Breast cancer diagnosis in digitized mammograms using curvelet moments

BACKGROUND

Feature extraction is a key issue in designing a computer aided diagnosis system. Recent researches on breast cancer diagnosis have reported the effectiveness of multiscale transforms (wavelets and curvelets) for mammogram analysis and have shown the superiority of curvelet transform. However, the curse of dimensionality problem arises when using the curvelet coefficients and therefore a reduction method is required to extract a reduced set of discriminative features.

METHODS

This paper deals with this problem and proposes a feature extraction method based on curvelet transform and moment theory for mammogram description. First, we performed discrete curvelet transform and we computed the four first-order moments from curvelet coefficients distribution. Hence, two feature sets can be obtained: moments from each band and moments from each level. In this work, both sets are studied. Then, the t-test ranking technique was applied to select the best features from each set. Finally, a k-nearest neighbor classifier was used to distinguish between normal and abnormal breast tissues and to classify tumors as malignant or benign. Experiments were performed on 252 mammograms from the Mammographic Image Analysis Society (mini-MIAS) database using the leave-one-out cross validation as well as on 11553 mammograms from the Digital Database for Screening Mammography (DDSM) database using 2×5-fold cross validation.

RESULTS

Experimental results prove the effectiveness and the superiority of curvelet moments for mammogram analysis. Indeed, results on the mini-MIAS database show that curvelet moments yield an accuracy of 91.27% (resp. 81.35 %) with 10 (resp. 8) features for abnormality (resp. malignancy) detection. In addition, empirical comparisons of the proposed method against state-of-the-art curvelet-based methods on the DDSM database show that the suggested method does not only lead to a more reduced feature set, but it also statistically outperforms all the compared methods in terms of accuracy.

CONCLUSIONS

In summary, curvelet moments are an efficient and effective way to extract a reduced set of discriminative features for breast cancer diagnosis.

HER2 breast cancer biomarker detection using a sandwich optical fiber assay

Optical fiber-based surface plasmon resonance (OF-SPR) sensors have demonstrated high versatility and performances over the last years, which propelled the technique to the heart of numerous and original biosensing concepts. In this work, we contribute to this effort and present our recent findings about the detection of breast cancer HER2 biomarkers through OF-SPR optrodes. 1 cm-long sections of 400 μm core-diameter optical fibers were covered with a sputtered gold film, yielding enhanced sensitivity to surface refractive index changes. Studying the impacts of the gold film thickness on the plasmonic spectral response, we improved the quality and reproducibility of the sensors. These achievements were correlated in two ways, using both the central wavelengths of the plasmon resonance and its influence on the bulk refractive index sensitivity. Our dataset was fed by additional biosensing experiments with a direct and indirect approach, relying on aptamers and antibodies specifically implemented in a sandwich layout. HER2 biomarkers were specifically detected at 0.6 μg/mL (5.16 nM) in label-free while the amplification with HER2-antibodies provided a nearly hundredfold signal magnification, reaching 9.3 ng/mL (77.4 pM). We believe that these results harbinger the way for their further use in biomedical samples.

Early non-invasive detection of breast cancer using exhaled breath and urine analysis

The main focus of this pilot study is to develop a statistical approach that is suitable to model data obtained by different detection methods. The methods used in this study examine the possibility to detect early breast cancer (BC) by exhaled breath and urine samples analysis. Exhaled breath samples were collected from 48 breast cancer patients and 45 healthy women that served as a control group. Urine samples were collected from 37 patients who were diagnosed with breast cancer based on physical or mammography tests prior to any surgery, and from 36 healthy women. Two commercial electronic noses (ENs) were used for the exhaled breath analysis. Urine samples were analyzed using Gas-Chromatography Mass-Spectrometry (GC-MS). Statistical analysis of results is based on an artificial neural network (ANN) obtained following feature extraction and feature selection processes. The model obtained allows classification of breast cancer patients with an accuracy of 95.2% ± 7.7% using data of one EN, and an accuracy of 85% for the other EN and for urine samples. The developed statistical analysis method enables accurate classification of patients as healthy or with BC based on simple non-invasive exhaled breath and a urine sample analysis. This study demonstrates that available commercial ENs can be used, provided that the data analysis is carried out using an appropriate scheme.

Classification of Breast Masses Using a Computer-Aided Diagnosis Scheme of Contrast Enhanced Digital Mammograms

Contrast-enhanced digital mammography (CEDM) is a promising imaging modality in breast cancer diagnosis. This study aims to investigate how to optimally develop a computer-aided diagnosis (CAD) scheme of CEDM images to classify breast masses. A CEDM dataset of 111 patients was assembled, which includes 33 benign and 78 malignant cases. Each CEDM includes two types of images namely, low energy (LE) and dual-energy subtracted (DES) images. A CAD scheme was applied to segment mass regions depicting on LE and DES images separately. Optimal segmentation results generated from DES images were also mapped to LE images or vice versa. After computing image features, multilayer perceptron based machine learning classifiers that integrate with a correlation-based feature subset evaluator and leave-one-case-out cross-validation method were built to classify mass regions. When applying CAD to DES and LE images with original segmentation, areas under ROC curves (AUC) were 0.759 ± 0.053 and 0.753 ± 0.047, respectively. After mapping the mass regions optimally segmented on DES images to LE images, AUC significantly increased to 0.848 ± 0.038 (p < 0.01). Study demonstrated that DES images eliminated overlapping effect of dense breast tissue, which helps improve mass segmentation accuracy. The study demonstrated that applying a novel approach to optimally map mass region segmented from DES images to LE images enabled CAD to yield significantly improved performance.

Screening of salivary volatiles for putative breast cancer discrimination: an exploratory study involving geographically distant populations

Saliva is possibly the easiest biofluid to analyse and, despite its simple composition, contains relevant metabolic information. In this work, we explored the potential of the volatile composition of saliva samples as biosignatures for breast cancer (BC) non-invasive diagnosis. To achieve this, 106 saliva samples of BC patients and controls in two distinct geographic regions in Portugal and India were extracted and analysed using optimised headspace solid-phase microextraction gas chromatography mass spectrometry (HS-SPME/GC-MS, 2 mL acidified saliva containing 10% NaCl, stirred (800 rpm) for 45 min at 38 °C and using the CAR/PDMS SPME fibre) followed by multivariate statistical analysis (MVSA). Over 120 volatiles from distinct chemical classes, with significant variations among the groups, were identified. MVSA retrieved a limited number of volatiles, viz. 3-methyl-pentanoic acid, 4-methyl-pentanoic acid, phenol and p-tert-butyl-phenol (Portuguese samples) and acetic, propanoic, benzoic acids, 1,2-decanediol, 2-decanone, and decanal (Indian samples), statistically relevant for the discrimination of BC patients in the populations analysed. This work defines an experimental layout, HS-SPME/GC-MS followed by MVSA, suitable to characterise volatile fingerprints for saliva as putative biosignatures for BC non-invasive diagnosis. Here, it was applied to BC samples from geographically distant populations and good disease separation was obtained. Further studies using larger cohorts are therefore very pertinent to challenge and strengthen this proof-of-concept study. Graphical abstract ᅟ.

Surface plasmon resonance biosensor for exosome detection based on reformative tyramine signal amplification activated by molecular aptamer beacon

Human epidermal growth factor receptor 2 (HER2)-positive exosomes play an extremely important role in the diagnosis and treatment options of breast cancers. Herein, based on the reformative tyramine signal amplification (TSA) enabled by molecular aptamer beacon (MAB) conversion, a label-free surface plasmon resonance (SPR) biosensor was proposed for highly sensitive and specific detection of HER2-positive exosomes. The exosomes were captured by the HER2 aptamer region of MAB immobilized on the chip surface, which enabled the exposure of the G-quadruplex DNA (G4 DNA) that could form peroxidase-like G4-hemin. In turn, the formed G4-hemin catalyzed the deposition of plentiful tyramine-coated gold nanoparticles (AuNPs-Ty) on the exosome membrane with the help of H₂O₂, generating a significantly enhanced SPR signal. In the reformative TSA system, the horseradish peroxidase (HRP) as a major component was replaced with nonenzymic G4-hemin, bypassing the defects of natural enzymes. Moreover, the dual-recognition of the surface proteins and lipid membrane of the desired exosomes endowed the sensing strategy with high specificity without the interruption of free proteins. As a result, this developed SPR biosensor exhibited a wide linear range from 1.0 × 10⁴ to 1.0 × 10⁷ particles/mL. Importantly, this strategy was able to accurately distinguish HER2-positive breast cancer patients from healthy individuals, exhibiting great potential clinical application.

A new fruit fly optimization algorithm enhanced support vector machine for diagnosis of breast cancer based on high-level features

BACKGROUND

It is of great clinical significance to develop an accurate computer aided system to accurately diagnose the breast cancer. In this study, an enhanced machine learning framework is established to diagnose the breast cancer. The core of this framework is to adopt fruit fly optimization algorithm (FOA) enhanced by Levy flight (LF) strategy (LFOA) to optimize two key parameters of support vector machine (SVM) and build LFOA-based SVM (LFOA-SVM) for diagnosing the breast cancer. The high-level features abstracted from the volunteers are utilized to diagnose the breast cancer for the first time.

RESULTS

In order to verify the effectiveness of the proposed method, 10-fold cross-validation method is used to make comparison among the proposed method, FOA-SVM (model based on original FOA), PSO-SVM (model based on original particle swarm optimization), GA-SVM (model based on genetic algorithm), random forest, back propagation neural network and SVM. The main novelty of LFOA-SVM lies in the combination of FOA with LF strategy that enhances the quality for FOA, thus improving the convergence rate of the FOA optimization process as well as the probability of escaping from local optimal solution.

CONCLUSIONS

The experimental results demonstrate that the proposed LFOA-SVM method can beat other counterparts in terms of various performance metrics. It can very well distinguish malignant breast cancer from benign ones and assist the doctor with clinical diagnosis.

Deep learning-based segmentation of breast masses in dedicated breast CT imaging: Radiomic feature stability between radiologists and artificial intelligence

A deep learning (DL) network for 2D-based breast mass segmentation in unenhanced dedicated breast CT images was developed and validated, and its robustness in radiomic feature stability and diagnostic performance compared to manual annotations of multiple radiologists was investigated. 93 mass-like lesions were extensively augmented and used to train the network (n = 58 masses), which was then tested (n = 35 masses) against manual ground truth of a qualified breast radiologist with experience in breast CT imaging using the Conformity coefficient (with a value equal to 1 indicating a perfect performance). Stability and diagnostic power of 672 radiomic descriptors were investigated between the computerized segmentation, and 4 radiologists' annotations for the 35 test set cases. Feature stability and diagnostic performance in the discrimination between benign and malignant cases were quantified using intraclass correlation (ICC) and multivariate analysis of variance (MANOVA), performed for each segmentation case (4 radiologists and DL algorithm). DL-based segmentation resulted in a Conformity of 0.85 ± 0.06 against the annotated ground truth. For the stability analysis, although modest agreement was found among the four annotations performed by radiologists (Conformity 0.78 ± 0.03), over 90% of all radiomic features were found to be stable (ICC>0.75) across multiple segmentations. All MANOVA analyses were statistically significant (p ≤ 0.05), with all dimensions equal to 1, and Wilks' lambda ≤0.35. In conclusion, DL-based mass segmentation in dedicated breast CT images can achieve high segmentation performance, and demonstrated to provide stable radiomic descriptors with comparable discriminative power in the classification of benign and malignant tumors to expert radiologist annotation.

An immune-inspired semi-supervised algorithm for breast cancer diagnosis

Breast cancer is the most frequently and world widely diagnosed life-threatening cancer, which is the leading cause of cancer death among women. Early accurate diagnosis can be a big plus in treating breast cancer. Researchers have approached this problem using various data mining and machine learning techniques such as support vector machine, artificial neural network, etc. The computer immunology is also an intelligent method inspired by biological immune system, which has been successfully applied in pattern recognition, combination optimization, machine learning, etc. However, most of these diagnosis methods belong to a supervised diagnosis method. It is very expensive to obtain labeled data in biology and medicine. In this paper, we seamlessly integrate the state-of-the-art research on life science with artificial intelligence, and propose a semi-supervised learning algorithm to reduce the need for labeled data. We use two well-known benchmark breast cancer datasets in our study, which are acquired from the UCI machine learning repository. Extensive experiments are conducted and evaluated on those two datasets. Our experimental results demonstrate the effectiveness and efficiency of our proposed algorithm, which proves that our algorithm is a promising automatic diagnosis method for breast cancer.

A novel cognitive interpretation of breast cancer thermography with complementary learning fuzzy neural memory structure

Early detection of breast cancer is the key to improve survival rate. Thermogram is a promising front-line screening tool as it is able to warn women of breast cancer up to 10 years in advance. However, analysis and interpretation of thermogram are heavily dependent on the analysts, which may be inconsistent and error-prone. In order to boost the accuracy of preliminary screening using thermogram without incurring additional financial burden, Complementary Learning Fuzzy Neural Network (CLFNN), FALCON-AART is proposed as the Computer-Assisted Intervention (CAI) tool for thermogram analysis. CLFNN is a neuroscience-inspired technique that provides intuitive fuzzy rules, human-like reasoning, and good classification performance. Confluence of thermogram and CLFNN offers a promising tool for fighting breast cancer.

Second opinion strategies in breast pathology: a decision analysis addressing over-treatment, under-treatment, and care costs

PURPOSE

To estimate the potential near-term population impact of alternative second opinion breast biopsy pathology interpretation strategies.

METHODS

Decision analysis examining 12-month outcomes of breast biopsy for nine breast pathology interpretation strategies in the U.S. health system. Diagnoses of 115 practicing pathologists in the Breast Pathology Study were compared to reference-standard-consensus diagnoses with and without second opinions. Interpretation strategies were defined by whether a second opinion was sought universally or selectively (e.g., 2nd opinion if invasive). Main outcomes were the expected proportion of concordant breast biopsy diagnoses, the proportion involving over- or under-interpretation, and cost of care in U.S. dollars within one-year of biopsy.

RESULTS

Without a second opinion, 92.2% of biopsies received a concordant diagnosis. Concordance rates increased under all second opinion strategies, and the rate was highest (95.1%) and under-treatment lowest (2.6%) when all biopsies had second opinions. However, over-treatment was lowest when second opinions were sought selectively for initial diagnoses of invasive cancer, DCIS, or atypia (1.8 vs. 4.7% with no 2nd opinions). This strategy also had the lowest projected 12-month care costs ($5.907 billion vs. $6.049 billion with no 2nd opinions).

CONCLUSIONS

Second opinion strategies could lower overall care costs while reducing both over- and under-treatment. The most accurate cost-saving strategy required second opinions for initial diagnoses of invasive cancer, DCIS, or atypia.

A review of optical breast imaging: Multi-modality systems for breast cancer diagnosis

This review of optical breast imaging describes basic physical and system principles and summarizes technological evolution with a focus on multi-modality platforms and recent clinical trial results. Ultrasound-guided diffuse optical tomography and co-registered ultrasound and photoacoustic imaging systems are emphasized as models of state of the art optical technology that are most conducive to clinical translation.

Breast Camps for Awareness and Early Diagnosis of Breast Cancer in Countries With Limited Resources: A Multidisciplinary Model From Kenya

BACKGROUND

Breast cancer is the most common cancer of women in Kenya. There are no national breast cancer early diagnosis programs in Kenya.

OBJECTIVE

The objective was to conduct a pilot breast cancer awareness and diagnosis program at three different types of facilities in Kenya.

METHODS

This program was conducted at a not-for-profit private hospital, a faith-based public hospital, and a government public referral hospital. Women aged 15 years and older were invited. Demographic, risk factor, knowledge, attitudes, and screening practice data were collected. Breast health information was delivered, and clinical breast examinations (CBEs) were performed. When appropriate, ultrasound imaging, fine-needle aspirate (FNA) diagnoses, core biopsies, and onward referrals were provided.

RESULTS

A total of 1,094 women were enrolled in the three breast camps. Of those, 56% knew the symptoms and signs of breast cancer, 44% knew how breast cancer was diagnosed, 37% performed regular breast self-exams, and 7% had a mammogram or breast ultrasound in the past year. Of the 1,094 women enrolled, 246 (23%) had previously noticed a lump in their breast. A total of 157 participants (14%) had abnormal CBEs, of whom 111 had ultrasound exams, 65 had FNAs, and 18 had core biopsies. A total of 14 invasive breast cancers and 1 malignant phyllodes tumor were diagnosed

CONCLUSION

Conducting a multidisciplinary breast camp awareness and early diagnosis program is feasible in different types of health facilities within a low- and middle-income country setting. This can be a model for breast cancer awareness and point-of-care diagnosis in countries with limited resources like Kenya.

IMPLICATIONS FOR PRACTICE

This work describes a novel breast cancer awareness and early diagnosis demonstration program in a low- and middle-income country within a limited resource setting. The program includes breast self-awareness and breast cancer education, clinical exams, and point-of-care diagnostics for women in three different types of health facilities in Kenya. This pilot program has the potential of being replicated on a national scale to create awareness about breast cancer and downstage its presentation.

The Japanese Breast Cancer Society Clinical Practice Guidelines for Breast Cancer Screening and Diagnosis, 2018 Edition

This article updates readers as to what is new in the Japanese Breast Cancer Society Clinical Practice Guidelines for Breast Cancer Screening and Diagnosis, 2018 Edition. Breast cancer screening issues are covered, including matters of breast density and possible supplemental modalities, along with appropriate pre-operative/follow-up diagnostic breast imaging tests. Up-to-date clinical practice guidelines for breast cancer screening and diagnosis should help to provide patients and clinicians with not only evidence-based breast imaging options, but also accurate and balanced information about the benefits and harms of intervention, which ultimately enables shared decision making about imaging test plans.

Multi-parametric MRI lesion heterogeneity biomarkers for breast cancer diagnosis

PURPOSE

To identify intra-lesion imaging heterogeneity biomarkers in multi-parametric Magnetic Resonance Imaging (mpMRI) for breast lesion diagnosis.

METHODS

Dynamic 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.

RESULTS

LASSO 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.

CONCLUSION

Capturing 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.

Clustering-based undersampling with random over sampling examples and support vector machine for imbalanced classification of breast cancer diagnosis

To overcome the two-class imbalanced classification problem existing in the diagnosis of breast cancer, a hybrid of Random Over Sampling Example, K-means and Support vector machine (RK-SVM) model is proposed which is based on sample selection. Random Over Sampling Example (ROSE) is utilized to balance the dataset and further improve the diagnosis accuracy by Support Vector Machine (SVM). As there is one different sample selection factor via clustering that encourages selecting the samples near the class boundary. The purpose of clustering here is to reduce the risk of removing useful samples and improve the efficiency of sample selection. To test the performance of the new hybrid classifier, it is implemented on breast cancer datasets and the other three datasets from the University of California Irvine (UCI) machine learning repository, which are commonly used datasets in class imbalanced learning. The extensive experimental results show that our proposed hybrid method outperforms most of the competitive algorithms in term of G-mean and accuracy indices. Additionally, experimental results show that this method also performs superiorly for binary problems.

Breast MRI: Clinical Indications, Recommendations, and Future Applications in Breast Cancer Diagnosis

PURPOSE OF REVIEW

This article aims to provide an updated overview of the indications for diagnostic breast magnetic resonance imaging (MRI), discusses the available and novel imaging exams proposed for breast cancer detection, and discusses considerations when performing breast MRI in the clinical setting.

RECENT FINDINGS

Breast MRI is superior in identifying lesions in women with a very high risk of breast cancer or average risk with dense breasts. Moreover, the application of breast MRI has benefits in numerous other clinical cases as well; e.g., the assessment of the extent of disease, evaluation of response to neoadjuvant therapy (NAT), evaluation of lymph nodes and primary occult tumor, evaluation of lesions suspicious of Paget's disease, and suspicious discharge and breast implants. Breast cancer is the most frequently detected tumor among women around the globe and is often diagnosed as a result of abnormal findings on mammography. Although effective multimodal therapies significantly decline mortality rates, breast cancer remains one of the leading causes of cancer death. A proactive approach to identifying suspicious breast lesions at early stages can enhance the efficacy of anti-cancer treatments, improve patient recovery, and significantly improve long-term survival. However, the currently applied mammography to detect breast cancer has its limitations. High false-positive and false-negative rates are observed in women with dense breasts. Since approximately half of the screening population comprises women with dense breasts, mammography is often incorrectly used. The application of breast MRI should significantly impact the correct cases of breast abnormality detection in women. Radiomics provides valuable data obtained from breast MRI, further improving breast cancer diagnosis. Introducing these constantly evolving algorithms in clinical practice will lead to the right breast detection tool, optimized surveillance program, and individualized breast cancer treatment.

A knowledge-driven feature learning and integration method for breast cancer diagnosis on multi-sequence MRI

BACKGROUND

The classification of benign versus malignant breast lesions on multi-sequence Magnetic Resonance Imaging (MRI) is a challenging task since breast lesions are heterogeneous and complex. Recently, deep learning methods have been used for breast lesion diagnosis with raw image input. However, without the guidance of domain knowledge, these data-driven methods cannot ensure that the features extracted from images are comprehensive for breast cancer diagnosis. Specifically, these features are difficult to relate to clinically relevant phenomena.

PURPOSE

Inspired by the cognition process of radiologists, we propose a Knowledge-driven Feature Learning and Integration (KFLI) framework, to discriminate between benign and malignant breast lesions using Multi-sequences MRI.

METHODS

Starting from sequence division based on characteristics, we use domain knowledge to guide the feature learning process so that the feature vectors of sub-sequence are constrained to lie in characteristic-related semantic space. Then, different deep networks are designed to extract various sub-sequence features. Furthermore, a weighting module is employed for the integration of the features extracted from different sub-sequence images adaptively.

RESULTS

The KFLI is a domain knowledge and deep network ensemble, which can extract sufficient and effective features from each sub-sequence for a comprehensive diagnosis of breast cancer. Experiments on 100 MRI studies have demonstrated that the KFLI achieves sensitivity, specificity, and accuracy of 84.6%, 85.7% and 85.0%, respectively, which outperforms other state-of-the-art algorithms.

False-positive reduction in computer-aided mass detection using mammographic texture analysis and classification

BACKGROUND AND OBJECTIVE

The aim of computer-aided-detection (CAD) systems for mammograms is to assist radiologists by marking region of interest (ROIs) depicting abnormalities. However, the confusing appearance of some normal tissues that visually look like masses results in a large proportion of marked ROIs with normal tissues. This paper copes with this problem and proposes a framework to reduce false positive masses detected by CAD.

METHODS

To avoid the error induced by the segmentation step, we proposed a segmentation-free framework with particular attention to improve feature extraction and classification steps. We investigated for the first time in mammogram analysis, Hilbert's image representation, Kolmogorov-Smirnov distance and maximum subregion descriptors. Then, a feature selection step is performed to select the most discriminative features. Moreover, we considered several classifiers such as Random Forest, Support Vector Machine and Decision Tree to distinguish between normal tissues and masses. Our experiments were carried out on a large dataset of 10168 ROIs (8254 normal tissues and 1914 masses) constructed from the Digital Database for Screening Mammography (DDSM). To simulate practical scenario, our normal regions are false positives asserted by a CAD system from healthy cases.

RESULTS

The combination of all the descriptors yields better results than each feature set used alone, and the difference is statistically significant. Besides, the feature selection steps yields a statistically significant increase in the accuracy values for the three classifiers. Finally, the random forest achieves the highest accuracy (81.09%), outperforming the SVM classifier (80.01%)) and decision tree (79.12%), but the difference is not statistically significant.

CONCLUSIONS

The accuracy of discrimination between normal and abnormal ROIs in mammograms obtained with the proposed gray level texture features sets are encouraging and comparable to these obtained with multiresolution features. Combination of several features as well as feature selection steps improve the results. To improve false positives reduction in CAD systems for breast cancer diagnosis, these features could be combined with multiresolution features.

Clinical impact of LncRNA XIST and LncRNA NEAT1 for diagnosis of high-risk group breast cancer patients

Long noncoding RNAs (lncRNAs) are evolving as contributing biomarkers for many diseases. Among these lncRNAs, X inactive-specific transcript (XIST), and nuclear paraspeckle assembly transcript 1 (NEAT1) were studied as undesirable upregulated nucleic acid markers for unfavorable prognosis of cancer. The authors aimed to investigate their role as diagnostic markers for breast cancer (BC) patients with high-risk factors. Serum samples were obtained from BC patients (n = 121), patients with benign breast lesions (n = 35), and healthy volunteers (n = 22). Assessment of lncRNA XIST, and lncRNA NEAT1 expression was performed using real time PCR. Expression levels of the investigated lncRNAs were significantly higher in BC patients as compared to the other groups. Both lncRNAs were significantly correlated with BC laterality, lymph node involvement, and clinical stages. LncRNA NEAT1 reported a significant aberrant expression with pathological types, histological grading and, hormonal status. The sensitivity of lncRNA NEAT1 was superior for detection of BC with high risk-factors as compared to lncRNA XIST. In conclusion, the detection of lncRNAs in body fluids has demonstrated a significant importance for detecting BC patients with high-risk factors, and was related to hormonal receptors, thus may be used for determining the direction of treatment strategy.

Hybrid high-definition microvessel imaging/shear wave elastography improves breast lesion characterization

BACKGROUND

Low specificity in current breast imaging modalities leads to increased unnecessary follow-ups and biopsies. The purpose of this study is to evaluate the efficacy of combining the quantitative parameters of high-definition microvasculature imaging (HDMI) and 2D shear wave elastography (SWE) with clinical factors (lesion depth and age) for improving breast lesion differentiation.

METHODS

In this prospective study, from June 2016 through April 2021, patients with breast lesions identified on diagnostic ultrasound and recommended for core needle biopsy were recruited. HDMI and SWE were conducted prior to biopsies. Two new HDMI parameters, Murray's deviation and bifurcation angle, and a new SWE parameter, mass characteristic frequency, were included for quantitative analysis. Lesion malignancy prediction models based on HDMI only, SWE only, the combination of HDMI and SWE, and the combination of HDMI, SWE and clinical factors were trained via elastic net logistic regression with 70% (360/514) randomly selected data and validated with the remaining 30% (154/514) data. Prediction performances in the validation test set were compared across models with respect to area under the ROC curve as well as sensitivity and specificity based on optimized threshold selection.

RESULTS

A total of 508 participants (mean age, 54 years ± 15), including 507 female participants and 1 male participant, with 514 suspicious breast lesions (range, 4-72 mm, median size, 13 mm) were included. Of the lesions, 204 were malignant. The SWE-HDMI prediction model, combining quantitative parameters from SWE and HDMI, with AUC of 0.973 (95% CI 0.95-0.99), was significantly higher than the result predicted with the SWE model or HDMI model alone. With an optimal cutoff of 0.25 for the malignancy probability, the sensitivity and specificity were 95.5% and 89.7%, respectively. The specificity was further improved with the addition of clinical factors. The corresponding model defined as the SWE-HDMI-C prediction model had an AUC of 0.981 (95% CI 0.96-1.00).

CONCLUSIONS

The SWE-HDMI-C detection model, a combination of SWE estimates, HDMI quantitative biomarkers and clinical factors, greatly improved the accuracy in breast lesion characterization.

An effective approach for breast cancer diagnosis based on routine blood analysis features

Breast cancer is a widespread disease and one of the primary causes of cancer mortality among women all over the world. Computer-aided methods are used to assist medical doctors to make early diagnosis of the disease. The aim of this study is to build an effective prediction model for breast cancer diagnosis based on anthropometric data and parameters collected through routine blood analysis. The proposed approach innovatively exploits principal component analysis (PCA) technique cascaded by median filtering so as to transform original features into a form of containing less distractive noise not to cause overfitting. Since a generalized regression neural network (GRNN) model is adopted to classify patterns of the transformed features, the computational load imposed in the training of artificial neural network model is kept minimized thanks to the non-iterative nature of GRNN training. The proposed method has been devised and tested on the recent Breast Cancer Coimbra Dataset (BCCD) that contains 9 clinical features measured for each of 116 subjects. Outperforming all of the existing studies on BCCD, our method achieved a mean accuracy rate of 0.9773. Experimental results evidence that this study achieves the best prediction performance ever reported on this dataset. The fact that our proposed approach has accomplished such a boosted performance of breast cancer diagnosis based on routine blood analysis features offers a great potential to be used in a widespread manner to detect the disease in its inception phase. Graphical abstract.

Breaking bad news of a breast cancer diagnosis over the telephone: an emerging trend

PURPOSE

This study evaluated how breast cancer diagnoses were shared with patients.

METHODS

Current members of the Dr. Susan Love Research Foundation's Army of Women cohort were sent one email with a link to a survey assessing how their breast cancer diagnosis was communicated, a description of their support system during treatment, basic demographic information, and breast cancer diagnosis details.

RESULTS

Participants (n = 2896) were more likely to be given their diagnosis over the telephone in more recent years (OR 1.07, 95% CI 1.06-1.08). Up until about 10 years ago (1967-2006), breast cancer diagnoses were communicated in person more often than by telephone. Since 2006, more than half of participants learned about their diagnosis over the telephone. From 2015 to 2017, almost 60% of participants learned about their diagnosis over the telephone. Among those who heard the news in person, a steady 40% were alone. Characteristics of those who received the news over the telephone included having identified support members, heterosexual identity, and a diagnosis of in situ breast cancer.

CONCLUSIONS

Receiving a telephone call about breast cancer diagnosis may be the norm rather than the exception in health care today. Trends in practice, as well as current best practices based primarily on expert opinion, may not provide optimal care for women diagnosed with breast cancer. Patient outcome research to guide future practice, such as the impact of modes of delivery of bad news, is urgently needed to determine appropriate patient-centered approaches for notification of breast cancer diagnoses.

Rates and indications for surgical breast biopsies in a community-based health system

BACKGROUND

High rates of surgical breast biopsies in community hospitals have been reported but may misrepresent actual practice.

METHODS

Patient-level data from 5,757 women who underwent breast biopsies in a large integrated health system were evaluated to determine biopsy types, rates, indications, and diagnoses.

RESULTS

Between 2008 and 2010, 6,047 breast biopsies were performed on 5,757 women. Surgical biopsy was the initial diagnostic procedure in 16% (n = 942) of women overall and in 6% (72 of 1,236) of women with newly diagnosed invasive breast cancer. Invasive breast cancer was diagnosed in 72 women (8%) undergoing surgical biopsy compared with 1,164 (24%) undergoing core needle biopsy (P < .001, age adjusted). Main indications for surgical biopsies included symptomatic abnormalities, technical challenges, and patient choice.

CONCLUSIONS

Surgical biopsy was the initial diagnostic procedure in 16% of women with breast abnormalities, comparable with rates at academic centers. Rates could be improved by more careful consideration of indications.

Automation of immunohistochemical evaluation in breast cancer using image analysis

AIM: To automate breast cancer diagnosis and to study the inter-observer and intra-observer variations in the manual evaluations.

METHODS: Breast tissue specimens from sixty cases were stained separately for estrogen receptor (ER), progesterone receptor (PR) and human epidermal growth factor receptor-2 (HER-2/neu). All cases were assessed by manual grading as well as image analysis. The manual grading was performed by an experienced expert pathologist. To study inter-observer and intra-observer variations, we obtained readings from another pathologist as the second observer from a different laboratory who has a little less experience than the first observer. We also took a second reading from the second observer to study intra-observer variations. Image analysis was carried out using in-house developed software (TissueQuant). A comparison of the results from image analysis and manual scoring of ER, PR and HER-2/neu was also carried out.

RESULTS: The performance of the automated analysis in the case of ER, PR and HER-2/neu expressions was compared with the manual evaluations. The performance of the automated system was found to correlate well with the manual evaluations. The inter-observer variations were measured using Spearman correlation coefficient r and 95% confidence interval. In the case of ER expression, Spearman correlation r = 0.53, in the case of PR expression, r = 0.63, and in the case of HER-2/neu expression, r = 0.68. Similarly, intra-observer variations were also measured. In the case of ER, PR and HER-2/neu expressions, r = 0.46, 0.66 and 0.70, respectively.

CONCLUSION: The automation of breast cancer diagnosis from immunohistochemically stained specimens is very useful for providing objective and repeatable evaluations.