Performance Comparison of Object Detection Networks for Shrapnel Identification in Ultrasound Images
Bioengineering · 05.07.2023 · 10 (7) · 807
DOI: 10.3390/bioengineering10070807 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioengineering, online erschienen am 05.07.2023. Verfasst von Sofia I Hernandez-Torres und 2 weiteren Autor:innen. Beteiligte Einrichtung: U.S. Army Institute of Surgical Research, JBSA Fort Sam Houston, San Antonio, TX 78234, USA. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: United States Department of Defense, Oak Ridge Associated Universities, U.S. Army Medical Research and Development Command.
Abstract (Originalsprache)
Ultrasound imaging is a critical tool for triaging and diagnosing subjects but only if images can be properly interpreted. Unfortunately, in remote or military medicine situations, the expertise to interpret images can be lacking. Machine-learning image interpretation models that are explainable to the end user and deployable in real time with ultrasound equipment have the potential to solve this problem. We have previously shown how a YOLOv3 (You Only Look Once) object detection algorithm can be used for tracking shrapnel, artery, vein, and nerve fiber bundle features in a tissue phantom. However, real-time implementation of an object detection model requires optimizing model inference time. Here, we compare the performance of five different object detection deep-learning models with varying architectures and trainable parameters to determine which model is most suitable for this shrapnel-tracking ultrasound image application. We used a dataset of more than 16,000 ultrasound images from gelatin tissue phantoms containing artery, vein, nerve fiber, and shrapnel features for training and evaluating each model. Every object detection model surpassed 0.85 mean average precision except for the detection transformer model. Overall, the YOLOv7tiny model had the higher mean average precision and quickest inference time, making it the obvious model choice for this ultrasound imaging application. Other object detection models were overfitting the data as was determined by lower testing performance compared with higher training performance. In summary, the YOLOv7tiny object detection model had the best mean average precision and inference time and was selected as optimal for this application. Next steps will implement this object detection algorithm for real-time applications, an important next step in translating AI models for emergency and military medicine.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- U.S. Army Institute of Surgical Research, JBSA Fort Sam Houston, San Antonio, TX 78234, USA.
ORCID-Profile: Eric J Snider
Förderung
- United States Department of Defense
- Oak Ridge Associated Universities
- U.S. Army Medical Research and Development Command
- National Institutes of Health (NIH)
Zitieren
APA
Hernandez-Torres, S. I., Hennessey, R. P., & Snider, E. J. (2023). Performance Comparison of Object Detection Networks for Shrapnel Identification in Ultrasound Images. Bioengineering, 10(7), 807. https://doi.org/10.3390/bioengineering10070807
Vancouver
Hernandez-Torres SI, Hennessey RP, Snider EJ. Performance Comparison of Object Detection Networks for Shrapnel Identification in Ultrasound Images. Bioengineering. 2023;10(7):807. doi:10.3390/bioengineering10070807
BibTeX
@article{HernandezTorres2023,
author = {Hernandez-Torres, Sofia I and Hennessey, Ryan P and Snider, Eric J},
title = {Performance Comparison of Object Detection Networks for Shrapnel Identification in Ultrasound Images},
journal = {Bioengineering},
year = {2023},
volume = {10},
number = {7},
pages = {807},
doi = {10.3390/bioengineering10070807}
}
EUVIMED