An efficient transfer learning based cross model classification (TLBCM) technique for the prediction of breast cancer

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18450%2F23%3A50020376" target="_blank" >RIV/62690094:18450/23:50020376 - isvavai.cz</a>

Result on the web

<a href="https://peerj.com/articles/cs-1281/" target="_blank" >https://peerj.com/articles/cs-1281/</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.7717/peerj-cs.1281" target="_blank" >10.7717/peerj-cs.1281</a>

Result language

angličtina

Original language name

An efficient transfer learning based cross model classification (TLBCM) technique for the prediction of breast cancer

Original language description

Breast cancer has been the most life-threatening disease in women in the last few decades. The high mortality rate among women is due to breast cancer because of less awareness and a minimum number of medical facilities to detect the disease in the early stages. In the recent era, the situation has changed with the help of many technological advancements and medical equipment to observe breast cancer development. The machine learning technique supports vector machines (SVM), logistic regression, and random forests have been used to analyze the images of cancer cells on different data sets. Although the particular technique has performed better on the smaller data set, accuracy still needs to catch up in most of the data, which needs to be fairer to apply in the real-time medical environment. In the proposed research, state-of-the-art deep learning techniques, such as transfer learning, based cross model classification (TLBCM), convolution neural network (CNN) and transfer learning, residual network (ResNet), and Densenet proposed for efficient prediction of breast cancer with the minimized error rating. The convolution neural network and transfer learning are the most prominent techniques for predicting the main features in the data set. The sensitive data is protected using a cyber-physical system (CPS) while using the images virtually over the network. CPS act as a virtual connection between human and networks. While the data is transferred in the network, it must monitor using CPS. The ResNet changes the data on many layers without compromising the minimum error rate. The DenseNet conciliates the problem of vanishing gradient issues. The experiment is carried out on the data sets Breast Cancer Wisconsin (Diagnostic) and Breast Cancer Histopathological Dataset (BreakHis). The convolution neural network and the transfer learning have achieved a validation accuracy of 98.3%. The results of these proposed methods show the highest classification rate between the benign and the malignant data. The proposed method improves the efficiency and speed of classification, which is more convenient for discovering breast cancer in earlier stages than the previously proposed methodologies.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2023

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

PEERJ COMPUTER SCIENCE

ISSN

2376-5992

e-ISSN

2376-5992

Volume of the periodical

9

Issue of the periodical within the volume

March

Country of publishing house

GB - UNITED KINGDOM

Number of pages

23

Pages from-to

"Article Number: e1281"

UT code for WoS article

000956598000002

EID of the result in the Scopus database

—