China
Africa
Explore chapters and articles related to this topic
Machine Learning Algorithms Used in Medical Field with a Case Study
Published in K. Gayathri Devi, Kishore Balasubramanian, Le Anh Ngoc, Machine Learning and Deep Learning Techniques for Medical Science, 2022
A worldwide significant health issue among women in current scenario is breast cancer. It represents the majority of the cancer problems and cancer-related diseases and deaths. Early prognosis of these types of cancer could promote timely clinical treatment and improve the chance of survival significantly. Further, undergoing unnecessary treatments can be avoided by accurate classification of benign tumors in an early stage. Prompt diagnosis of breast cancer and classification of the tumor cells into malignant or benign groups is to a great extent needed and is now an important area of research. As machine learning techniques has exceptional compensation like serious features recognition particularly in medical field, they are extensively chosen for breast cancer classification and forecast modelling. The research work in this chapter aims to experiment the cancer dataset for prediction of malignant and benign cells using the classifiers such as Decision Tree Classifier, Random Forest Classifier, Naive Bayes Classifier, Support Vector Machines, Logistic Regression, and K Nearest Neighbor. Training time and dimensionality can be reduced by machine learning models with preprocessing techniques. The effect of outliers has also been analyzed and reduced. The accuracy and other performance metrics of machine learning algorithms are compared and an optimal algorithm is suggested.
Medical Images of Breast Tumors
Published in Abdel-Badeeh M. Salem, Innovative Smart Healthcare and Bio-Medical Systems, 2020
Yuriy Zaychenko, Galib Hamidov
The most part of last papers referring to the field of breast cancer classification were oriented on integer image (Doyle et al., 2008; Singh et al., 2015; Zhang et al., 2013; Zhang, Zhang, Coenen, Xiau, & Lu, 2014). Widespread implementation of breast image classification (BIC) and other forms of digital pathology, however, face barriers such as high cost of implementation, insufficient productivity compared to the amount of clinic procedures, interior technological problems, and opposition from pathologists and anatomists. Until now, most of the works based on histology breast cancer analysis were performed on small data sets. Some improvement in medical images data sets presented data set with 7,909 breast images obtained from 82 patients (Spanhol Oliveira, Petitjean, & Heutte, 2016). In this research, the authors estimated various texture descriptors and various classifiers and carried out their experiments with 82%–85% accuracy. The alternative to this approach is the application of convolutional neural network (CNN) for medical images processing and diagnostics, which is considered and developed in the present research.
Dopamine and Tumorigenesis in Reproductive Tissues
Published in Nira Ben-Jonathan, Dopamine, 2020
In recent years, various molecular techniques, particularly gene expression profiling, have been used increasingly to refine the classification of breast cancer and to assess prognosis and response to therapy. As shown in Figure 12.5, based on the genes expressed by the cancer cells, four molecular subtypes of breast cancer are recognized: (1) Luminal A is hormone-receptor positive [ER and progesterone receptor (PR)], HER2 negative, with low levels of the proliferation index. This is the most common breast cancer subtype, occurring in half of the patients. These low-grade cancers tend to grow slowly and have the best prognosis. (2) Luminal B is hormone-receptor positive and is either HER2 positive or HER2 negative, with high levels of proliferation index. These cancers, which occur in about 25% of the cases, generally grow slightly faster than luminal A cancers, and their prognosis is slightly worse. (3) HER2-enriched is hormone-receptor negative and HER2 enriched. These cancers tend to grow faster than luminal cancers, and can have a worse prognosis. However, they are often successfully treated with targeted therapies aimed at the HER2 protein. (4) Basal-like triple-negative is hormone-receptor negative and HER2 negative. This cancer subtype is more common in women with BRCA1 gene mutations, as well as in younger and African-American women. Most triple-negative breast cancers are more aggressive, with poor prognosis. As covered in [28], there are additional refinements of breast cancer classification, including the status of claudins, transmembrane proteins that are enriched in tight junctions involved in the migration and epithelial mesenchymal transition (EMT), which have been considered as tumor suppressors.
Use of classifiers to optimise the identification and characterisation of metastatic breast cancer in a nationwide administrative registry
Published in Acta Oncologica, 2021
Antonis Valachis, Peter Carlqvist, Máté Szilcz, Jonatan Freilich, Simona Vertuani, Barbro Holm, Henrik Lindman
It is important to know primary breast cancer classification when interrogating databases. Breast cancer classification according to stage and molecular sub-type, allows for more accurate exploration of MBC epidemiology with regards to treatment effects, healthcare resource use and overall survival. However, detailed data sources or registries with relevant information about stage, molecular subtype and treatment are not available at the national level. The above–mentioned information tends to be restricted to individual hospitals or regions, thereby limiting the generalisability of the findings. For example, although the Surveillance, Epidemiology, and End Results (SEER) database provides a record of the incidence and prevalence of breast cancer diagnosed in the US, it does not routinely provide data on disease recurrence [10]. This is a common situation for population–based registers across the world. Similarly, in Sweden, new cancer cases are registered in the national Swedish Cancer Register, with almost 100% coverage. Although this administrative dataset can facilitate nationwide population studies, it is limited due to no information on essential prognostic factors such as cancer recurrence.
The Impact of Micropapillary Component Ratio on the Prognosis of Patients With Invasive Micropapillary Breast Carcinoma
Published in Journal of Investigative Surgery, 2020
Cemal Kaya, Ramazan Uçak, Emre Bozkurt, Sinan Ömeroğlu, Kinyas Kartal, Pınar Yazıcı, Ufuk Oğuz İdiz, Mehmet Mihmanlı
Breast cancer is the most common cancer type in women and covers 23% of all female cancers and is the second leading cause of cancer-related deaths in women.1,2 The incidence of breast cancer increases in developing countries due to life expectancy increased urbanization and changing lifestyle. At the beginning of the last century, it was enough to know that the patient had breast malignancy, and the same type of treatment was applied to all of the breast cancer patients. The observation of different prognoses of patients with the same type of cancer over time and the increasing definition of different morphologic variants by pathologists over the past 50 years have led to a debate on breast cancer classification. Invasive breast cancer is currently classified as invasive ductal carcinoma – not otherwise specified (IDC-NOS) and other specific subtypes. IDC-NOS constitutes approximately 60–75% of all breast cancers while other special subtypes represent 20–25% of all breast cancers.3,4 Invasive micropapillary carcinoma (IMPC) ofFIGURE 1the breast, one of the variants of IDC-NOS, is a rare and unique subtype of increasing interest in recent years.
Case report: acromegaly and breast cancer in a woman with turner syndrome
Published in Gynecological Endocrinology, 2021
Sabine Naessén, Kerstin Landin-Wilhelmsen
Tubular breast cancers are usually positive for the estrogen and/or progesterone receptors (ER/PR+) and negative for the HER2 receptor (HER2−), and less likely to involve the lymph nodes, is more responsive to treatment, and may have a better prognosis than more common types of invasive ductal cancer. This patient had neither lymph node involvement nor more than grade 1, according to Elston–Ellis (most widely used system for histological grading of breast cancer) classification [21].