Download Source Code
About
This project page presents the implementation for the uncertainty driven multi loss fully convolutional networks
proposed in [1] for learning the weighting coffecients in multi loss functions.
In this code there is also a tensorflow implementation of the topology-aware FCN model presented in [2].
The code released here is provided "as is" without any implied
warranties for any particular purpose. In no event shall the authors of this site be liable for any damage or
tort arising from the use of this source code, even if we are advised of the possibility of such damage.
This source code is not for commercial use. For commercial interest please contact Prof. Ghassan Hamarneh.
If you use this code, please cite the following paper [1]:
[1] Uncertainty Driven Multi Loss Fully Convolutional Networks for Histopathology Image Analysis
Aïcha BenTaieb and Ghassan Hamarneh
Intravascular Imaging and Computer Assisted Stenting, and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis (MICCAI-LABELS)
volume 9900, pages 460-468, 2016
[2] Topology Aware Fully Convolutional Networks For Histology Gland Segmentation
Aïcha BenTaieb and Ghassan Hamarneh
Lecture Notes in Computer Science, Medical Image Computing and Computer-Assisted Intervention (MICCAI)
pages 155--163, 2017
DOI: 978-3-319-46723-8_53