Efficient Diagnoses of Breast Cancer Disease Using Deep Learning Technique

Document Type

Conference Proceeding

Source of Publication

ACM International Conference Proceeding Series

Publication Date

4-26-2024

Abstract

According to WHO 2023 survey, each year more than 2.3 million breast cancer cases are reported. Breast cancer is the either first or second biggest disease in females that is the cause of death in almost 95% of countries. Diagnosing breast cancer in its early stage can be helpful to overcome this disease and result in an increase in the survival chance of the patient. Machine learning (ML) models and well-established methods for encoding categorical data have produced a wide variety of surprising outcomes when used to diagnose breast cancer using datasets that are imbalanced from testing. Early experiments also used an artificial neural network(ANN) to extract characteristics without understanding the sequencing data. In this study, we present a hybrid deep learning (DL) BiLSTM-CNN model, in order to diagnose breast cancer efficiently from patient data. The BiLSTM-CNN model was applied after dataset balancing. Contrasting to previous investigations, the experimental results of our suggested hybrid DL model were outstanding, with an accuracy of 99.3%, a precision of 99%, a recall of 99%, and an F1-score of 99%.

ISBN

[9798400717055]

Publisher

ACM

First Page

136

Last Page

143

Disciplines

Computer Sciences | Medicine and Health Sciences

Keywords

Breast Cancer Diagnoses, Deep Learning, Disease prediction, hybrid deep learning

Scopus ID

85203793448

Indexed in Scopus

yes

Open Access

no

Link to Full Text

Share

COinS