Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

RECOMIA—a cloud-based platform for artificial intelligence research in nuclear medicine and radiology

Trägårdh, Elin LU ; Borrelli, Pablo ; Kaboteh, Reza ; Gillberg, Tony ; Ulén, Johannes LU ; Enqvist, Olof LU and Edenbrandt, Lars LU (2020) In EJNMMI Physics 7(1).
Abstract

Background: Artificial intelligence (AI) is about to transform medical imaging. The Research Consortium for Medical Image Analysis (RECOMIA), a not-for-profit organisation, has developed an online platform to facilitate collaboration between medical researchers and AI researchers. The aim is to minimise the time and effort researchers need to spend on technical aspects, such as transfer, display, and annotation of images, as well as legal aspects, such as de-identification. The purpose of this article is to present the RECOMIA platform and its AI-based tools for organ segmentation in computed tomography (CT), which can be used for extraction of standardised uptake values from the corresponding positron emission tomography (PET) image.... (More)

Background: Artificial intelligence (AI) is about to transform medical imaging. The Research Consortium for Medical Image Analysis (RECOMIA), a not-for-profit organisation, has developed an online platform to facilitate collaboration between medical researchers and AI researchers. The aim is to minimise the time and effort researchers need to spend on technical aspects, such as transfer, display, and annotation of images, as well as legal aspects, such as de-identification. The purpose of this article is to present the RECOMIA platform and its AI-based tools for organ segmentation in computed tomography (CT), which can be used for extraction of standardised uptake values from the corresponding positron emission tomography (PET) image. Results: The RECOMIA platform includes modules for (1) local de-identification of medical images, (2) secure transfer of images to the cloud-based platform, (3) display functions available using a standard web browser, (4) tools for manual annotation of organs or pathology in the images, (5) deep learning-based tools for organ segmentation or other customised analyses, (6) tools for quantification of segmented volumes, and (7) an export function for the quantitative results. The AI-based tool for organ segmentation in CT currently handles 100 organs (77 bones and 23 soft tissue organs). The segmentation is based on two convolutional neural networks (CNNs): one network to handle organs with multiple similar instances, such as vertebrae and ribs, and one network for all other organs. The CNNs have been trained using CT studies from 339 patients. Experienced radiologists annotated organs in the CT studies. The performance of the segmentation tool, measured as mean Dice index on a manually annotated test set, with 10 representative organs, was 0.93 for all foreground voxels, and the mean Dice index over the organs were 0.86 (0.82 for the soft tissue organs and 0.90 for the bones). Conclusion: The paper presents a platform that provides deep learning-based tools that can perform basic organ segmentations in CT, which can then be used to automatically obtain the different measurement in the corresponding PET image. The RECOMIA platform is available on request at www.recomia.org for research purposes.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Artificial intelligence, CNN, Deep learning, PET-CT, Segmentation
in
EJNMMI Physics
volume
7
issue
1
article number
51
publisher
Springer
external identifiers
  • scopus:85089080340
  • pmid:32754893
ISSN
2197-7364
DOI
10.1186/s40658-020-00316-9
language
English
LU publication?
yes
id
04c6e6dc-233b-483e-8342-3cd93d98e0e7
date added to LUP
2020-08-17 09:39:15
date last changed
2024-07-24 23:16:25
@article{04c6e6dc-233b-483e-8342-3cd93d98e0e7,
  abstract     = {{<p>Background: Artificial intelligence (AI) is about to transform medical imaging. The Research Consortium for Medical Image Analysis (RECOMIA), a not-for-profit organisation, has developed an online platform to facilitate collaboration between medical researchers and AI researchers. The aim is to minimise the time and effort researchers need to spend on technical aspects, such as transfer, display, and annotation of images, as well as legal aspects, such as de-identification. The purpose of this article is to present the RECOMIA platform and its AI-based tools for organ segmentation in computed tomography (CT), which can be used for extraction of standardised uptake values from the corresponding positron emission tomography (PET) image. Results: The RECOMIA platform includes modules for (1) local de-identification of medical images, (2) secure transfer of images to the cloud-based platform, (3) display functions available using a standard web browser, (4) tools for manual annotation of organs or pathology in the images, (5) deep learning-based tools for organ segmentation or other customised analyses, (6) tools for quantification of segmented volumes, and (7) an export function for the quantitative results. The AI-based tool for organ segmentation in CT currently handles 100 organs (77 bones and 23 soft tissue organs). The segmentation is based on two convolutional neural networks (CNNs): one network to handle organs with multiple similar instances, such as vertebrae and ribs, and one network for all other organs. The CNNs have been trained using CT studies from 339 patients. Experienced radiologists annotated organs in the CT studies. The performance of the segmentation tool, measured as mean Dice index on a manually annotated test set, with 10 representative organs, was 0.93 for all foreground voxels, and the mean Dice index over the organs were 0.86 (0.82 for the soft tissue organs and 0.90 for the bones). Conclusion: The paper presents a platform that provides deep learning-based tools that can perform basic organ segmentations in CT, which can then be used to automatically obtain the different measurement in the corresponding PET image. The RECOMIA platform is available on request at www.recomia.org for research purposes.</p>}},
  author       = {{Trägårdh, Elin and Borrelli, Pablo and Kaboteh, Reza and Gillberg, Tony and Ulén, Johannes and Enqvist, Olof and Edenbrandt, Lars}},
  issn         = {{2197-7364}},
  keywords     = {{Artificial intelligence; CNN; Deep learning; PET-CT; Segmentation}},
  language     = {{eng}},
  number       = {{1}},
  publisher    = {{Springer}},
  series       = {{EJNMMI Physics}},
  title        = {{RECOMIA—a cloud-based platform for artificial intelligence research in nuclear medicine and radiology}},
  url          = {{http://dx.doi.org/10.1186/s40658-020-00316-9}},
  doi          = {{10.1186/s40658-020-00316-9}},
  volume       = {{7}},
  year         = {{2020}},
}