# `Project & Excite' Modules for Segmentation of Volumetric Medical Scans

## TL;DR

This paper introduces 'Project & Excite' modules for 3D medical image segmentation, extending squeeze and excitation techniques to volumetric data, improving accuracy with minimal added complexity.

## Contribution

It proposes PE modules that operate on 3D images, preserving spatial information and enhancing segmentation performance in medical imaging.

## Key findings

- Boosts segmentation accuracy by 5% Dice points
- Increases model complexity by only 2%
- Effective on MRI and CT segmentation tasks

## Abstract

Fully Convolutional Neural Networks (F-CNNs) achieve state-of-the-art performance for image segmentation in medical imaging. Recently, squeeze and excitation (SE) modules and variations thereof have been introduced to recalibrate feature maps channel- and spatial-wise, which can boost performance while only minimally increasing model complexity. So far, the development of SE has focused on 2D images. In this paper, we propose `Project & Excite' (PE) modules that base upon the ideas of SE and extend them to operating on 3D volumetric images. `Project & Excite' does not perform global average pooling, but squeezes feature maps along different slices of a tensor separately to retain more spatial information that is subsequently used in the excitation step. We demonstrate that PE modules can be easily integrated in 3D U-Net, boosting performance by 5% Dice points, while only increasing the model complexity by 2%. We evaluate the PE module on two challenging tasks, whole-brain segmentation of MRI scans and whole-body segmentation of CT scans. Code: https://github.com/ai-med/squeeze_and_excitation