Survey of machine learning algorithms for breast cancer detection using mammogram images

Breast cancer is one of the leading causes of mortality between women, with one in eight women diagnosed with the disease, but early detection can reduce death rates. Therefore, continuous effort is being made to advance more effective methods for the early and effective diagnosis of breast cancer with high accuracy without human intervention. Classical attempts were manual, time- consuming and ineffective in many situations. The purpose of this work is to detect and locate the presence of malignant tissues in the breast using the morphological technique in mammogram images to diagnose breast cancer because morphology is one of the most reliable methods for early detection of breast cancer. The proposed algorithm is developed using watershed segmentation after the preprocessing is completed by the median filter to eliminate any expected noise, and contouring the tumor by morphological techniques to take the best diagnostic for breast cancer in a mammogram image. Good results are obtained for the measurements used like MSE, PSNR, SNR, entropy for the mammogram images.

Optimization and normalization strategies for long term untargeted HILIC-LC-qTOF-MS based metabolomics analysis: Early diagnosis of breast cancer

Breast cancer is a serious potential health problem for all women. The current screening and imaging techniques such as X-ray mammography, clinical examination, ultrasound, and MRI, even combined in some way, provide only 73% accuracy in detecting breast cancer. This motivates researchers with biomedical background to investigate new techniques to advance the screening techniques aiming for early detection of breast cancer. In particular, the electromagnetic (EM) community has been researching potential techniques for breast cancer detection. Potential EM techniques are discussed in this paper.

Since reporting cases of breast cancer are on the rise all over the world. Especially in regions such as Pakistan, Saudi Arabia, and the United States. Efficient methods for the early detection and diagnosis of breast cancer are needed. The usual diagnosis procedures followed by physicians has been updated with modern diagnostic approaches that include computer-aided support for better accuracy. Machine learning based practices has increased the accuracy and efficiency of medical diagnosis, which has helped save lives of many patients. There is much research in the field of medical imaging diagnostics that can be applied to the variety of data such as magnetic resonance images (MRIs), mammograms, X-rays, ultrasounds, and histopathological images, but magnetic resonance (MR) and mammogram imaging have proved to present the promising results. The proposed paper has presented the results of classification algorithms over Breast Cancer (BC) mammograms from a novel dataset taken from hospitals in the Qassim health cluster of Saudi Arabia. This paper has developed a novel approach called the novel spectral extraction algorithm (NSEA) that uses feature extraction and fusion by using local binary pattern (LBP) and bilateral algorithms, as well as a support vector machine (SVM) as a classifier. The NSEA with the SVM classifier demonstrated a promising accuracy of 94% and an elapsed time of 0.68 milliseconds, which were significantly better results than those of comparative experiments from classifiers named Naïve Bayes, logistic regression, K-Nearest Neighbor (KNN), Gaussian Discriminant Analysis (GDA), AdaBoost and Extreme Learning Machine (ELM). ELM produced the comparative accuracy of 94% however has a lower elapsed time of 1.35 as compared to SVM. Adaboost has produced a fairly well accuracy of 82%, KNN has a low accuracy of 66%. However Logistic Regression, GDA and Naïve Bayes have produced the lowest accuracies of 47%, 43% and 42%.

Early detection and diagnosis of breast cancer are critical for saving lives. This paper addresses two major challenges associated with this task: the vast amount of data processing involved and the need for early detection of breast cancer. To tackle these issues, we developed thirty hybrid architectures by combining five deep learning techniques (Xception, Inception-V3, ResNet50, VGG16, VGG19) as feature extractors and six classifiers (random forest, logistic regression, naive Bayes, gradient-boosted tree, decision tree, and support vector machine) implemented on the Spark framework. We evaluated the performance of these architectures using four classification criteria. The results, analyzed using Scott Knott's statistical test, demonstrated the effectiveness of merging deep learning feature extraction techniques with traditional classifiers for classifying breast cancer into malignant and benign tumors. Notably, the hybrid architecture using logistic regression as the classifier and ResNet50 for feature extraction (RESLR) emerged as the top performer. It achieved impressive accuracy scores of 98.20%, 96.59%, 96.64%, and 94.84% across the Break-His dataset at different magnifications (40X, 100X, 200X, and 400X) respectively. Additionally, RESLR achieved an accuracy of 97.05% on the ICIAR dataset and a remarkable accuracy of 95.31% on the FNAC dataset.

BackgroundBreast cancer is the second leading cause of cancer related deaths in women worldwide. Reports about the early diagnosis of breast cancer are suggestive of an improved clinical outcome and overall survival rate in cancer patients. Therefore, cancer screening biomarker for early detection and diagnosis is urgently required for timely treatment and better cancer management. In this context, we investigated an association of cancer testis antigen, A-Kinase anchor protein 4 (AKAP4) with breast carcinoma.Methodology/FindingsWe first compared the AKAP4 gene and protein expression in four breast cancer cells (MCF7, MDA-MB-231, SK-BR3 and BT474) and normal human mammary epithelial cells. In addition, 91 clinical specimens of breast cancer patients of various histotypes including ductal carcinoma in situ, infiltrating ductal carcinoma and infiltrating lobular carcinoma and 83 available matched adjacent non-cancerous tissues were examined for AKAP4 gene and protein expression by employing in situ RNA hybridization and immunohistochemistry respectively. Humoral response against AKAP4 was also investigated in breast cancer patients employing ELISA. Our in vitro studies in all breast cancer cells revealed AKAP4 gene and protein expression whereas, normal human mammary epithelial cells failed to show any expression. Using in situ RNA hybridization and immunohistochemistry, 85% (77/91) tissue specimens irrespective of histotypes, stages and grades of breast cancer clinical specimens revealed AKAP4 gene and protein expression. However, matched adjacent non-cancerous tissues failed to display any AKAP4 gene and protein expression. Furthermore, humoral response was observed in 79% (72/91) of total breast cancer patients. Interestingly, we observed that 94% (72/77) of breast cancer patients found positive for AKAP4 protein expression generated humoral response against AKAP4 protein.ConclusionsCollectively, our data suggests that AKAP4 may be used as serum based diagnostic test for an early detection and diagnosis of breast cancer and may be a potential target for immunotherapeutic use.

As I wrote in my review of the first edition,<i>Dr. Susan Love's Breast Book</i>covers the breast from A to Z in a scientific, noncondescending, readable style. For this second edition, Dr Love has reorganized, updated, and added new material, which has expanded the book from 455 to 627 pages. The book's seven parts include, "The Healthy Breast," "Common Problems of the Breast," "Diagnosis of Breast Problems," "The Causes of Breast Cancer," "The Diagnosis of Breast Cancer," "Treating Breast Cancer," and "Living With Breast Cancer." Six appendixes provide information on, among other things, drugs used for systemic breast cancer treatment, regional support organizations,journal references, and comprehensive cancer centers. A marked change from the first edition is Dr Love's dismissal and even condemnation of the practice of breast self-examination (BSE) as a technique for breast cancer detection. She feels that while women should get to know their breasts, the monthly

Breast cancer is one of the main causes of death in women and ranks first in cancer cases in Indonesia. Therefore, an early detection and prevention of breast cancer is necessary, one of which is through mammography procedures. A machine learning classifier such as Support Vector Machines (SVM) could be used as an aid to the doctors and radiologist in diagnosing breast cancer from the mammogram images. The aim of this paper is to compare two feature extraction methods used in SVM, namely the Gray Level Co-Occurrence Matrix (GLCM) and first order with two kernels for each method, namely Gaussian and Polynomial. Classification using SVM method is carried out by testing several parameters such as the value of C, gamma, degree and varying the pixel spacing values ​​in GLCM, which usually in previous studies only used the default pixel spacing. The dataset consists of 500 mammogram images containing 250 benign and malignant images, respectively. This study is expected to find out the best method with the highest accuracy between these two texture feature extractions and and able to distinguish between benign and malignant classes correctly. The result achieved that Gray Level Co-Occurrence Matrix (GLCM) feature extraction method with both Gaussian and Polynomial kernel yields the best performance with an accuracy of 89%.

Simple SummaryEarly diagnosis of breast cancer greatly increases the chance of cure and survival from the disease. The mammogram is widely used for early detection of breast cancer, but its effectiveness and accuracy have been a concern for a long time as well as its inability in detecting small cancers, especially in women with dense breast tissues. Therefore, it is an unmet clinical need to develop a simple, convenient test to overcome the shortcomings of mammography. Liquid biopsy, which is based on the analysis of body fluids, has attracted much attention in the search for cancer biomarkers. Recent advances in analytical techniques have gradually made it possible to detect breast cancer early through a biomarker analysis of blood, nipple aspirate fluid, sweat, urine, tears, or the breath. We envision that a simple blood or breath test holds great promise as a biomarker for early detection of breast cancer in the near future.Breast cancer is the most common cancer in women worldwide. Accurate early diagnosis of breast cancer is critical in the management of the disease. Although mammogram screening has been widely used for breast cancer screening, high false-positive and false-negative rates and radiation from mammography have always been a concern. Over the last 20 years, the emergence of “omics” strategies has resulted in significant advances in the search for non-invasive biomarkers for breast cancer diagnosis at an early stage. Circulating carcinoma antigens, circulating tumor cells, circulating cell-free tumor nucleic acids (DNA or RNA), circulating microRNAs, and circulating extracellular vesicles in the peripheral blood, nipple aspirate fluid, sweat, urine, and tears, as well as volatile organic compounds in the breath, have emerged as potential non-invasive diagnostic biomarkers to supplement current clinical approaches to earlier detection of breast cancer. In this review, we summarize the current progress of research in these areas.

Tumor antigens, expressed early in disease, which can induce specific antibody response could serve as biomarkers for early detection of human breast cancer. However, the ability to obtain sera from women prior to the development of breast cancer is limited, which makes it difficult to identify early antigens directly from breast cancer patients. Transgenic mouse models have been proved to demonstrate similar antigen repertoire to breast cancer patients. Therefore, we propose to identify early tumor antigens in neu transgenic mice and use them as diagnostic targets for early detection of human breast cancer. We have collected serial sera from neu transgenic mice, sera collected before the animals develop palpable tumor “pre-diagnostic sera”. With serological analysis of recombinant cDNA expression libraries (SEREX) approach, we were able to identify nine tumor antigens from pre-diagnostic sera, Rpl5, TNFaip3/A20, Pdhx, Otud6b, Stk39, Zfp238, Dnajc10, Lgals8 and Vps35. These antigens demonstrated detectable IgG antibody response prior to tumor development in neu transgenic mice. IgM is the first antibody to be produced during a humoral immune response, so we questioned whether including antigen specific IgM with IgG responses could achieve a better diagnostic performance. Firstly, we analyzed receiver-operating-characteristic (ROC) curves of these antigens by IgG and IgM ELISA analysis in neu transgenic mice and 26 FVB control mice. By combining IgG and IgM ELISA, we were able to achieve a higher AUC: Otud6b and Stk39 show an AUC of 0.882, and adding Lgals8 IgG ELISA to this panel can achieve an AUC of 0.924 in discriminating cases from control mice. We documented that these autoantibodies are also detectable in the serum of women with breast cancer and then screened a panel of sera derived from the Women's Health Initiative cohort (samples obtained 6-18 months prior to the development of breast cancer) and case matched controls. We evaluated serum for the presence of IgG and IgM specific autoantibodies to Pdhx, Otud6b, and Stk39. With both IgG and IgM ELISA analysis, a panel combining the three antigens demonstrates an AUC of 0.633 in patients diagnosed within 5 month and an AUC of 0.688 in patients diagnosed within 5-18 month of the blood draw. In summary, we conclude that tumor antigens identified in neu transgenic mouse model can be used for early detection and diagnosis of breast cancer in women. The combination of antigen specific IgG and IgM antibodies may enhance the sensitivity of the assay for early detection. Citation Format: {Authors}. {Abstract title} [abstract]. In: Proceedings of the 102nd Annual Meeting of the American Association for Cancer Research; 2011 Apr 2-6; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2011;71(8 Suppl):Abstract nr 2683. doi:10.1158/1538-7445.AM2011-2683

Breast cancer is a leading threaten of woman's health, and mammography is widely used in the early detection and diagnosis of breast cancer. Mass is a common sign observed on mammograms, and the automatic identification of benign and malignant breast mammography mass images is a challenging task. The CAD techniques have been used to improve the classification performance. Deep learning is powerful classification technique, however, it needs a lot of training data, which is not practical for mass detection or classification. In this paper, based on the observation that natural images are greatly different from medical images, we proposed a new network (SE-DenseNet) which combines the Dense convolutional neural network (DenseNet) and the “Squeeze-and-Excitation” (SE) block, and twice fine-tuning method to classify breast mass. We first use the mass and normal breast to fine-tune our model (trained on ImageNet) and then use breast mass dataset (benign and malignant) to further fine-tuning the model. The correctness of the model is verified by a large number of experiments on the BCDR dataset and quantitative comparison with other methods. The proposed model achieved better performance on the BCDR dataset(AUC is 0.984, accuracy is 0.982).

Breast cancer is the primary malignant tumor that endangers women's health. The incidence of breast cancer is increasing rapidly in recent years. Accurate disease evaluation before treatment is the key to the selection of treatment options. Biomedical imaging technology plays an irreplaceable role in the diagnosis and staging of tumors. Various imaging methods can provide excellent temporal and spatial resolution from multiple levels and perspectives and have become one of the most commonly used means of breast cancer early detection. With the development of radiomics, it has been found that early imaging diagnosis of breast cancer plays an important guiding role in clinical decision-making. The purpose of this study is to explore the characteristics of various breast cancer imaging technologies, promote the development of individualized accurate diagnosis and treatment of imaging, and improve the clinical application value of radiomics in the early diagnosis of breast cancer.

&lt;span lang="EN-US"&gt;Unchecked breast cell growth is one of the leading causes of death in women globally and is the cause of breast cancer. The only method to avoid breast cancer-related deaths is through early detection and treatment. The proper classification of malignancies is one of the most significant challenges in the medical industry. Due to their high precision and accuracy, machine learning techniques are extensively employed for identifying and classifying various forms of cancer. The authors of this review studied numerous data mining algorithms and implemented them such that clinicians might use them to accurately detect cancer cells early on. This article introduces several techniques, including support vector machine (SVM), K star (K*) classifier, additive regression (AR), back propagation (BP) neural network, and Bagging. These algorithms are trained using a set of data that contains tumor parameters from breast cancer patients. Comparing the results, the authors found that SVM and Bagging had the highest precision and accuracy, respectively. Also assess the number of studies that provide machine learning techniques for breast cancer detection.&lt;/span&gt;

PurposeOne of the main reasons for increase in mortality rate in woman is breast cancer. Accurate early detection of breast cancer seems to be the only solution for diagnosis. In the field of breast cancer research, many new computer-aided diagnosis systems have been developed to reduce the diagnostic test false positives because of the subtle appearance of breast cancer tissues. The purpose of this study is to develop the diagnosis technique for breast cancer using LCFS and TreeHiCARe classifier model.Design/methodology/approachThe proposed diagnosis methodology initiates with the pre-processing procedure. Subsequently, feature extraction is performed. In feature extraction, the image features which preserve the characteristics of the breast tissues are extracted. Consequently, feature selection is performed by the proposed least-mean-square (LMS)-Cuckoo search feature selection (LCFS) algorithm. The feature selection from the vast range of the features extracted from the images is performed with the help of the optimal cut point provided by the LCS algorithm. Then, the image transaction database table is developed using the keywords of the training images and feature vectors. The transaction resembles the itemset and the association rules are generated from the transaction representation based on a priori algorithm with high conviction ratio and lift. After association rule generation, the proposed TreeHiCARe classifier model emanates in the diagnosis methodology. In TreeHICARe classifier, a new feature index is developed for the selection of a central feature for the decision tree centered on which the classification of images into normal or abnormal is performed.FindingsThe performance of the proposed method is validated over existing works using accuracy, sensitivity and specificity measures. The experimentation of proposed method on Mammographic Image Analysis Society database resulted in classification of normal and abnormal cancerous mammogram images with an accuracy of 0.8289, sensitivity of 0.9333 and specificity of 0.7273.Originality/valueThis paper proposes a new approach for the breast cancer diagnosis system by using mammogram images. The proposed method uses two new algorithms: LCFS and TreeHiCARe. LCFS is used to select optimal feature split points, and TreeHiCARe is the decision tree classifier model based on association rule agreements.

Breast cancer is one of the most prevalent and chronic disease that affect women. To overcome this disease, effective medical treatment is required. Early detection of the disease plays an important role for suitable medication and survival of patient. To identify the breast cancer in the patients, standard imaging technique mammography is used. Due to the subtle and varied nature of cancer tissues interpreting mammogram images can be a challenge to doctors. Machine learning (ML) and Deep Learning (DL) techniques offer promising solutions that provide efficient breast cancer detection from mammograms. In this review paper a comprehensive review of ML and DL algorithms and their applications in mammogram image analysis are presented. Various supervised and unsupervised learning techniques, such as convolutional neural networks (CNNs), support vector machines (SVMs), random forests, and other popular ML and DL models are discussed in paper. The integration of these DL methods that are efficiently used in image preprocessing techniques, feature extraction, and classification strategies. The overall survey focusses on various performance metrics, datasets, and benchmarks used in existing studies. Further the strengths and limitations of different approaches used by various researchers are identified. By understating current research trends this paper aims to contribute to the ongoing development of more accurate and reliable breast cancer detection systems using advanced ML techniques.