We explore the use of deep learning for breast mass segmentation in mammograms. By integrating the merits of residual learning and probabilistic graphical modelling with standard U-Net, we propose a new deep network, Conditional Residual U-Net (CRU-Net), to improve the U-Net segmentation performance. Benefiting from the advantage of probabilistic graphical modelling in the pixel-level labelling, and the structure insights of a deep residual network in the feature extraction, the CRU-Net provides excellent mass segmentation performance. Evaluations based on INbreast and DDSM-BCRP datasets demonstrate that the CRU-Net achieves the best mass segmentation performance compared to the state-of-art methodologies. Moreover, neither tedious pre-processing nor post-processing techniques are not required in our algorithm.
|Title of host publication||Image Analysis for Moving Organ, Breast, and Thoracic Images|
|Publication status||Published - 16 Sep 2018|
|Event||4th International Workshop, BIA 2018 - |
Duration: 16 Sep 2018 → 20 Sep 2018
|Conference||4th International Workshop, BIA 2018|
|Period||16/09/18 → 20/09/18|