MaLASeg

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

Left Atrium Segmentation in 3D Ultrasound Using Volumetric Convolutional Neural Networks

Supervision: Prof. Dr. Nassir Navab, Shadi Albarqouni

Abstract

Segmentation of the left atrium and deriving its size can help to predict and detect various cardiovascular conditions. Automation of this process in three-dimensional Ultrasound image data is desirable, since manual delineations are time-consuming, challenging and operator-dependent. Convolutional neural networks have made improvements in computer vision and in medical image processing. Fully convolutional networks have successfully been applied to segmentation tasks and were extended to work on volumetric data. This work examines the performance of a combined neural network architecture of existing models on left atrial segmentation. The loss function merges the objectives of volumetric segmentation, incorporation of a shape prior and the unsupervised adaptation to different Ultrasound imaging devices.

Requirements:

  • Good understanding of Ultrasound Imaging
  • Good understanding of statistics and machine learning methods.
  • Very good programming skills in Python & TensorFlow? / pyTorch

Location:

  • Garching

Literature

Resultant Paper

M. Degel, N. Navab, S. Albarqouni
Domain and Geometry Agnostic CNNs for Left Atrium Segmentation in 3D Ultrasound
Proceedings of 21st International Conference on Medical Image Computing and Computer Assisted Interventions (MICCAI), Granada, Spain, September 2018
A pre-print version is available online at arXiv.
(bib)

ProjectForm
Title: Left Atrium Segmentation in 3D Ultrasound Using Volumetric Convolutional Neural Networks
Abstract: Segmentation of the left atrium and deriving its size can help to predict and detect various cardiovascular conditions. Automation of this process in three-dimensional Ultrasound image data is desirable, since manual delineations are time-consuming, challenging and operator-dependent. Convolutional neural networks have made improvements in computer vision and in medical image processing. Fully convolutional networks have successfully been applied to segmentation tasks and were extended to work on volumetric data. This work examines the performance of a combined neural network architecture of existing models on left atrial segmentation. The loss function merges the objectives of volumetric segmentation, incorporation of a shape prior and the unsupervised adaptation to different Ultrasound imaging devices.
Student: Markus Degel
Director: Prof. Dr. Nassir Navab
Supervisor: Shadi Albarqouni
Type: Master Thesis
Area: Machine Learning, Medical Imaging
Status: finished
Start:  
Finish:  
Thesis (optional):  
Picture:  


Edit | Attach | Refresh | Diffs | More | Revision r1.3 - 14 Jul 2018 - 19:05 - ShadiAlbarqouni