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

Author:

Hammer Simone1,Nunes Danilo Weber2,Hammer Michael2,Zeman Florian3,Akers Michael1,Götz Andrea1,Balla Annika1,Doppler Michael Christian4,Fellner Claudia1,Platz Batista da Silva Natascha1,Thurn Sylvia1,Verloh Niklas4,Stroszczynski Christian1,Wohlgemuth Walter Alexander5,Palm Christoph26,Uller Wibke4

Affiliation:

1. Department of Radiology, Medical Center Universityof Regensburg, Faculty of Medicine, University of Regensburg, Regensburg, Germany

2. Regensburg Medical Image Computing (ReMIC), Ostbayerische Technische Hochschule Regensburg (OTH Regensburg), Regensburg, Germany

3. Center for Clinical Trials, Medical Center University of Regensburg, Faculty of Medicine, University of Regensburg, Regensburg, Germany

4. Department of Diagnostic and Interventional Radiology, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany

5. Department of Radiology, Medical Center University of Halle (Saale), Faculty of Medicine, University of Halle (Saale), Halle, Germany

6. Regensburg Center of Biomedical Engineering (RCBE), OTH Regensburg and University of Regensburg, Regensburg, Germany

Abstract

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.

Publisher

IOS Press

Subject

Physiology (medical),Cardiology and Cardiovascular Medicine,Hematology,Physiology

Reference30 articles.

1. Individualized treatment of congenital vascular malformations of the tongue;Guntau;Clinical Hemorheology and Microcirculation,2023

2. Development of hemodynamically relevant acquired arterio-venous fistulae in patients with venous malformations;Schramm;Clinical Hemorheology and Microcirculation,2023

3. Periphere kongenitale Gefäßanomalien –Grundlagen der periinterventionellen Bildgebung;Sadick;RoFo Fortschritteauf dem Gebiete der Rontgenstrahlen und der Nuklearmedizin,2020

4. Classification of pediatric vascular lesions;Mulliken;Plastic and Reconstructive Surgery,1982

5. Hemangiomas and vascular malformations in infants and children: a classification based on endothelial characteristics;Mulliken;Plastic and Reconstructive Surgery,1982

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3