Breast cancer diagnosis and classification using machine learning approach

Title : Breast cancer diagnosis and classification using machine learning approach

Abstract:

Breast cancer continues to be the most frequent cancer in females, affecting about 1 in 8 and causing the highest number of cancer-related deaths in females worldwide despite remarkable progress in early diagnosis, screening, and patient management. All breast lesions are not malignant and all the benign lesions do not progress to cancer. However, the accuracy of diagnosis can be increased by a combination or preoperative tests such as physical examination, mammography, fine-needle aspiration cytology, and core needle biopsy. These procedures are more accurate, reliable, and acceptable when compared with a single adopted diagnostic procedure despite of having their limitations. Recent studies showed an accurate prediction and diagnosis of breast cancer using machine learning (ML) approaches. The objective of this study was to explore the application of ML approaches to classify breast cancer based on feature values generated from a digitized image of a fine-needle aspiration of a breast mass.  To achieve this objective, we used ML algorithms and  collected scientific datasets of 569 breast cancer patients from Kaggle (https://www.kaggle.com/uciml/breast-cancer-wisconsin-data) and interpreted these dataset based on ten real-valued features (radius, texture, perimeter, area, smoothness, compactness, concavity, concave points, symmetry, and fractal dimension) from a digitized image of a fine needle aspirate (FNA) of a breast mass. Among the 569 patients tested, 63% were diagnosed with benign prostate cancer and 37% were diagnosed with malignant prostate cancer. Benign tumor grows slowly and does not spread while malignant tumor grows rapidly and spread to other parts of the body.

Keywords: Breast cancer; malignant, benign, machine learning, computer-based learning

What will audience learn from your presentation?

• This work presents a novel computer-aided diagnosis system for the prediction, diagnosis, and classification of breast cancer using machine learning technique.
• Audience will learn machine learning approaches can be used to screen large dataset, diagnose, and treat breast cancer.

Biography:

Clement G. Yedjou is an Associate Professor in the Department of Biology at Florida Agricultural and Mechanical University. His research focuses on the assessment of medicinal plants as anti-cancer agents in the management of prostate cancer, and breast cancer using neoplastic cancer cells and mouse models. He has secured external competitive grants as a Principal Investigator (PI) or Co-PI and so far, he has published 72 peer-reviewed articles in prestigious journals and his work has been cited more than 8,700 times. He authored 8 book chapters and has presented several short courses and more than 120 keynote and invited talks in the United States, Canada, and Europe.