# From Gradient Clipping to Structural Refinement: Improving DPSGD for Medical Image Segmentation

arXiv: https://arxiv.org/abs/2606.21763 · HTML: https://mlsanity.com/paper/2606.21763/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 29 references that are in the map.
- First posted on arXiv 19 Jun 2026.

## Builds on (most cited first, 14 of 14)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Opacus: User-Friendly Differential Privacy Library in PyTorch](https://mlsanity.com/paper/2109.12298/) (2021)
- [Topology-Preserving Deep Image Segmentation](https://mlsanity.com/paper/1906.05404/) (2019)
- [Inf-Net: Automatic COVID-19 Lung Infection Segmentation from CT Images](https://mlsanity.com/paper/2004.14133/) (2020)
- [Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger](https://mlsanity.com/paper/2206.07136/) (2022)
- [Shape-Aware Organ Segmentation by Predicting Signed Distance Maps](https://mlsanity.com/paper/1912.03849/) (2019)
- [Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimization](https://mlsanity.com/paper/2206.13033/) (2022)
- [Differentially Private Learning with Per-Sample Adaptive Clipping](https://mlsanity.com/paper/2212.00328/) (2022)
- [A Comprehensive Review on Deep Supervision: Theories and Applications](https://mlsanity.com/paper/2207.02376/) (2022)
- [Membership Inference Attacks Against Semantic Segmentation Models](https://mlsanity.com/paper/2212.01082/) (2022)
- [Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications](https://mlsanity.com/paper/2506.00660/) (2025)

## Abstract (arXiv)

Medical image segmentation is widely used for disease detection but relies on sensitive data, raising privacy concerns as trained models can leak information. Differential privacy, typically implemented via Differential Private Stochastic Gradient Descent (DPSGD), provides a solution, though at the cost of reduced utility. Recent DPSGD variants, including Automatic clipping (Auto-S), Normalised SGD with perturbation (NSGD), and Per-sample adaptive clipping (PSAC), have shown promise in image classification, but their behavior in medical segmentation remains underexplored. We evaluate these methods across binary and multi-class tasks and analyze gradient alignment, showing that prior assumptions, particularly for PSAC, do not consistently hold. We further demonstrate that combining clipping strategies with morphological refinement improves segmentation quality under privacy constraints. Finally, we propose an adaptive DP-Morph variant that captures class-specific structures and enhances performance in multi-class settings.