AutoSNAP: Automatically Learning Neural Architectures for Instrument Pose Estimation
Pages 375 - 384
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.
References
[1]
Bae W, Lee S, Lee Y, Park B, Chung M, Jung K-H, et al. Shen D et al. Resource optimized neural architecture search for 3D medical image segmentation Medical Image Computing and Computer Assisted Intervention – MICCAI 2019 2019 Cham Springer 228-236
[2]
Balakrishnan G, Zhao A, Sabuncu MR, Guttag J, and Dalca AV VoxelMorph: a learning framework for deformable medical image registration IEEE Trans. Med. Imaging 2019 38 8 1788-1800
[3]
Dong N, Xu M, Liang X, Jiang Y, Dai W, Xing E, et al. Shen D et al. Neural architecture search for adversarial medical image segmentation Medical Image Computing and Computer Assisted Intervention – MICCAI 2019 2019 Cham Springer 828-836
[4]
Elsken, T., Metzen, J.H., Hutter, F.: Neural architecture search: a survey 20, 1–21 (2019). http://jmlr.org/papers/v20/18-598.html
[5]
Hajj HA et al. CATARACTS: challenge on automatic tool annotation for cataract surgery Med. IA 2019 52 24-41
[6]
Kim S, et al., et al. Shen D, et al., et al. Scalable neural architecture search for 3D medical image segmentation Medical Image Computing and Computer Assisted Intervention – MICCAI 2019 2019 Cham Springer 220-228
[7]
Kügler, D., et al.: i3posnet: instrument pose estimation from x-ray in temporal bone surgery. Int. J. Comput. Assist. Radiol. Surg. 15(7), 1137–1145 (2020).
[8]
Liu, H., Simonyan, K., Yang, Y.: DARTS: differentiable architecture search. In: ICLR 2019 (2019). https://arxiv.org/pdf/1806.09055
[9]
Luo, R., Tian, F., Qin, T., Chen, E., Liu, T.Y.: Neural architecture optimization. In: Bengio, S., et al. (eds.) Advances in NeurIPS, vol. 31. Curran Associates, Inc. (2018)
[10]
Maier-Hein L et al. Surgical data science for next-generation interventions Nat. BioMed. Eng. 2017 1 9 691-696
[11]
Miao S, Wang ZJ, and Liao R A CNN regression approach for real-time 2D/3D registration IEEE Trans. Med. Imaging 2016 35 5 1352-1363
[12]
Schipper J et al. Navigation as a quality management tool in cochlear implant surgery J. Laryngol. Otol. 2004 118 10 764-770
[13]
Twinanda AP, Shehata S, Mutter D, Marescaux J, de Mathelin M, and Padoy N EndoNet: a deep architecture for recognition tasks on laparoscopic videos IEEE Trans. Med. Imaging 2017 36 1 86-97
[14]
Unberath M et al. Enabling machine learning in x-ray-based procedures via realistic simulation of image formation Int. J. Comput. Assist. Radiol. Surg. 2019 14 9 1517-1528
[15]
Vercauteren T, Unberath M, Padoy N, and Navab N CAI4CAI: the rise of contextual artificial intelligence in computer assisted interventions Proc. IEEE 2020 108 1 198-214
[16]
Weng Y, Zhou T, Li Y, and Qiu X NAS-Unet: neural architecture search for medical image segmentation IEEE Access 2019 7 44247-44257
[17]
Yu, Q., et al.: C2FNAS: coarse-to-fine neural architecture search for 3D medical image segmentation (2019). https://arxiv.org/pdf/1912.09628
[18]
Zhu, Z., Liu, C., Yang, D., Yuille, A., Xu, D.: V-NAS: neural architecture search for volumetric medical image segmentation. In: 2019 International Conference on 3D Vision, pp. 240–248. IEEE Computer Society, Conference Publishing Services, Los Alamitos (2019)
[19]
Zoph, B., Vasudevan, V., Shlens, J., Le, V.Q.: Learning transferable architectures for scalable image recognition. In: Brown, M.S., et al. (eds.) CVPR Proceedings (2018)
Index Terms
- AutoSNAP: Automatically Learning Neural Architectures for Instrument Pose Estimation
Index terms have been assigned to the content through auto-classification.
Recommendations
Neural architecture search: a survey
Deep Learning has enabled remarkable progress over the last years on a variety of tasks, such as image recognition, speech recognition, and machine translation. One crucial aspect for this progress are novel neural architectures. Currently employed ...
Automation of Deep Learning - Theory and Practice
ICMR '20: Proceedings of the 2020 International Conference on Multimedia RetrievalThe growing interest in both the automation of machine learning and deep learning has inevitably led to the development of a wide variety of methods to automate deep learning. The choice of network architecture has proven critical, and many improvements ...
Searching part-specific neural fabrics for human pose estimation
Highlights- We propose a novel micro and macro gradient-based architecture search space: parameterized cell-based neural fabric (CNF).
AbstractNeural architecture search (NAS) has emerged in many domains to jointly learn the architectures and weights of neural networks. The core spirit behind NAS is to automatically search neural architectures for target tasks with better ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Oct 2020
826 pages
ISBN:978-3-030-59715-3
DOI:10.1007/978-3-030-59716-0
© Springer Nature Switzerland AG 2020.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 04 October 2020
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 24 Nov 2024
Other Metrics
Citations
View Options
View options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in