Synthesis of Convolutional Neural Network architectures for biomedical image classification

Oleh Berezsky, Petro Liashchynskyi, Oleh Pitsun, Ivan Izonin

Abstract: Highlights•CNNs are pivotal in biomedical image classification, particularly in oncology.•We introduced an automated method for efficiently searching optimal CNN architectures.•The developed method stands out for its efficiency, according to the short search time.•Our method outperforms well-known CNN architectures (VGG-16, AlexNet, or LeNet-5).