Ignacio Arganda-Carreras1,2,3, Verena Kaynig4, Curtis Rueden5, Kevin W Eliceiri5, Johannes Schindelin5, Albert Cardona6, H Sebastian Seung7. 1. Ikerbasque, Basque Foundation for Science, Bilbao 48013, Spain. 2. Computer Science and Artificial Intelligence Department, Basque Country University, San Sebastian 20018, Spain. 3. Donostia International Physics Center, San Sebastian 20018, Spain. 4. Harvard John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA 02138, USA. 5. Laboratory for Optical and Computational Instrumentation, University of Wisconsin, Madison, WI 53706, USA. 6. Howard Hughes Medical Institute, Janelia Research Campus, Ashburn, VA 20147, USA. 7. Neuroscience Institute and Computer Science Department, Princeton University, NJ 08544, USA.
Abstract
SUMMARY: State-of-the-art light and electron microscopes are capable of acquiring large image datasets, but quantitatively evaluating the data often involves manually annotating structures of interest. This process is time-consuming and often a major bottleneck in the evaluation pipeline. To overcome this problem, we have introduced the Trainable Weka Segmentation (TWS), a machine learning tool that leverages a limited number of manual annotations in order to train a classifier and segment the remaining data automatically. In addition, TWS can provide unsupervised segmentation learning schemes (clustering) and can be customized to employ user-designed image features or classifiers. AVAILABILITY AND IMPLEMENTATION: TWS is distributed as open-source software as part of the Fiji image processing distribution of ImageJ at http://imagej.net/Trainable_Weka_Segmentation . CONTACT: ignacio.arganda@ehu.eus. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
SUMMARY: State-of-the-art light and electron microscopes are capable of acquiring large image datasets, but quantitatively evaluating the data often involves manually annotating structures of interest. This process is time-consuming and often a major bottleneck in the evaluation pipeline. To overcome this problem, we have introduced the Trainable Weka Segmentation (TWS), a machine learning tool that leverages a limited number of manual annotations in order to train a classifier and segment the remaining data automatically. In addition, TWS can provide unsupervised segmentation learning schemes (clustering) and can be customized to employ user-designed image features or classifiers. AVAILABILITY AND IMPLEMENTATION: TWS is distributed as open-source software as part of the Fiji image processing distribution of ImageJ at http://imagej.net/Trainable_Weka_Segmentation . CONTACT: ignacio.arganda@ehu.eus. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Authors: Mariska van Lier; M Hadi Saiepour; Koen Kole; Juliette E Cheyne; Nawal Zabouri; Thomas Blok; Yi Qin; Emma Ruimschotel; J Alexander Heimel; Christian Lohmann; Christiaan N Levelt Journal: J Neurosci Date: 2020-06-11 Impact factor: 6.167
Authors: Jan Van den Bulcke; Marijn A Boone; Jelle Dhaene; Denis Van Loo; Luc Van Hoorebeke; Matthieu N Boone; Francis Wyffels; Hans Beeckman; Joris Van Acker; Tom De Mil Journal: Ann Bot Date: 2019-11-15 Impact factor: 4.357
Authors: Gadea Mata; Miroslav Radojević; Carlos Fernandez-Lozano; Ihor Smal; Niels Werij; Miguel Morales; Erik Meijering; Julio Rubio Journal: Neuroinformatics Date: 2019-04
Authors: Zoe L Grant; Lachlan Whitehead; Vickie Hy Wong; Zheng He; Richard Y Yan; Abigail R Miles; Andrew V Benest; David O Bates; Claudia Prahst; Katie Bentley; Bang V Bui; Robert Ca Symons; Leigh Coultas Journal: J Clin Invest Date: 2020-08-03 Impact factor: 14.808
Authors: Wesley A Leigh; Guillermo Del Valle; Sharif Amit Kamran; Bernard T Drumm; Alireza Tavakkoli; Kenton M Sanders; Salah A Baker Journal: Cell Calcium Date: 2020-07-28 Impact factor: 6.817