Recalibrating 3D ConvNets with Project Excite

02/25/2020
by   Anne-Marie Rickmann, et al.
0

Fully Convolutional Neural Networks (F-CNNs) achieve state-of-the-art performance for segmentation tasks in computer vision and medical imaging. Recently, computational blocks termed squeeze and excitation (SE) have been introduced to recalibrate F-CNN feature maps both channel- and spatial-wise, boosting segmentation performance while only minimally increasing the model complexity. So far, the development of SE blocks has focused on 2D architectures. For volumetric medical images, however, 3D F-CNNs are a natural choice. In this article, we extend existing 2D recalibration methods to 3D and propose a generic compress-process-recalibrate pipeline for easy comparison of such blocks. We further introduce Project Excite (PE) modules, customized for 3D networks. In contrast to existing modules, Project & Excite does not perform global average pooling but compresses feature maps along different spatial dimensions of the tensor separately to retain more spatial information that is subsequently used in the excitation step. We evaluate the modules on two challenging tasks, whole-brain segmentation of MRI scans and whole-body segmentation of CT scans. We demonstrate that PE modules can be easily integrated into 3D F-CNNs, boosting performance up to 0.3 in Dice Score and outperforming 3D extensions of other recalibration blocks, while only marginally increasing the model complexity. Our code is publicly available on https://github.com/ai-med/squeeze_and_excitation .

READ FULL TEXT

page 1

page 8

page 9

research
06/11/2019

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

Fully Convolutional Neural Networks (F-CNNs) achieve state-of-the-art pe...
research
08/23/2018

Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks

In a wide range of semantic segmentation tasks, fully convolutional neur...
research
03/07/2018

Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks

Fully convolutional neural networks (F-CNNs) have set the state-of-the-a...
research
06/06/2018

Adaptive feature recombination and recalibration for semantic segmentation: application to brain tumor segmentation in MRI

Convolutional neural networks (CNNs) have been successfully used for bra...
research
03/03/2022

Robust Segmentation of Brain MRI in the Wild with Hierarchical CNNs and no Retraining

Retrospective analysis of brain MRI scans acquired in the clinic has the...
research
08/15/2018

Holographic Visualisation of Radiology Data and Automated Machine Learning-based Medical Image Segmentation

Within this thesis we propose a platform for combining Augmented Reality...
research
11/30/2020

Reducing Textural Bias Improves Robustness of Deep Segmentation CNNs

Despite current advances in deep learning, domain shift remains a common...

Please sign up or login with your details

Forgot password? Click here to reset