TU Darmstadt / ULB / TUbiblio

AutoSNAP: Automatically Learning Neural Architectures for Instrument Pose Estimation

Kügler, David and Uecker, Marc and Kuijper, Arjan and Mukhopadhyay, Anirban (2020):
AutoSNAP: Automatically Learning Neural Architectures for Instrument Pose Estimation.
In: Medical Image Computing and Computer Assisted Intervention – MICCAI 2020, pp. 375-384,
Springer, 23rd International Conference on Medical Image Computing an Computer-Assisted Intervention (MICCAI 2020), virtual Conference, 04.-08.10., ISSN 03029743,
DOI: 10.1007/978-3-030-59716-0_36,
[Conference or Workshop Item]

Abstract

Despite recent successes, the advances in Deep Learning have not yet been fully translated to Computer Assisted Intervention (CAI) problems such as pose estimation of surgical instruments. Currently, neural architectures for classification and segmentation tasks are adopted ignoring significant discrepancies between CAI and these tasks. We propose an automatic framework (AutoSNAP) for instrument pose estimation problems, which discovers and learns architectures for neural networks. We introduce 1) an efficient testing environment for pose estimation, 2) a powerful architecture representation based on novel Symbolic Neural Architecture Patterns (SNAPs), and 3) an optimization of the architecture using an efficient search scheme. Using AutoSNAP, we discover an improved architecture (SNAPNet) which outperforms both the hand-engineered i3PosNet and the state-of-the-art architecture search method DARTS.

Item Type: Conference or Workshop Item
Erschienen: 2020
Creators: Kügler, David and Uecker, Marc and Kuijper, Arjan and Mukhopadhyay, Anirban
Title: AutoSNAP: Automatically Learning Neural Architectures for Instrument Pose Estimation
Language: English
Abstract:

Despite recent successes, the advances in Deep Learning have not yet been fully translated to Computer Assisted Intervention (CAI) problems such as pose estimation of surgical instruments. Currently, neural architectures for classification and segmentation tasks are adopted ignoring significant discrepancies between CAI and these tasks. We propose an automatic framework (AutoSNAP) for instrument pose estimation problems, which discovers and learns architectures for neural networks. We introduce 1) an efficient testing environment for pose estimation, 2) a powerful architecture representation based on novel Symbolic Neural Architecture Patterns (SNAPs), and 3) an optimization of the architecture using an efficient search scheme. Using AutoSNAP, we discover an improved architecture (SNAPNet) which outperforms both the hand-engineered i3PosNet and the state-of-the-art architecture search method DARTS.

Title of Book: Medical Image Computing and Computer Assisted Intervention – MICCAI 2020
Publisher: Springer
Uncontrolled Keywords: Interventional techniques, Medical applications, Medical imaging, Deep learning
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
20 Department of Computer Science > Mathematical and Applied Visual Computing
Event Title: 23rd International Conference on Medical Image Computing an Computer-Assisted Intervention (MICCAI 2020)
Event Location: virtual Conference
Event Dates: 04.-08.10.
Date Deposited: 19 Oct 2020 08:27
DOI: 10.1007/978-3-030-59716-0_36
Additional Information:

Part of the Lecture Notes in Computer Science book series (LNCS, volume 12263)

Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details