Kidney OCT 3D images classification using machine learning

Abstract

The goal of this research is to make a classification program for 3D images by using a CNN model. The images to classify are kidney images that have 3 different classes: Pelvis, Medulla and Cortex.

To do so, a data preprocessing was needed. The data preprocessing went through two big steps: cropping the 3D images to have smaller image volume and rotating the images to get a data enrichment. \bigskip

After that data preprocessing, the next step is to build a model that can achieve a better accuracy than 2D models that were used previously.