Accurate Diagnosis Of Breast Cancer Research Articles

Clinical value of color Doppler ultrasound combined with serum CA153, CEA and TSGF detection in the diagnosis of breast cancer.

In the present retrospective study, the clinical value of color Doppler ultrasound combined with the detection of the serum tumor markers carbohydrate antigen 153 (CA153), carcinoembryonic antigen (CEA) and tumor specific growth factor (TSGF) as diagnostic tools for breast cancer was investigated. A total of 103 patients with breast cancer and 50 patients with benign breast lesions were enrolled in the study. All patients were examined by color Doppler ultrasonography. Electrochemiluminescence was used to measure the expression levels of CA153 and CEA, and chemical colorimetric assay for the measurement of TSGF expression. The differences in mass boundary, morphology, internal echo, calcification, peak blood flow velocity (Vmax), resistance index (RI), pulsatility index (PI) and blood flow signal classification between the two groups were statistically significant (P<0.05). The expression levels of CA153, CEA and TSGF in the serum of patients in the breast cancer group were significantly higher than those in the benign lesion group (P<0.01). In the breast cancer group, CA153, CEA and TSGF expression levels were significantly higher in patients with high-stage cancer and recurrence, compared with the patients with low-stage cancer and no recurrence. The sensitivity, accuracy and negative predictive value of the combined detection were significantly improved compared with those of the single tests (P<0.01). Color Doppler ultrasound combined with the detection of CA153, CEA and TSGF levels in the serum of patients can be used as an effective tool that can improve the accuracy of breast cancer diagnosis leading to early diagnosis and clinical intervention.

Fluorescence imaging and Raman spectroscopy applied for the accurate diagnosis of breast cancer with deep learning algorithms.

Deep learning is usually combined with a single detection technique in the field of disease diagnosis. This study focused on simultaneously combining deep learning with multiple detection technologies, fluorescence imaging and Raman spectroscopy, for breast cancer diagnosis. A number of fluorescence images and Raman spectra were collected from breast tissue sections of 14 patients. Pseudo-color enhancement algorithm and a convolutional neural network were applied to the fluorescence image processing, so that the discriminant accuracy of test sets, 88.61%, was obtained. Two different BP-neural networks were applied to the Raman spectra that mainly comprised collagen and lipid, so that the discriminant accuracy of 95.33% and 98.67% of test sets were gotten, respectively. Then the discriminant results of fluorescence images and Raman spectra were counted and arranged into a characteristic variable matrix to predict the breast tissue samples with partial least squares (PLS) algorithm. As a result, the predictions of all samples are correct, with minor error of predictive value. This study proves that deep learning algorithms can be applied into multiple diagnostic optics/spectroscopy techniques simultaneously to improve the accuracy in disease diagnosis.

Abstract PD9-03: A combination of intra- and peri-lesional deep learning classifiers from multiple views enables accurate diagnosis of architectural distortion malignancy with digital breast tomosynthesis

Abstract Background: 3D digital breast tomosynthesis (DBT) offers greater sensitivity than 2D mammography to the presence of architectural distortions (AD), a suspicious finding requiring biopsy. This higher sensitivity to AD is only beneficial if DBT can differentiate benign AD, such as radial scars (RS) from malignant AD (MAD). Automated analysis of clinical images using a neural network has potential to enhance the accuracy of breast cancer diagnosis, but such applications focus on screening and currently struggle with more challenging diagnoses (e.g. MAD vs. RS) where computer assistance would provide great clinical utility. In this work, we define a deep learning (DL) framework utilizing amalgamate predictions from a group of neural networks, specialized for multiple lesion regions and different acquisitional views to distinguish MAD from RS. Methods: A retrospective analysis was conducted of 69 patients screened at a single institution, each with AD visible on one or more DBT views. Stereotactic core biopsy determined 42 AD to be MAD and the remaining 27 to be RS. An attending breast radiologist manually identified a circular region of interest (ROI) containing the AD on a single slice of the mediolateral (ML, n=72) and/or craniocaudal (CC, n=68) views. 56 patients were utilized for training and tuning the DL networks in cross-validation, while 25 volumes from 13 patients (8 MAD, 5 RS) were held for independent testing. Volumetric samples of size 24x24x12 pixels were extracted randomly within each ROI for input to the networks. Two neural networks were trained to separately recognize patterns of MAD at the intra- and peri-lesional region. Pairs of networks were trained separately for analysis of the CC and the MLO view, resulting in 4 possible network variations. These networks were first assessed individually by cross-validation in the training set, then predictions from each were combined for diagnosis in the independent testing set. Performance was assessed by area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy. Results: All networks individually achieved strong performance in distinguishing RS from MAD when assessed via cross-validation in the training set. On the independent test set, networks trained to recognize patterns of malignancy at the center of the distortion outperformed those focused on the lesion margin. The CC view was found to be most discriminating in neural network assessment. Independent Test PerformanceNetwork TypeAUCSensitivitySpecificityIntralesional, CC0.650.800.50Perilesional, CC0.510.400.63Intralesional, ML0.490.600.38Perilesional, ML0.550.600.50Combined Performance0.800.601.0 When predictions from these networks were combined for diagnosis on the independent validation set, performance increased significantly to an AUC of 0.8, with a sensitivity of 0.6 and a specificity of 1.0. Conclusions: In this investigation, we demonstrated that specialized deep learning classifiers, created to address the diagnosis of MAD vs RS, can assist in diagnostic settings without generating false negatives. Our approach combines neural networks to make a diagnosis based on various spatial regions from multiple DBT views. Our approach demonstrated very high specificity which may reduce the number of benign RS biopsies and surgical excisions for AD detected by DBT. Future work will further validate these findings on a larger, multi-institutional cohort and explore their influence on clinical decision-making. Citation Format: Tristan Maidment, Nathaniel Braman, Yijiang Chen, Farhad Mehrkhani, Uliyana Yankevich, Donna Plecha, Anant Madabhushi. A combination of intra- and peri-lesional deep learning classifiers from multiple views enables accurate diagnosis of architectural distortion malignancy with digital breast tomosynthesis [abstract]. In: Proceedings of the 2019 San Antonio Breast Cancer Symposium; 2019 Dec 10-14; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2020;80(4 Suppl):Abstract nr PD9-03.

Fully automated scheme for computer‐aided detection and breast cancer diagnosis using digitised mammograms

Breast cancer becomes a significant public health problem in the world. During the early detection of breast cancer, it is a very challenging task to classify accurately the benign–malignant patterns in digital mammograms. This study proposes a new fully automated computer-aided diagnosis (CAD) system for breast cancer diagnosis with high-accuracy and low-computational requirements. The expectation–maximisation algorithm is investigated to extract automatically the region of interests (ROIs) within mammograms. The standard shape, statistical, and textural features of ROIs are extracted and combined with multi-resolution and multi-orientation features derived from a new feature extraction technique based on wavelet-based contourlet transform. A hybrid feature selection approach based on combining the support vector machine recursive feature elimination with correlation bias reduction algorithm is proposed. Also, the authors investigate a new similarity-based learning algorithm, called Q, for benign–malignant classification. The proposed CAD system is applied to real clinical mammograms, and the experimental results demonstrate the superior performance of the proposed CAD system over other existing CAD systems in terms of accuracy 98.16%, sensitivity 98.63%, specificity 97.80%, and computational time 2.2 s. This reveals the effectiveness of the proposed CAD system in improving the accuracy of breast cancer diagnosis in real-time systems.

Breast Mass Classification Using eLFA Algorithm Based on CRNN Deep Learning Model

Breast cancer is known to be common in many developed countries. It is reported as the most common type of cancer in the US, affecting one in eight women. In Korea, thyroid cancer is the most common type of cancer, followed by breast cancer in women. Considering this, early detection and accurate diagnosis of breast cancer are crucial for reducing the associated death rate. Recently, cancer diagnosis systems using medical images have attracted significant attention. Medical imaging methods, such as computed tomography and magnetic resonance imaging, can reveal the overall shape, heterogeneity, and growth speed of carcinoma and are, thus, more commonly employed for diagnoses. Medical imaging has gained popularity since a recent study identified that it could reflect the gene phenotype of a patient. However, an aided diagnosis system based on medical images requires high-specification equipment to analyze high-resolution data. Therefore, this article proposes an edge extraction algorithm and a modified convolutional recurrent neural network (CRNN) model to accurately assess breast cancer based on medical imaging. The proposed algorithm extracts line-segment information from a breast mass image. The extracted line segments were classified into 16 types. Each type was uniquely labeled and compressed. The image compressed in this process was used as the input for the modified CRNN model. Traditional deep learning models were used to evaluate the performance of the proposed algorithm. The results show that the proposed model had the highest accuracy and lowest loss (99.75% and 0.0257, respectively).

Enhancement Of Breast Cancer Diagnosis Accuracy With Deep Learning

Breast cancer is a highly fatal disease that is very prevalent among the female population. In this study, a new type of approach is proposed with the aim of improving the accuracy of breast cancer diagnosis, an important problem of our present time, by means of deep learning, one of the techniques in machine learning. In the designed method, the original data set of Breast Cancer Wisconsin being available in the Irvine Machine Learning Repository of University of California was used. Within this data set, there were 699 data consisting of 10 independent variables and 1 dependent variable. The complete utilization of the entire data set was ensured by correction of 16 incorrect data. A normalization process was applied in the data set for the purpose of reducing the time required for learning process. The used data set was allocated as 80% for training, 10% for validation, and 10% for testing. An artificial neural network was designed for the deep learning model. The neural network was set up of a total of 5 layers which were an input layer with 10 neurons, 3 hidden layers with 1000 neurons for each layer, and an output layer with 3 neurons. The software, developed for implementation was written by using Spyder which is an interactive development environment for Python programming language. In addition, Keras neural network API was used. The performance of the model was evaluated with Confusion Matrix and ROC (Receiver Operating Characteristic) analysis. According to the test data obtained at the end of the training, it was observed that the implemented model provided successful results. It is considered that the proposed method will contribute to the improvement of breast cancer diagnosis accuracy.

Propagation-based x-ray phase-contrast tomography of mastectomy samples using synchrotron radiation.

Propagation-based phase-contrast computed tomography (PB-CT) is a method for three-dimensional x-ray imaging that utilizes refraction, as well as absorption, of x rays in the tissues to increase the signal-to-noise ratio (SNR) in the resultant images, in comparison with equivalent conventional absorption-only x-ray tomography (CT). Importantly, the higher SNR is achieved without sacrificing spatial resolution or increasing the radiation dose delivered to the imaged tissues. The present work has been carried out in the context of the current development of a breast CT imaging facility at the Australian Synchrotron. Seven unfixed complete mastectomy samples with and without breast cancer lesions have been imaged using absorption-only CT and PB-CT techniques under controlled experimental conditions. The radiation doses delivered to the mastectomy samples during the scans were comparable to those approved for mammographic screening. Physical characteristics of the reconstructed images, such as spatial resolution and SNR, have been measured and compared with the results of the radiological quality assessment of the complete absorption CT and PB-CT image stacks. Despite the presence of some image artefacts, the PB-CT images have outperformed comparable absorption CT images collected at the same radiation dose, in terms of both the measured objective image characteristics and the radiological image scores. The outcomes of these experiments are shown to be consistent with predictions of the theory of PB-CT imaging and previous reported experimental studies of this imaging modality. The results presented in this paper demonstrate that PB-CT holds a high potential for improving on the quality and diagnostic value of images obtained using existing medical x-ray technologies, such as mammography and digital breast tomosynthesis (DBT). If implemented at suitable synchrotron imaging facilities, PB-CT can be used to complement existing imaging modalities, leading to more accurate breast cancer diagnosis.

Improving the performance of support-vector machine by selecting the best features by Gray Wolf algorithm to increase the accuracy of diagnosis of breast cancer

One of the most common diseases among women is breast cancer, the early diagnosis of which is of paramount importance. Given the time-consuming nature of the diagnosis process of the disease, using new methods such as computer science is extremely important for early detection of the condition. Today, the main emphasis is on the science of data mining as one of the computer methods in the field of diagnosis. In the present study, we used data mining as a combination of feature selection method by Gray Wolf Optimization (GWO) and support vector machine (SVM), which is a new technique with high accuracy compared to other methods in this classification, to increase the accuracy of breast cancer diagnosis. The UCI dataset and functional parameters and various statistical criteria were applied to evaluate the proposed method and assess the validity of the results in MATLAB, respectively. Application of the proposed method increased the improvement of the evaluated criteria, which increased the accuracy of diagnosis by 27.68%, compared to former works in the field. As such, it could be concluded that the proposed method had a higher ability to diagnose breast cancer, compared to previous techniques.

CWV-BANN-SVM ensemble learning classifier for an accurate diagnosis of breast cancer

This paper presents a new data mining technique for an accurate prediction of breast cancer (BC), which is one of the major mortality causes among women around the globe. The main objective of our study is to expand an automatic expert system (ES) to provide an accurate diagnosis of BC. Both, Support Vector Machines (SVMs) and Artificial Neural Networks (ANNs) were applied to analyze BC data. The well-known Wisconsin Breast Cancer Dataset (WBCD), available in the UCI repository, was examined in our study. We first tested the SVM algorithm using various values of the C, ɛ and γ parameters. As a result of the first experiment, we were able to observe that the adjustment of these regularization parameters can greatly improve the performance of the traditional SVM algorithm applied for BC detection. The highest obtained accuracy at the first step was 99.71%. Then, we performed a new BC detection approach based on two ensemble learning techniques: the confidence-weighted voting method and the boosting ensemble technique. Our model, called CWV-BANNSVM, combines boosting ANNs (BANN) and two SVMs, using optimal parameters selected during the first experiment. The performance of the applied methods was evaluated using several popular metrics, such as specificity, sensitivity, precision, FPR, FNR, F1 score, AUC, Gini and accuracy. The proposed CWV-BANNSVM model was able to improve the performance of the traditional machine learning algorithms applied to BC detection, reaching the accuracy of 100%. To overcome the overfitting issue, we determined and used some appropriate parameter values of polynomial SVM. Our comparison with the existing studies dedicated to BC prediction suggests that the proposed CWV-BANN-SVM model provides one of the best prediction performances overall.

Machine Learning Classification Techniques for Breast Cancer Diagnosis

Breast cancer is one of the most widely spread disease and the second leading cause of cancer death among women. Breast cancer starts when malignant lumps which are cancerous begin to grow from the breast cells. Doctors may wrongly diagnose benign tumor (which is non-cancerous) as malignant tumor. There is need for a computer aided detection (CAD) systems which uses machine learning approach to provide accurate diagnosis of breast cancer. These CAD systems can aid in detecting breast cancer at an early stage. When, breast cancer is detected early enough, the survival rate increases because better treatment can be provided. This paper aims at investigating Support Vector Machine (using radial basis kernel), Artificial Neural Networks and Naïve Bayes using the Wisconsin Diagnostic Breast Cancer (WDBC) Dataset. The focus of this paper is to integrate these machine learning techniques with feature selection/feature extraction methods and compare their performances to identify the most suitable approach. The goal is combining the advantages of dimensionality reduction and machine learning. This paper proposed a hybrid approach for breast cancer diagnosis by reducing the high dimensionality of features using linear discriminant analysis (LDA), and then applying the new reduced feature dataset to Support Vector Machine. The proposed approach obtained an accuracy of 98.82%, sensitivity of 98.41%, specificity of 99.07% and area under the receiver operating characteristic curve of 0.9994.

Cancer Diagnostics: Quantitative and Specific Detection of Exosomal miRNAs for Accurate Diagnosis of Breast Cancer Using a Surface‐Enhanced Raman Scattering Sensor Based on Plasmonic Head‐Flocked Gold Nanopillars (Small 17/2019)

Cancer Diagnostics: Quantitative and Specific Detection of Exosomal miRNAs for Accurate Diagnosis of Breast Cancer Using a Surface‐Enhanced Raman Scattering Sensor Based on Plasmonic Head‐Flocked Gold Nanopillars (Small 17/2019)

Quantitative and Specific Detection of Exosomal miRNAs for Accurate Diagnosis of Breast Cancer Using a Surface-Enhanced Raman Scattering Sensor Based on Plasmonic Head-Flocked Gold Nanopillars.

MicroRNAs in exosomes (exosomal miRNAs) have attracted increased attention as cancer biomarkers for early diagnosis and prognosis owing to their stability in body fluids. Since strong association exists between exosomal miRNA expression levels and breast cancer, the development of effective methods that can monitor exosomal miRNA expression both over broad concentration ranges and in ultralow amounts is critical. Here, a surface-enhanced Raman scattering (SERS)-based sensing platform is developed for the quantitative determination of exosomal miRNAs. Ultrasensitive exosomal miRNA detection with single-nucleotide specificity is obtained from enhanced SERS signals from a uniform plasmonic head-flocked gold nanopillar substrate, which generates multiple hotspots and enables hybridization between short oligonucleotides, i.e., miRNAs and locked nucleic acid probes. The proposed SERS sensor shows an extremely low detection limit without any amplification process, a wide dynamic range (1 am to 100 nm), multiplex sensing capability and sound miRNA recovery in serum. Furthermore, this sensor allows reliable observation of exosomal miRNA expression patterns from breast cancer cell lines and can discriminate breast cancer subtype based on the difference between these patterns. The results suggest that this sensor can be used for universal cancer diagnosis and further biomedical applications through the quantitative measurement of exosomal miRNAs in bodily fluids.

Abstract P6-01-02: Machine learning-based structural analysis and oxygen saturation measurement of tumor-associated vessels in breast cancer using a photoacoustic tomography system

Abstract Introduction Breast cancer induces angiogenesis, one of the primary factors responsible for tumor progression. Therefore, the ability to visualize angiogenesis at a higher resolution is crucial. Photoacoustic tomography is a noninvasive method of visualizing angiogenesis involving light absorption and ultrasonic wave emission. If the irradiation light wavelength is adjusted for hemoglobin, vascular imaging is possible. Furthermore, using two wavelengths for oxidized and reduced hemoglobin, “S-factor,” can be calculated, which nearly corresponds to oxygen saturation. Therefore, photoacoustic imaging allows the assessment of breast lesions from vascular structural and functional viewpoints. Objectives This study aimed to demonstrate the possible utility of photoacoustic tomography for clinical application focusing on the morphologic features and oxygen saturation status of breast tumor-related vessels. Methods For the morphological analysis, we applied a machine learning-based method for automatic vessel extraction, and for the functional analysis we evaluated hemoglobin oxygen saturation calculating signals obtained at two wavelengths. In our system, a 3D ultrasound image was simultaneously acquired as a volume image of a tumor, which helped analyze the positional relationship between the vessels and the tumor. Results On morphological analysis, the fine structure of tumor-related vessels was rendered in high resolution. In our system, the blood vessels branched toward the tumor 2-3 more times more frequently than observed on contrast-enhanced MRI, illustrating a finer level of blood vessels near the tumor on our system than on MRI. Next, we analyzed the six morphologic features of vessels (radius, volume, curvature, contraction, maximum angle and vessel branch number) that are associated with the pathologic condition in neuroscience. We determined that the feature distribution of vessels located close to the tumor differed from that located away from the tumor. For example, vessels near the tumor had higher curvature, which means they are more tortuous than healthy vessels. The difference in the distribution of all six features was statistically significant on the Kolmogorov-Smirnov test. On functional analysis, S-factor measurement of the healthy human breast demonstrated clearly demarcated arteries and veins. The S-factor of any artery was nearly 100%, while that of the veins inside the breast cancer tended to be a little higher (approximately 5%) compared to that in the healthy part. This tendency of veins was not recognized in benign tumors. This could show arteriovenous shunt in cancer microenvironment. We found low saturation signals emerging in the tumor tissue following bevacizumab-containing chemotherapy, indicating the possibility that our system reveals microenvironment changes. Discussion If our system can identify the structure or oxygen saturation characteristics unique to tumor-associated vasculature, it could contribute to the improved accuracy of breast cancer diagnosis and allow the observation of tumor vessel normalization because of the drug treatment. An earlier grasp of the therapeutic effect could lead to the provision of individualized medicine. Citation Format: Matsumoto Y, Gu L, Bise R, Asao Y, Sekiguchi H, Yoshikawa A, Ishii T, Takada M, Kataoka M, Sakurai T, Yagi T, Sato I, Togashi K, Shiina T, Toi M. Machine learning-based structural analysis and oxygen saturation measurement of tumor-associated vessels in breast cancer using a photoacoustic tomography system [abstract]. In: Proceedings of the 2018 San Antonio Breast Cancer Symposium; 2018 Dec 4-8; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2019;79(4 Suppl):Abstract nr P6-01-02.

Computer-aided diagnosis system for breast ultrasound images using deep learning

Introduction Ultrasonography has been recommended as an adjunctive modality to mammography, which is insufficient for accurate diagnosis of breast cancer in women with dense breast tissue. However, ultrasonography has the disadvantage of being operator dependent, requiring proficiency in reading ultrasound (US) images and increasing the false positive rate. To overcome these problems, we aimed to develop a computer-aided diagnosis (CAD) system for classification of breast malignant and benign masses on ultrasonography based on the convolutional neural network (CNN), a state-of-the-art deep learning technique. Methods From a large ultrasound (US) image database, managed by Japan Association of Breast and Thyroid Sonology (JABTS), we collected images of 1536 breast masses (897 malignant and 639 benign) confirmed by pathological examinations, with each breast mass captured from various angles using the US imaging probe. We constructed an ensemble network by combining two CNN models (VGG192 and ResNe1523) fine-tuned on balanced training data with the data augmentation which is a popular technique for synthetically generating new samples from the original and used the mass level classification method enabling the CNN to classify a given mass using all views. We explored the grounds of classification by generating a heatmap capable of presenting important regions used by the CNN for classification in humans. Results On an independent 154 test masses (77 malignant and 77 benign), our network showed outstanding classification performance with a sensitivity of 90.9%, a specificity of 87.0%, and an AUC of 0.951 compared with the two CNN models. In addition, our study indicated that not only breast masses but also surrounding tissues are important regions for correct classification. Conclusion This CNN-based CAD system is expected to assist doctors from the viewpoint of second opinion and improve the diagnosis of breast cancer in clinical practice.

Discriminative Pattern Mining for Breast Cancer Histopathology Image Classification via Fully Convolutional Autoencoder

Accurate diagnosis of breast cancer in histopathology images is challenging due to the heterogeneity of cancer cell growth as well as of a variety of benign breast tissue proliferative lesions. In this paper, we propose a practical and self-interpretable invasive cancer diagnosis solution. With minimum annotation information, the proposed method mines contrast patterns between normal and malignant images in unsupervised manner and generates a probability map of abnormalities to verify its reasoning. Particularly, a fully convolutional autoencoder is used to learn the dominant structural patterns among normal image patches. Patches that do not share the characteristics of this normal population are detected and analyzed by one-class support vector machine and 1-layer neural network. We apply the proposed method to a public breast cancer image set. Our results, in consultation with a senior pathologist, demonstrate that the proposed method outperforms existing methods. The obtained probability map could benefit the pathology practice by providing visualized verification data and potentially leads to a better understanding of data-driven diagnosis solutions.

A New Knowledge-Based System for Diagnosis of Breast Cancer by a combination of the Affinity Propagation and Firefly Algorithms

Breast cancer has become a widespread disease around the world in young women. Expert systems, developed by data mining techniques, are valuable tools in diagnosis of breast cancer and can help physicians for decision making process. This paper presents a new hybrid data mining approach to classify two groups of breast cancer patients (malignant and benign). The proposed approach, AP-AMBFA, consists of two phases. In the first phase, the Affinity Propagation (AP) clustering method is used as instances reduction technique which can find noisy instance and eliminate them. In the second phase, feature selection and classification are conducted by the Adaptive Modified Binary Firefly Algorithm (AMBFA) for selection of the most related predictor variables to target variable and Support Vectors Machine (SVM) technique as classifier. It can reduce the computational complexity and speed up the data mining process. Experimental results on Wisconsin Diagnostic Breast Cancer (WDBC) datasets show higher predictive accuracy. The obtained classification accuracy is 98.606%, a very promising result compared to the current state-of-the-art classification techniques applied to the same database. Hence this method will help physicians in more accurate diagnosis of breast cancer.

Multiparametric MRI model with dynamic contrast‐enhanced and diffusion‐weighted imaging enables breast cancer diagnosis with high accuracy

BackgroundThe MRI Breast Imaging‐Reporting and Data System (BI‐RADS) lexicon recommends that a breast MRI protocol contain T2‐weighted and dynamic contrast‐enhanced (DCE) MRI sequences. The addition of diffusion‐weighted imaging (DWI) significantly improves diagnostic accuracy. This study aims to clarify which descriptors from DCE‐MRI, DWI, and T2‐weighted imaging are most strongly associated with a breast cancer diagnosis.Purpose/HypothesisTo develop a multiparametric MRI (mpMRI) model for breast cancer diagnosis incorporating American College of Radiology (ACR) BI‐RADS recommended descriptors for breast MRI with DCE, T2‐weighted imaging, and DWI with apparent diffusion coefficient (ADC) mapping.Study TypeRetrospective.SubjectsIn all, 188 patients (mean 51.6 years) with 210 breast tumors (136 malignant and 74 benign) who underwent mpMRI from December 2010 to September 2014.Field Strength/SequenceIR inversion recovert DCE‐MRI dynamic contrast‐enhanced magnetic resonance imaging VIBE Volume‐Interpolated‐Breathhold‐Examination FLASH turbo fast‐low‐angle‐shot TWIST Time‐resolved angiography with stochastic Trajectories.AssessmentTwo radiologists in consensus and another radiologist independently evaluated the mpMRI data. Characteristics for mass (n = 182) and nonmass (n = 28) lesions were recorded on DCE and T2‐weighted imaging according to BI‐RADS, as well as DWI descriptors. Two separate models were analyzed, using DCE‐MRI BI‐RADS descriptors, T2‐weighted imagines, and ADCmean as either a continuous or binary form using a previously published ADC cutoff value of ≤1.25 × 10−3 mm2/sec for differentiation between benign and malignant lesions. Histopathology was the standard of reference.Statistical Testsχ2 test, Fisher's exact test, Kruskal–Wallis test, Pearson correlation coefficient, multivariate logistic regression analysis, Hosmer–Lemeshow test of goodness‐of‐fit, receiver operating characteristics analysis.ResultsIn Model 1, ADCmean (P = 0.0031), mass margins with DCE (P = 0.0016), and delayed enhancement with DCE (P = 0.0016) were significantly and independently associated with breast cancer diagnosis; Model 2 identified ADCmean (P = 0.0031), mass margins with DCE (P = 0.0012), initial enhancement (P = 0.0422), and delayed enhancement with DCE (P = 0.0065) to be significantly independently associated with breast cancer diagnosis. T2‐weighted imaging variables were not included in the final models.Data ConclusionmpMRI with DCE‐MRI and DWI with ADC mapping enables accurate breast cancer diagnosis. A model using quantitative and qualitative descriptors from DCE‐MRI and DWI identifies breast cancer with a high diagnostic accuracy. T2‐weighted imaging does not significantly contribute to breast cancer diagnosis. Level of Evidence: 3 Technical Efficacy: Stage 2J. Magn. Reson. Imaging 2019;49:864–874.

Effect of MRI combined with serum levels of CA153, CEA and CYFRA21-1 on the diagnostic efficacy of breast cancer patients

Objective To investigate the effect of color magnetic resonance imaging (MRI) combined with serum levels of carbohydrate antigen 153 (CA153), carcinoembryonic antigen (CEA) and cytokeratin 19 fragment antigen 21-1 (CYFRA21-1) on the diagnostic efficacy of breast cancer patients. Methods From December 2015 to December 2017, 80 cases of breast cancer in our hospital were selected as the observation group. Another 98 patients with benign breast diseases as control group A, and 94 healthy women as control group B. The serum levels of CA153, CEA and CYFRA21-1in the three groups were measured by electrochemiluminescence and the level of the above serum indexes in patients with different disease stages (stage Ⅰ to Ⅱ, Ⅲ to Ⅳ) in the observation group were compared. The 3 groups were examined by color Doppler high frequency ultrasound. The specificity, sensitivity and accuracy of color Doppler ultrasound combined with serum CA153, CEA and CYFRA21-1 or detecting alone in the diagnosis of breast cancer analyzed. Results There were significant differences in the levels of serum CA153, CEA and CYFRA21-1 in the 3 groups (P<0.05), and the level of serum CA153, CEA and CYFRA21-1 in the observation group was higher than that in the control group A and the control group B (P<0.05). The levels of serum CA153, CEA and CYFRA21-1 in patients in stage Ⅲ to Ⅳ of the observation group were higher than those in patients in stage Ⅰ to Ⅱ (P<0.05). The sensitivity and accuracy of color Doppler ultrasound combined with serum CA153, CEA and CYFRA21-1 in the diagnosis of breast cancer were 96.25% (77/80) and 84.93% (231/272), respectively, which were all higher than those of serum CA153, CEA and CYFRA21-1 alone (P<0.05). And the sensitivity of combined diagnosis was higher than that of color Doppler high frequency ultrasound alone (P<0.05). Conclusions Color Doppler ultrasound combined with serum levels of CA153, CEA and CYFRA21-1 can significantly improve the sensitivity and accuracy of breast cancer diagnosis, reduce the risk of missed diagnosis, and provide a strong basis for diagnosis and treatment of breast cancer. Key words: Breast neoplasms/DI; Magnetic resonance imaging; CA-15-3 Antigen/BL; Carcinoembryonic antigen/BL; Keratin-19/BL; Antigens, neoplasm

Modeling of Breast Cancer Diagnosis Classification Based on Hospital Medical Records

Accuracy of breast cancer diagnosis is required to provide appropriate action or treatment. Classification of breast cancer diagnosis can be divided into various stadiums from stages 0 through IV. The classification of the breast cancer stadiums is probably related to risk factors, clinical complaints and outcome of the given treatment. The aim of the study was to determine the most appropriate model of breast cancer classification in diagnosis based on risk factors, clinical symptoms and treatment received by the patients. Therefore, predictor factors in this study was consisting of the location of cancer, the presence of metastasis, chemotherapy, age, weight, marital status and parity. The data came from medical records of breast cancer patients treated at the hospital Dr. Wahidin Sudirohusodo, Makassar, Indonesia during the year 2016 as many as 261 where drawn 181 samples. The purpose of analysis was to determine the magnitude of the association between predictors and the classification of breast cancer diagnoses in logistic regression models. The most appropriate logistic regression model test was multinomial logistics where the values of Pearson and Deviance Chi-square Goodness of Fit showed statistically accepted, with pseudo r-square Nagelkerke 0.658. In addition, McFadden value 0.421 means this model is able to explain the variation of breast cancer stage classification by 42%. The analysis showed that the value of simultaneous test of logistic regression -2log-likelihood was 209.914 (p <0,001), where the main predictors were age and chemotherapy with g0(x) = −42,903 − 0,069Age − 1,987 Chemotheraphy; g2(x) = −42,646 − 0,069Age − 1,987 Chemotheraphy and. g3(x) = −24,254 − 0,069Age − 1,987 Chemotheraphy Moreover, without chemotherapy, breast cancer patients had an increased chance of getting into a higher stage with age, proportional to the stage of breast cancer diagnosis. The model explain the chances of an increased likelihood of clinical stages was related to the age and chemotherapy treatment.

Abstract P6-03-07: An automated DNA methylation assay (QM-MSP) for rapid breast cancer diagnosis in underdeveloped countries

Abstract BACKGROUND: Underdeveloped countries reported 882,900 new cases of breast cancer and 324,000 deaths in 2012, likely to be a gross underestimation according to recent reports. Often, mammography screening is not available, primary care services are limited, and pathology and treatment services are available only in the regional hospitals. Because of the lack of access to diagnostic and treatment services, it is estimated that more than 90% of patients with breast cancer never present for medical treatment. To address this situation, an accurate, easy-to-perform diagnostic test appropriate for use in remote clinics is desperately needed. Johns Hopkins (JH) and Cepheid partnered to translate a robust Quantitative Multiplex Methylation-Specific PCR (QM-MSP) assay to an automated, cartridge-based system that provides quantitative measures of DNA methylation within hours of fine needle aspiration or core biopsy of image-detected suspicious lesions. METHODS: With a goal of discriminating malignant from benign breast disease with high sensitivity and specificity, we evaluated 24 breast cancer-specific DNA methylation markers (selected through comprehensive methylome analysis) in 119 invasive ductal carcinomas and 186 benign breast tissues. QM-MSP was performed on sections of formalin-fixed paraffin-embedded (FFPE) tissues to quantify DNA methylation. The dynamic range and performance of quantitative methylation detection was tested using a subset of 9 genes in the cartridge-based system. RESULTS: QM-MSP was performed in a Training set consisting of 93 tissues [n=43 IDC, n=50 benign lesions (25 usual ductal hyperplasia, UDH, and 25 papilloma)] from the US. We selected 9 DNA markers significantly (p&amp;lt;0.05) more methylated in malignant compared to benign lesions, which had low or no methylation. An independent Test set consisted of benign (n=26) and malignant (n=10) tissues (mostly Caucasian; JH Test Set). As a panel, the 9 markers were significantly more methylated in malignant than benign tissue (p&amp;lt;0.001), revealing a sensitivity of 90% and specificity of 92%, using a laboratory cutoff of 9.5 CMI units (900 unit scale) based on receiver operator characteristic statistics (ROC; p&amp;lt;0.0001, AUC=0.977). To determine if the markers characterized in the JH Test Set could perform as well in samples from a different geography, the panel was tested on 176 tissues from Wuhan, China (China Test Set). In this cohort (66 IDC and 110 benign tissues - 49 fibroadenoma, 19 benign cyst, 12 UDH, 30 papilloma), sensitivity was 89% and specificity was 89% for detection of breast cancer with ROC AUC=0.945. An advanced version of the cartridge with up to 12 methylated DNA markers is under development, thus far showing robust signals in cancer and low background in benign tissues. Current work at JH is focused on optimizing the technical performance of the cartridge. CONCLUSIONS: We identified a panel of methylated DNA markers that discriminate malignant from benign breast lesions and built a prototype automated cartridge-based assay with promising sensitivity and specificity for breast cancer. Such an assay has the potential to aid in specimen triage in the pathology lab and provide fast, low cost and accurate diagnosis of breast cancer in LMIC settings. Citation Format: Fackler MJ, Downs BM, Mercado-Rodriguez C, Cimino-Mathews A, Chen C, Yuan J, Cope LM, Kohlway A, Kocmond K, Lai E, Weidler J, Visvanathan K, Umbricht CB, Harvey S, Wolff AC, Bates M, Sukumar S. An automated DNA methylation assay (QM-MSP) for rapid breast cancer diagnosis in underdeveloped countries [abstract]. In: Proceedings of the 2017 San Antonio Breast Cancer Symposium; 2017 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2018;78(4 Suppl):Abstract nr P6-03-07.