Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Classification of point-of-care ultrasound in breast imaging using deep learning

Karlsson, Jennie LU ; Arvidsson, Ida LU ; Sahlin, Freja ; Åström, Kalle LU orcid ; Overgaard, Niels Christian LU ; Lång, Kristina LU and Heyden, Anders LU orcid (2023) SPIE Medical Imaging 2023 In Proceedings of SPIE 12465.
Abstract

Early detection of breast cancer is important to reduce morbidity and mortality. Access to breast imaging is limited in low- and middle-income countries compared to high-income countries. This contributes to advance-stage breast cancer presentation with poor survival. Pocket-sized portable ultrasound device, also known as point-of-care ultrasound (POCUS), aided by decision support using deep learning-based algorithms for lesion classification could be a cost-effective way to enable access to breast imaging in low-resource settings. A previous study, where using convolutional neural networks (CNN) to classify breast cancer in conventional ultrasound (US) images, showed promising results. The aim of the present study is to classify POCUS... (More)

Early detection of breast cancer is important to reduce morbidity and mortality. Access to breast imaging is limited in low- and middle-income countries compared to high-income countries. This contributes to advance-stage breast cancer presentation with poor survival. Pocket-sized portable ultrasound device, also known as point-of-care ultrasound (POCUS), aided by decision support using deep learning-based algorithms for lesion classification could be a cost-effective way to enable access to breast imaging in low-resource settings. A previous study, where using convolutional neural networks (CNN) to classify breast cancer in conventional ultrasound (US) images, showed promising results. The aim of the present study is to classify POCUS breast images. A POCUS data set containing 1100 breast images was collected. To increase the size of the data set, a Cycle-Consistent Adversarial Network (CycleGAN) was trained on US images to generate synthetic POCUS images. A CNN was implemented, trained, validated and tested on POCUS images. To improve performance, the CNN was trained with different combinations of data consisting of POCUS images, US images, CycleGAN-generated POCUS images and spatial augmentation. The best result was achieved by a CNN trained on a combination of POCUS images and CycleGAN-generated POCUS images and augmentation. This combination achieved a 95% confidence interval for AUC between 93.5% - 96.6%.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Breast Cancer, Breast Ultrasound, Convolutional Neural Networks, CycleGAN, Point-of-Care Ultrasound
host publication
Medical Imaging 2023 : Computer-Aided Diagnosis - Computer-Aided Diagnosis
series title
Proceedings of SPIE
editor
Iftekharuddin, Khan M. and Chen, Weijie
volume
12465
article number
124650Y
publisher
SPIE
conference name
SPIE Medical Imaging 2023
conference dates
2023-02-19 - 2023-02-23
external identifiers
  • scopus:85160213715
ISSN
1605-7422
2410-9045
ISBN
9781510660359
DOI
10.1117/12.2654251
language
English
LU publication?
yes
id
11be8846-1022-424a-a5d7-93fcfb5e7d7e
date added to LUP
2023-04-26 13:46:25
date last changed
2024-02-19 19:03:33
@inproceedings{11be8846-1022-424a-a5d7-93fcfb5e7d7e,
  abstract     = {{<p>Early detection of breast cancer is important to reduce morbidity and mortality. Access to breast imaging is limited in low- and middle-income countries compared to high-income countries. This contributes to advance-stage breast cancer presentation with poor survival. Pocket-sized portable ultrasound device, also known as point-of-care ultrasound (POCUS), aided by decision support using deep learning-based algorithms for lesion classification could be a cost-effective way to enable access to breast imaging in low-resource settings. A previous study, where using convolutional neural networks (CNN) to classify breast cancer in conventional ultrasound (US) images, showed promising results. The aim of the present study is to classify POCUS breast images. A POCUS data set containing 1100 breast images was collected. To increase the size of the data set, a Cycle-Consistent Adversarial Network (CycleGAN) was trained on US images to generate synthetic POCUS images. A CNN was implemented, trained, validated and tested on POCUS images. To improve performance, the CNN was trained with different combinations of data consisting of POCUS images, US images, CycleGAN-generated POCUS images and spatial augmentation. The best result was achieved by a CNN trained on a combination of POCUS images and CycleGAN-generated POCUS images and augmentation. This combination achieved a 95% confidence interval for AUC between 93.5% - 96.6%.</p>}},
  author       = {{Karlsson, Jennie and Arvidsson, Ida and Sahlin, Freja and Åström, Kalle and Overgaard, Niels Christian and Lång, Kristina and Heyden, Anders}},
  booktitle    = {{Medical Imaging 2023 : Computer-Aided Diagnosis}},
  editor       = {{Iftekharuddin, Khan M. and Chen, Weijie}},
  isbn         = {{9781510660359}},
  issn         = {{1605-7422}},
  keywords     = {{Breast Cancer; Breast Ultrasound; Convolutional Neural Networks; CycleGAN; Point-of-Care Ultrasound}},
  language     = {{eng}},
  publisher    = {{SPIE}},
  series       = {{Proceedings of SPIE}},
  title        = {{Classification of point-of-care ultrasound in breast imaging using deep learning}},
  url          = {{http://dx.doi.org/10.1117/12.2654251}},
  doi          = {{10.1117/12.2654251}},
  volume       = {{12465}},
  year         = {{2023}},
}