Automatic localization of locally similar structures based on the scale-widening random regression forest. Štern, D., Ebner, T., & Urschler, M. In 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI), pages 1422-1425, 2016. IEEE. ![Automatic localization of locally similar structures based on the scale-widening random regression forest [link]](https://bibbase.org/img/filetypes/link.svg "link")
Website abstract bibtex © 2016 IEEE. Selection of set of training pixels and feature range show to be critical scale-related parameters with high impact on results in localization methods based on random regression forests (RRF). Trained on pixels randomly selected from images with long range features, RRF captures the variation in landmark location but often without reaching satisfying accuracy. Conversely, training an RRF with short range features in a landmark's close surroundings enables accurate localization, but at the cost of ambiguous localization results in the presence of locally similar structures. We present a scale-widening RRF method that effectively handles such ambiguities. On a challenging hand radiography image data set, we achieve median and 90th percentile localization errors of 0.81 and 2.64mm, respectively, outperforming related state-of-the-art methods.
@inProceedings{
title = {Automatic localization of locally similar structures based on the scale-widening random regression forest},
type = {inProceedings},
year = {2016},
identifiers = {[object Object]},
keywords = {anatomical landmark localization,hand X-ray,random regression forest,scale range of features},
pages = {1422-1425},
websites = {http://ieeexplore.ieee.org/document/7493534/},
publisher = {IEEE},
city = {Prague},
id = {ae8d4669-9b1b-33f1-8907-5a05bc95f8db},
created = {2018-02-18T20:51:33.093Z},
file_attached = {false},
profile_id = {53d1e3c7-2f16-3c81-9a84-dccd45be4841},
last_modified = {2018-02-22T08:05:51.573Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Stern2016b},
notes = {Oral},
private_publication = {false},
abstract = {© 2016 IEEE. Selection of set of training pixels and feature range show to be critical scale-related parameters with high impact on results in localization methods based on random regression forests (RRF). Trained on pixels randomly selected from images with long range features, RRF captures the variation in landmark location but often without reaching satisfying accuracy. Conversely, training an RRF with short range features in a landmark's close surroundings enables accurate localization, but at the cost of ambiguous localization results in the presence of locally similar structures. We present a scale-widening RRF method that effectively handles such ambiguities. On a challenging hand radiography image data set, we achieve median and 90th percentile localization errors of 0.81 and 2.64mm, respectively, outperforming related state-of-the-art methods.},
bibtype = {inProceedings},
author = {Štern, Darko and Ebner, Thomas and Urschler, Martin},
booktitle = {2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI)}
}
Downloads: 0
{"_id":"7PZ7JNbCmkaYvFdB8","bibbaseid":"tern-ebner-urschler-automaticlocalizationoflocallysimilarstructuresbasedonthescalewideningrandomregressionforest-2016","authorIDs":["5dc49ed5d87d2edf0100002b"],"author_short":["Štern, D.","Ebner, T.","Urschler, M."],"bibdata":{"title":"Automatic localization of locally similar structures based on the scale-widening random regression forest","type":"inProceedings","year":"2016","identifiers":"[object Object]","keywords":"anatomical landmark localization,hand X-ray,random regression forest,scale range of features","pages":"1422-1425","websites":"http://ieeexplore.ieee.org/document/7493534/","publisher":"IEEE","city":"Prague","id":"ae8d4669-9b1b-33f1-8907-5a05bc95f8db","created":"2018-02-18T20:51:33.093Z","file_attached":false,"profile_id":"53d1e3c7-2f16-3c81-9a84-dccd45be4841","last_modified":"2018-02-22T08:05:51.573Z","read":false,"starred":false,"authored":"true","confirmed":"true","hidden":false,"citation_key":"Stern2016b","notes":"Oral","private_publication":false,"abstract":"© 2016 IEEE. Selection of set of training pixels and feature range show to be critical scale-related parameters with high impact on results in localization methods based on random regression forests (RRF). Trained on pixels randomly selected from images with long range features, RRF captures the variation in landmark location but often without reaching satisfying accuracy. Conversely, training an RRF with short range features in a landmark's close surroundings enables accurate localization, but at the cost of ambiguous localization results in the presence of locally similar structures. We present a scale-widening RRF method that effectively handles such ambiguities. On a challenging hand radiography image data set, we achieve median and 90th percentile localization errors of 0.81 and 2.64mm, respectively, outperforming related state-of-the-art methods.","bibtype":"inProceedings","author":"Štern, Darko and Ebner, Thomas and Urschler, Martin","booktitle":"2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI)","bibtex":"@inProceedings{\n title = {Automatic localization of locally similar structures based on the scale-widening random regression forest},\n type = {inProceedings},\n year = {2016},\n identifiers = {[object Object]},\n keywords = {anatomical landmark localization,hand X-ray,random regression forest,scale range of features},\n pages = {1422-1425},\n websites = {http://ieeexplore.ieee.org/document/7493534/},\n publisher = {IEEE},\n city = {Prague},\n id = {ae8d4669-9b1b-33f1-8907-5a05bc95f8db},\n created = {2018-02-18T20:51:33.093Z},\n file_attached = {false},\n profile_id = {53d1e3c7-2f16-3c81-9a84-dccd45be4841},\n last_modified = {2018-02-22T08:05:51.573Z},\n read = {false},\n starred = {false},\n authored = {true},\n confirmed = {true},\n hidden = {false},\n citation_key = {Stern2016b},\n notes = {Oral},\n private_publication = {false},\n abstract = {© 2016 IEEE. Selection of set of training pixels and feature range show to be critical scale-related parameters with high impact on results in localization methods based on random regression forests (RRF). Trained on pixels randomly selected from images with long range features, RRF captures the variation in landmark location but often without reaching satisfying accuracy. Conversely, training an RRF with short range features in a landmark's close surroundings enables accurate localization, but at the cost of ambiguous localization results in the presence of locally similar structures. We present a scale-widening RRF method that effectively handles such ambiguities. On a challenging hand radiography image data set, we achieve median and 90th percentile localization errors of 0.81 and 2.64mm, respectively, outperforming related state-of-the-art methods.},\n bibtype = {inProceedings},\n author = {Štern, Darko and Ebner, Thomas and Urschler, Martin},\n booktitle = {2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI)}\n}","author_short":["Štern, D.","Ebner, T.","Urschler, M."],"urls":{"Website":"http://ieeexplore.ieee.org/document/7493534/"},"bibbaseid":"tern-ebner-urschler-automaticlocalizationoflocallysimilarstructuresbasedonthescalewideningrandomregressionforest-2016","role":"author","keyword":["anatomical landmark localization","hand X-ray","random regression forest","scale range of features"],"downloads":0},"bibtype":"inProceedings","creationDate":"2019-11-07T22:46:45.714Z","downloads":0,"keywords":["anatomical landmark localization","hand x-ray","random regression forest","scale range of features"],"search_terms":["automatic","localization","locally","similar","structures","based","scale","widening","random","regression","forest","štern","ebner","urschler"],"title":"Automatic localization of locally similar structures based on the scale-widening random regression forest","year":2016}