Naslov
Breast cancer classification

Autori
Radovanović, Nikola

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the International Scientific Student Conference RI-STEM-2021 / Lorencin, Ivan ; Baressi Šegota, Sandi - Rijeka, 2021, 129-133

ISBN
978-953-8246-22-7

Skup
International Student Scientific Conference (Ri-STEM 2021)

Mjesto i datum
Rijeka, Hrvatska, 10.06.2021. - 11.06.2021

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Breast cancer ; Classification ; Cross-validation ; Decision tree ; Feature selection ; K-Nearest neighbours ; Random forest

Sažetak
Breast cancer is most frequently diagnosed cancer and the second most frequent cause of death in women. Early detection and treatment is the key for the patient’s health and reduced mortality. Machine learning classification can be used to help physicians in early diagnosis and classification of breast tumours. In this paper, three types of classifiers are presented: Random forest, Decision tree, and K-nearest neighbours for breast cancer classification. The classifiers are evaluated and compared. Techniques for improvement: feature selection, grid search and hyperparameter tuning reduce training time and improve performances of the classifiers. The highest accuracy is achieved by Random forest classifier (99.41%).

Izvorni jezik
Engleski

Znanstvena područja
Interdisciplinarne tehničke znanosti, Temeljne medicinske znanosti

POVEZANOST RADA