Cargando…

Head and Neck Cancer Segmentation in FDG PET Images: Performance Comparison of Convolutional Neural Networks and Vision Transformers

Convolutional neural networks (CNNs) have a proven track record in medical image segmentation. Recently, Vision Transformers were introduced and are gaining popularity for many computer vision applications, including object detection, classification, and segmentation. Machine learning algorithms suc...

Descripción completa

Detalles Bibliográficos
Autores principales: Xiong, Xiaofan, Smith, Brian J., Graves, Stephen A., Graham, Michael M., Buatti, John M., Beichel, Reinhard R.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10611182/
https://www.ncbi.nlm.nih.gov/pubmed/37888743
http://dx.doi.org/10.3390/tomography9050151
_version_ 1785128431435907072
author Xiong, Xiaofan
Smith, Brian J.
Graves, Stephen A.
Graham, Michael M.
Buatti, John M.
Beichel, Reinhard R.
author_facet Xiong, Xiaofan
Smith, Brian J.
Graves, Stephen A.
Graham, Michael M.
Buatti, John M.
Beichel, Reinhard R.
author_sort Xiong, Xiaofan
collection PubMed
description Convolutional neural networks (CNNs) have a proven track record in medical image segmentation. Recently, Vision Transformers were introduced and are gaining popularity for many computer vision applications, including object detection, classification, and segmentation. Machine learning algorithms such as CNNs or Transformers are subject to an inductive bias, which can have a significant impact on the performance of machine learning models. This is especially relevant for medical image segmentation applications where limited training data are available, and a model’s inductive bias should help it to generalize well. In this work, we quantitatively assess the performance of two CNN-based networks (U-Net and U-Net-CBAM) and three popular Transformer-based segmentation network architectures (UNETR, TransBTS, and VT-UNet) in the context of HNC lesion segmentation in volumetric [F-18] fluorodeoxyglucose (FDG) PET scans. For performance assessment, 272 FDG PET-CT scans of a clinical trial (ACRIN 6685) were utilized, which includes a total of 650 lesions (primary: 272 and secondary: 378). The image data used are highly diverse and representative for clinical use. For performance analysis, several error metrics were utilized. The achieved Dice coefficient ranged from 0.833 to 0.809 with the best performance being achieved by CNN-based approaches. U-Net-CBAM, which utilizes spatial and channel attention, showed several advantages for smaller lesions compared to the standard U-Net. Furthermore, our results provide some insight regarding the image features relevant for this specific segmentation application. In addition, results highlight the need to utilize primary as well as secondary lesions to derive clinically relevant segmentation performance estimates avoiding biases.
format Online
Article
Text
id pubmed-10611182
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-106111822023-10-28 Head and Neck Cancer Segmentation in FDG PET Images: Performance Comparison of Convolutional Neural Networks and Vision Transformers Xiong, Xiaofan Smith, Brian J. Graves, Stephen A. Graham, Michael M. Buatti, John M. Beichel, Reinhard R. Tomography Article Convolutional neural networks (CNNs) have a proven track record in medical image segmentation. Recently, Vision Transformers were introduced and are gaining popularity for many computer vision applications, including object detection, classification, and segmentation. Machine learning algorithms such as CNNs or Transformers are subject to an inductive bias, which can have a significant impact on the performance of machine learning models. This is especially relevant for medical image segmentation applications where limited training data are available, and a model’s inductive bias should help it to generalize well. In this work, we quantitatively assess the performance of two CNN-based networks (U-Net and U-Net-CBAM) and three popular Transformer-based segmentation network architectures (UNETR, TransBTS, and VT-UNet) in the context of HNC lesion segmentation in volumetric [F-18] fluorodeoxyglucose (FDG) PET scans. For performance assessment, 272 FDG PET-CT scans of a clinical trial (ACRIN 6685) were utilized, which includes a total of 650 lesions (primary: 272 and secondary: 378). The image data used are highly diverse and representative for clinical use. For performance analysis, several error metrics were utilized. The achieved Dice coefficient ranged from 0.833 to 0.809 with the best performance being achieved by CNN-based approaches. U-Net-CBAM, which utilizes spatial and channel attention, showed several advantages for smaller lesions compared to the standard U-Net. Furthermore, our results provide some insight regarding the image features relevant for this specific segmentation application. In addition, results highlight the need to utilize primary as well as secondary lesions to derive clinically relevant segmentation performance estimates avoiding biases. MDPI 2023-10-18 /pmc/articles/PMC10611182/ /pubmed/37888743 http://dx.doi.org/10.3390/tomography9050151 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Xiong, Xiaofan
Smith, Brian J.
Graves, Stephen A.
Graham, Michael M.
Buatti, John M.
Beichel, Reinhard R.
Head and Neck Cancer Segmentation in FDG PET Images: Performance Comparison of Convolutional Neural Networks and Vision Transformers
title Head and Neck Cancer Segmentation in FDG PET Images: Performance Comparison of Convolutional Neural Networks and Vision Transformers
title_full Head and Neck Cancer Segmentation in FDG PET Images: Performance Comparison of Convolutional Neural Networks and Vision Transformers
title_fullStr Head and Neck Cancer Segmentation in FDG PET Images: Performance Comparison of Convolutional Neural Networks and Vision Transformers
title_full_unstemmed Head and Neck Cancer Segmentation in FDG PET Images: Performance Comparison of Convolutional Neural Networks and Vision Transformers
title_short Head and Neck Cancer Segmentation in FDG PET Images: Performance Comparison of Convolutional Neural Networks and Vision Transformers
title_sort head and neck cancer segmentation in fdg pet images: performance comparison of convolutional neural networks and vision transformers
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10611182/
https://www.ncbi.nlm.nih.gov/pubmed/37888743
http://dx.doi.org/10.3390/tomography9050151
work_keys_str_mv AT xiongxiaofan headandneckcancersegmentationinfdgpetimagesperformancecomparisonofconvolutionalneuralnetworksandvisiontransformers
AT smithbrianj headandneckcancersegmentationinfdgpetimagesperformancecomparisonofconvolutionalneuralnetworksandvisiontransformers
AT gravesstephena headandneckcancersegmentationinfdgpetimagesperformancecomparisonofconvolutionalneuralnetworksandvisiontransformers
AT grahammichaelm headandneckcancersegmentationinfdgpetimagesperformancecomparisonofconvolutionalneuralnetworksandvisiontransformers
AT buattijohnm headandneckcancersegmentationinfdgpetimagesperformancecomparisonofconvolutionalneuralnetworksandvisiontransformers
AT beichelreinhardr headandneckcancersegmentationinfdgpetimagesperformancecomparisonofconvolutionalneuralnetworksandvisiontransformers