2D-3D Fully Convolutional Neural Networks for Cardiac MR Segmentation
| Autor: | Jay Patravali, Sasank Chilamkurthy, Shubham Jain |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2017 |
| Předmět: |
FOS: Computer and information sciences
business.industry Computer science Computer Vision and Pattern Recognition (cs.CV) Deep learning Computer Science - Computer Vision and Pattern Recognition Pattern recognition 02 engineering and technology Function (mathematics) Convolutional neural network End systole Cross entropy 3d segmentation 0202 electrical engineering electronic engineering information engineering Key (cryptography) 020201 artificial intelligence & image processing Segmentation Artificial intelligence business cs.CV |
| Zdroj: | Lecture Notes in Computer Science ISBN: 9783319755403 STACOM@MICCAI Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges |
| Popis: | In this paper, we develop a 2D and 3D segmentation pipelines for fully automated cardiac MR image segmentation using Deep Convolutional Neural Networks (CNN). Our models are trained end-to-end from scratch using the ACD Challenge 2017 dataset comprising of 100 studies, each containing Cardiac MR images in End Diastole and End Systole phase. We show that both our segmentation models achieve near state-of-the-art performance scores in terms of distance metrics and have convincing accuracy in terms of clinical parameters. A comparative analysis is provided by introducing a novel dice loss function and its combination with cross entropy loss. By exploring different network structures and comprehensive experiments, we discuss several key insights to obtain optimal model performance, which also is central to the theme of this challenge. Accepted in STACOM '17 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|