3D Image Segmentation for Lung Cancer Using U-Net Architecture

EasyChair Preprint 8924, version 2

Abstract

In this paper, we present a new method of medical image segmentation based on U-Net algorithm. The general idea is to create an optimal segmentation that allowed the medical staff to distinct the different parts of the tumor using the U-Net architecture which represent the more elegant architecture, called a fully convolutional network. The main idea is to complete a contracting network by successive layers; pooling operations are replaced by oversampling operators. Therefore, these layers increase the resolution of the output. This technique is employed to merge different data sources in order to increase the quality of the information and to obtain an optimal segmented image. Segmentation results from the proposed method are validated and the classification accuracy for the test data available is evaluated, and then a comparative study versus existing techniques is presented. The experimental results demonstrate the superiority of using Modified U-NET for image segmentation.

Keyphrases: Classification., Conventional network, Segmentation, UNet architecture

@booklet{EasyChair:8924,
  author    = {Elloumi Nabila and Ben Chaabane Salim and Seddik Hassen},
  title     = {3D Image Segmentation for Lung Cancer Using U-Net Architecture},
  howpublished = {EasyChair Preprint 8924},
  year      = {EasyChair, 2022}}