# Unimodal-uniform Constrained Wasserstein Training for Medical Diagnosis

arXiv: https://arxiv.org/abs/1911.02475 · HTML: https://mlsanity.com/paper/1911.02475/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Nov 2019.

## Built on by (most cited first, 13 of 13)

- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [Adapting Off-the-Shelf Source Segmenter for Target Medical Image Segmentation](https://mlsanity.com/paper/2106.12497/) (2021)
- [Subtype-aware Unsupervised Domain Adaptation for Medical Diagnosis](https://mlsanity.com/paper/2101.00318/) (2021)
- [Energy-constrained Self-training for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2101.00316/) (2021)
- [Recursively Conditional Gaussian for Ordinal Unsupervised Domain Adaptation](https://mlsanity.com/paper/2107.13467/) (2021)
- [Identity-aware Facial Expression Recognition in Compressed Video](https://mlsanity.com/paper/2101.00317/) (2021)
- [Improved Diversity-Promoting Collaborative Metric Learning for Recommendation](https://mlsanity.com/paper/2409.01012/) (2024)
- [Navigation-Oriented Scene Understanding for Robotic Autonomy: Learning to Segment Driveability in Egocentric Images](https://mlsanity.com/paper/2109.07245/) (2021)
- [Embedding Semantic Hierarchy in Discrete Optimal Transport for Risk Minimization](https://mlsanity.com/paper/2105.00101/) (2021)
- [Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning](https://mlsanity.com/paper/2408.00309/) (2024)
- [Subtype-Aware Dynamic Unsupervised Domain Adaptation](https://mlsanity.com/paper/2208.07754/) (2022)
- [Deep 3D-CNN for Depression Diagnosis with Facial Video Recording of Self-Rating Depression Scale Questionnaire](https://mlsanity.com/paper/2107.10712/) (2021)
- [Automated interpretation of congenital heart disease from multi-view echocardiograms](https://mlsanity.com/paper/2311.18788/) (2023)

## Abstract (arXiv)

The labels in medical diagnosis task are usually discrete and successively distributed. For example, the Diabetic Retinopathy Diagnosis (DR) involves five health risk levels: no DR (0), mild DR (1), moderate DR (2), severe DR (3) and proliferative DR (4). This labeling system is common for medical disease. Previous methods usually construct a multi-binary-classification task or propose some re-parameter schemes in the output unit. In this paper, we target on this task from the perspective of loss function. More specifically, the Wasserstein distance is utilized as an alternative, explicitly incorporating the inter-class correlations by pre-defining its ground metric. Then, the ground metric which serves as a linear, convex or concave increasing function w.r.t. the Euclidean distance in a line is explored from an optimization perspective. Meanwhile, this paper also proposes of constructing the smoothed target labels that model the inlier and outlier noises by using a unimodal-uniform mixture distribution. Different from the one-hot setting, the smoothed label endues the computation of Wasserstein distance with more challenging features. With either one-hot or smoothed target label, this paper systematically concludes the practical closed-form solution. We evaluate our method on several medical diagnosis tasks (e.g., Diabetic Retinopathy and Ultrasound Breast dataset) and achieve state-of-the-art performance.