Integrating spatial configuration into heatmap regression based CNNs for landmark localization. Payer, C., Štern, D., Bischof, H., & Urschler, M. Medical Image Analysis, 54:207-219, 5, 2019.
Integrating spatial configuration into heatmap regression based CNNs for landmark localization [link]Website  doi  abstract   bibtex   
In many medical image analysis applications, only a limited amount of training data is available due to the costs of image acquisition and the large manual annotation effort required from experts. Training recent state-of-the-art machine learning methods like convolutional neural networks (CNNs) from small datasets is a challenging task. In this work on anatomical landmark localization, we propose a CNN architecture that learns to split the localization task into two simpler sub-problems, reducing the overall need for large training datasets. Our fully convolutional SpatialConfiguration-Net (SCN) learns this simplification due to multiplying the heatmap predictions of its two components and by training the network in an end-to-end manner. Thus, the SCN dedicates one component to locally accurate but ambiguous candidate predictions, while the other component improves robustness to ambiguities by incorporating the spatial configuration of landmarks. In our extensive experimental evaluation, we show that the proposed SCN outperforms related methods in terms of landmark localization error on a variety of size-limited 2D and 3D landmark localization datasets, i.e., hand radiographs, lateral cephalograms, hand MRIs, and spine CTs.
@article{
 title = {Integrating spatial configuration into heatmap regression based CNNs for landmark localization},
 type = {article},
 year = {2019},
 keywords = {Anatomical landmarks,Fully convolutional networks,Heatmap regression,Localization},
 pages = {207-219},
 volume = {54},
 websites = {https://linkinghub.elsevier.com/retrieve/pii/S1361841518305784},
 month = {5},
 id = {af1f2af2-fd2c-346f-98fe-d2893121d281},
 created = {2019-11-08T00:43:16.467Z},
 file_attached = {false},
 profile_id = {53d1e3c7-2f16-3c81-9a84-dccd45be4841},
 last_modified = {2019-11-08T01:39:21.158Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Payer2019MIAHeatmap},
 folder_uuids = {0ec41d70-75f1-4a99-820b-0a83ccc37f54},
 private_publication = {false},
 abstract = {In many medical image analysis applications, only a limited amount of training data is available due to the costs of image acquisition and the large manual annotation effort required from experts. Training recent state-of-the-art machine learning methods like convolutional neural networks (CNNs) from small datasets is a challenging task. In this work on anatomical landmark localization, we propose a CNN architecture that learns to split the localization task into two simpler sub-problems, reducing the overall need for large training datasets. Our fully convolutional SpatialConfiguration-Net (SCN) learns this simplification due to multiplying the heatmap predictions of its two components and by training the network in an end-to-end manner. Thus, the SCN dedicates one component to locally accurate but ambiguous candidate predictions, while the other component improves robustness to ambiguities by incorporating the spatial configuration of landmarks. In our extensive experimental evaluation, we show that the proposed SCN outperforms related methods in terms of landmark localization error on a variety of size-limited 2D and 3D landmark localization datasets, i.e., hand radiographs, lateral cephalograms, hand MRIs, and spine CTs.},
 bibtype = {article},
 author = {Payer, Christian and Štern, Darko and Bischof, Horst and Urschler, Martin},
 doi = {10.1016/j.media.2019.03.007},
 journal = {Medical Image Analysis}
}
Downloads: 0
About
Documentation
Keywords
Search
Users
Terms and Conditions of Use
Privacy Policy
Sitemap
© BibBase.org 2021