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

Channel-Wise Attention Mechanism in the 3D Convolutional Network for Lung Nodule Detection

Pulmonary nodule detection is essential to reduce the mortality of lung cancer. One-stage detection methods have recently emerged as high-performance and lower-power alternatives to two-stage lung nodule detection methods. However, it is difficult for existing one-stage detection networks to balance sensitivity and specificity. In this paper, we propose an end-to-end detection mechanism combined with a channel-wise attention mechanism based on a 3D U-shaped residual network. First, an improved attention gate (AG) is introduced to reduce the false positive rate by employing critical feature dimensions at skip connections for feature propagation. Second, a channel interaction unit (CIU) is designed before the detection head to further improve detection sensitivity. Furthermore, the gradient harmonizing mechanism (GHM) loss function is adopted to solve the problem caused by the imbalance of positive and negative samples. We conducted experiments on the LUNA16 dataset and achieved a performance with a competition performance metric (CPM) score of 89.5% and sensitivity of 95%. The proposed method outperforms existing models in terms of sensitivity and specificity while maintaining the attractiveness of being lightweight, making it suitable for automatic lung nodule detection.

Prediction of chemotherapy response in breast cancer patients at pre-treatment using second derivative texture of CT images and machine learning

•

Textural and second derivative textural features of CT images can be used in conjunction with machine learning models to predict breast cancer response to chemotherapy prior to the start of treatment.

•

The proposed predictive model separates the patients at pre-treatment into two cohorts (responders/non-responders) with significantly different survival.

•

The proposed methodology is a step forward towards the precision oncology paradigm for breast cancer patients.

Although neoadjuvant chemotherapy (NAC) is a crucial component of treatment for locally advanced breast cancer (LABC), only about 70% of patients respond to it. Effective adjustment of NAC for individual patients can significantly improve survival rates of those resistant to standard regimens. Thus, the early prediction of NAC outcome is of great importance in facilitating a personalized paradigm for breast cancer therapeutics. In this study, quantitative computed tomography (qCT) parametric imaging in conjunction with machine learning techniques were investigated to predict LABC tumor response to NAC. Textural and second derivative textural (SDT) features of CT images of 72 patients diagnosed with LABC were analysed before the initiation of NAC to quantify intra-tumor heterogeneity. These quantitative features were processed through a correlation-based feature reduction followed by a sequential feature selection with a bootstrap 0.632+ area under the receiver operating characteristic (ROC) curve (AUC0.632+) criterion. The best feature subset consisted of a combination of one textural and three SDT features. Using these features, an AdaBoost decision tree could predict the patient response with a cross-validated AUC0.632+ accuracy, sensitivity and specificity of 0.88, 85%, 88% and 75%, respectively. This study demonstrates, for the first time, that a combination of textural and SDT features of CT images can be used to predict breast cancer response NAC prior to the start of treatment which can potentially facilitate early therapy adjustments.

On the performance of lung nodule detection, segmentation and classification

Computed tomography (CT) screening is an effective way for early detection of lung cancer in order to improve the survival rate of such a deadly disease. For more than two decades, image processing techniques such as nodule detection, segmentation, and classification have been extensively studied to assist physicians in identifying nodules from hundreds of CT slices to measure shapes and HU distributions of nodules automatically and to distinguish their malignancy. Thanks to new parallel computation, multi-layer convolution, nonlinear pooling operation, and the big data learning strategy, recent development of deep-learning algorithms has shown great progress in lung nodule screening and computer-assisted diagnosis (CADx) applications due to their high sensitivity and low false positive rates. This paper presents a survey of state-of-the-art deep-learning-based lung nodule screening and analysis techniques focusing on their performance and clinical applications, aiming to help better understand the current performance, the limitation, and the future trends of lung nodule analysis.

A priori prediction of tumour response to neoadjuvant chemotherapy in breast cancer patients using quantitative CT and machine learning

Response to Neoadjuvant chemotherapy (NAC) has demonstrated a high correlation to survival in locally advanced breast cancer (LABC) patients. An early prediction of responsiveness to NAC could facilitate treatment adjustments on an individual patient basis that would be expected to improve treatment outcomes and patient survival. This study investigated, for the first time, the efficacy of quantitative computed tomography (qCT) parametric imaging to characterize intra-tumour heterogeneity and its application in predicting tumour response to NAC in LABC patients. Textural analyses were performed on CT images acquired from 72 patients before the start of chemotherapy to determine quantitative features of intra-tumour heterogeneity. The best feature subset for response prediction was selected through a sequential feature selection with bootstrap 0.632 + area under the receiver operating characteristic (ROC) curve (\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{A}\mathrm{U}\mathrm{C}}_{0.632+}$$\end{document}AUC0.632+) as a performance criterion. Several classifiers were evaluated for response prediction using the selected feature subset. Amongst the applied classifiers an Adaboost decision tree provided the best results with cross-validated \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${\mathrm{A}\mathrm{U}\mathrm{C}}_{0.632+}$$\end{document}AUC0.632+, accuracy, sensitivity and specificity of 0.89, 84%, 80% and 88%, respectively. The promising results obtained in this study demonstrate the potential of the proposed biomarkers to be used as predictors of LABC tumour response to NAC prior to the start of treatment.

Imbalanced biomedical data classification using self-adaptive multilayer ELM combined with dynamic GAN

BACKGROUND

Imbalanced data classification is an inevitable problem in medical intelligent diagnosis. Most of real-world biomedical datasets are usually along with limited samples and high-dimensional feature. This seriously affects the classification performance of the model and causes erroneous guidance for the diagnosis of diseases. Exploring an effective classification method for imbalanced and limited biomedical dataset is a challenging task.

METHODS

In this paper, we propose a novel multilayer extreme learning machine (ELM) classification model combined with dynamic generative adversarial net (GAN) to tackle limited and imbalanced biomedical data. Firstly, principal component analysis is utilized to remove irrelevant and redundant features. Meanwhile, more meaningful pathological features are extracted. After that, dynamic GAN is designed to generate the realistic-looking minority class samples, thereby balancing the class distribution and avoiding overfitting effectively. Finally, a self-adaptive multilayer ELM is proposed to classify the balanced dataset. The analytic expression for the numbers of hidden layer and node is determined by quantitatively establishing the relationship between the change of imbalance ratio and the hyper-parameters of the model. Reducing interactive parameters adjustment makes the classification model more robust.

RESULTS

To evaluate the classification performance of the proposed method, numerical experiments are conducted on four real-world biomedical datasets. The proposed method can generate authentic minority class samples and self-adaptively select the optimal parameters of learning model. By comparing with W-ELM, SMOTE-ELM, and H-ELM methods, the quantitative experimental results demonstrate that our method can achieve better classification performance and higher computational efficiency in terms of ROC, AUC, G-mean, and F-measure metrics.

CONCLUSIONS

Our study provides an effective solution for imbalanced biomedical data classification under the condition of limited samples and high-dimensional feature. The proposed method could offer a theoretical basis for computer-aided diagnosis. It has the potential to be applied in biomedical clinical practice.

A novel adaptive ensemble classification framework for ADME prediction

AECF is a GA based ensemble method. It includes four components which are (1) data balancing, (2) generating individual models, (3) combining individual models, and (4) optimizing the ensemble.

Enhancement of hepatitis virus immunoassay outcome predictions in imbalanced routine pathology data by data balancing and feature selection before the application of support vector machines

Background

Data mining techniques such as support vector machines (SVMs) have been successfully used to predict outcomes for complex problems, including for human health. Much health data is imbalanced, with many more controls than positive cases.

Methods

The impact of three balancing methods and one feature selection method is explored, to assess the ability of SVMs to classify imbalanced diagnostic pathology data associated with the laboratory diagnosis of hepatitis B (HBV) and hepatitis C (HCV) infections. Random forests (RFs) for predictor variable selection, and data reshaping to overcome a large imbalance of negative to positive test results in relation to HBV and HCV immunoassay results, are examined. The methodology is illustrated using data from ACT Pathology (Canberra, Australia), consisting of laboratory test records from 18,625 individuals who underwent hepatitis virus testing over the decade from 1997 to 2007.

Results

Overall, the prediction of HCV test results by immunoassay was more accurate than for HBV immunoassay results associated with identical routine pathology predictor variable data. HBV and HCV negative results were vastly in excess of positive results, so three approaches to handling the negative/positive data imbalance were compared. Generating datasets by the Synthetic Minority Oversampling Technique (SMOTE) resulted in significantly more accurate prediction than single downsizing or multiple downsizing (MDS) of the dataset. For downsized data sets, applying a RF for predictor variable selection had a small effect on the performance, which varied depending on the virus. For SMOTE, a RF had a negative effect on performance. An analysis of variance of the performance across settings supports these findings. Finally, age and assay results for alanine aminotransferase (ALT), sodium for HBV and urea for HCV were found to have a significant impact upon laboratory diagnosis of HBV or HCV infection using an optimised SVM model.

Conclusions

Laboratories looking to include machine learning via SVM as part of their decision support need to be aware that the balancing method, predictor variable selection and the virus type interact to affect the laboratory diagnosis of hepatitis virus infection with routine pathology laboratory variables in different ways depending on which combination is being studied. This awareness should lead to careful use of existing machine learning methods, thus improving the quality of laboratory diagnosis.

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 ℓ_{2, 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 ℓ_{2, 1} regularized multiple kernel learning algorithm. The first optimization algorithm adapts a proximal gradient method for solving the ℓ_{2, 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 ℓ_{2, 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 ℓ_{2, 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.

Multiclass imbalance learning: Improving classification of pediatric brain tumors from magnetic resonance spectroscopy

Purpose

Classification of pediatric brain tumors from ¹H‐magnetic resonance spectroscopy (MRS) can aid diagnosis and management of brain tumors. However, varied incidence of the different tumor types leads to imbalanced class sizes and introduces difficulties in classifying rare tumor groups. This study assessed different imbalanced multiclass learning techniques and compared the use of complete spectra and quantified metabolite profiles for classification of three main childhood brain tumor types.

Methods

Single‐voxel, Short echo time MRS data were collected from 90 patients with pilocytic astrocytoma (n = 42), medulloblastoma (n = 38), or ependymoma (n = 10). Both spectra and metabolite profiles were used to develop the learning algorithms. The borderline synthetic minority oversampling technique and AdaboostM1 were used to correct for the skewed distribution. Classifiers were trained using five different pattern recognition algorithms.

Results

Use of imbalanced learning techniques improved the balanced accuracy rate (BAR) of all classification methods (average BAR over all classification methods for spectra: oversampled data = 0.81, original = 0.63, P < 0.001; metabolite concentration: oversampled‐data = 0.91, original = 0.75, P < 0.0001). Performance of all classifiers in discriminating ependymomas increased when oversampled data were used compared with original data for both complete spectra (F‐measure P < 0.01) and metabolite profile (F‐measure P < 0.001).

Conclusion

Imbalanced learning techniques improve the classification accuracy of childhood brain tumors from MRS where group sizes differ and facilitate the inclusion of rarer tumor types into clinical decision support systems. Magn Reson Med 77:2114–2124, 2017. © 2016 The Authors Magnetic Resonance in Medicine published by Wiley Periodicals, Inc. on behalf of International Society for Magnetic Resonance in Medicine. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

HOSVD-Based 3D Active Appearance Model: Segmentation of Lung Fields in CT Images

An Active Appearance Model (AAM) is a computer vision model which can be used to effectively segment lung fields in CT images. However, the fitting result is often inadequate when the lungs are affected by high-density pathologies. To overcome this problem, we propose a Higher-order Singular Value Decomposition (HOSVD)-based Three-dimensional (3D) AAM. An evaluation was performed on 310 diseased lungs form the Lung Image Database Consortium Image Collection. Other contemporary AAMs operate directly on patterns represented by vectors, i.e., before applying the AAM to a 3D lung volume,it has to be vectorized first into a vector pattern by some technique like concatenation. However, some implicit structural or local contextual information may be lost in this transformation. According to the nature of the 3D lung volume, HOSVD is introduced to represent and process the lung in tensor space. Our method can not only directly operate on the original 3D tensor patterns, but also efficiently reduce the computer memory usage. The evaluation resulted in an average Dice coefficient of 97.0 % ± 0.59 %, a mean absolute surface distance error of 1.0403 ± 0.5716 mm, a mean border positioning errors of 0.9187 ± 0.5381 pixel, and a Hausdorff Distance of 20.4064 ± 4.3855, respectively. Experimental results showed that our methods delivered significant and better segmentation results, compared with the three other model-based lung segmentation approaches, namely 3D Snake, 3D ASM and 3D AAM.

Three-dimensional SVM with latent variable: application for detection of lung lesions in CT images

The study aims to improve the performance of current computer-aided schemes for the detection of lung lesions, especially the low-contrast in gray density or irregular in shape. The relative position between suspected lesion and whole lung is, for the first time, added as a latent feature to enrich current Three-dimensional (3D) features such as shape, texture. Subsequently, 3D matrix patterns-based Support Vector Machine (SVM) with the latent variable, referred to as L-SVM3Dmatrix, was constructed accordingly. A CT image database containing 750 abnormal cases with 1050 lesions was used to train and evaluate several similar computer-aided detection (CAD) schemes: traditional features-based SVM (SVMfeature), 3D matrix patterns-based SVM (SVM3Dmatrix) and L-SVM3Dmatrix. The classifier performances were evaluated by computing the area under the ROC curve (AUC), using a 5-fold cross-validation. The L-SVM3Dmatrix sensitivity was 93.0 with 1.23% percentage of False Positive (FP), the SVM3Dmatrix sensitivity was 88.4 with 1.49% percentage of FP, and the SVMfeature sensitivity was 87.2 with 1.78% percentage of FP. The L-SVM3Dmatrix outperformed other current lung CAD schemes, especially regarding the difficult lesions.

Refinement of lung nodule candidates based on local geometric shape analysis and Laplacian of Gaussian kernels

This work is focused on application of a new technique in the first steps of computer-aided detection (CAD) of lung nodules. The scheme includes segmenting the lung volume and detecting most of the nodules with a low number of false positive (FP) objects. The juxtapleural nodules were properly included and the airways excluded in the lung segmentation. Among the suspicious regions obtained from the multiscale dot enhancement filter, those containing the center of nodule candidates, were determined. These center points were achieved from a 3D blob detector based on Laplacian of Gaussian kernels. Then the volumetric shape index (SI) that encodes the 3D local shape information was calculated for voxels in the determined regions. The performance of the scheme was evaluated by using 42 CT images from the Lung Image Database Consortium (LIDC). The results show that the average number of FPs reaches to 38.8 per scan with the sensitivity of 95.9% in the initial detections. The scheme is adaptable to detect nodules with wide variations in size, shape, intensity and location. Comparison of results with previously reported ones indicates that the proposed scheme can be satisfactory applied for initial detection of lung nodules in the chest CT images.