MedYOLO: A Medical Image Object Detection Framework
Journal of Imaging Informatics in Medicine · 06.06.2024 · 37 (6) · 3208-3216
DOI: 10.1007/s10278-024-01138-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging Informatics in Medicine, online erschienen am 06.06.2024. Verfasst von Joseph Sobek und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Mayo Clinic, Rochester, MN, USA. sobek.joseph@mayo.edu. Hauptthemen laut MEDLINE: Neural Networks, Computer, Tomography, X-Ray Computed. Die Arbeit wurde bisher 60-mal zitiert (Crossref) und nennt 17 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Artificial intelligence-enhanced identification of organs, lesions, and other structures in medical imaging is typically done using convolutional neural networks (CNNs) designed to make voxel-accurate segmentations of the region of interest. However, the labels required to train these CNNs are time-consuming to generate and require attention from subject matter experts to ensure quality. For tasks where voxel-level precision is not required, object detection models offer a viable alternative that can reduce annotation effort. Despite this potential application, there are few options for general-purpose object detection frameworks available for 3-D medical imaging. We report on MedYOLO, a 3-D object detection framework using the one-shot detection method of the YOLO family of models and designed for use with medical imaging. We tested this model on four different datasets: BRaTS, LIDC, an abdominal organ Computed tomography (CT) dataset, and an ECG-gated heart CT dataset. We found our models achieve high performance on a diverse range of structures even without hyperparameter tuning, reaching mean average precision (mAP) at intersection over union (IoU) 0.5 of 0.861 on BRaTS, 0.715 on the abdominal CT dataset, and 0.995 on the heart CT dataset. However, the models struggle with some structures, failing to converge on LIDC resulting in a mAP@0.5 of 0.0.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Radiology, Mayo Clinic, Rochester, MN, USA. sobek.joseph@mayo.edu.
- Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN, USA.
- Division of Epidemiology, Department of Quantitative Health Sciences, Mayo Clinic, Rochester, MN, USA.
- Department of Radiology, Mayo Clinic, Rochester, MN, USA.
ORCID-Profile: Joseph Sobek
Zitieren
APA
Sobek, J., Medina Inojosa, J. R., Medina Inojosa, B. J., Rassoulinejad-Mousavi, S. M., Conte, G. M., Lopez-Jimenez, F., & Erickson, B. J. (2024). MedYOLO: A Medical Image Object Detection Framework. Journal of Imaging Informatics in Medicine, 37(6), 3208-3216. https://doi.org/10.1007/s10278-024-01138-2
Vancouver
Sobek J, Medina Inojosa JR, Medina Inojosa BJ, Rassoulinejad-Mousavi SM, Conte GM, Lopez-Jimenez F, et al. MedYOLO: A Medical Image Object Detection Framework. Journal of Imaging Informatics in Medicine. 2024;37(6):3208-3216. doi:10.1007/s10278-024-01138-2
BibTeX
@article{Sobek2024,
author = {Sobek, Joseph and Medina Inojosa, Jose R and Medina Inojosa, Betsy J and Rassoulinejad-Mousavi, S M and Conte, Gian Marco and Lopez-Jimenez, Francisco and Erickson, Bradley J},
title = {MedYOLO: A Medical Image Object Detection Framework},
journal = {Journal of Imaging Informatics in Medicine},
year = {2024},
volume = {37},
number = {6},
pages = {3208--3216},
doi = {10.1007/s10278-024-01138-2}
}
EUVIMED