Breast Cancer Detection classifier built from the The Breast Cancer Histopathological Image Classification (BreakHis) dataset composed of 7,909 microscopic images.

Computer-aided diagnosis in histopathological images of the Endometrium

Patoloji Atlası

2020 - Machine Learning License Project

Created an algorithm to identify metastatic cancer in small image patches taken from larger digital pathology scans. The data used for this competition is a slightly modified version of the PatchCamelyon (PCam) benchmark dataset.

Developed a fine-tuned EfficientNetB0 model which is a pre-trained Convolutional Neural Network (CNN) model to train using lungs and colon cancer dataset and classify if the unseen image belonged to benign, adenocarcinoma or squamous cell carcinoma cancer type.

Breast Cancer Histopathological Image Classification

Pathology Atlas (English version of Patoloji Atlası)

Histopathologic Cancer Detection

This is the course project of PRML course. In this project, we have implemented various deep learning algorithms like Transfer Learning, CNN and MLP, and some other classification algorithms like Random Forest, LightGBM etc. to classify histopathological images to reduce the human intervention yet providing accurate classification results.

Created an algorithm to identify metastatic cancer in small image patches taken from larger digital pathology scans. The data used for this competition is a slightly modified version of the PatchCamelyon (PCam) benchmark dataset (does not contain duplicates)