MedYOLO: A Medical Image Object Detection Framework

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-...

Full description

Saved in:
Bibliographic Details
Published in:Journal of digital imaging 2024-12, Vol.37 (6), p.3208-3216
Main Authors: Sobek, Joseph, Medina Inojosa, Jose R., Medina Inojosa, Betsy J., Rassoulinejad-Mousavi, S. M., Conte, Gian Marco, Lopez-Jimenez, Francisco, Erickson, Bradley J.
Format: Article
Language:English
Subjects:
Algorithms
Annotations
Artificial Intelligence
Artificial neural networks
Computed tomography
Datasets
EKG
Heart - diagnostic imaging
Humans
Image enhancement
Image processing
Image Processing, Computer-Assisted - methods
Imaging
Imaging, Three-Dimensional - methods
Medical imaging
Medicine
Medicine & Public Health
Neural networks
Neural Networks, Computer
Object recognition
Radiology
Tomography, X-Ray Computed - methods
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:0897-1889
2948-2933
2948-2925
2948-2933
1618-727X
DOI:10.1007/s10278-024-01138-2