X-ray In-Depth Decomposition

Supervision: Prof. Dr. Nassir Navab, Shadi Albarqouni

Abstract

In this project, we would like to work further on X-ray In-Depth decomposition presented in [1] modelling the physics of X-ray to recover the depth information.

Tasks:

• Modelling the decomposition problem
• Employing Deep Learning to attack the problem
• Validate the proposed algorithm

Requirements:

• Good understanding of medical physics
• Good understanding of statistics and deep learning methods. In particular Generative Adversarial Networks.
• Very good programming skills in Python/Matlab
• Willingness to closely collaborate with physicians and experts in machine learning.

Location:

• Garching

Literature

	(bib)
	This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each authors copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

	S. Albarqouni, U. Konrad, L. Wang, N. Navab, S. Demirci Single-View X-Ray Depth Recovery: Towards a Novel Concept for Image-Guided Interventions International Journal of Computer Assisted Radiology and Surgery (IJCARS), 2016, June 2016, Volume 11, Issue 6, pp 873-880. (bib)
	Abstract Purpose: X-ray imaging is widely used for guiding minimally-invasive surgeries. Despite ongoing efforts in particular towards advanced visualization incorporating mixed reality concepts, correct depth perception from X-ray imaging is still hampered due to its projective nature. Methods: In this paper, we introduce a radically new concept for predicting depth information from single view X-ray images. Patient-specific training data for depth and corresponding X-ray attenuation information is constructed using readily available preoperative 3D image information. The corresponding depth model is learned employing a novel label consistent dictionary learning method incorporating atlas and spatial prior constraints to allow for efficient reconstruction performance. Results: We have validated our algorithm on patient data acquired for different anatomy focus (abdomen and thorax). Of 100 image pairs per each of 6 experimental instances, 80 images have been used for training, and 20 for testing. Depth estimation results have been compared to ground truth depth values. Conclusions: We have achieved around 4.40% ± 2.04 and 11.47% ± 2.27 mean squared error on abdomen and thorax datasets respectively, visual results of our proposed method are very promising. We have therefore presented a radically new concept for enhancing depth perception for image guided interventions.
	This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each authors copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Resultant Paper