Vaginitis, the most common disease of female genital tract infections, mainly relies on the morphological detection of the vaginal micro-ecological system to diagnose under the microscope. It affects women's normal life seriously, even their fertility. Since the morphological detection is very dependent on the experience of the observer, while the experienced doctors are mostly concentrated in large cities, the problem of diagnosis of vaginitis in rural women is extremely serious. Convolutional neural network (CNN), the typical algorithm of artificial intelligence, has shown great potential in many visual classification tasks. However, it is difficult to apply CNN method directly to the diagnosis of vaginitis. To solve the problem, this paper proposes an algorithm combining CNN with decision-making tree (CNNDMT) based on medical expert consensus. In a way of incorporating features automatically extracted by the machine and expert knowledge, automatic diagnosis of vaginitis disease is realized. Experimental results show that the CNN-DMT approach improves test accuracy by 8.46% over the leading CNN method, while enhancing the accuracy of normal bacterial flora by more than 15%.
Super-resolution (SR) is an effective approach to enhance image spatial resolution. Although many SR algorithms have been proposed by far, little progress has been made to improve resolution for a noisy image. Conventional approaches always adopt the denoising step before applying the SR method to noisy low-resolution images. However, some high-frequency details lose during the denoising step and cannot be restored by the following SR step. Therefore, motivated by the success of deep learning in different computer vision missions, we propose a novel method named Denoising Super-Resolution Deep Convolutional Network (DSR-DCN), to combine both denoising and SR step in a single deep model. The proposed deep model straightly learns an end-to-end mapping from noisy LR space to the corresponding HR space. To equip the proposed network with the capability of blind denoising, Gaussian noise, with a range of standard deviation instead of constant value, is added to each patch of the LR space during training. Experiment results demonstrate that DSR-DCN achieves superior performance and better visual effects than the conventional approaches.