Center for Neuroscience and Regenerative Medicine Attribution Non-Commercial Share Alike Yes Henry Jackson Foundation NITRC Fast Lesion Extraction using Convolutional Neural Networks Dzung Pham FLEXCONN (Fast Lesion Extraction using Convolutional Neural Networks) is a toolbox for segmenting white matter lesions from multi-contrast MR images. Using T1-w and FLAIR images, a fully convolutional neural network (CNN) is trained using manually labeled training data. The trained CNN model can be applied to pre-processed pair of T1 and FLAIR images to generate a lesion membership as well as a hard segmentation. The algorithm is described in the following paper: https://arxiv.org/abs/1803.09172 Python codes for training and prediction are provided. Trained models using manually labeled atlases from ISBI-2015 challenge (https://www.nitrc.org/projects/longitudinal_ms) are also provided. The CNN is implemented in Tensorflow and Keras (https://github.com/fchollet/keras). This work was developed with funding support from the National Multiple Sclerosis Society (RG-1507-05243) and from the Center for Neuroscience and Regenerative Medicine in the Department of Defense. 2017-10-18 Codes 2017-10-17 Atlases Fast Lesion Extraction using Convolutional Neural Networks MR, Attribution Non-Commercial Share Alike http://www.nitrc.org/projects/flexconn/ pham@jhu.edu