• Breast cancer malignancy class...

Treffer: Breast cancer malignancy classification based on breast histopathology images using convolutional neural network.

Title:
Breast cancer malignancy classification based on breast histopathology images using convolutional neural network.
Authors:
Noviandini, Farah1 (AUTHOR) endarko@physics.its.ac.id, Darmawan, Bunga Mastiti1 (AUTHOR), Agustin, Rizki Wulan1 (AUTHOR), Endarko1 (AUTHOR)
Source:
AIP Conference Proceedings. 2022, Vol. 2542 Issue 1, p1-7. 7p.
Subject Terms:
*CONVOLUTIONAL neural networks, *BREAST, *BREAST cancer, *TUMOR classification, *BREAST imaging, *MEDICAL personnel
Geographic Terms:
INDONESIA
Database:
Academic Search Index

Weitere Informationen

Breast cancer is one of the main causes of women's death in Indonesia. The prediction of the breast by medical personnel to classified the type of the breast histopathology image (BreakHis) with high accuracy in a short time is needed. This study aims to determine BreakHis' malignancy classification, including in the benign or malignant class using the CNN (Convolutional Neural Network) algorithm and determine the optimization's results of the accuracy benign class and malignant class using architectures of MobileNetV2 and ResNet50V2. In this study, 7891 BreakHis datasets are used with 40×, 100×, 200×, and 400× factors from the Kaggle website. The whole image is resized to 224×224 pixels and used Jupiter with the Python programming language to perform this study. The results showed the highest accuracy in the ResNet50V2 model with accuracy values of 100% for training data, 95.8% for testing, and 97% for validation. [ABSTRACT FROM AUTHOR]