Academia EduSoft
Published 2024 | Version v1
Figure Open

Classification of Breast Cancer Tumors from Histopathological Images through a Modified ResNet-50 Architecture - Figure 1. The architecture of our proposed method

Authors/Creators

  • 1. National University of Science and Technology Politehnica Bucharest, Romania
  • 2. Vasile Alecsandri University of Bacau, Romania

Description

We propose a supervised learning approach based on a slightly modified ResNet-50 (He et al., 2016) architecture, which can be observed in Figure 1. We add a sequential part at the end of the ResNet50 architecture which comprises an extra Batch Normalization Layer in front of a Fully Connected layer with 256 elements, using a ReLu activation function. Then the output of these layers is reduced to just one, since we are only interested in classifying if cancer is present or not, for which we use a Sigmoid activation function.

Notes

https://brain.edusoft.ro/index.php/brain/article/view/1598

Files

Classification of Breast Cancer Tumors from Histopathological Images through a Modified ResNet-50 Architecture fig(1).png

Files (19.7 kB)