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 commonly present medium and large-sized structures such as the heart, liver, and pancreas even without hyperparameter tuning. However, the models struggle with very small or rarely present structures.

翻译：人工智能增强的医学影像中器官、病灶及其他结构的识别，通常采用卷积神经网络（CNN）来实现对感兴趣区域的体素级精确分割。然而，训练这些CNN所需的标注耗时且需要领域专家参与以确保质量。对于无需体素级精度的任务，目标检测模型提供了一种可行的替代方案，能够减少标注工作量。尽管存在这一潜在应用，目前可用于三维医学影像的通用目标检测框架选择有限。本文介绍了MedYOLO，一个基于YOLO系列模型单次检测方法的三维目标检测框架，专为医学影像设计。我们在四个不同数据集上测试了该模型：BRaTS、LIDC、腹部器官计算机断层扫描（CT）数据集以及心电图门控心脏CT数据集。研究发现，即使未经超参数调优，我们的模型在常见的中大型结构（如心脏、肝脏和胰腺）上仍能实现高性能。然而，该模型在处理极小或罕见结构时仍面临挑战。