Deep Learning in Cardiothoracic Ratio Calculation and Cardiomegaly Detection
Journal of Clinical Medicine · 17.07.2024 · 13 (14) · 4180
DOI: 10.3390/jcm13144180 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Clinical Medicine, online erschienen am 17.07.2024. Verfasst von Jakub Kufel und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology and Nuclear Medicine, Faculty of Medical Sciences in Katowice, Medical University of Silesia, Medyków 14, 40-752 Katowice, Po…. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Objectives
The purpose of this study is to evaluate the performance of our deep learning algorithm in calculating cardiothoracic ratio (CTR) and thus in the assessment of cardiomegaly or pericardial effusion occurrences on chest radiography (CXR).
Methods
From a database of 8000 CXRs, 13 folders with a comparable number of images were created. Then, 1020 images were chosen randomly, in proportion to the number of images in each folder. Afterward, CTR was calculated using RadiAnt Digital Imaging and Communications in Medicine (DICOM) Viewer software (2023.1). Next, heart and lung anatomical areas were marked in 3D Slicer. From these data, we trained an AI model which segmented heart and lung anatomy and determined the CTR value.
Results
Our model achieved an Intersection over Union metric of 88.28% for the augmented training subset and 83.06% for the validation subset. F1-score for subsets were accordingly 90.22% and 90.67%. In the comparative analysis of artificial intelligence (AI) vs. humans, significantly lower transverse thoracic diameter (TTD) (p < 0.001), transverse cardiac diameter (TCD) (p < 0.001), and CTR (p < 0.001) values obtained using the neural network were observed.
Conclusions
Results confirm that there is a significant correlation between the measurements made by human observers and the neural network. After validation in clinical conditions, our method may be used as a screening test or advisory tool when a specialist is not available, especially on Intensive Care Units (ICUs) or Emergency Departments (ERs) where time plays a key role.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiology and Nuclear Medicine, Faculty of Medical Sciences in Katowice, Medical University of Silesia, Medyków 14, 40-752 Katowice, Poland.
- Tytus Chalubinski's Hospital in Zakopane, 34-500 Zakopane, Poland.
- Bright Coders' Factory, Technologiczna 2, 45-837 Opole, Poland.
- Faculty of Medicine in Katowice, Medical University of Silesia, Medyków 18, 40-752 Katowice, Poland.
- Students' Scientific Association of Computer Analysis and Artificial Intelligence, Department of Radiology and Nuclear Medicine, Medical University of Silesia, Medyków 14, 40-752 Katowice, Poland.
- Paediatric Radiology Students' Scientific Association, Division of Diagnostic Imaging, Department of Radiology and Nuclear Medicine, Faculty of Medical Science in Katowice, Medical University of Silesia, 40-752 Katowice…
ORCID-Profile: Jakub Kufel, Iga Paszkiewicz, Szymon Kocot, Anna Lis, Łukasz Czogalik, Maciej Koźlik, Maciej Cebula, Katarzyna Gruszczyńska, Zbigniew Nawrat
Zitieren
APA
Kufel, J., Paszkiewicz, I., Kocot, S., Lis, A., Dudek, P., Czogalik, Ł., Janik, M., Bargieł-Łączek, K., Bartnikowska, W., Koźlik, M., Cebula, M., Gruszczyńska, K., & Nawrat, Z. (2024). Deep Learning in Cardiothoracic Ratio Calculation and Cardiomegaly Detection. Journal of Clinical Medicine, 13(14), 4180. https://doi.org/10.3390/jcm13144180
Vancouver
Kufel J, Paszkiewicz I, Kocot S, Lis A, Dudek P, Czogalik Ł, et al. Deep Learning in Cardiothoracic Ratio Calculation and Cardiomegaly Detection. Journal of Clinical Medicine. 2024;13(14):4180. doi:10.3390/jcm13144180
BibTeX
@article{Kufel2024,
author = {Kufel, Jakub and Paszkiewicz, Iga and Kocot, Szymon and Lis, Anna and Dudek, Piotr and Czogalik, Łukasz and Janik, Michał and Bargieł-Łączek, Katarzyna and Bartnikowska, Wiktoria and Koźlik, Maciej and Cebula, Maciej and Gruszczyńska, Katarzyna and Nawrat, Zbigniew},
title = {Deep Learning in Cardiothoracic Ratio Calculation and Cardiomegaly Detection},
journal = {Journal of Clinical Medicine},
year = {2024},
volume = {13},
number = {14},
pages = {4180},
doi = {10.3390/jcm13144180}
}
EUVIMED