Breast lesion characterization using Quantitative Ultrasound (QUS) and derivative texture methods

PurposeAccurate and timely diagnosis of breast cancer is extremely important because of its high incidence and high morbidity. Early diagnosis of breast cancer through screening can improve overall prognosis. Currently, biopsy remains as the gold standard for tumor pathological confirmation. Development of diagnostic imaging techniques for rapid and accurate characterization of breast lesions is required. We aim to evaluate the usefulness of texture-derivate features of QUS spectral parametric images for non-invasive characterization of breast lesions.MethodsQUS Spectroscopy was used to determine parametric images of mid-band fit (MBF), spectral slope (SS), spectral intercept (SI), average scatterer diameter (ASD), and average acoustic concentration (AAC) in 204 patients with suspicious breast lesions. Subsequently, texture analysis techniques were used to generate texture maps from parametric images to quantify heterogeneities of QUS parametric images. Further, a second-pass texture analysis was applied to obtain texture-derivate features. QUS parameters, texture-parameters and texture-derivate parameters were determined from both tumor core and a 5-mm tumor margin and were used in comparison to histopathological analysis in order to develop a diagnostic model for classifying breast lesions as either benign or malignant. Both leave-one-out and hold-out cross-validations were used to evaluate the performance of the diagnostic model. Three standard classification algorithms including a linear discriminant analysis (LDA), k-nearest neighbors (KNN), and support vector machines-radial basis function (SVM-RBF) were evaluated.ResultsCore and margin information using the SVM-RBF attained the best classification performance of 90% sensitivity, 92% specificity, 91% accuracy, and 0.93 AUC utilizing QUS parameters and their texture derivatives, evaluated using leave-one-out cross-validation. Implementation of hold-out cross-validation using combination of both core and margin information and SVM-RBF achieved average accuracy and AUC of 88% and 0.92, respectively.ConclusionsQUS-based framework and derivative texture methods enable accurate classification of breast lesions. Evaluation of the proposed technique on a large cohort using hold-out cross-validation demonstrates its robustness and its generalization.     

Mass type-specific sparse representation for mass classification in computer-aided detection on mammograms

Background

Breast cancer is the leading cause of both incidence and mortality in women population. For this reason, much research effort has been devoted to develop Computer-Aided Detection (CAD) systems for early detection of the breast cancers on mammograms. In this paper, we propose a new and novel dictionary configuration underpinning sparse representation based classification (SRC). The key idea of the proposed algorithm is to improve the sparsity in terms of mass margins for the purpose of improving classification performance in CAD systems.

Methods

The aim of the proposed SRC framework is to construct separate dictionaries according to the types of mass margins. The underlying idea behind our method is that the separated dictionaries can enhance the sparsity of mass class (true-positive), leading to an improved performance for differentiating mammographic masses from normal tissues (false-positive). When a mass sample is given for classification, the sparse solutions based on corresponding dictionaries are separately solved and combined at score level. Experiments have been performed on both database (DB) named as Digital Database for Screening Mammography (DDSM) and clinical Full Field Digital Mammogram (FFDM) DBs. In our experiments, sparsity concentration in the true class (SCTC) and area under the Receiver operating characteristic (ROC) curve (AUC) were measured for the comparison between the proposed method and a conventional single dictionary based approach. In addition, a support vector machine (SVM) was used for comparing our method with state-of-the-arts classifier extensively used for mass classification.

Results

Comparing with the conventional single dictionary configuration, the proposed approach is able to improve SCTC of up to 13.9% and 23.6% on DDSM and FFDM DBs, respectively. Moreover, the proposed method is able to improve AUC with 8.2% and 22.1% on DDSM and FFDM DBs, respectively. Comparing to SVM classifier, the proposed method improves AUC with 2.9% and 11.6% on DDSM and FFDM DBs, respectively.

Conclusions

The proposed dictionary configuration is found to well improve the sparsity of dictionaries, resulting in an enhanced classification performance. Moreover, the results show that the proposed method is better than conventional SVM classifier for classifying breast masses subject to various margins from normal tissues.

     

Deep Learning-Based Metaheuristic Weighted K-Nearest Neighbor Algorithm for the Severity Classification of Breast Cancer

ObjectiveThe most widespread and intrusive cancer type among women is breast cancer. Globally, this type of cancer causes more mortality among women, next to lung cancer. This made the researchers to focus more on developing effective Computer-Aided Detection (CAD) methodologies for the classification of such deadly cancer types. In order to improve the rate of survival and earlier diagnosis, an optimistic research methodology is required in the classification of breast cancer. Consequently, an improved methodology that integrates the principle of deep learning with metaheuristic and classification algorithms is proposed for the severity classification of breast cancer. Hence to enhance the recent findings, an improved CAD methodology is proposed for redressing the healthcare problem.Material and MethodsThe work intends to cast a light-of-research towards classifying the severities present in digital mammogram images. For evaluating the work, the publicly available MIAS, INbreast, and WDBC databases are utilized. The proposed work employs transfer learning for extricating the features. The novelty of the work lies in improving the classification performance of the weighted k-nearest neighbor (wKNN) algorithm using particle swarm optimization (PSO), dragon-fly optimization algorithm (DFOA), and crow-search optimization algorithm (CSOA) as a transformation technique i.e., transforming non-linear input features into minimal linear separable feature vectors.ResultsThe results obtained for the proposed work are compared then with the Gaussian Naïve Bayes and linear Support Vector Machine algorithms, where the highest accuracy for classification is attained for the proposed work (CSOA-wKNN) with 84.35% for MIAS, 83.19% for INbreast, and 97.36% for WDBC datasets respectively.ConclusionThe obtained results reveal that the proposed Computer-Aided-Diagnosis (CAD) tool is robust for the severity classification of breast cancer.     

Glioblastomas and brain metastases differentiation following an MRI texture analysis-based radiomics approach

PurposeTo evaluate the potential of 2D texture features extracted from magnetic resonance (MR) images for differentiating brain metastasis (BM) and glioblastomas (GBM) following a radiomics approach.MethodsThis retrospective study included 50 patients with BM and 50 with GBM who underwent T1-weighted MRI between December 2010 and January 2017. Eighty-eight rotation-invariant texture features were computed for each segmented lesion using six texture analysis methods. These features were also extracted from the four images obtained after applying the discrete wavelet transform (88 features × 4 images). Three feature selection methods and five predictive models were evaluated. A 5-fold cross-validation scheme was used to randomly split the study group into training (80 patients) and testing (20 patients), repeating the process ten times. Classification was evaluated computing the average area under the receiver operating characteristic curve. Sensibility, specificity and accuracy were also computed. The whole process was tested quantizing the images with different gray-level values to evaluate their influence in the final results.ResultsHighest classification accuracy was obtained using the original images quantized with 128 gray-levels and a feature selection method based on the p-value. The best overall performance was achieved using a support vector machine model with a subset of 32 features (AUC = 0.896 ± 0.067, sensitivity of 82% and specificity of 80%). Naïve Bayes and k-nearest neighbors models showed also valuable results (AUC ≈ 0.8) with a lower number of features (<13), thus suggesting that these models may be more generalizable when using external validations.ConclusionThe proposed radiomics MRI approach is able to discriminate between GBM and BM with high accuracy employing a set of 2D texture features, thus helping in the diagnosis of brain lesions in a fast and non-invasive way.     

Gaussian Dropout Based Stacked Ensemble CNN for Classification of Breast Tumor in Ultrasound Images

ObjectiveBreast cancer and breast tumors have been considered to be the most pervasive form of cancer in medical practice. Breast tumors are life-threatening to women, and their early detection could save lives with the proper treatment. Physical methods for detection of Breast Cancer are time-consuming and often prone to a misdiagnosis at classifying tumors. Recent trends in radiological imaging have significantly improved the efficiency and veracity of breast tumor classification. Artificial intelligence techniques could be used as an automated detection and classification system.Materials and methodsIn this research, we propose a novel configuration of a Stacking Ensemble with custom Convolutional Neural Network architectures to classify breast tumors from ultrasound images into ‘Normal’, ‘Benign’, and ‘Malignant’ categories.ResultsAfter thorough experimentation, our ensemble has performed with an accuracy, f1-score, precision, and recall of 92.15%, 92.21%, 92.26%, 92.17% respectively.ConclusionThe presented ensemble leverages three Stacked Feature Extractors coupled with a characteristic meta-learner to provide an overall balanced classification performance, with better accuracy and lower false positives. The architecture works in association with gaussian dropout layers to improve the computation and an alternative pooling scheme to retain essential features.     

Diagnosis of Breast Masses from Dynamic Contrast-Enhanced and Diffusion-Weighted MR: A Machine Learning Approach

Purpose

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is increasingly used for breast cancer diagnosis as supplementary to conventional imaging techniques. Combining of diffusion-weighted imaging (DWI) of morphology and kinetic features from DCE-MRI to improve the discrimination power of malignant from benign breast masses is rarely reported.

Materials and Methods

The study comprised of 234 female patients with 85 benign and 149 malignant lesions. Four distinct groups of features, coupling with pathological tests, were estimated to comprehensively characterize the pictorial properties of each lesion, which was obtained by a semi-automated segmentation method. Classical machine learning scheme including feature subset selection and various classification schemes were employed to build prognostic model, which served as a foundation for evaluating the combined effects of the multi-sided features for predicting of the types of lesions. Various measurements including cross validation and receiver operating characteristics were used to quantify the diagnostic performances of each feature as well as their combination.

Results

Seven features were all found to be statistically different between the malignant and the benign groups and their combination has achieved the highest classification accuracy. The seven features include one pathological variable of age, one morphological variable of slope, three texture features of entropy, inverse difference and information correlation, one kinetic feature of SER and one DWI feature of apparent diffusion coefficient (ADC). Together with the selected diagnostic features, various classical classification schemes were used to test their discrimination power through cross validation scheme. The averaged measurements of sensitivity, specificity, AUC and accuracy are 0.85, 0.89, 90.9% and 0.93, respectively.

Conclusion

Multi-sided variables which characterize the morphological, kinetic, pathological properties and DWI measurement of ADC can dramatically improve the discriminatory power of breast lesions.     

Multi-parametric MRI lesion heterogeneity biomarkers for breast cancer diagnosis

PurposeTo identify intra-lesion imaging heterogeneity biomarkers in multi-parametric Magnetic Resonance Imaging (mpMRI) for breast lesion diagnosis.MethodsDynamic Contrast Enhanced (DCE) and Diffusion Weighted Imaging (DWI) of 73 female patients, with 85 histologically verified breast lesions were acquired. Non-rigid multi-resolution registration was utilized to spatially align sequences. Four (4) DCE (2^nd post-contrast frame, Initial-Enhancement, Post-Initial-Enhancement and Signal-Enhancement-Ratio) and one (1) DWI (Apparent-Diffusion-Coefficient) representations were analyzed, considering a representative lesion slice. 11 1^st-order-statistics and 16 texture features (Gray-Level-Co-occurrence-Matrix (GLCM) and Gray-Level-Run-Length-Matrix (GLRLM) based) were derived from lesion segments, provided by Fuzzy C-Means segmentation, across the 5 representations, resulting in 135 features. Least-Absolute-Shrinkage and Selection-Operator (LASSO) regression was utilized to select optimal feature subsets, subsequently fed into 3 classification schemes: Logistic-Regression (LR), Random-Forest (RF), Support-Vector-Machine-Sequential-Minimal-Optimization (SVM-SMO), assessed with Receiver-Operating-Characteristic (ROC) analysis.ResultsLASSO regression resulted in 7, 6 and 7 features subsets from DCE, DWI and mpMRI, respectively. Best classification performance was obtained by the RF multi-parametric scheme (Area-Under-ROC-Curve, (AUC) ± Standard-Error (SE), AUC ± SE = 0.984 ± 0.025), as compared to DCE (AUC ± SE = 0.961 ± 0.030) and DWI (AUC ± SE = 0.938 ± 0.032) and statistically significantly higher as compared to DWI. The selected mpMRI feature subset highlights the significance of entropy (1^st-order-statistics and 2^nd-order-statistics (GLCM)) and percentile features extracted from 2^nd post-contrast frame, PIE, SER maps and ADC map.ConclusionCapturing breast intra-lesion heterogeneity, across mpMRI lesion segments with 1^st-order-statistics and texture features (GLCM and GLRLM based), offers a valuable diagnostic tool for breast cancer.     

A Hybrid Deep Learning Model for Predicting Molecular Subtypes of Human Breast Cancer Using Multimodal Data

BackgroundThe prediction of breast cancer subtypes plays a key role in the diagnosis and prognosis of breast cancer. In recent years, deep learning (DL) has shown good performance in the intelligent prediction of breast cancer subtypes. However, most of the traditional DL models use single modality data, which can just extract a few features, so it cannot establish a stable relationship between patient characteristics and breast cancer subtypes.DatasetWe used the TCGA-BRCA dataset as a sample set for molecular subtype prediction of breast cancer. It is a public dataset that can be obtained through the following link: https://portal.gdc.cancer.gov/projects/TCGA-BRCAMethodsIn this paper, a Hybrid DL model based on the multimodal data is proposed. We combine the patient's gene modality data with image modality data to construct a multimodal fusion framework. According to the different forms and states, we set up feature extraction networks respectively, and then we fuse the output of the two feature networks based on the idea of weighted linear aggregation. Finally, the fused features are used to predict breast cancer subtypes. In particular, we use the principal component analysis to reduce the dimensionality of high-dimensional data of gene modality and filter the data of image modality. Besides, we also improve the traditional feature extraction network to make it show better performance.ResultsThe results show that compared with the traditional DL model, the Hybrid DL model proposed in this paper is more accurate and efficient in predicting breast cancer subtypes. Our model achieved a prediction accuracy of 88.07% in 10 times of 10-fold cross-validation. We did a separate AUC test for each subtype, and the average AUC value obtained was 0.9427. In terms of subtype prediction accuracy, our model is about 7.45% higher than the previous average.     

Automatic Detection and Classification of Mammograms Using Improved Extreme Learning Machine with Deep Learning

Background and objectiveBreast cancer, the most intrusive form of cancer affecting women globally. Next to lung cancer, breast cancer is the one that provides a greater number of cancer deaths among women. In recent times, several intelligent methodologies were come into existence for building an effective detection and classification of such noxious type of cancer. For further improving the rate of early diagnosis and for increasing the life span of victims, optimistic light of research is essential in breast cancer classification. Accordingly, a new customized method of integrating the concept of deep learning with the extreme learning machine (ELM), which is optimized using a simple crow-search algorithm (ICS-ELM). Thus, to enhance the state-of-the-art workings, an improved deep feature-based crow-search optimized extreme learning machine is proposed for addressing the health-care problem. The paper pours a light-of-research on detecting the input mammograms as either normal or abnormal. Subsequently, it focuses on further classifying the type of abnormal severities i.e., benign type or malignant.Materials and methodsThe digital mammograms for this work are taken from the Curated Breast Imaging Subset of DDSM (CBIS-DDSM), Mammographic Image Analysis Society (MIAS), and INbreast datasets. Herein, the work employs 570 digital mammograms (250 normal, 200 benign and 120 malignant cases) from CBIS-DDSM dataset, 322 digital mammograms (207 normal, 64 benign and 51 malignant cases) from MIAS database and 179 full-field digital mammograms (66 normal, 56 benign and 57 malignant cases) from INbreast dataset for its evaluation. The work utilizes ResNet-18 based deep extracted features with proposed Improved Crow-Search Optimized Extreme Learning Machine (ICS-ELM) algorithm.ResultsThe proposed work is finally compared with the existing Support Vector Machines (RBF kernel), ELM, particle swarm optimization (PSO) optimized ELM, and crow-search optimized ELM, where the maximum overall classification accuracy is obtained for the proposed method with 97.193% for DDSM, 98.137% for MIAS and 98.266% for INbreast datasets, respectively.ConclusionThe obtained results reveal that the proposed Computer-Aided-Diagnosis (CAD) tool is robust for the automatic detection and classification of breast cancer.     

Performance evaluation of contrast-detail in full field digital mammography systems using ideal (Hotelling) observer vs. conventional automated analysis of CDMAM images for quality control of contrast-detail characteristics

PurposeThe purpose of this work was to evaluate the contrast-detail performance of full field digital mammography (FFDM) systems using ideal (Hotelling) observer Signal-to-Noise Ratio (SNR) methodology and ascertain whether it can be considered an alternative to the conventional, automated analysis of CDMAM phantom images.MethodsFive FFDM units currently used in the national breast screening programme were evaluated, which differed with respect to age, detector, Automatic Exposure Control (AEC) and target/filter combination. Contrast-detail performance was analysed using CDMAM and ideal observer SNR methodology. The ideal observer SNR was calculated for input signal originating from gold discs of varying thicknesses and diameters, and then used to estimate the threshold gold thickness for each diameter as per CDMAM analysis. The variability of both methods and the dependence of CDMAM analysis on phantom manufacturing discrepancies also investigated.ResultsResults from both CDMAM and ideal observer methodologies were informative differentiators of FFDM systems' contrast-detail performance, displaying comparable patterns with respect to the FFDM systems' type and age. CDMAM results suggested higher threshold gold thickness values compared with the ideal observer methodology, especially for small-diameter details, which can be attributed to the behaviour of the CDMAM phantom used in this study. In addition, ideal observer methodology results showed lower variability than CDMAM results.ConclusionThe Ideal observer SNR methodology can provide a useful metric of the FFDM systems' contrast detail characteristics and could be considered a surrogate for conventional, automated analysis of CDMAM images.     

Automatic Grading System for Diagnosis of Breast Cancer Exploiting Co-occurrence Shearlet Transform and Histogram Features

ObjectivesBreast cancer (BC) is one of the most commonly reported health issues worldwide, especially in females. Early detection and diagnosis of BC can greatly reduce mortality rates. Samples obtained with different imaging methods such as mammography, computerized tomography, magnetic resonance, ultrasound, and biopsy are used in the diagnosis of BC. Histopathological images obtained from a biopsy contain vital information about the stage of the BC. Computer-aided systems are important tools to assist pathologists in the early detection of BC.Material and methodsIn the current study, the use of gray-level co-occurrence matrix (GLCM) of Shearlet Transform (ST) coefficients were first scrutinized as textural features. ST is an advanced decomposition-based method that can analyze images in various directions and is sensitive to edge singularities. These features make ST more robust than other decomposition methods such as Fourier and wavelet. Color channel histogram features were also utilized for a second level of evaluation in the diagnosis of the BC stage. These features are considered one of the most important building blocks that pathologists consider in the course of grading histopathological images. Then, by combining these two features, the classification results were re-assessed utilizing Support Vector Machine (SVM) as a classifier.ResultsThe assessments were performed on a BreaKHis dataset containing benign and malignant histopathological samples. The average accuracy scores were reported as being 98.2%, 97.2%, 97.8%, and 97.3% in the sub-databases with 40×, 100×, 200×, and 400× magnification factors, respectively.ConclusionsThe obtained results showed that the proposed method was quite efficient in histopathological image classification. Despite the relative simplicity of the approach, the obtained results were far superior to previously reported results.     

Radiomics software for breast imaging optimization and simulation studies

Background and ObjectiveThe development, control and optimisation of new x-ray breast imaging modalities could benefit from a quantitative assessment of the resulting image textures. The aim of this work was to develop a software tool for routine radiomics applications in breast imaging, which will also be available upon request.MethodsThe tool (developed in MATLAB) allows image reading, selection of Regions of Interest (ROI), analysis and comparison. Requirements towards the tool also included convenient handling of common medical and simulated images, building and providing a library of commonly applied algorithms and a friendly graphical user interface. Initial set of features and analyses have been selected after a literature search. Being open, the tool can be extended, if necessary.ResultsThe tool allows semi-automatic extracting of ROIs, calculating and processing a total of 23 different metrics or features in 2D images and/or in 3D image volumes. Computations of the features were verified against computations with other software packages performed with test images. Two case studies illustrate the applicability of the tool – (i) features on a series of 2D ‘left’ and ‘right’ CC mammograms acquired on a Siemens Inspiration system were computed and compared, and (ii) evaluation of the suitability of newly proposed and developed breast phantoms for x-ray-based imaging based on reference values from clinical mammography images. Obtained results could steer the further development of the physical breast phantoms.ConclusionsA new image analysis toolbox was realized and can now be used in a multitude of radiomics applications, on both clinical and test images.     

乳腺良恶性病变剪切波弹性成像的典型表现及其鉴别诊断价值

目的:观察乳腺良恶性病变的剪切波弹性成像(SWE)的典型表现,探讨SWE对乳腺良恶性病变的鉴别诊断价值。方法:选取2017年6月～2019年6月我院收治的162例行SWE检查的乳腺肿块患者,经组织活检或病理证实良性肿块105例(良性组)、恶性肿块57例(恶性组)。对比良、恶性组SWE的典型表现、SWE参数[最大值(Emax)、最小值(Emin)、平均值(Emean)、标准差(SD)、病灶与邻近脂肪弹性比值(SWE-Ratio)]的差异,分析SWE鉴别诊断乳腺良恶性病变的价值。结果:恶性组乳腺肿块"硬边征"检出率、Ⅲ型～Ⅴ型弹性图像检出率、Emax、Emean、SD、SWE-Ratio均高于良性组(P0.05),Emin低于良性组(P0.05)。Logistic多元回归分析结果显示,"硬边征"、Emax、Emean、SWE-Ratio与病理诊断乳腺肿块性质独立相关(P0.05)。受试者工作特征(ROC)曲线分析结果显示,"硬边征"、Emax、Emean、SWE-Ratio鉴别诊断乳腺良恶性病变的曲线下面积(AUC)分别为0.923、0.686、0.873、0.879。结论:SWE是诊断乳腺良恶性病变的有效影像手段,SWE的"硬边征"、SWE-Ratio、Emean对乳腺良恶性病变具有较高的鉴别价值。     

Deep learning for predicting subtype classification and survival of lung adenocarcinoma on computed tomography

ObjectivesThe subtype classification of lung adenocarcinoma is important for treatment decision. This study aimed to investigate the deep learning and radiomics networks for predicting histologic subtype classification and survival of lung adenocarcinoma diagnosed through computed tomography (CT) images.MethodsA dataset of 1222 patients with lung adenocarcinoma were retrospectively enrolled from three medical institutions. The anonymised preoperative CT images and pathological labels of atypical adenomatous hyperplasia, adenocarcinoma in situ, minimally invasive adenocarcinoma, invasive adenocarcinoma (IAC) with five predominant components were obtained. These pathological labels were divided into 2-category classification (IAC; non-IAC), 3-category and 8-category. We modeled the classification task of histological subtypes based on modified ResNet-34 deep learning network, radiomics strategies and deep radiomics combined algorithm. Then we established the prognostic models in lung adenocarcinoma patients with survival outcomes. The accuracy (ACC), area under ROC curves (AUCs) and C-index were primarily performed to evaluate the algorithms.ResultsThis study included a training set (n = 802) and two validation cohorts (internal, n = 196; external, n = 224). The ACC of deep radiomics algorithm in internal validation achieved 0.8776, 0.8061 in the 2-category, 3-category classification, respectively. Even in 8 classifications, the AUC ranged from 0.739 to 0.940 in internal set. Further, we constructed a prognosis model that C-index was 0.892(95% CI: 0.846–0.937) in internal validation set.ConclusionsThe automated deep radiomics based triage system has achieved the great performance in the subtype classification and survival predictability in patients with CT-detected lung adenocarcinoma nodules, providing the clinical guide for treatment strategies.     

Classification of Motor Imagery EEG Based on Time-Domain and Frequency-Domain Dual-Stream Convolutional Neural Network

Background and objectiveAn important task of the brain-computer interface (BCI) of motor imagery is to extract effective time-domain features, frequency-domain features or time-frequency domain features from the raw electroencephalogram (EEG) signals for classification of motor imagery. However, choosing an appropriate method to combine time domain and frequency domain features to improve the performance of motor imagery recognition is still a research hotspot.MethodsIn order to fully extract and utilize the time-domain and frequency-domain features of EEG in classification tasks, this paper proposed a novel dual-stream convolutional neural network (DCNN), which can use time domain signal and frequency domain signal as the inputs, and the extracted time-domain features and frequency-domain features are fused by linear weighting for classification training. Furthermore, the weight can be learned by the DCNN automatically.ResultsThe experiments based on BCI competition II dataset III and BCI competition IV dataset 2a showed that the model proposed by this study has better performance than other conventional methods. The model used time-frequency signal as the inputs had better performance than the model only used time-domain signals or frequency-domain signals. The accuracy of classification was improved for each subject compared with the models only used one signals as the inputs.ConclusionsFurther analysis shown that the fusion weight of different subject is specifically, adjusting the weight coefficient automatically is helpful to improve the classification accuracy.     

Network-based logistic regression integration method for biomarker identification

Background

Many mathematical and statistical models and algorithms have been proposed to do biomarker identification in recent years. However, the biomarkers inferred from different datasets suffer a lack of reproducibilities due to the heterogeneity of the data generated from different platforms or laboratories. This motivates us to develop robust biomarker identification methods by integrating multiple datasets.

Methods

In this paper, we developed an integrative method for classification based on logistic regression. Different constant terms are set in the logistic regression model to measure the heterogeneity of the samples. By minimizing the differences of the constant terms within the same dataset, both the homogeneity within the same dataset and the heterogeneity in multiple datasets can be kept. The model is formulated as an optimization problem with a network penalty measuring the differences of the constant terms. The L₁ penalty, elastic penalty and network related penalties are added to the objective function for the biomarker discovery purpose. Algorithms based on proximal Newton method are proposed to solve the optimization problem.

Results

We first applied the proposed method to the simulated datasets. Both the AUC of the prediction and the biomarker identification accuracy are improved. We then applied the method to two breast cancer gene expression datasets. By integrating both datasets, the prediction AUC is improved over directly merging the datasets and MetaLasso. And it’s comparable to the best AUC when doing biomarker identification in an individual dataset. The identified biomarkers using network related penalty for variables were further analyzed. Meaningful subnetworks enriched by breast cancer were identified.

Conclusion

A network-based integrative logistic regression model is proposed in the paper. It improves both the prediction and biomarker identification accuracy.

     

Prediction of unfavourable response to checkpoint blockade in lung cancer patients through an integrated tumour-immune expression score

BackgroundTreatment by immune checkpoint blockade (ICB) provides a remarkable survival benefit for multiple cancer types. However, disease aggravation occurs in a proportion of patients after the first couple of treatment cycles.MethodsRNA sequencing data was retrospectively collected. 6 tumour-immune related features were extracted and combined to build a lung cancer-specific predictive model to distinguish responses as progression disease (PD) or non-PD. This model was trained by 3 public pan-cancer datasets and a lung cancer cohort from our institute, and generated a lung cancer-specific integrated gene expression score, which we call LITES. It was finally tested in another lung cancer dataset.ResultsLITES is a promising predictor for checkpoint blockade (area under the curve [AUC]=0.86), superior to traditional biomarkers. It is independent of PD-L1 expression and tumour mutation burden. The sensitivity and specificity of LITES was 85.7% and 70.6%, respectively. Progression free survival (PFS) was longer in high-score group than in low-score group (median PFS: 6.0 vs. 2.4 months, hazard ratio=0.45, P=0.01). The mean AUC of 6 features was 0.70 (range=0.61-0.75), lower than in LITES, indicating that the combination of features had synergistic effects. Among the genes identified in the features, patients with high expression of NRAS and PDPK1 tended to have a PD response (P=0.001 and 0.01, respectively). Our model also functioned well for patients with advanced melanoma and was specific for ICB therapy.ConclusionsLITES is a promising biomarker for predicting an impaired response in lung cancer patients and for clarifying the biological mechanism underlying ICB therapy.     

A deep learning classifier for digital breast tomosynthesis

PurposeTo develop a computerized detection system for the automatic classification of the presence/absence of mass lesions in digital breast tomosynthesis (DBT) annotated exams, based on a deep convolutional neural network (DCNN).Materials and MethodsThree DCNN architectures working at image-level (DBT slice) were compared: two state-of-the-art pre-trained DCNN architectures (AlexNet and VGG19) customized through transfer learning, and one developed from scratch (DBT-DCNN). To evaluate these DCNN-based architectures we analysed their classification performance on two different datasets provided by two hospital radiology departments. DBT slice images were processed following normalization, background correction and data augmentation procedures. The accuracy, sensitivity, and area-under-the-curve (AUC) values were evaluated on both datasets, using receiver operating characteristic curves. A Grad-CAM technique was also implemented providing an indication of the lesion position in the DBT slice.Results Accuracy, sensitivity and AUC for the investigated DCNN are in-line with the best performance reported in the field. The DBT-DCNN network developed in this work showed an accuracy and a sensitivity of (90% ± 4%) and (96% ± 3%), respectively, with an AUC as good as 0.89 ± 0.04. A k-fold cross validation test (with k = 4) showed an accuracy of 94.0% ± 0.2%, and a F1-score test provided a value as good as 0.93 ± 0.03. Grad-CAM maps show high activation in correspondence of pixels within the tumour regions.Conclusions We developed a deep learning-based framework (DBT-DCNN) to classify DBT images from clinical exams. We investigated also a possible application of the Grad-CAM technique to identify the lesion position.     

Regulation of Brain-Derived Neurotrophic Factor (BDNF) and Cerebral Dopamine Neurotrophic Factor (CDNF) by Anti-Parkinsonian Drug Therapy In Vivo

Available treatment for Parkinson’s disease (PD) is mainly symptomatic instead of halting or reversing degenerative processes affecting the disease. Research on the molecular pathogenesis of PD has suggested reduced trophic support as a possible cause or mediator of neurodegeneration. In animal models of the disease, neurotrophic factors prevent neurodegeneration and induce behavioral recovery. Some anti-Parkinsonian drugs show neuroprotective activity, but it is not known whether the drug-induced neuroprotection is mediated by neurotrophic factors. In this study, we have investigated the influence of two neuroprotective anti-Parkinsonian drugs, the monoamine oxidase B inhibitor selegiline and the adenosine A_2A antagonist SCH 58261, on the levels of brain-derived neurotrophic factor (BDNF) and cerebral dopamine neurotrophic factor (CDNF) in the mouse brain. Protein levels of BDNF and CDNF were quantified by western blot after 2 weeks of treatment with either of the drugs or placebo. CDNF levels were not significantly influenced by selegiline or SCH 58261 in any brain area studied. Selegiline treatment significantly increased BDNF levels in the anterior cingulate cortex (1.55 ± 0.22, P < 0.05, Student’s t-test). In the striatum, selegiline increased BDNF content by 32%, but this change did not reach statistical significance (1.32 ± 0.15, P < 0.13, Student’s t-test). Our data suggest that neurotrophic factors, particularly BDNF may play a role in the neuroprotective effects of selegiline, but do not support the hypothesis that anti-Parkinsonian drugs would work by increasing the levels of CDNF in brain.