Medical Image Segmentation Method Based on Improved Unet

Abstract

This paper is an attempt to apply 3DUnet system to medical image segmentation. The classifying model is built based on actual medical images from MSD Cardiac dataset. The 3DUnet system, which is developed on Convolutional Neural Networks will be of great significance in medical diagnosis and analysis. The paper analyzes and contains details of the 3DUnet system we built and the algorithms we applied. We applied the method of cutting the input images into patches and K-fold cross validation to obtain better results. The final average value of Dice is over 87%. Codes are available: https://github.com/LRXuanxuan/jubilant-chainsaw.