Ordinal Regression with Neuron Stick-Breaking for Medical Diagnosis
Abstract
The classification for medical diagnosis usually involves inherently ordered labels corresponding to the level of health risk. Previous multi-task classifiers on ordinal data often use several binary classification branches to compute a series of cumulative probabilities. However, these cumulative probabilities are not guaranteed to be monotonically decreasing. It also introduces a large number of hyper-parameters to be fine-tuned manually. This paper aims to eliminate or at least largely reduce the effects of those problems. We propose a simple yet efficient way to rephrase the output layer of the conventional deep neural network. We show that our methods lead to the state-of-the-art accuracy on Diabetic Retinopathy dataset and Ultrasound Breast dataset with very little additional cost.
Cite
Text
Liu et al. "Ordinal Regression with Neuron Stick-Breaking for Medical Diagnosis." European Conference on Computer Vision Workshops, 2018. doi:10.1007/978-3-030-11024-6_23Markdown
[Liu et al. "Ordinal Regression with Neuron Stick-Breaking for Medical Diagnosis." European Conference on Computer Vision Workshops, 2018.](https://mlanthology.org/eccvw/2018/liu2018eccvw-ordinal/) doi:10.1007/978-3-030-11024-6_23BibTeX
@inproceedings{liu2018eccvw-ordinal,
title = {{Ordinal Regression with Neuron Stick-Breaking for Medical Diagnosis}},
author = {Liu, Xiaofeng and Zou, Yang and Song, Yuhang and Yang, Chao and You, Jane and Kumar, B. V. K. Vijaya},
booktitle = {European Conference on Computer Vision Workshops},
year = {2018},
pages = {335-344},
doi = {10.1007/978-3-030-11024-6_23},
url = {https://mlanthology.org/eccvw/2018/liu2018eccvw-ordinal/}
}