Image pre-processing: We used a 2D Gaussian filter to generate fuzzy ground truth.
Deep Learning Network Architecture: We developed a deep learning U-Net Convolutional Neural Network (CNN) followed by binary classifier to delineate the nucleus and detect the tumor malignancy. Next, we develop a Convolutional Neural Network model (U-Net Network Architecture) to analyze image dataset and detect nucleus.
The final module of the pipeline is classification of the generated nucleus patches into two classes of cancer and healthy.
