Wang Long, Fang Shu, Chen Xiaoxia, Pan Changjie, Meng Mingzhu
Department of Radiology, The Second People's Hospital of Changzhou, The Third Affiliated Hospital of Nanjing Medical University, Changzhou Medical Center, Nanjing Medical University, Nanjing, Jiangsu, China.
Department of Radiology, Changzhou Municipal Hospital of Traditional Chinese Medicine, Changzhou, Jiangsu, China.
Medicine (Baltimore). 2025 Jun 6;104(23):e42683. doi: 10.1097/MD.0000000000042683.
Various deep learning models have been developed and employed for medical image classification. This study conducted comprehensive experiments on 12 models, aiming to establish reliable benchmarks for research on breast dynamic contrast-enhanced magnetic resonance imaging image classification. Twelve deep learning models were systematically compared by analyzing variations in 4 key hyperparameters: optimizer (Op), learning rate, batch size (BS), and data augmentation. The evaluation criteria encompassed a comprehensive set of metrics including accuracy (Ac), loss value, precision, recall rate, F1-score, and area under the receiver operating characteristic curve. Furthermore, the training times and model parameter counts were assessed for holistic performance comparison. Adjustments in the BS within Adam Op had a minimal impact on Ac in the convolutional neural network models. However, altering the Op and learning rate while maintaining the same BS significantly affected the Ac. The ResNet152 network model exhibited the lowest Ac. Both the recall rate and area under the receiver operating characteristic curve for the ResNet152 and Vision transformer-base (ViT) models were inferior compared to the others. Data augmentation unexpectedly reduced the Ac of ResNet50, ResNet152, VGG16, VGG19, and ViT models. The VGG16 model boasted the shortest training duration, whereas the ViT model, before data augmentation, had the longest training time and smallest model weight. The ResNet152 and ViT models were not well suited for image classification tasks involving small breast dynamic contrast-enhanced magnetic resonance imaging datasets. Although data augmentation is typically beneficial, its application should be approached cautiously. These findings provide important insights to inform and refine future research in this domain.
已经开发并应用了各种深度学习模型用于医学图像分类。本研究对12种模型进行了全面实验，旨在为乳腺动态对比增强磁共振成像图像分类研究建立可靠的基准。通过分析4个关键超参数的变化，即优化器（Op）、学习率、批量大小（BS）和数据增强，对12种深度学习模型进行了系统比较。评估标准包括一套综合指标，如准确率（Ac）、损失值、精确率、召回率、F1分数和接收器操作特征曲线下的面积。此外，还评估了训练时间和模型参数数量以进行整体性能比较。在Adam Op中调整BS对卷积神经网络模型的Ac影响最小。然而，在保持相同BS的情况下改变Op和学习率会显著影响Ac。ResNet152网络模型的Ac最低。ResNet152和视觉变换器基础（ViT）模型的召回率和接收器操作特征曲线下的面积均低于其他模型。数据增强意外地降低了ResNet50、ResNet152、VGG16、VGG19和ViT模型的Ac。VGG16模型的训练持续时间最短，而ViT模型在数据增强之前训练时间最长且模型权重最小。ResNet152和ViT模型不太适合涉及小乳腺动态对比增强磁共振成像数据集的图像分类任务。尽管数据增强通常是有益的，但其应用应谨慎对待。这些发现为该领域未来的研究提供了重要的见解，以指导和完善研究。
