jcell 0.0.1rc0

Software package for training and testing deep learning based method applied to image segmentation

JCELL

jcell is an image segmentation software primarily dedicated to biological cells. The software is an implementation of our latest developments in cell segmentation using deep learning approaches specially aimed at segmenting clustered cells. We pioneered the use of multiclass segmentation to improve segmenting tightly packed cells (see ICIP2018) and recently introduced a combination of Youden's J Statistics and cross entropy as a robust loss working in tandem to promote a sharp classification of pixels/voxels (see ISBI2020). Due to J, highly imbalanced data can be directly trained bypassing the need of complicated data balancing strategies. This is the software used for winning DIC-C2DH-Hela and PhC-C2DH-U373 Cell segmentation challenges (http://celltrackingchallenge.net/latest-csb-results/).

For an in depth understading how the methods work check our publications [ICIP2018], [MICCAIW2019], [ISBI2020].

See documentation for more details on how to use this software.

[ISBI2020] J Regularization Improves Imbalanced Multiclass Segmentation. Fidel A. Guerrero Peña, Pedro D. Marrero Fernandez, Paul T. Tarr, Tsang Ing Ren, Elliot M. Meyerowitz, Alexandre Cunha. IEEE 17th International Symposium on Biomedical Imaging (ISBI). 2020. https://ieeexplore.ieee.org/abstract/document/9098550. Arxiv https://arxiv.org/abs/1910.09783.

[MICCAIW2019] A Weakly Supervised Method for Instance Segmentation of Biological Cells. Fidel A. Guerrero Pena, Pedro D. Marrero Fernandez, Tsang Ing Ren, Alexandre Cunha. Domain Adaptation and Representation Transfer and Medical Image Learning with Less Labels and Imperfect Data. Springer. 2019. https://link.springer.com/chapter/10.1007/978-3-030-33391-1_25. Arxiv https://arxiv.org/abs/1908.09891.

[ICIP2018] Multiclass Weighted Loss for Instance Segmentation of Cluttered Cells. Fidel A. Guerrero Pena, Pedro D. Marrero Fernandez, Tsang Ing Ren, Mary Yui, Ellen Rothenberg, Alexandre Cunha. IEEE International Conference on Image Processing (ICIP). 2018. https://ieeexplore.ieee.org/abstract/document/8451187/. Arxiv https://arxiv.org/abs/1802.07465.