Building classification models from clinical data often requires human experts for example labeling. However, it is difficult to obtain a perfect set of labels due to the complexity of the medical data and the large variability between experts. In this study we present a neural-network training strategy that is more robust to unreliable labeling by explicitly modeling the label noise as part of the network architecture. Our method is demonstrated on breast microcalcifications classification into benign and malignant categories, given multi-view mammograms. We show that the proposed training procedure outperforms standard training methods that ignore the existence of label noise.
|Title of host publication||2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018|
|Publisher||IEEE Computer Society|
|Number of pages||4|
|State||Published - 23 May 2018|
|Event||15th IEEE International Symposium on Biomedical Imaging, ISBI 2018 - Washington, United States|
Duration: 4 Apr 2018 → 7 Apr 2018
|Name||Proceedings - International Symposium on Biomedical Imaging|
|Conference||15th IEEE International Symposium on Biomedical Imaging, ISBI 2018|
|Period||4/04/18 → 7/04/18|
Bibliographical notePublisher Copyright:
© 2018 IEEE.
- Robust training