Annotation cost is a bottleneck for collecting massive data in mammography, especially for training deep neural networks. In this paper, we study the use of heterogeneous levels of annotation granularity to improve predictive performances. More precisely, we introduce a multi-task learning scheme for training convolutional neural network (ConvNets), which combines segmentation and classification, using image-level and pixel-level annotations. In this way, different objectives can be used to regularize training by sharing intermediate deep representations. Successful experiments are carried out on the Digital Database of Screening Mammography (DDSM) to validate the relevance of the proposed approach.
@article{arxiv.1909.05397,
title = {Multitask Classification and Segmentation for Cancer Diagnosis in Mammography},
author = {Thi-Lam-Thuy Le and Nicolas Thome and Sylvain Bernard and Vincent Bismuth and Fanny Patoureaux},
journal= {arXiv preprint arXiv:1909.05397},
year = {2019}
}
Comments
International Conference on Medical Imaging with Deep Learning 2019. MIDL 2019 [arXiv:1907.08612]