going to be assembled further. When built on the selected texture features, each individual SVM showed a higher diagnostic performance for the training set and the test set. The classification performance after an ensemble was 0.997 and 0.961 of the AUC value for the training and test sets, respectively. The final results were 0.974 ± 0.018 for AUC value and 0.929 ± 0.018 for accuracy.

Conclusion

The integrated SVM model built on the selected feature set showed the highest diagnostic performance among all individual SVM models. The model has good potential in diagnosing pneumoconiosis based on digital chest radiographs.

Contourlet textual features: improving the diagnosis of solitary pulmonary nodules in two dimensional CT images

Objective

To determine the value of contourlet textural features obtained from solitary pulmonary nodules in two dimensional CT images used in diagnoses of lung cancer.

Materials and Methods

A total of 6,299 CT images were acquired from 336 patients, with 1,454 benign pulmonary nodule images from 84 patients (50 male, 34 female) and 4,845 malignant from 252 patients (150 male, 102 female). Further to this, nineteen patient information categories, which included seven demographic parameters and twelve morphological features, were also collected. A contourlet was used to extract fourteen types of textural features. These were then used to establish three support vector machine models. One comprised a database constructed of nineteen collected patient information categories, another included contourlet textural features and the third one contained both sets of information. Ten-fold cross-validation was used to evaluate the diagnosis results for the three databases, with sensitivity, specificity, accuracy, the area under the curve (AUC), precision, Youden index, and F-measure were used as the assessment criteria. In addition, the synthetic minority over-sampling technique (SMOTE) was used to preprocess the unbalanced data.

Results

Using a database containing textural features and patient information, sensitivity, specificity, accuracy, AUC, precision, Youden index, and F-measure were: 0.95, 0.71, 0.89, 0.89, 0.92, 0.66, and 0.93 respectively. These results were higher than results derived using the database without textural features (0.82, 0.47, 0.74, 0.67, 0.84, 0.29, and 0.83 respectively) as well as the database comprising only textural features (0.81, 0.64, 0.67, 0.72, 0.88, 0.44, and 0.85 respectively). Using the SMOTE as a pre-processing procedure, new balanced database generated, including observations of 5,816 benign ROIs and 5,815 malignant ROIs, and accuracy was 0.93.

Conclusion

Our results indicate that the combined contourlet textural features of solitary pulmonary nodules in CT images with patient profile information could potentially improve the diagnosis of lung cancer.

Combination of radiological and gray level co-occurrence matrix textural features used to distinguish solitary pulmonary nodules by computed tomography

The objective of this study was to investigate the method of the combination of radiological and textural features for the differentiation of malignant from benign solitary pulmonary nodules by computed tomography. Features including 13 gray level co-occurrence matrix textural features and 12 radiological features were extracted from 2,117 CT slices, which came from 202 (116 malignant and 86 benign) patients. Lasso-type regularization to a nonlinear regression model was applied to select predictive features and a BP artificial neural network was used to build the diagnostic model. Eight radiological and two textural features were obtained after the Lasso-type regularization procedure. Twelve radiological features alone could reach an area under the ROC curve (AUC) of 0.84 in differentiating between malignant and benign lesions. The 10 selected characters improved the AUC to 0.91. The evaluation results showed that the method of selecting radiological and textural features appears to yield more effective in the distinction of malignant from benign solitary pulmonary nodules by computed tomography.

Real-data comparison of data mining methods in prediction of diabetes in iran

OBJECTIVES

Diabetes is one of the most common non-communicable diseases in developing countries. Early screening and diagnosis play an important role in effective prevention strategies. This study compared two traditional classification methods (logistic regression and Fisher linear discriminant analysis) and four machine-learning classifiers (neural networks, support vector machines, fuzzy c-mean, and random forests) to classify persons with and without diabetes.

METHODS

The data set used in this study included 6,500 subjects from the Iranian national non-communicable diseases risk factors surveillance obtained through a cross-sectional survey. The obtained sample was based on cluster sampling of the Iran population which was conducted in 2005-2009 to assess the prevalence of major non-communicable disease risk factors. Ten risk factors that are commonly associated with diabetes were selected to compare the performance of six classifiers in terms of sensitivity, specificity, total accuracy, and area under the receiver operating characteristic (ROC) curve criteria.

RESULTS

Support vector machines showed the highest total accuracy (0.986) as well as area under the ROC (0.979). Also, this method showed high specificity (1.000) and sensitivity (0.820). All other methods produced total accuracy of more than 85%, but for all methods, the sensitivity values were very low (less than 0.350).

CONCLUSIONS

The results of this study indicate that, in terms of sensitivity, specificity, and overall classification accuracy, the support vector machine model ranks first among all the classifiers tested in the prediction of diabetes. Therefore, this approach is a promising classifier for predicting diabetes, and it should be further investigated for the prediction of other diseases.

Computer-aided diagnosis for early-stage lung cancer based on longitudinal and balanced data

Background

Lung cancer is one of the most common forms of cancer resulting in over a million deaths per year worldwide. Typically, the problem can be approached by developing more discriminative diagnosis methods. In this paper, computer-aided diagnosis was used to facilitate the prediction of characteristics of solitary pulmonary nodules in CT of lungs to diagnose early-stage lung cancer.

Methods

The synthetic minority over-sampling technique (SMOTE) was used to account for raw data in order to balance the original training data set. Curvelet-transformation textural features, together with 3 patient demographic characteristics, and 9 morphological features were used to establish a support vector machine (SVM) prediction model. Longitudinal data as the test data set was used to evaluate the classification performance of predicting early-stage lung cancer.

Results

Using the SMOTE as a pre-processing procedure, the original training data was balanced with a ratio of malignant to benign cases of 1∶1. Accuracy based on cross-evaluation for the original unbalanced data and balanced data was 80% and 97%, respectively. Based on Curvelet-transformation textural features and other features, the SVM prediction model had good classification performance for early-stage lung cancer, with an area under the curve of the SVMs of 0.949 (P<0.001). Textural feature (standard deviation) showed benign cases had a higher change in the follow-up period than malignant cases.

Conclusions

With textural features extracted from a Curvelet transformation and other parameters, a sensitive support vector machine prediction model can increase the rate of diagnosis for early-stage lung cancer. This scheme can be used as an auxiliary tool to differentiate between benign and malignant early-stage lung cancers in CT images.

Automatic segmentation of ground-glass opacities in lung CT images by using Markov random field-based algorithms

Chest radiologists rely on the segmentation and quantificational analysis of ground-glass opacities (GGO) to perform imaging diagnoses that evaluate the disease severity or recovery stages of diffuse parenchymal lung diseases. However, it is computationally difficult to segment and analyze patterns of GGO while compared with other lung diseases, since GGO usually do not have clear boundaries. In this paper, we present a new approach which automatically segments GGO in lung computed tomography (CT) images using algorithms derived from Markov random field theory. Further, we systematically evaluate the performance of the algorithms in segmenting GGO in lung CT images under different situations. CT image studies from 41 patients with diffuse lung diseases were enrolled in this research. The local distributions were modeled with both simple and adaptive (AMAP) models of maximum a posteriori (MAP). For best segmentation, we used the simulated annealing algorithm with a Gibbs sampler to solve the combinatorial optimization problem of MAP estimators, and we applied a knowledge-guided strategy to reduce false positive regions. We achieved AMAP-based GGO segmentation results of 86.94%, 94.33%, and 94.06% in average sensitivity, specificity, and accuracy, respectively, and we evaluated the performance using radiologists' subjective evaluation and quantificational analysis and diagnosis. We also compared the results of AMAP-based GGO segmentation with those of support vector machine-based methods, and we discuss the reliability and other issues of AMAP-based GGO segmentation. Our research results demonstrate the acceptability and usefulness of AMAP-based GGO segmentation for assisting radiologists in detecting GGO in high-resolution CT diagnostic procedures.

Pre-operative prediction of advanced prostatic cancer using clinical decision support systems: accuracy comparison between support vector machine and artificial neural network

Objective

The purpose of the current study was to develop support vector machine (SVM) and artificial neural network (ANN) models for the pre-operative prediction of advanced prostate cancer by using the parameters acquired from transrectal ultrasound (TRUS)-guided prostate biopsies, and to compare the accuracies between the two models.

Materials and Methods

Five hundred thirty-two consecutive patients who underwent prostate biopsies and prostatectomies for prostate cancer were divided into the training and test groups (n = 300 versus n = 232). From the data in the training group, two clinical decision support systems (CDSSs-[SVM and ANN]) were constructed with input (age, prostate specific antigen level, digital rectal examination, and five biopsy parameters) and output data (the probability for advanced prostate cancer [> pT3a]). From the data of the test group, the accuracy of output data was evaluated. The areas under the receiver operating characteristic (ROC) curve (AUC) were calculated to summarize the overall performances, and a comparison of the ROC curves was performed (p < 0.05).

Results

The AUC of SVM and ANN is 0.805 and 0.719, respectively (p = 0.020), in the pre-operative prediction of advanced prostate cancer.

Conclusion

The performance of SVM is superior to ANN in the pre-operative prediction of advanced prostate cancer.

Data mining methods in the prediction of Dementia: A real-data comparison of the accuracy, sensitivity and specificity of linear discriminant analysis, logistic regression, neural networks, support vector machines, classification trees and random forests

Background

Dementia and cognitive impairment associated with aging are a major medical and social concern. Neuropsychological testing is a key element in the diagnostic procedures of Mild Cognitive Impairment (MCI), but has presently a limited value in the prediction of progression to dementia. We advance the hypothesis that newer statistical classification methods derived from data mining and machine learning methods like Neural Networks, Support Vector Machines and Random Forests can improve accuracy, sensitivity and specificity of predictions obtained from neuropsychological testing. Seven non parametric classifiers derived from data mining methods (Multilayer Perceptrons Neural Networks, Radial Basis Function Neural Networks, Support Vector Machines, CART, CHAID and QUEST Classification Trees and Random Forests) were compared to three traditional classifiers (Linear Discriminant Analysis, Quadratic Discriminant Analysis and Logistic Regression) in terms of overall classification accuracy, specificity, sensitivity, Area under the ROC curve and Press'Q. Model predictors were 10 neuropsychological tests currently used in the diagnosis of dementia. Statistical distributions of classification parameters obtained from a 5-fold cross-validation were compared using the Friedman's nonparametric test.

Results

Press' Q test showed that all classifiers performed better than chance alone (p < 0.05). Support Vector Machines showed the larger overall classification accuracy (Median (Me) = 0.76) an area under the ROC (Me = 0.90). However this method showed high specificity (Me = 1.0) but low sensitivity (Me = 0.3). Random Forest ranked second in overall accuracy (Me = 0.73) with high area under the ROC (Me = 0.73) specificity (Me = 0.73) and sensitivity (Me = 0.64). Linear Discriminant Analysis also showed acceptable overall accuracy (Me = 0.66), with acceptable area under the ROC (Me = 0.72) specificity (Me = 0.66) and sensitivity (Me = 0.64). The remaining classifiers showed overall classification accuracy above a median value of 0.63, but for most sensitivity was around or even lower than a median value of 0.5.

Conclusions

When taking into account sensitivity, specificity and overall classification accuracy Random Forests and Linear Discriminant analysis rank first among all the classifiers tested in prediction of dementia using several neuropsychological tests. These methods may be used to improve accuracy, sensitivity and specificity of Dementia predictions from neuropsychological testing.

3D matrix pattern based Support Vector Machines for identifying pulmonary cancer in CT scanned images

A novel algorithm of Three Dimension matrix (3D matrix) pattern based Minimum Within-Class Scatter Support Vector Machines (MCSVMs(3Dmatrix)) is presented. Combining Minimum Within-Class Scatter Support Vector Machines (MCSVMs) and higher-order tensor technology, decision functions of MCSVMs(3Dmatrix) are calculated along with three orthogonal directions in the 3D space. And then the final decision is made by Majority Vote Method. In previous reports, each CT image is solely processed and the relation among successive CT scanned images is neglected. The case results in defective judgment at whiles. The proposed method solves the problem effectively and improves the accuracy of classification to a certain extent.