Article: Automated invasive cervical cancer disease detection at early stage through deep learning Journal: International Journal of Bioinformatics Research and Applications (IJBRA) 2023 Vol.19 No.4 pp.306 - 326 Abstract: Within the whole world, cervical cancer is one of the major causes of mortality for women. Currently, it is quite difficult for medical personnel to find such cancer before it spreads quickly. In order to predict cervical cancer using risk factors, this study employed a variety of machine learning classification techniques. Early discovery and forecast of cervical cancer can significantly increase the probability of fruitful treatment and lower mortality rates. Machine learning's profound learning sub-field has demonstrated significant guarantees within the elucidation and determination of medical pictures. This considers current improvements within the early discovery and expectation of cervical cancer utilising profound learning calculations. This work uses a dataset of 856 patients to propose a deep-learning method for the early diagnosis and prediction of cervical cancer. The flowchart for the suggested system shows the collection of acute patient's information, data pre-processing, model training, threshold prediction, cross-validation, and report creation. Inderscience Publishers - linking academia, business and industry through research

Title: Automated invasive cervical cancer disease detection at early stage through deep learning

Authors: Subhasish Mohapatra; Mohammed Siddique; Bijay Kumar Paikaray; Shaik Riyazbanu

Addresses: Department of CSE, Adamas University, Kolkata, India ' Department of Mathematics, Centurion University of Technology and Management, Odisha, India ' Faculty of Emerging Technologies, Sri Sri University, Cuttack, India ' Department of CSE, KSRM College of Engineering Kadapa, Andhra Pradesh, India

Abstract: Within the whole world, cervical cancer is one of the major causes of mortality for women. Currently, it is quite difficult for medical personnel to find such cancer before it spreads quickly. In order to predict cervical cancer using risk factors, this study employed a variety of machine learning classification techniques. Early discovery and forecast of cervical cancer can significantly increase the probability of fruitful treatment and lower mortality rates. Machine learning's profound learning sub-field has demonstrated significant guarantees within the elucidation and determination of medical pictures. This considers current improvements within the early discovery and expectation of cervical cancer utilising profound learning calculations. This work uses a dataset of 856 patients to propose a deep-learning method for the early diagnosis and prediction of cervical cancer. The flowchart for the suggested system shows the collection of acute patient's information, data pre-processing, model training, threshold prediction, cross-validation, and report creation.

Keywords: cervical cancer; early diagnosis; prediction; deep learning; machine learning; medical image analysis; mortality rates; challenges; future directions.

DOI: 10.1504/IJBRA.2023.135365

International Journal of Bioinformatics Research and Applications, 2023 Vol.19 No.4, pp.306 - 326

Received: 12 Jul 2023
Accepted: 18 Sep 2023
Published online: 06 Dec 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Automated invasive cervical cancer disease detection at early stage through deep learning

Keep up-to-date