A 3D Deep Neural Network for Liver Volumetry in 3T Contrast-Enhanced MRI
- Publication type:
- Journal article
- Metadata:
-
- Autoren
- Hinrich Winther
- Christian Hundt
- Kristina Imeen Ringe
- Frank K Wacker
- Bertil Schmidt
- Julian Juergens
- Michael Haimerl
- Lukas Philipp Beyer
- Christian Stroszczynski
- Philipp Wiggermann
- Niklas Verloh
- Autoren-URL
- https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=fis-test-1&SrcAuth=WosAPI&KeyUT=WOS:000575474300009&DestLinkType=FullRecord&DestApp=WOS_CPL
- DOI
- 10.1055/a-1238-2887
- eISSN
- 1438-9010
- Externe Identifier
- Clarivate Analytics Document Solution ID: QM1MK
- PubMed Identifier: 32882724
- ISSN
- 1438-9029
- Ausgabe der Veröffentlichung
- 03
- Zeitschrift
- ROFO-FORTSCHRITTE AUF DEM GEBIET DER RONTGENSTRAHLEN UND DER BILDGEBENDEN VERFAHREN
- Schlüsselwörter
- liver segmentation
- liver volumetry
- semantic segmentation
- fully automated segmentation
- contrast-enhanced liver MRI
- Paginierung
- 305 - 314
- Datum der Veröffentlichung
- 2021
- Status
- Published
- Titel
- A 3D Deep Neural Network for Liver Volumetry in 3T Contrast-Enhanced MRI
- Sub types
- Article
- Ausgabe der Zeitschrift
- 193
Data source: Web of Science (Lite)
- Other metadata sources:
-
- Abstract
- <jats:p> Purpose To create a fully automated, reliable, and fast segmentation tool for Gd-EOB-DTPA-enhanced MRI scans using deep learning.</jats:p><jats:p> Materials and Methods Datasets of Gd-EOB-DTPA-enhanced liver MR images of 100 patients were assembled. Ground truth segmentation of the hepatobiliary phase images was performed manually. Automatic image segmentation was achieved with a deep convolutional neural network.</jats:p><jats:p> Results Our neural network achieves an intraclass correlation coefficient (ICC) of 0.987, a Sørensen–Dice coefficient of 96.7 ± 1.9 % (mean ± std), an overlap of 92 ± 3.5 %, and a Hausdorff distance of 24.9 ± 14.7 mm compared with two expert readers who corresponded to an ICC of 0.973, a Sørensen–Dice coefficient of 95.2 ± 2.8 %, and an overlap of 90.9 ± 4.9 %. A second human reader achieved a Sørensen–Dice coefficient of 95 % on a subset of the test set.</jats:p><jats:p> Conclusion Our study introduces a fully automated liver volumetry scheme for Gd-EOB-DTPA-enhanced MR imaging. The neural network achieves competitive concordance with the ground truth regarding ICC, Sørensen–Dice, and overlap compared with manual segmentation. The neural network performs the task in just 60 seconds.</jats:p><jats:p> Key Points: </jats:p><jats:p> Citation Format </jats:p>
- Autoren
- Hinrich Winther
- Christian Hundt
- Kristina Imeen Ringe
- Frank K Wacker
- Bertil Schmidt
- Julian Jürgens
- Michael Haimerl
- Lukas Philipp Beyer
- Christian Stroszczynski
- Philipp Wiggermann
- Niklas Verloh
- DOI
- 10.1055/a-1238-2887
- eISSN
- 1438-9010
- ISSN
- 1438-9029
- Ausgabe der Veröffentlichung
- 03
- Zeitschrift
- RöFo - Fortschritte auf dem Gebiet der Röntgenstrahlen und der bildgebenden Verfahren
- Sprache
- de
- Online publication date
- 2020
- Paginierung
- 305 - 314
- Datum der Veröffentlichung
- 2021
- Status
- Published
- Herausgeber
- Georg Thieme Verlag KG
- Herausgeber URL
- http://dx.doi.org/10.1055/a-1238-2887
- Datum der Datenerfassung
- 2021
- Titel
- A 3D Deep Neural Network for Liver Volumetry in 3T Contrast-Enhanced MRI
- Ausgabe der Zeitschrift
- 193
Data source: Crossref
- Abstract
- <h4>Purpose</h4> To create a fully automated, reliable, and fast segmentation tool for Gd-EOB-DTPA-enhanced MRI scans using deep learning.<h4>Materials and methods</h4> Datasets of Gd-EOB-DTPA-enhanced liver MR images of 100 patients were assembled. Ground truth segmentation of the hepatobiliary phase images was performed manually. Automatic image segmentation was achieved with a deep convolutional neural network.<h4>Results</h4> Our neural network achieves an intraclass correlation coefficient (ICC) of 0.987, a Sørensen-Dice coefficient of 96.7 ± 1.9 % (mean ± std), an overlap of 92 ± 3.5 %, and a Hausdorff distance of 24.9 ± 14.7 mm compared with two expert readers who corresponded to an ICC of 0.973, a Sørensen-Dice coefficient of 95.2 ± 2.8 %, and an overlap of 90.9 ± 4.9 %. A second human reader achieved a Sørensen-Dice coefficient of 95 % on a subset of the test set.<h4>Conclusion</h4> Our study introduces a fully automated liver volumetry scheme for Gd-EOB-DTPA-enhanced MR imaging. The neural network achieves competitive concordance with the ground truth regarding ICC, Sørensen-Dice, and overlap compared with manual segmentation. The neural network performs the task in just 60 seconds.<h4>Key points</h4> · The proposed neural network helps to segment the liver accurately, providing detailed information about patient-specific liver anatomy and volume.. · With the help of a deep learning-based neural network, fully automatic segmentation of the liver on MRI scans can be performed in seconds.. · A fully automatic segmentation scheme makes liver segmentation on MRI a valuable tool for treatment planning..<h4>Citation format</h4>· Winther H, Hundt C, Ringe KI et al. A 3D Deep Neural Network for Liver Volumetry in 3T Contrast-Enhanced MRI. Fortschr Röntgenstr 2021; 193: 305 - 314.
- Addresses
- Department of Diagnostic and Interventional Radiology, Hannover Medical School, Hannover, Germany.
- Autoren
- Hinrich Winther
- Christian Hundt
- Kristina Imeen Ringe
- Frank K Wacker
- Bertil Schmidt
- Julian Jürgens
- Michael Haimerl
- Lukas Philipp Beyer
- Christian Stroszczynski
- Philipp Wiggermann
- Niklas Verloh
- DOI
- 10.1055/a-1238-2887
- eISSN
- 1438-9010
- Externe Identifier
- PubMed Identifier: 32882724
- Open access
- false
- ISSN
- 1438-9029
- Ausgabe der Veröffentlichung
- 3
- Zeitschrift
- RoFo : Fortschritte auf dem Gebiete der Rontgenstrahlen und der Nuklearmedizin
- Schlüsselwörter
- Liver
- Humans
- Magnetic Resonance Imaging
- Image Processing, Computer-Assisted
- Neural Networks, Computer
- Sprache
- eng
- Medium
- Print-Electronic
- Online publication date
- 2020
- Paginierung
- 305 - 314
- Datum der Veröffentlichung
- 2021
- Status
- Published
- Datum der Datenerfassung
- 2020
- Titel
- A 3D Deep Neural Network for Liver Volumetry in 3T Contrast-Enhanced MRI.
- Sub types
- Journal Article
- Ausgabe der Zeitschrift
- 193
Data source: Europe PubMed Central
- Abstract
- PURPOSE: To create a fully automated, reliable, and fast segmentation tool for Gd-EOB-DTPA-enhanced MRI scans using deep learning. MATERIALS AND METHODS: Datasets of Gd-EOB-DTPA-enhanced liver MR images of 100 patients were assembled. Ground truth segmentation of the hepatobiliary phase images was performed manually. Automatic image segmentation was achieved with a deep convolutional neural network. RESULTS: Our neural network achieves an intraclass correlation coefficient (ICC) of 0.987, a Sørensen-Dice coefficient of 96.7 ± 1.9 % (mean ± std), an overlap of 92 ± 3.5 %, and a Hausdorff distance of 24.9 ± 14.7 mm compared with two expert readers who corresponded to an ICC of 0.973, a Sørensen-Dice coefficient of 95.2 ± 2.8 %, and an overlap of 90.9 ± 4.9 %. A second human reader achieved a Sørensen-Dice coefficient of 95 % on a subset of the test set. CONCLUSION: Our study introduces a fully automated liver volumetry scheme for Gd-EOB-DTPA-enhanced MR imaging. The neural network achieves competitive concordance with the ground truth regarding ICC, Sørensen-Dice, and overlap compared with manual segmentation. The neural network performs the task in just 60 seconds. KEY POINTS: · The proposed neural network helps to segment the liver accurately, providing detailed information about patient-specific liver anatomy and volume.. · With the help of a deep learning-based neural network, fully automatic segmentation of the liver on MRI scans can be performed in seconds.. · A fully automatic segmentation scheme makes liver segmentation on MRI a valuable tool for treatment planning.. CITATION FORMAT: · Winther H, Hundt C, Ringe KI et al. A 3D Deep Neural Network for Liver Volumetry in 3T Contrast-Enhanced MRI. Fortschr Röntgenstr 2021; 193: 305 - 314.
- Autoren
- Hinrich Winther
- Christian Hundt
- Kristina Imeen Ringe
- Frank K Wacker
- Bertil Schmidt
- Julian Jürgens
- Michael Haimerl
- Lukas Philipp Beyer
- Christian Stroszczynski
- Philipp Wiggermann
- Niklas Verloh
- Autoren-URL
- https://www.ncbi.nlm.nih.gov/pubmed/32882724
- DOI
- 10.1055/a-1238-2887
- eISSN
- 1438-9010
- Ausgabe der Veröffentlichung
- 3
- Zeitschrift
- Rofo
- Schlüsselwörter
- Humans
- Image Processing, Computer-Assisted
- Liver
- Magnetic Resonance Imaging
- Neural Networks, Computer
- Sprache
- eng
- Country
- Germany
- Paginierung
- 305 - 314
- Datum der Veröffentlichung
- 2021
- Status
- Published
- Datum, an dem der Datensatz öffentlich gemacht wurde
- 2021
- Titel
- A 3D Deep Neural Network for Liver Volumetry in 3T Contrast-Enhanced MRI.
- Sub types
- Journal Article
- Ausgabe der Zeitschrift
- 193
Data source: PubMed
- Beziehungen:
- Property of