INVESTIGATING DEEP LEARNING BASED BREAST CANCER SUBTYPING USING PAN-CANCER AND MULTI-OMIC DATA
ABSTARCT :
Breast Cancer comprises multiple subtypes implicated in prognosis. Existing stratification methods rely on the expression quantification of small gene sets. Next Generation Sequencing promises large amounts of omic data in the next years. In this scenario, we explore the potential of machine learning and, particularly, deep learning for breast cancer subtyping.a. When multi-omic data types are combined together, performance of deep models shows little (if any) improvement in accuracy, indicating the need for further analysis on larger datasets of multi-omic data as and when they become available. We make use of multi-omic data, including microRNA expressions and copy number alterations, and we provide an in-depth investigation of several supervised and semi-supervised architectures Obtained accuracy results show simpler models to perform at least as well as the deep semi-supervised approaches on our task over gene expression data a. When multi-omic data types are combined together, performance of deep models shows little (if any) improvement in accuracy, indicating the need for further analysis on larger datasets of multi-omic data as and when they become available
EXISTING SYSTEM :
? In Existing system Several multigene prognostic molecular tests have been proposed for BRCA over the last decade, contributing to a better stratification, analysis, and understanding of its prognosisrelated molecular subtypes.
? Notwithstanding their proven predictive power, these tests still use classification models based on gene expression values of only a few genes, leaving much of the additional BRCA traits and heterogeneity unexplained
PROPOSED SYSTEM :
? This work will review existing computational and digital pathology methods for breast cancer diagnosis with a special focus on deep learning. The paper starts by reviewing public datasets related to breast cancer diagnosis.
? Additionally, existing deep learning methods for breast cancer diagnosis are reviewed. The publicly available code repositories are introduced as well. The paper is closed by highlighting challenges and future works for deep learning-based diagnosis
ADVANTAGE :
? breast cancer diagnosis OR malignant growth OR tumor AND (deep learning OR machine learning)
? Other studies reported that estrogen receptor status (trauma centers) is a fundamental atomic marker used to diagnose and select treatment options
? A limited set of samples with lesion-level annotation was used in the first phase of training.
? breast cancer diagnosis OR malignant growth OR tumor AND (deep learning OR machine learning)
? Other studies reported that estrogen receptor status (trauma centers) is a fundamental atomic marker used to diagnose and select treatment options
? A limited set of samples with lesion-level annotation was used in the first phase of training.
|