Canales-Fiscal Martha Rebeca, Tamez-Peña José Gerardo
Tecnológico de Monterrey, Escuela de Ingeniería y Ciencias, Monterrey, NL, Mexico.
Tecnológico de Monterrey, Escuela de Medicina y Ciencias de la Salud, Monterrey, NL, Mexico.
Front Artif Intell. 2023 Sep 19;6:1253183. doi: 10.3389/frai.2023.1253183. eCollection 2023.
Training deep Convolutional Neural Networks (CNNs) presents challenges in terms of memory requirements and computational resources, often resulting in issues such as model overfitting and lack of generalization. These challenges can only be mitigated by using an excessive number of training images. However, medical image datasets commonly suffer from data scarcity due to the complexities involved in their acquisition, preparation, and curation. To address this issue, we propose a compact and hybrid machine learning architecture based on the Morphological and Convolutional Neural Network (MCNN), followed by a Random Forest classifier. Unlike deep CNN architectures, the MCNN was specifically designed to achieve effective performance with medical image datasets limited to a few hundred samples. It incorporates various morphological operations into a single layer and uses independent neural networks to extract information from each signal channel. The final classification is obtained by utilizing a Random Forest classifier on the outputs of the last neural network layer. We compare the classification performance of our proposed method with three popular deep CNN architectures (ResNet-18, ShuffleNet-V2, and MobileNet-V2) using two training approaches: full training and transfer learning. The evaluation was conducted on two distinct medical image datasets: the ISIC dataset for melanoma classification and the ORIGA dataset for glaucoma classification. Results demonstrate that the MCNN method exhibits reliable performance in melanoma classification, achieving an AUC of 0.94 (95% CI: 0.91 to 0.97), outperforming the popular CNN architectures. For the glaucoma dataset, the MCNN achieved an AUC of 0.65 (95% CI: 0.53 to 0.74), which was similar to the performance of the popular CNN architectures. This study contributes to the understanding of mathematical morphology in shallow neural networks for medical image classification and highlights the potential of hybrid architectures in effectively learning from medical image datasets that are limited by a small number of case samples.
训练深度卷积神经网络（CNN）在内存需求和计算资源方面存在挑战，常常导致模型过度拟合和缺乏泛化能力等问题。只有通过使用大量训练图像才能缓解这些挑战。然而，由于医学图像数据集在采集、准备和管理过程中涉及的复杂性，它们通常存在数据稀缺的问题。为了解决这个问题，我们提出了一种基于形态学和卷积神经网络（MCNN）的紧凑混合机器学习架构，随后是随机森林分类器。与深度CNN架构不同，MCNN专门设计用于在仅有几百个样本的医学图像数据集上实现有效性能。它将各种形态学操作整合到单个层中，并使用独立的神经网络从每个信号通道提取信息。最终分类通过对最后一个神经网络层的输出使用随机森林分类器来获得。我们使用两种训练方法：完全训练和迁移学习，将我们提出的方法的分类性能与三种流行的深度CNN架构（ResNet-18、ShuffleNet-V2和MobileNet-V2）进行比较。评估是在两个不同的医学图像数据集上进行的：用于黑色素瘤分类的ISIC数据集和用于青光眼分类的ORIGA数据集。结果表明，MCNN方法在黑色素瘤分类中表现出可靠的性能，AUC为0.94（95%置信区间：0.91至0.97），优于流行的CNN架构。对于青光眼数据集，MCNN的AUC为0.65（95%置信区间：0.53至0.74），与流行的CNN架构的性能相似。这项研究有助于理解浅层神经网络中用于医学图像分类的数学形态学，并突出了混合架构在从受少量病例样本限制的医学图像数据集中有效学习的潜力。
