CMEMS-UMinho Research Unit, University of Minho, Campus Azurém, 4800-058 Guimarães, Portugal; LABBELS -Associate Laboratory, Braga, Guimarães, Portugal.
CMEMS-UMinho Research Unit, University of Minho, Campus Azurém, 4800-058 Guimarães, Portugal; LABBELS -Associate Laboratory, Braga, Guimarães, Portugal.
Artif Intell Med. 2022 Apr;126:102275. doi: 10.1016/j.artmed.2022.102275. Epub 2022 Mar 6.
This paper confronts two approaches to classify bladder lesions shown in white light cystoscopy images when using small datasets: the classical one, where handcrafted-based features feed pattern recognition systems and the modern deep learning-based (DL) approach. In between, there are alternative DL models that had not received wide attention from the scientific community, even though they can be more appropriate for small datasets such as the human brain motivated capsule neural networks (CapsNets). However, CapsNets have not yet matured hence presenting lower performances than the most classic DL models. These models require higher computational resources, more computational skills from the physician and are more prone to overfitting, making them sometimes prohibitive in the routine of clinical practice. This paper shows that carefully handcrafted features used with more robust models can reach similar performances to the conventional DL-based models and deep CapsNets, making them more useful for clinical applications. Concerning feature extraction, it is proposed a new feature fusion approach for Ta and T1 bladder tumor detection by using decision fusion from multiple classifiers in a scheme known as stacking of classifiers. Three Neural Networks perform classification on three different feature sets, namely: Covariance of Color Histogram of Oriented Gradients, proposed in the ambit of this paper; Local Binary Patterns and Wavelet Coefficients taken from lower scales. Data diversity is ensured by a fourth Neural Network, which is used for decision fusion by combining the outputs of the ensemble elements to produce the classifier output. Both Feed Forward Neural Networks and Radial Basis Functions are used in the experiments. Contrarily, DL-based models extract automatically the best features at the cost of requiring huge amounts of training data, which in turn can be alleviated by using the Transfer Learning (TL) strategy. In this paper VGG16 and ResNet-34 pretrained in ImageNet were used for TL, slightly outperforming the proposed ensemble. CapsNets may overcome CNNs given their ability to deal with objects rotational invariance and spatial relationships. Therefore, they can be trained from scratch in applications using small amounts of data, which was beneficial for the current case, improving accuracy from 94.6% to 96.9%.
一种是基于手工制作特征的经典方法，另一种是基于现代深度学习（DL）的方法。在这两者之间，还有一些替代的 DL 模型，尽管它们可能更适合于像人脑启发的胶囊神经网络（CapsNets）这样的小数据集，但它们并没有受到科学界的广泛关注。然而，CapsNets 还不够成熟，因此性能比最经典的 DL 模型要差。这些模型需要更高的计算资源，需要医生具备更多的计算技能，并且更容易出现过拟合现象，这使得它们在临床实践的常规工作中有时不太可行。本文表明，使用更稳健的模型仔细提取手工制作的特征可以达到与传统基于 DL 的模型和深度 CapsNets 相似的性能，从而使其更适用于临床应用。在特征提取方面，本文提出了一种新的 Ta 和 T1 膀胱癌检测特征融合方法，该方法通过在一个称为分类器堆叠的方案中使用来自多个分类器的决策融合来实现。三个神经网络分别对三个不同的特征集进行分类，即：本文提出的基于颜色直方图的协方差的 Oriented Gradients、局部二值模式和来自较低尺度的小波系数。第四个神经网络通过结合集成元素的输出来进行决策融合，从而确保数据多样性，产生分类器输出。在实验中，既使用了前馈神经网络，也使用了径向基函数。相反，基于 DL 的模型通过使用大量的训练数据自动提取最佳特征，从而实现了自动提取最佳特征的功能，而代价是需要大量的训练数据，这可以通过使用迁移学习（TL）策略来缓解。在本文中，使用了在 ImageNet 上进行预训练的 VGG16 和 ResNet-34 进行 TL，它们的性能略优于所提出的集成。CapsNets 可以克服 CNN，因为它们能够处理物体的旋转不变性和空间关系。因此，它们可以在使用少量数据的应用程序中从头开始进行训练，这对当前的情况很有帮助，将准确率从 94.6%提高到了 96.9%。
