Trainable Weka Segmentation: a machine learning tool for microscopy pixel classification

• DOI: 10.1093/bioinformatics/btx180
• Publication Date: 2017-03-28T14:04:40Z
• Authors: Ignacio Arganda-C...; Verena Kaynig; Curtis Rueden; Kevin W Eliceiri; Johannes Schindelin; Albert Cardona; H Sebastian Seung
• Keywords: Machine Learning; Microscopy; 0303 health sciences; 03 medical and health sciences; Image Processing, Computer-Assisted; Animals; Drosophila; Software

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 interest. This process is time-consuming a major bottleneck in evaluation pipeline. To overcome this problem, we have introduced Trainable Weka Segmentation (TWS), machine learning tool that leverages limited number manual annotations order to train classifier segment remaining automatically. In addition, TWS can provide unsupervised segmentation schemes (clustering) be customized employ user-designed features or classifiers.TWS distributed as open-source software part Fiji processing distribution ImageJ at http://imagej.net/Trainable_Weka_Segmentation [e-mail] available Bioinformatics online.