AMLP-Conv, a 3D Axial Long-range Interaction Multilayer Perceptron for CNNs

Savinien Bonheur*, Michael Pienn, Horst Olschewski, Horst Bischof, Martin Urschler

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

Abstract

While Convolutional neural networks (CNN) have been the backbone of medical image analysis for years, their limited long-range interaction restrains their ability to encode long distance anatomical relationships. On the other hand, the current approach to capture long distance relationships, Transformers, is constrained by their quadratic scaling and their data inefficiency (arising from their lack of inductive biases). In this paper, we introduce the 3D Axial Multilayer Perceptron (AMLP), a long-range interaction module whose complexity scales linearly with spatial dimensions. This module is merged with CNNs to form the AMLP-Conv module, a long-range augmented convolution with strong inductive biases. Once combined with U-Net, our AMLP-Conv module leads to significant improvement, outperforming most transformer based U-Nets on the ACDC dataset, and reaching a new state-of-the-art result on the Multi-Modal Whole Heart Segmentation (MM-WHS) dataset with an almost 1.1% Dice score improvement over the previous scores on the Computed Tomography (CT) modality.

Original languageEnglish
Title of host publicationMachine Learning in Medical Imaging - 13th International Workshop, MLMI 2022, Held in Conjunction with MICCAI 2022, Proceedings
EditorsChunfeng Lian, Xiaohuan Cao, Islem Rekik, Xuanang Xu, Zhiming Cui
PublisherSpringer Science and Business Media Deutschland GmbH
Pages328-337
Number of pages10
ISBN (Print)9783031210136
DOIs
Publication statusPublished - 2022
Event13th International Workshop on Machine Learning in Medical Imaging, MLMI 2022, held in conjunction with 25th International Conference on Medical Image Computing and Computer_Assisted Intervention, MICCAI 2022 - Singapore, Singapore
Duration: 18 Sept 202218 Sept 2022

Publication series

NameLecture Notes in Computer Science
Volume13583
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference13th International Workshop on Machine Learning in Medical Imaging, MLMI 2022, held in conjunction with 25th International Conference on Medical Image Computing and Computer_Assisted Intervention, MICCAI 2022
Country/TerritorySingapore
CitySingapore
Period18/09/2218/09/22

Keywords

  • 3D semantic segmentation
  • Axial attention
  • Convolutional neural network
  • Heart segmentation
  • MLP
  • Multi-label

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Fingerprint

Dive into the research topics of 'AMLP-Conv, a 3D Axial Long-range Interaction Multilayer Perceptron for CNNs'. Together they form a unique fingerprint.

Cite this