scholarly journals A Deep Learning Technique for Classification of Breast Cancer Disease

2021 ◽  
Vol 11 (1) ◽  
pp. 9-14
Author(s):  
Dr.Yelepi Usha Rani ◽  
◽  
Lakshmi Sowmya Kotturi ◽  
Dr. G. Sudhakar ◽  
◽  
...  
Keyword(s):  
Breast Cancer ◽  
Breast Cancers ◽  
Cancer Disease ◽  
Cancer Breast ◽  
Performance Metric ◽  
Subsequent Decrease ◽  
Learning Technique ◽  
Proper Diagnosis ◽  
Imbalanced Class Distribution

In recent years researchers are intensely using machine learning and employing AI techniques in the medical field particularly in the domain of cancer. Breast cancer is one such example and many studies have proposed CAD systems and algorithms to efficiently detect cancer cells and tumors. Breast cancer is one of the dreadful cancers accounting for a large portion of deaths caused due to cancer worldwide mostly affecting women, needs early detection for proper diagnosis, and subsequent decrease in death rate. Thus, for efficient classification, we implemented different ML techniques on Wisconsin dataset [1] namely SVM, KNN, Decision Tree, Random Forest, Naive Bayes using accuracy as a performance metric, and as per observance, SVM has shown better results when compared to other algorithms. Also, we worked on Breast Histopathology Images [2] scanned at 40x which had images of IDC which is one of the most common types of breast cancers. And to work with the image dataset along with EDA we used high-end techniques like a mobile net where smote a resampling was used to handle imbalanced class distribution, CNN, SVC, InceptionResNetV2 where frameworks like Tensor Flow, Keras were loaded for supporting the environment and smoothly implement the algorithms.

scholarly journals Counteracting Chemoresistance with Metformin in Breast Cancers: Targeting Cancer Stem Cells

Cancers ◽  
2020 ◽  
Vol 12 (9) ◽  
pp. 2482
Author(s):  
Samson Mathews Samuel ◽  
Elizabeth Varghese ◽  
Lenka Koklesová ◽  
Alena Líšková ◽  
Peter Kubatka ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Stem Cells ◽  
Cancer Stem Cells ◽  
Molecular Mechanisms ◽  
Epithelial Mesenchymal Transition ◽  
Acquired Resistance ◽  
Breast Cancers ◽  
Intrinsic Resistance ◽  
Mesenchymal Transition ◽  
Cancer Breast

Despite the leaps and bounds in achieving success in the management and treatment of breast cancers through surgery, chemotherapy, and radiotherapy, breast cancer remains the most frequently occurring cancer in women and the most common cause of cancer-related deaths among women. Systemic therapeutic approaches, such as chemotherapy, although beneficial in treating and curing breast cancer subjects with localized breast tumors, tend to fail in metastatic cases of the disease due to (a) an acquired resistance to the chemotherapeutic drug and (b) the development of intrinsic resistance to therapy. The existence of cancer stem cells (CSCs) plays a crucial role in both acquired and intrinsic chemoresistance. CSCs are less abundant than terminally differentiated cancer cells and confer chemoresistance through a unique altered metabolism and capability to evade the immune response system. Furthermore, CSCs possess active DNA repair systems, transporters that support multidrug resistance (MDR), advanced detoxification processes, and the ability to self-renew and differentiate into tumor progenitor cells, thereby supporting cancer invasion, metastasis, and recurrence/relapse. Hence, current research is focusing on targeting CSCs to overcome resistance and improve the efficacy of the treatment and management of breast cancer. Studies revealed that metformin (1, 1-dimethylbiguanide), a widely used anti-hyperglycemic agent, sensitizes tumor response to various chemotherapeutic drugs. Metformin selectively targets CSCs and improves the hypoxic microenvironment, suppresses the tumor metastasis and inflammation, as well as regulates the metabolic programming, induces apoptosis, and reverses epithelial–mesenchymal transition and MDR. Here, we discuss cancer (breast cancer) and chemoresistance, the molecular mechanisms of chemoresistance in breast cancers, and metformin as a chemo-sensitizing/re-sensitizing agent, with a particular focus on breast CSCs as a critical contributing factor to acquired and intrinsic chemoresistance. The review outlines the prospects and directions for a better understanding and re-purposing of metformin as an anti-cancer/chemo-sensitizing drug in the treatment of breast cancer. It intends to provide a rationale for the use of metformin as a combinatory therapy in a clinical setting.

Pathologic characteristics of breast cancer with special emphasis on prevalence of triple-negative breast cancer from Kenya: A 4-year experience.

2011 ◽  
Vol 29 (27_suppl) ◽  
pp. 35-35
Author(s):  
S. Sayed ◽  
Z. Moloo ◽  
S. Mukono ◽  
R. Wasike ◽  
R. R. Chauhan ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Triple Negative Breast Cancer ◽  
Triple Negative ◽  
Ductal Carcinoma ◽  
Significant Proportion ◽  
Small Sample ◽  
University Hospital ◽  
Breast Cancers ◽  
Grade 3

35 Background: Previous sub classification of breast cancer in Kenya has been fraught by small sample size, non uniform staining methodology and lack of independent review. Triple Negative Breast Cancer (TNBC) is a “special interest” cancer since it represents a significant proportion of breast cancer patients and is associated with a poorer prognosis. We aimed to determine the estrogen receptor (ER), progesterone receptor (PR) and Her2/neu receptor characteristics of breast cancers and the prevalence of TNBC diagnosed at Aga Khan University Hospital, Nairobi (AKUHN) between 2007 to date. Methods: Slides and blocks of archived invasive breast cancers diagnosed at AKUHN were identified, retrieved and reviewed by two independent pathologists. Histological type, grade and pathological stage were documented. Representative sections from available blocks were stained for ER, PR, Her2 with appropriate internal controls. Scores for ER/PR were interpreted based on the ALLRED system, Her2 /neu scoring followed CAP guidelines. The initial 111 cases were validated and confirmed at Sunnybrook Health Sciences Centre, Toronto. Results: 456 cases of invasive breast cancers were diagnosed at AKUHN during the study period. 91% of cases were invasive ductal carcinomas (NOS).The rest were special types. 37% of the tumors were grade 3 and 63% were grade 2. Blocks for 318 of 456 cases were available for receptor analysis. 54% were ER and/or PR positive, with 52% of these in women < 50 yrs. 86% of the ER and/or PR positive tumors were grade 2. Only 12% were Her2/neu positive. Of the 318 cases studied, 111 (32%) were identified as TNBC. Median age was 53 yrs. 88% were grade 3. Conclusions: Invasive ductal carcinoma (NOS) was the most common breast cancer in our study. Nearly half of our cases were ER and/or PR positive and a third were TNBC. Both occurred predominantly in women less than 50 yrs. This represents the largest validated pathologic sub classification of breast cancer from a tertiary academic hospital in Kenya. Expansion of this study to encompass all breast cancers diagnosed in Kenya is underway.

Low-fat dietary pattern and long-term breast cancer incidence and mortality: The Women’s Health Initiative randomized clinical trial.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. 520-520 ◽  
Author(s):  
Rowan T. Chlebowski ◽  
Aaron K Aragaki ◽  
Garnet L Anderson ◽  
Kathy Pan ◽  
Marian L Neuhouser ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Clinical Trial ◽  
Dietary Pattern ◽  
Dietary Intervention ◽  
Breast Cancer Incidence ◽  
Intervention Group ◽  
Fat Intake ◽  
Breast Cancers ◽  
Low Fat ◽  
Cancer Breast

520 Background: Observational studies of dietary fat intake and breast cancer have inconsistent findings. To address this issue, the Women’s Health Initiative (WHI) Dietary Modification (DM) clinical trial assessed a low-fat dietary pattern influence on breast cancer incidence and outcome. Methods: The WHI DM trial is a randomized, controlled clinical trial conducted at 40 US centers, where 48,835 postmenopausal women, aged 50-79 years, with no previous breast cancer and dietary fat intake ≥32% of total energy, were randomly assigned, from 1993-1998, to a usual diet comparison group (60%) or dietary intervention group (40%) with goals to reduce fat intake to 20% of energy and increase vegetables, fruit, and grain intake. This study is registered as: NCT00000611. Results: The dietary intervention significantly reduced fat intake; increased fruit, vegetable and grain intake with modest weight loss (3%) (all P< 0.001). During 8.5 years of dietary intervention, there were 8% fewer breast cancers and deaths from breast cancer were somewhat lower in the intervention group but the rates were not significantly different. However, deaths after breast cancer (breast cancer followed by death from any cause) were significantly reduced in the intervention group, both during intervention (hazard ratio [HR] 0·65 95% confidence interval [CI] 0·45-0·95) and through 16.1 year (median) cumulative follow-up. Now, after long- term, cumulative 19.6 year (median) follow-up, with 3,374 incident breast cancers, the significant reduction in deaths after breast cancer continued (with 1,011 deaths, HR 0·85 95% CI 0·74-0·96) and a significant reduction in deaths from breast cancer (breast cancer followed by death attributed to the breast cancer) emerged (with 383 deaths, HR 0·79 95% CI 0·64-0·97). Conclusions: Adoption of a low-fat dietary pattern associated with increased vegetable, fruit, and grain intake, demonstrably achievable by many, significantly reduced the risk of death from breast cancer in postmenopausal women. To our review, these findings provide the first randomized clinical trial evidence that a dietary change can reduce a postmenopausal woman’s risk of dying from breast cancer. Clinical trial information: NCT00000611.

Triple-Negative Breast Cancer

2019 ◽  
Author(s):  
Diane M. Radford ◽  
Jame Abraham ◽  
Stephen R. Grobmyer
Keyword(s):  
Breast Cancer ◽  
African American Women ◽  
Triple Negative Breast Cancer ◽  
Triple Negative ◽  
Growth Factor Receptor ◽  
Breast Cancers ◽  
Cancer Breast ◽  
Gene Testing ◽  
Visceral Metastases ◽  
Epidermal Growth

Triple-negative breast cancers (TNBCs), negative for estrogen receptor, progesterone receptor, and human epidermal growth factor receptor 2, account for 15 to 20% of all female breast cancers. TNBC is heterogeneous based on gene expression microarray, and identification of TNBC subtypes and their behavior has the potential to enable more targeted, neoadjuvant, and adjuvant interventions. TNBCs usually are higher grade (Nottingham score 3) and are more common in younger, Hispanic, and African American women. They are more aggressive, have an increased likelihood of distant disease and mortality, are larger at presentation, and are more likely to be associated with lymph node metastases. Patients with TNBC are at a higher risk for visceral metastases early in the course of the disease. Genetic risk evaluation is recommended for patients with TNBC diagnosed at or before 60 years of age. Surgical management may be influenced by gene testing results. Standard adjuvant chemotherapy is anthracycline or taxane based. This review contains 5 figures, 8 tables, and 51 references. Key Words: adjuvant, BRCA, chemotherapy, hormone receptor negative, neoadjuvant, genetics, triple-negative breast cancer, breast neoplasm.

scholarly journals Circulating miRNAs in HER2-Positive and Triple Negative Breast Cancers: Potential Biomarkers and Therapeutic Targets

2020 ◽  
Vol 21 (18) ◽  
pp. 6750
Author(s):  
Ishita Gupta ◽  
Balsam Rizeq ◽  
Semir Vranic ◽  
Ala-Eddin Al Moustafa ◽  
Halema Al Farsi
Keyword(s):  
Breast Cancer ◽  
Estrogen Receptor ◽  
Triple Negative ◽  
Therapeutic Targets ◽  
Breast Cancers ◽  
Breast Cancer Patients ◽  
Circulating Mirnas ◽  
Her2 Positive ◽  
Cancer Disease ◽  
Estrogen Receptor Negative

Breast cancer is one of the most prevalent diseases among women worldwide and is highly associated with cancer-related mortality. Of the four major molecular subtypes, HER2-positive and triple-negative breast cancer (TNBC) comprise more than 30% of all breast cancers. While the HER2-positive subtype lacks estrogen and progesterone receptors and overexpresses HER2, the TNBC subtype lacks estrogen, progesterone and HER2 receptors. Although advances in molecular biology and genetics have substantially ameliorated breast cancer disease management, targeted therapies for the treatment of estrogen-receptor negative breast cancer patients are still restricted, particularly for TNBC. On the other hand, it has been demonstrated that microRNAs, miRNAs or small non-coding RNAs that regulate gene expression are involved in diverse biological processes, including carcinogenesis. Moreover, circulating miRNAs in serum/plasma are among the most promising diagnostic/therapeutic tools as they are stable and relatively easy to quantify. Various circulating miRNAs have been identified in several human cancers including specific breast cancer subtypes. This review aims to discuss the role of circulating miRNAs as potential diagnostic and prognostic biomarkers as well as therapeutic targets for estrogen-receptor negative breast cancers, HER2+ and triple negative.

scholarly journals Machine Learning Algorithms: Diagnosing Breast Cancer

2019 ◽  
Vol 8 (2S6) ◽  
pp. 849-851
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Benign Tumor ◽  
Nearest Neighbor ◽  
Machine Learning Algorithms ◽  
K Nearest Neighbor ◽  
Cancer Breast ◽  
Cancer Tumor ◽  
The Common

Breast Cancer has become one of the common diseases not only in women but also in few men. According to research, the demise rate of females has increased mainly because of Breast Cancer tumor. One out of every eight women and one out of every thousand men are diagnosed with breast cancer. Breast cancer tumors are mainly classified into two types: Benign tumor which is a non-cancerous tumor and other one is malignant tumor which is a cancerous tumor. In order to know which type of tumor a patient has; the accurate and early diagnosis is a very crucial step. Machine Learning (ML) algorithms have been used to develop and train the model for classification of the type of tumor. For accurate and better classification several classification algorithms in ML have been trained and tested on the dataset that was collected. Already algorithms like Naïve Bayes, Random Forest, K-Nearest Neighbor and SVM showed better accuracy for classification of tumor. When we implemented Multilayer Perceptron (MLP) algorithm it gave us the best accuracy levels among all both during training as well as testing .i.e. 97%. So, the exact classification using this model will help the doctors to diagnose the type of tumor in patients quickly and accurately

scholarly journals Efficient method for breast cancer classification based on ensemble hoffeding tree and naïve Bayes

2020 ◽  
Vol 18 (2) ◽  
pp. 1074
Author(s):  
Royida A. Ibrahem Alhayali ◽  
Munef Abdullah Ahmed ◽  
Yasmin Makki Mohialden ◽  
Ahmed H. Ali
Keyword(s):  
Breast Cancer ◽  
Naive Bayes ◽  
Class Imbalance ◽  
Naïve Bayes ◽  
Small Sample ◽  
Cancer Breast ◽  
Improving Accuracy ◽  
Distribution Class ◽  
Supervised Classification Methods

<p><span>The most dangerous type of cancer suffered by women above 35 years of age is breast cancer. Breast Cancer datasets are normally characterized by missing data, high dimensionality, non-normal distribution, class imbalance, noisy, and inconsistency. Classification is a machine learning (ML) process which has a significant role in the prediction of outcomes, and one of the outstanding supervised classification methods in data mining is Naives Bayess Classification (NBC). Naïve Bayes Classifications is good at predicting outcomes and often outperforms other classifications techniques. Ones of the reasons behind this strong performance of NBC is the assumptions of conditional Independences among the initial parameters and the predictors. However, this assumption is not always true and can cause loss of accuracy. Hoeffding trees assume the suitability of using a small sample to select the optimal splitting attribute. This study proposes a new method for improving accuracy of classification of breast cancer datasets. The method proposes the use of Hoeffding trees for normal classification and naïve Bayes for reducing data dimensionality.</span></p>

Sign in / Sign up

Export Citation Format

Share Document