# PAN: Projective Adversarial Network for Medical Image Segmentation

arXiv: https://arxiv.org/abs/1906.04378 · HTML: https://mlsanity.com/paper/1906.04378/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2019.

## Built on by (most cited first, 8 of 8)

- [Hierarchical 3D Feature Learning for Pancreas Segmentation](https://mlsanity.com/paper/2109.01667/) (2021)
- [Transformer based Generative Adversarial Network for Liver Segmentation](https://mlsanity.com/paper/2205.10663/) (2022)
- [Generative Adversarial U-Net for Domain-free Medical Image Augmentation](https://mlsanity.com/paper/2101.04793/) (2021)
- [Generalizable Pancreas Segmentation via a Dual Self-Supervised Learning Framework](https://mlsanity.com/paper/2505.07165/) (2025)
- [REN: Anatomically-Informed Mixture-of-Experts for Interstitial Lung Disease Diagnosis](https://mlsanity.com/paper/2510.04923/) (2025)
- [Detection and Segmentation of Pancreas using Morphological Snakes and Deep Convolutional Neural Networks](https://mlsanity.com/paper/2302.06356/) (2023)
- [Comparing Adversarial and Supervised Learning for Organs at Risk Segmentation in CT images](https://mlsanity.com/paper/2303.17941/) (2023)
- [Advances in Medical Image Segmentation: A Comprehensive Survey with a Focus on Lumbar Spine Applications](https://mlsanity.com/paper/2510.03318/) (2025)

## Abstract (arXiv)

Adversarial learning has been proven to be effective for capturing long-range and high-level label consistencies in semantic segmentation. Unique to medical imaging, capturing 3D semantics in an effective yet computationally efficient way remains an open problem. In this study, we address this computational burden by proposing a novel projective adversarial network, called PAN, which incorporates high-level 3D information through 2D projections. Furthermore, we introduce an attention module into our framework that helps for a selective integration of global information directly from our segmentor to our adversarial network. For the clinical application we chose pancreas segmentation from CT scans. Our proposed framework achieved state-of-the-art performance without adding to the complexity of the segmentor.