Photometric Transformer Networks and Label Adjustment for Breast Density Prediction
Authors:
- 1 October 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 460-466
Abstract
Grading breast density is highly sensitive to normalization settings of digital mammogram as the density is tightly correlated with the distribution of pixel intensity. Also, the grade varies with readers due to uncertain grading criteria. These issues are inherent in the density assessment of digital mammography. They are problematic when designing a computer-aided prediction model for breast density and become worse if the data comes from multiple sites. In this paper, we proposed two novel deep learning techniques for breast density prediction: 1) photometric transformation which adaptively normalizes the input mammograms, and 2) label distillation which adjusts the label by using its output prediction. The photometric transformer network predicts optimal parameters for photometric transformation on the fly, learned jointly with the main prediction network. The label distillation, a type of pseudo-label techniques, is intended to mitigate the grading variation. We experimentally showed that the proposed methods are beneficial in terms of breast density prediction, resulting in significant performance improvement compared to various previous approaches.Keywords
This publication has 10 references indexed in Scilit:
- Mammographic Breast Density Assessment Using Deep Learning: Clinical ImplementationRadiology, 2019
- Joint Optimization Framework for Learning with Noisy Labels2018
- Breast Density Classification with Deep Convolutional Neural Networks2018
- A deep learning method for classifying mammographic breast density categoriesMedical Physics, 2017
- Learning from Noisy Labels with Distillation2017
- Unsupervised Deep Learning Applied to Breast Density Segmentation and Mammographic Risk ScoringIEEE Transactions on Medical Imaging, 2016
- Estimation of breast percent density in raw and processed full field digital mammography images via adaptive fuzzy c‐means clustering and support vector machine segmentationMedical Physics, 2012
- Mammographic Density and the Risk and Detection of Breast CancerNew England Journal of Medicine, 2007
- Effect of Age, Breast Density, and Family History on the Sensitivity of First Screening MammographyJAMA, 1996
- Adaptive histogram equalization and its variationsComputer Vision, Graphics, and Image Processing, 1987