# Robustness of Segmentation Models

## 9: The impact of U-Net architecture choices and skip connections on the robustness of segmentation across texture variations

This work was [published](https://doi.org/10.1016/j.compbiomed.2025.111056) in [Computers in Biology and Medicine](https://www.sciencedirect.com/journal/computers-in-biology-and-medicine) (CiBM). More details about this work is included in [Chapter 9](chapter9.md).

## 10: Do We Really Need that Skip-Connection? Understanding Its Interplay with Task Complexity

This work was presented as a [poster](https://link.springer.com/chapter/10.1007/978-3-031-43901-8_29) at [MICCAI 2023](https://conferences.miccai.org/2023/papers/).

## 11: How do 3D image segmentation networks behave across the context versus foreground ratio trade-off?

This work was presented as a [poster](https://www.cse.cuhk.edu.hk/~qdou/public/medneurips2022/72.pdf) at [Medical Imaging meets NeurIPS 2022](https://sites.google.com/view/med-neurips-2022/home).

**Ongoing connection:** These architecture studies continue as a broader [robust-segmentation program](https://amithjkamath.github.io/projects/Theme-Robustness/) and inform [personalized contour models](https://amithjkamath.github.io/projects/Theme-Correction/) whose output diversity should reflect genuine ambiguity rather than instability.

```{toctree}
:maxdepth: 2
:caption: Contents
chapter9
chapter10
chapter11