Here you can find the papers for some of the projects that I have done.

VisiCell

VisiCell is an web and mobile application that automates counting of cells dyed with trypan blue. GitHub

• In English

Glacier Mass Change Prediction (Polar Research Projects Competition)

In this project we have trained a regression model using 6 independent variables to find their relation to glacier mass change. Then we use Prophet procedure to forecast this data 10 years into future and made predictions about future glacier mass change.

• In Turkish

Disease Detection From Abdominal CT Scan (Teknofest)

For this competition we developed a machine learning model network comprising of six YOLOv4-P6 models for detection of appendicitis, cholecystitis, pancreatitis, kidney and bladder stone, diverticulitis, aortic aneurysm and dissection from abdominal CT scans. Model achieved 0.743 accuracy at mAP.5 metric for all diseases combined on a dataset given by Ministry of Health. GitHub

• In Turkish

Breast Cancer Detection From Mammograms (Teknofest)

For this competition we trained EfficientNet-B3 models to detect breast composition and BI-RADS category. Trained model achieved 0.6713 accuracy on a given test dataset of 3,972 patients. GitHub

• In Turkish

Labtoolkit

Labtoolkit is a previous version of VisiCell which uses classical image processing methods instead of machine learning. GitHub