Medical Image Classification Using a Light-Weighted Hybrid Neural Network Based on PCANet and DenseNet

Abstract

Medical image classification plays an important role in disease diagnosis since it can provide important reference information for doctors. The supervised convolutional neural networks (CNNs) such as DenseNet provide the versatile and effective method for medical image classification tasks, but they require large amounts of data with labels and involve complex and time-consuming training process. The unsupervised CNNs such as principal component analysis network (PCANet) need no labels for training but cannot provide desirable classification accuracy. To realize the accurate medical image classification in the case of a small training dataset, we have proposed a light-weighted hybrid neural network which consists of a modified PCANet cascaded with a simplified DenseNet. The modified PCANet has two stages, in which the network produces the effective feature maps at each stage by convoluting inputs with various learned kernels. The following simplified DenseNet with a small number of weights will take all feature maps produced by the PCANet as inputs and employ the dense shortcut connections to realize accurate medical image classification. To appreciate the performance of the proposed method, some experiments have been done on mammography and osteosarcoma histology images. Experimental results show that the proposed hybrid neural network is easy to train and it outperforms such popular CNN models as PCANet, ResNet and DenseNet in terms of classification accuracy, sensitivity and specificity. INDEX TERMS Medical image classification, hybrid neural network, PCANet, DenseNet.

3E-Net: Entropy-Based Elastic Ensemble of Deep Convolutional Neural Networks for Grading of Invasive Breast Carcinoma Histopathological Microscopic Images

“…DenseNet-161 has demonstrated a superb performance for ILSVRC ImageNet classification task [ 43 ]. Moreover, DenseNet-161 has shown a great success in several histopathological image analysis pipelines [ 10 , 44 , 45 , 46 , 47 , 48 , 49 , 50 , 51 ]. In order to supply the patch-wise feature extractor network with image patches, we extract a number of patches k based on the following equation [ 7 ]: where W and H are width and height dimensions of the input image, respectively.…”

COVID-19 detection method based on SVRNet and SVDNet in lung x-rays

“…4(b) ] adds separable convolution to VGG16 as well as the layer-jumping connection structure of DenseNet. DenseNet 27 can connect each layer in the network with the previous layer to enhance feature utilization, reorganize all feature maps at the end to achieve maximum utilization of resources and compression of calculations, and increase the speed as much as possible while improving model classification capabilities.…”

A Selective Mitigation Technique of Soft Errors for DNN Models Used in Healthcare Applications: DenseNet201 Case Study

“…DenseNet201 present state-of-art CNNs is notable for its astonishing performance in benchmark tasks such as CIFAR-100 and ImageNet, which require competitive object recognition. Recent studies have shown that DenseNet is useful in healthcare applications such as diagnosis [38], medical image [39], anatomical Brain segmentation [40], and surgical [40] as it is considerably more accurate with fewer parameters. This model's performance hinged mainly on its ability to offer better parameters and training efficiency through the reuse of features.…”