Cargando…

Evaluation of a Deep Learning Algorithm for Automated Spleen Segmentation in Patients with Conditions Directly or Indirectly Affecting the Spleen

The aim of this study was to develop a deep learning-based algorithm for fully automated spleen segmentation using CT images and to evaluate the performance in conditions directly or indirectly affecting the spleen (e.g., splenomegaly, ascites). For this, a 3D U-Net was trained on an in-house datase...

Descripción completa

Detalles Bibliográficos
Autores principales: Meddeb, Aymen, Kossen, Tabea, Bressem, Keno K., Hamm, Bernd, Nagel, Sebastian N.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8704906/
https://www.ncbi.nlm.nih.gov/pubmed/34941650
http://dx.doi.org/10.3390/tomography7040078
_version_ 1784621818625130496
author Meddeb, Aymen
Kossen, Tabea
Bressem, Keno K.
Hamm, Bernd
Nagel, Sebastian N.
author_facet Meddeb, Aymen
Kossen, Tabea
Bressem, Keno K.
Hamm, Bernd
Nagel, Sebastian N.
author_sort Meddeb, Aymen
collection PubMed
description The aim of this study was to develop a deep learning-based algorithm for fully automated spleen segmentation using CT images and to evaluate the performance in conditions directly or indirectly affecting the spleen (e.g., splenomegaly, ascites). For this, a 3D U-Net was trained on an in-house dataset (n = 61) including diseases with and without splenic involvement (in-house U-Net), and an open-source dataset from the Medical Segmentation Decathlon (open dataset, n = 61) without splenic abnormalities (open U-Net). Both datasets were split into a training (n = 32.52%), a validation (n = 9.15%) and a testing dataset (n = 20.33%). The segmentation performances of the two models were measured using four established metrics, including the Dice Similarity Coefficient (DSC). On the open test dataset, the in-house and open U-Net achieved a mean DSC of 0.906 and 0.897 respectively (p = 0.526). On the in-house test dataset, the in-house U-Net achieved a mean DSC of 0.941, whereas the open U-Net obtained a mean DSC of 0.648 (p < 0.001), showing very poor segmentation results in patients with abnormalities in or surrounding the spleen. Thus, for reliable, fully automated spleen segmentation in clinical routine, the training dataset of a deep learning-based algorithm should include conditions that directly or indirectly affect the spleen.
format Online
Article
Text
id pubmed-8704906
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-87049062021-12-25 Evaluation of a Deep Learning Algorithm for Automated Spleen Segmentation in Patients with Conditions Directly or Indirectly Affecting the Spleen Meddeb, Aymen Kossen, Tabea Bressem, Keno K. Hamm, Bernd Nagel, Sebastian N. Tomography Article The aim of this study was to develop a deep learning-based algorithm for fully automated spleen segmentation using CT images and to evaluate the performance in conditions directly or indirectly affecting the spleen (e.g., splenomegaly, ascites). For this, a 3D U-Net was trained on an in-house dataset (n = 61) including diseases with and without splenic involvement (in-house U-Net), and an open-source dataset from the Medical Segmentation Decathlon (open dataset, n = 61) without splenic abnormalities (open U-Net). Both datasets were split into a training (n = 32.52%), a validation (n = 9.15%) and a testing dataset (n = 20.33%). The segmentation performances of the two models were measured using four established metrics, including the Dice Similarity Coefficient (DSC). On the open test dataset, the in-house and open U-Net achieved a mean DSC of 0.906 and 0.897 respectively (p = 0.526). On the in-house test dataset, the in-house U-Net achieved a mean DSC of 0.941, whereas the open U-Net obtained a mean DSC of 0.648 (p < 0.001), showing very poor segmentation results in patients with abnormalities in or surrounding the spleen. Thus, for reliable, fully automated spleen segmentation in clinical routine, the training dataset of a deep learning-based algorithm should include conditions that directly or indirectly affect the spleen. MDPI 2021-12-13 /pmc/articles/PMC8704906/ /pubmed/34941650 http://dx.doi.org/10.3390/tomography7040078 Text en © 2021 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
Meddeb, Aymen
Kossen, Tabea
Bressem, Keno K.
Hamm, Bernd
Nagel, Sebastian N.
Evaluation of a Deep Learning Algorithm for Automated Spleen Segmentation in Patients with Conditions Directly or Indirectly Affecting the Spleen
title Evaluation of a Deep Learning Algorithm for Automated Spleen Segmentation in Patients with Conditions Directly or Indirectly Affecting the Spleen
title_full Evaluation of a Deep Learning Algorithm for Automated Spleen Segmentation in Patients with Conditions Directly or Indirectly Affecting the Spleen
title_fullStr Evaluation of a Deep Learning Algorithm for Automated Spleen Segmentation in Patients with Conditions Directly or Indirectly Affecting the Spleen
title_full_unstemmed Evaluation of a Deep Learning Algorithm for Automated Spleen Segmentation in Patients with Conditions Directly or Indirectly Affecting the Spleen
title_short Evaluation of a Deep Learning Algorithm for Automated Spleen Segmentation in Patients with Conditions Directly or Indirectly Affecting the Spleen
title_sort evaluation of a deep learning algorithm for automated spleen segmentation in patients with conditions directly or indirectly affecting the spleen
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8704906/
https://www.ncbi.nlm.nih.gov/pubmed/34941650
http://dx.doi.org/10.3390/tomography7040078
work_keys_str_mv AT meddebaymen evaluationofadeeplearningalgorithmforautomatedspleensegmentationinpatientswithconditionsdirectlyorindirectlyaffectingthespleen
AT kossentabea evaluationofadeeplearningalgorithmforautomatedspleensegmentationinpatientswithconditionsdirectlyorindirectlyaffectingthespleen
AT bressemkenok evaluationofadeeplearningalgorithmforautomatedspleensegmentationinpatientswithconditionsdirectlyorindirectlyaffectingthespleen
AT hammbernd evaluationofadeeplearningalgorithmforautomatedspleensegmentationinpatientswithconditionsdirectlyorindirectlyaffectingthespleen
AT nagelsebastiann evaluationofadeeplearningalgorithmforautomatedspleensegmentationinpatientswithconditionsdirectlyorindirectlyaffectingthespleen