Deep learning-based differentiation of peripheral high-flow and low-flow vascular malformations in T2-weighted short tau inversion recovery MRI

  • BACKGROUND Differentiation of high-flow from low-flow vascular malformations (VMs) is crucial for therapeutic management of this orphan disease. OBJECTIVE A convolutional neural network (CNN) was evaluated for differentiation of peripheral vascular malformations (VMs) on T2-weighted short tau inversion recovery (STIR) MRI. METHODS 527 MRIs (386 low-flow and 141 high-flow VMs) were randomly divided into training, validation and test set for this single-center study. 1) Results of the CNN's diagnostic performance were compared with that of two expert and four junior radiologists. 2) The influence of CNN's prediction on the radiologists' performance and diagnostic certainty was evaluated. 3) Junior radiologists' performance after self-training was compared with that of the CNN. RESULTS Compared with the expert radiologists the CNN achieved similar accuracy (92% vs. 97%, p = 0.11), sensitivity (80% vs. 93%, p = 0.16) and specificity (97% vs. 100%, p = 0.50). In comparison to the junior radiologists, the CNN had a higher specificity and accuracy (97% vs. 80%, p <  0.001; 92% vs. 77%, p <  0.001). CNN assistance had no significant influence on their diagnostic performance and certainty. After self-training, the junior radiologists' specificity and accuracy improved and were comparable to that of the CNN. CONCLUSIONS Diagnostic performance of the CNN for differentiating high-flow from low-flow VM was comparable to that of expert radiologists. CNN did not significantly improve the simulated daily practice of junior radiologists, self-training was more effective.

Export metadata

Additional Services

Share in Twitter Search Google Scholar Statistics
Metadaten
Author:Simone Hammer, Danilo Weber Nunes, Michael Hammer, Florian Zeman, Michael Akers, Andrea Götz, Annika Balla, Michael Christian Doppler, Claudia Fellner, Natascha Da Platz Batista Silva, Sylvia Thurn, Niklas Verloh, Christian Stroszczynski, Walter Alexander Wohlgemuth, Christoph PalmORCiDGND, Wibke Uller
DOI:https://doi.org/10.3233/CH-232071
Pubmed Id:https://pubmed.ncbi.nlm.nih.gov/38306026
Parent Title (English):Clinical hemorheology and microcirculation
Publisher:IOP Press
Document Type:Article
Language:English
Year of first Publication:2024
Release Date:2024/02/09
Tag:Vascular malformation; deep learning; magnetic resonance imaging
Edition:Pre-press
First Page:1
Last Page:15
Institutes:Fakultät Informatik und Mathematik
Fakultät Informatik und Mathematik / Regensburg Medical Image Computing (ReMIC)
research focus:Lebenswissenschaften und Ethik
Licence (German):Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG