# Patch Network for medical image Segmentation

## TL;DR

This paper introduces PNet, a hybrid convolutional-transformer network for medical image segmentation that balances speed and accuracy, achieving state-of-the-art results on multiple datasets.

## Contribution

The paper proposes a novel Patch Network integrating Swin Transformer concepts into CNNs, enhancing contextual feature learning while maintaining efficiency.

## Key findings

- PNet achieves state-of-the-art performance in speed and accuracy.
- PNet outperforms existing methods on polyp and skin lesion datasets.
- The hybrid approach effectively balances computational cost and segmentation quality.

## Abstract

Accurate and fast segmentation of medical images is clinically essential, yet current research methods include convolutional neural networks with fast inference speed but difficulty in learning image contextual features, and transformer with good performance but high hardware requirements. In this paper, we present a Patch Network (PNet) that incorporates the Swin Transformer notion into a convolutional neural network, allowing it to gather richer contextual information while achieving the balance of speed and accuracy. We test our PNet on Polyp(CVC-ClinicDB and ETIS- LaribPolypDB), Skin(ISIC-2018 Skin lesion segmentation challenge dataset) segmentation datasets. Our PNet achieves SOTA performance in both speed and accuracy.