In recent years, convolutional neural networks (CNNs) have been widely used in various computer visual recognition tasks and have achieved good results compared with traditional methods. Image classification is one of the basic and important tasks of visual recognition, and the CNN architecture applied to other visual recognition tasks (such as object detection, object localization, and semantic segmentation) is generally derived from the network architecture in image classification. We first summarize the development history of CNNs and then analyze the architecture of various deep CNNs in image classification. Furthermore, not only the innovation of the network architecture is beneficial to the results of image classification, but also the improvement of the network optimization method or training method has improved the result of image classification. We also analyze each of these methods' effect. The experimental results of various methods are compared. Finally, the development of future CNNs is prospected.

As a lightweight deep neural network, MobileNet has fewer parameters and higher classification accuracy. In order to further reduce the number of network parameters and improve the classification accuracy, dense blocks that are proposed in DenseNets are introduced into MobileNet. In Dense-MobileNet models, convolution layers with the same size of input feature maps in MobileNet models are taken as dense blocks, and dense connections are carried out within the dense blocks. e new network structure can make full use of the output feature maps generated by the previous convolution layers in dense blocks, so as to generate a large number of feature maps with fewer convolution cores and repeatedly use the features. By setting a small growth rate, the network further reduces the parameters and the computation cost. Two Dense-MobileNet models, Dense1-MobileNet and Dense2-MobileNet, are designed. Experiments show that Dense2-MobileNet can achieve higher recognition accuracy than MobileNet, while only with fewer parameters and computation cost.

Background: Colonic polyps are more likely to be cancerous, especially those with large diameter, large number and atypical hyperplasia. If colonic polyps cannot be treated in early stage, they are likely to develop into colon cancer. Colonoscopy is easily limited by the operator's experience, and factors such as inexperience and visual fatigue will directly affect the accuracy of diagnosis. Cooperating with Hunan children's hospital, we proposed and improved a deep learning approach with global average pooling (GAP) in colonoscopy for assisted diagnosis. Our approach for assisted diagnosis in colonoscopy can prompt endoscopists to pay attention to polyps that may be ignored in real time, improve the detection rate, reduce missed diagnosis, and improve the efficiency of medical diagnosis. Methods: We selected colonoscopy images from the gastrointestinal endoscopy room of Hunan children's hospital to form the colonic polyp datasets. And we applied the image classification method based on Deep Learning to the classification of Colonic Polyps. The classic networks we used are VGGNets and ResNets. By using global average pooling, we proposed the improved approaches: VGGNets-GAP and ResNets-GAP. Results: The accuracies of all models in datasets exceed 98%. The TPR and TNR are above 96 and 98% respectively. In addition, VGGNets-GAP networks not only have high classification accuracies, but also have much fewer parameters than those of VGGNets. Conclusions: The experimental results show that the proposed approach has good effect on the automatic detection of colonic polyps. The innovations of our method are in two aspects: (1) the detection accuracy of colonic polyps has been improved. (2) our approach reduces the memory consumption and makes the model lightweight. Compared with the original VGG networks, the parameters of our VGG19-GAP networks are greatly reduced.

No abstract

No abstract