Improving domain adaptation in de-identification of electronic health records through self-training

Autor: Jiyang Chen, Shun Liao, Jamie Ryan Kiros, Ting Chen, Zhaolei Zhang

Publikováno v: J Am Med Inform Assoc

Objective De-identification is a fundamental task in electronic health records to remove protected health information entities. Deep learning models have proven to be promising tools to automate de-identification processes. However, when the target d

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::532eb45d50aee7cdda966a4f70e40c4b
https://pubmed.ncbi.nlm.nih.gov/34363664

Comparing algorithms for automated vessel segmentation in computed tomography scans of the lung: The VESSEL12 study

Autor: Pim A. de Jong, Raúl San José Estépar, Marius Staring, Valery Naranjo, Daniel Jimenez-Carretero, Christina Stöcker, Mathias Prokop, Maciej Orkisz, Catalin Fetita, Christophe Lefevre, Arantza Campo, Changyan Xiao, Bram van Ginneken, Karteek Popuri, Wenzhe Xue, Erik Smistad, Dennis Bosboom, Andres Santos, Michael Pienn, Carlos Ortiz-de-Solorzano, Michael Helmberger, Martin Urschler, James C. Ross, Kamuran A. Kadipasaoglu, Dana Cobzas, Devrim Unay, Rina D. Rudyanto, Hans Meine, Ryan Kiros, Eva M. van Rikxoort, Frank Lindseth, Markus Hüllebrand, Berend C. Stoel, Maria J. Ledesma-Carbayo, Amir Hossein Foruzan, Sjoerd Kerkstra, George R. Washko, Arrate Muñoz-Barrutia, Pierre Yves Brillet, Xiangjun Zhu, Anna Fabijańska, Ilkay Oksuz, Fernando L opez Mir, Eliseo Villanueva, Anne C. Elster, Juan Carlos Prieto, Marcela Hernández Hoyos, Jianming Liang

Publikováno v: Medical Image Analysis
Medical Image Analysis, Elsevier, 2014, 18 (7), pp.1217-1232
Medical Image Analysis, 18, 1217-1232
Medical Image Analysis, 18, pp. 1217-1232
Medical Image Analysis, 18(7), 1217-1232
HAL
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname

Contains fulltext : 137671.pdf (Publisher’s version ) (Open Access) The {VESSEL12} ({VES}sel {SE}mentation in the {L}ung) challenge objectively compares the performance of different algorithms to identify vessels in thoracic computed tomography ({C

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b72783300002656bb2017bcb303b26b9
https://hdl.handle.net/2066/137671

Stacked Multiscale Feature Learning for Domain Independent Medical Image Segmentation

Autor: Martin Jagersand, Ryan Kiros, Dana Cobzas, Karteek Popuri

Publikováno v: Machine Learning in Medical Imaging ISBN: 9783319105802
MLMI

In this work we propose a feature-based segmentation approach that is domain independent. While most existing approaches are based on application-specific hand-crafted features, we propose a framework for learning features from data itself at multipl

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::aff6cced9d886cbe5daaa748cf65f54b
https://doi.org/10.1007/978-3-319-10581-9_4