MEDUSA: Multi-Scale Encoder-Decoder Self-Attention Deep Neural Network Architecture for Medical Image Analysis

Medical image analysis continues to hold interesting challenges given the subtle characteristics of certain diseases and the significant overlap in appearance between diseases. In this study, we explore the concept of self-attention for tackling such subtleties in and between diseases. To this end,...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Frontiers in medicine Ročník 8; s. 821120
Hlavní autoři: Aboutalebi, Hossein, Pavlova, Maya, Gunraj, Hayden, Shafiee, Mohammad Javad, Sabri, Ali, Alaref, Amer, Wong, Alexander
Médium: Journal Article
Jazyk:angličtina
Vydáno: Switzerland Frontiers Media SA 15.02.2022
Frontiers Media S.A
Témata:
chest X-ray (CXR)
computer vision
COVID-19
Deep learning
deep neural net
diagnosis
Disease
Hypotheses
Infections
Medical imaging
Medicine
Neural networks
Severe acute respiratory syndrome coronavirus 2
Visual perception
COVID-19
chest X-ray (CXR)
diagnosis
deep neural net
computer vision
ISSN:2296-858X, 2296-858X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Medical image analysis continues to hold interesting challenges given the subtle characteristics of certain diseases and the significant overlap in appearance between diseases. In this study, we explore the concept of self-attention for tackling such subtleties in and between diseases. To this end, we introduce, a multi-scale encoder-decoder self-attention (MEDUSA) mechanism tailored for medical image analysis. While self-attention deep convolutional neural network architectures in existing literature center around the notion of multiple isolated lightweight attention mechanisms with limited individual capacities being incorporated at different points in the network architecture, MEDUSA takes a significant departure from this notion by possessing a single, unified self-attention mechanism with significantly higher capacity with multiple attention heads feeding into different scales in the network architecture. To the best of the authors' knowledge, this is the first “single body, multi-scale heads” realization of self-attention and enables explicit global context among selective attention at different levels of representational abstractions while still enabling differing local attention context at individual levels of abstractions. With MEDUSA, we obtain state-of-the-art performance on multiple challenging medical image analysis benchmarks including COVIDx, Radiological Society of North America (RSNA) RICORD, and RSNA Pneumonia Challenge when compared to previous work. Our MEDUSA model is publicly available.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Reviewed by: John Roubil, UMass Memorial Medical Center, United States; Ameer Elaimy, MetroWest Medical Center, United States
Edited by: Thomas J. FitzGerald, UMass Memorial Health Care, United States
This article was submitted to Translational Medicine, a section of the journal Frontiers in Medicine
ISSN:2296-858X
2296-858X
DOI:10.3389/fmed.2021.821120