PSTCNN: Explainable COVID-19 diagnosis using PSO-guided self-tuning CNN.

Since 2019, the coronavirus disease-19 (COVID-19) has been spreading rapidly worldwide, posing an unignorable threat to the global economy and human health. It is a disease caused by severe acute respiratory syndrome coronavirus 2, a single-stranded RNA virus of the genus Betacoronavirus. This virus is highly infectious and relies on its angiotensin-converting enzyme 2-receptor to enter cells. With the increase in the number of confirmed COVID-19 diagnoses, the difficulty of diagnosis due to the lack of global healthcare resources becomes increasingly apparent. Deep learning-based computer-aided diagnosis models with high generalisability can effectively alleviate this pressure. Hyperparameter tuning is essential in training such models and significantly impacts their final performance and training speed. However, traditional hyperparameter tuning methods are usually time-consuming and unstable. To solve this issue, we introduce Particle Swarm Optimisation to build a PSO-guided Self-Tuning Convolution Neural Network (PSTCNN), allowing the model to tune hyperparameters automatically. Therefore, the proposed approach can reduce human involvement. Also, the optimisation algorithm can select the combination of hyperparameters in a targeted manner, thus stably achieving a solution closer to the global optimum. Experimentally, the PSTCNN can obtain quite excellent results, with a sensitivity of 93.65%±1.86%, a specificity of 94.32%±2.07%, a precision of 94.30%±2.04%, an accuracy of 93.99%±1.78%, an F1-score of 93.97%±1.78%, Matthews Correlation Coefficient of 87.99%±3.56%, and Fowlkes-Mallows Index of 93.97%±1.78%. Our experiments demonstrate that compared to traditional methods, hyperparameter tuning of the model using an optimisation algorithm is faster and more effective.

AVNC: Attention-Based VGG-Style Network for COVID-19 Diagnosis by CBAM.

(Aim) To detect COVID-19 patients more accurately and more precisely, we proposed a novel artificial intelligence model. (Methods) We used previously proposed chest CT dataset containing four categories: COVID-19, community-acquired pneumonia, secondary pulmonary tuberculosis, and healthy subjects. First, we proposed a novel VGG-style base network (VSBN) as backbone network. Second, convolutional block attention module (CBAM) was introduced as attention module into our VSBN. Third, an improved multiple-way data augmentation method was used to resist overfitting of our AI model. In all, our model was dubbed as a 12-layer attention-based VGG-style network for COVID-19 (AVNC) (Results) This proposed AVNC achieved the sensitivity/precision/F1 per class all above 95%. Particularly, AVNC yielded a micro-averaged F1 score of 96.87%, which is higher than 11 state-of-the-art approaches. (Conclusion) This proposed AVNC is effective in recognizing COVID-19 diseases.

VISPNN: VGG-inspired Stochastic Pooling Neural Network.

Aim: Alcoholism is a disease that a patient becomes dependent or addicted to alcohol. This paper aims to design a novel artificial intelligence model that can recognize alcoholism more accurately. Methods: We propose the VGG-Inspired stochastic pooling neural network (VISPNN) model based on three components: (i) a VGG-inspired mainstay network, (ii) the stochastic pooling technique, which aims to outperform traditional max pooling and average pooling, and (iii) an improved 20-way data augmentation (Gaussian noise, salt-and-pepper noise, speckle noise, Poisson noise, horizontal shear, vertical shear, rotation, Gamma correction, random translation, and scaling on both raw image and its horizontally mirrored image). In addition, two networks (Net-I and Net-II) are proposed in ablation studies. Net-I is based on VISPNN by replacing stochastic pooling with ordinary max pooling. Net-II removes the 20-way data augmentation. Results: The results by ten runs of 10-fold cross-validation show that our VISPNN model gains a sensitivity of 97.98±1.32, a specificity of 97.80±1.35, a precision of 97.78±1.35, an accuracy of 97.89±1.11, an F1 score of 97.87±1.12, an MCC of 95.79±2.22, an FMI of 97.88±1.12, and an AUC of 0.9849, respectively. Conclusion: The performance of our VISPNN model is better than two internal networks (Net-I and Net-II) and ten state-of-the-art alcoholism recognition methods.

NAGNN: Classification of COVID-19 based on neighboring aware representation from deep graph neural network.

COVID-19 pneumonia started in December 2019 and caused large casualties and huge economic losses. In this study, we intended to develop a computer-aided diagnosis system based on artificial intelligence to automatically identify the COVID-19 in chest computed tomography images. We utilized transfer learning to obtain the image-level representation (ILR) based on the backbone deep convolutional neural network. Then, a novel neighboring aware representation (NAR) was proposed to exploit the neighboring relationships between the ILR vectors. To obtain the neighboring information in the feature space of the ILRs, an ILR graph was generated based on the k-nearest neighbors algorithm, in which the ILRs were linked with their k-nearest neighboring ILRs. Afterward, the NARs were computed by the fusion of the ILRs and the graph. On the basis of this representation, a novel end-to-end COVID-19 classification architecture called neighboring aware graph neural network (NAGNN) was proposed. The private and public data sets were used for evaluation in the experiments. Results revealed that our NAGNN outperformed all the 10 state-of-the-art methods in terms of generalization ability. Therefore, the proposed NAGNN is effective in detecting COVID-19, which can be used in clinical diagnosis.

Diagnosis of COVID-19 Pneumonia via a Novel Deep Learning Architecture.

COVID-19 is a contagious infection that has severe effects on the global economy and our daily life. Accurate diagnosis of COVID-19 is of importance for consultants, patients, and radiologists. In this study, we use the deep learning network AlexNet as the backbone, and enhance it with the following two aspects: 1) adding batch normalization to help accelerate the training, reducing the internal covariance shift; 2) replacing the fully connected layer in AlexNet with three classifiers: SNN, ELM, and RVFL. Therefore, we have three novel models from the deep COVID network (DC-Net) framework, which are named DC-Net-S, DC-Net-E, and DC-Net-R, respectively. After comparison, we find the proposed DC-Net-R achieves an average accuracy of 90.91% on a private dataset (available upon email request) comprising of 296 images while the specificity reaches 96.13%, and has the best performance among all three proposed classifiers. In addition, we show that our DC-Net-R also performs much better than other existing algorithms in the literature. Supplementary Information: The online version contains supplementary material available at 10.1007/s11390-020-0679-8.

Color painting predicts clinical symptoms in chronic schizophrenia patients via deep learning.

BACKGROUND: Individuals with psychiatric disorders perceive the world differently. Previous studies indicated impaired color vision and weakened color discrimination ability in psychotic patients. Examining the paintings from psychotic patients can measure the visual-motor function. However, few studies examined the potential changes in the color painting behavior in these individuals. The current study aims to discriminate schizophrenia patients from healthy controls (HCs) and predict PANSS scores of schizophrenia patients according to their paintings. METHODS: In the present study, we retrospectively analyzed the paintings colored by 281 chronic schizophrenia patients and 35 HCs. The images were scanned and processed using series of computational analyses. RESULTS: The results showed that schizophrenia patients tend to use less color and exhibit different strokes compared to HCs. Using a deep learning residual neural network (ResNet), we were able to discriminate patients from HCs with over 90% accuracy. Further, we developed a novel convolutional neural network to predict PANSS positive, negative, general psychopathology, and total scores. The Root Mean Square Error (RMSE) of the prediction was low, which indicates higher accuracy of prediction. CONCLUSION: In conclusion, the deep learning paradigm showed the large potential to discriminate schizophrenia patients from HCs based on color paintings. Besides, this color painting-based paradigm can effectively predict clinical symptom severity for chronic schizophrenia patients. The color paintings by schizophrenia patients show potential as a tool for clinical diagnosis and prognosis. These findings show potential as a tool for clinical diagnosis and prognosis among schizophrenia patients.

A Heuristic Neural Network Structure Relying on Fuzzy Logic for Images Scoring.

Traditional deep learning methods are sub-optimal in classifying ambiguity features, which often arise in noisy and hard to predict categories, especially, to distinguish semantic scoring. Semantic scoring, depending on semantic logic to implement evaluation, inevitably contains fuzzy description and misses some concepts, for example, the ambiguous relationship between normal and probably normal always presents unclear boundaries (normal - more likely normal - probably normal). Thus, human error is common when annotating images. Differing from existing methods that focus on modifying kernel structure of neural networks, this study proposes a dominant fuzzy fully connected layer (FFCL) for Breast Imaging Reporting and Data System (BI-RADS) scoring and validates the universality of this proposed structure. This proposed model aims to develop complementary properties of scoring for semantic paradigms, while constructing fuzzy rules based on analyzing human thought patterns, and to particularly reduce the influence of semantic conglutination. Specifically, this semantic-sensitive defuzzier layer projects features occupied by relative categories into semantic space, and a fuzzy decoder modifies probabilities of the last output layer referring to the global trend. Moreover, the ambiguous semantic space between two relative categories shrinks during the learning phases, as the positive and negative growth trends of one category appearing among its relatives were considered. We first used the Euclidean Distance (ED) to zoom in the distance between the real scores and the predicted scores, and then employed two sample t test method to evidence the advantage of the FFCL architecture. Extensive experimental results performed on the CBIS-DDSM dataset show that our FFCL structure can achieve superior performances for both triple and multiclass classification in BI-RADS scoring, outperforming the state-of-the-art methods.

ResGNet-C: A graph convolutional neural network for detection of COVID-19.

The widely spreading COVID-19 has caused thousands of hundreds of mortalities over the world in the past few months. Early diagnosis of the virus is of great significance for both of infected patients and doctors providing treatments. Chest Computerized tomography (CT) screening is one of the most straightforward techniques to detect pneumonia which was caused by the virus and thus to make the diagnosis. To facilitate the process of diagnosing COVID-19, we therefore developed a graph convolutional neural network ResGNet-C under ResGNet framework to automatically classify lung CT images into normal and confirmed pneumonia caused by COVID-19. In ResGNet-C, two by-products named NNet-C, ResNet101-C that showed high performance on detection of COVID-19 are simultaneously generated as well. Our best model ResGNet-C achieved an averaged accuracy at 0.9662 with an averaged sensitivity at 0.9733 and an averaged specificity at 0.9591 using five cross-validations on the dataset, which is comprised of 296 CT images. To our best knowledge, this is the first attempt at integrating graph knowledge into the COVID-19 classification task. Graphs are constructed according to the Euclidean distance between features extracted by our proposed ResNet101-C and then are encoded with the features to give the prediction results of CT images. Besides the high-performance system, which surpassed all state-of-the-art methods, our proposed graph construction method is simple, transferrable yet quite helpful for improving the performance of classifiers, as can be justified by the experimental results.

MIDCAN: A multiple input deep convolutional attention network for Covid-19 diagnosis based on chest CT and chest X-ray.

BACKGROUND: COVID-19 has caused 3.34m deaths till 13/May/2021. It is now still causing confirmed cases and ongoing deaths every day. METHOD: This study investigated whether fusing chest CT with chest X-ray can help improve the AI's diagnosis performance. Data harmonization is employed to make a homogeneous dataset. We create an end-to-end multiple-input deep convolutional attention network (MIDCAN) by using the convolutional block attention module (CBAM). One input of our model receives 3D chest CT image, and other input receives 2D X-ray image. Besides, multiple-way data augmentation is used to generate fake data on training set. Grad-CAM is used to give explainable heatmap. RESULTS: The proposed MIDCAN achieves a sensitivity of 98.10±1.88%, a specificity of 97.95±2.26%, and an accuracy of 98.02±1.35%. CONCLUSION: Our MIDCAN method provides better results than 8 state-of-the-art approaches. We demonstrate the using multiple modalities can achieve better results than individual modality. Also, we demonstrate that CBAM can help improve the diagnosis performance.

COVID-19 classification by CCSHNet with deep fusion using transfer learning and discriminant correlation analysis.

AIM: : COVID-19 is a disease caused by a new strain of coronavirus. Up to 18th October 2020, worldwide there have been 39.6 million confirmed cases resulting in more than 1.1 million deaths. To improve diagnosis, we aimed to design and develop a novel advanced AI system for COVID-19 classification based on chest CT (CCT) images. METHODS: : Our dataset from local hospitals consisted of 284 COVID-19 images, 281 community-acquired pneumonia images, 293 secondary pulmonary tuberculosis images; and 306 healthy control images. We first used pretrained models (PTMs) to learn features, and proposed a novel (L, 2) transfer feature learning algorithm to extract features, with a hyperparameter of number of layers to be removed (NLR, symbolized as L). Second, we proposed a selection algorithm of pretrained network for fusion to determine the best two models characterized by PTM and NLR. Third, deep CCT fusion by discriminant correlation analysis was proposed to help fuse the two features from the two models. Micro-averaged (MA) F1 score was used as the measuring indicator. The final determined model was named CCSHNet. RESULTS: : On the test set, CCSHNet achieved sensitivities of four classes of 95.61%, 96.25%, 98.30%, and 97.86%, respectively. The precision values of four classes were 97.32%, 96.42%, 96.99%, and 97.38%, respectively. The F1 scores of four classes were 96.46%, 96.33%, 97.64%, and 97.62%, respectively. The MA F1 score was 97.04%. In addition, CCSHNet outperformed 12 state-of-the-art COVID-19 detection methods. CONCLUSIONS: : CCSHNet is effective in detecting COVID-19 and other lung infectious diseases using first-line clinical imaging and can therefore assist radiologists in making accurate diagnoses based on CCTs.

Covid-19 classification by FGCNet with deep feature fusion from graph convolutional network and convolutional neural network.

(Aim) COVID-19 is an infectious disease spreading to the world this year. In this study, we plan to develop an artificial intelligence based tool to diagnose on chest CT images. (Method) On one hand, we extract features from a self-created convolutional neural network (CNN) to learn individual image-level representations. The proposed CNN employed several new techniques such as rank-based average pooling and multiple-way data augmentation. On the other hand, relation-aware representations were learnt from graph convolutional network (GCN). Deep feature fusion (DFF) was developed in this work to fuse individual image-level features and relation-aware features from both GCN and CNN, respectively. The best model was named as FGCNet. (Results) The experiment first chose the best model from eight proposed network models, and then compared it with 15 state-of-the-art approaches. (Conclusion) The proposed FGCNet model is effective and gives better performance than all 15 state-of-the-art methods. Thus, our proposed FGCNet model can assist radiologists to rapidly detect COVID-19 from chest CT images.

CGNet: A graph-knowledge embedded convolutional neural network for detection of pneumonia.

Pneumonia is a global disease that causes high children mortality. The situation has even been worsening by the outbreak of the new coronavirus named COVID-19, which has killed more than 983,907 so far. People infected by the virus would show symptoms like fever and coughing as well as pneumonia as the infection progresses. Timely detection is a public consensus achieved that would benefit possible treatments and therefore contain the spread of COVID-19. X-ray, an expedient imaging technique, has been widely used for the detection of pneumonia caused by COVID-19 and some other virus. To facilitate the process of diagnosis of pneumonia, we developed a deep learning framework for a binary classification task that classifies chest X-ray images into normal and pneumonia based on our proposed CGNet. In our CGNet, there are three components including feature extraction, graph-based feature reconstruction and classification. We first use the transfer learning technique to train the state-of-the-art convolutional neural networks (CNNs) for binary classification while the trained CNNs are used to produce features for the following two components. Then, by deploying graph-based feature reconstruction, we, therefore, combine features through the graph to reconstruct features. Finally, a shallow neural network named GNet, a one layer graph neural network, which takes the combined features as the input, classifies chest X-ray images into normal and pneumonia. Our model achieved the best accuracy at 0.9872, sensitivity at 1 and specificity at 0.9795 on a public pneumonia dataset that includes 5,856 chest X-ray images. To evaluate the performance of our proposed method on detection of pneumonia caused by COVID-19, we also tested the proposed method on a public COVID-19 CT dataset, where we achieved the highest performance at the accuracy of 0.99, specificity at 1 and sensitivity at 0.98, respectively.

MFBCNNC: Momentum factor biogeography convolutional neural network for COVID-19 detection via chest X-ray images.

AIM: By October 6, 2020, Coronavirus disease 2019 (COVID-19) was diagnosed worldwide, reaching 3,355,7427 people and 1,037,862 deaths. Detection of COVID-19 and pneumonia by the chest X-ray images is of great significance to control the development of the epidemic situation. The current COVID-19 and pneumonia detection system may suffer from two shortcomings: the selection of hyperparameters in the models is not appropriate, and the generalization ability of the model is poor. METHOD: To solve the above problems, our team proposed an improved intelligent global optimization algorithm, which is based on the biogeography-based optimization to automatically optimize the hyperparameters value of the models according to different detection objectives. In the optimization progress, after selecting the immigration of suitable index vector and the emigration of suitable index vector, we proposed adding a comparison operation to compare the value of them. According to the different numerical relationships between them, the corresponding operations are performed to improve the migration operation of biogeography-based optimization. The improved algorithm (momentum factor biogeography-based optimization) can better perform the automatic optimization operation. In addition, our team also proposed two frameworks: biogeography convolutional neural network and momentum factor biogeography convolutional neural network. And two methods for detection COVID-19 based on the proposed frameworks. RESULTS: Our method used three convolutional neural networks (LeNet-5, VGG-16, and ResNet-18) as the basic classification models for chest X-ray images detection of COVID-19, Normal, and Pneumonia. The accuracy of LeNet-5, VGG-16, and ResNet-18 is improved by 1.56%, 1.48%, and 0.73% after using biogeography-based optimization to optimize the hyperparameters of the models. The accuracy of LeNet-5, VGG-16, and ResNet-18 is improved by 2.87%, 6.31%, and 1.46% after using the momentum factor biogeography-based optimization to optimize the hyperparameters of the models. CONCLUSION: Under the same experimental conditions, the performance of the momentum factor biogeography-based optimization is superior to the biogeography-based optimization in optimizing the hyperparameters of the convolutional neural networks. Experimental results show that the momentum factor biogeography-based optimization can improve the detection performance of the state-of-the-art approaches in terms of overall accuracy. In future research, we will continue to use and improve other global optimization algorithms to enhance the application ability of deep learning in medical pathological image detection.

Advances in multimodal data fusion in neuroimaging: Overview, challenges, and novel orientation.

Multimodal fusion in neuroimaging combines data from multiple imaging modalities to overcome the fundamental limitations of individual modalities. Neuroimaging fusion can achieve higher temporal and spatial resolution, enhance contrast, correct imaging distortions, and bridge physiological and cognitive information. In this study, we analyzed over 450 references from PubMed, Google Scholar, IEEE, ScienceDirect, Web of Science, and various sources published from 1978 to 2020. We provide a review that encompasses (1) an overview of current challenges in multimodal fusion (2) the current medical applications of fusion for specific neurological diseases, (3) strengths and limitations of available imaging modalities, (4) fundamental fusion rules, (5) fusion quality assessment methods, and (6) the applications of fusion for atlas-based segmentation and quantification. Overall, multimodal fusion shows significant benefits in clinical diagnosis and neuroscience research. Widespread education and further research amongst engineers, researchers and clinicians will benefit the field of multimodal neuroimaging.

Advancing a High Throughput Glycotope-centric Glycomics Workflow Based on nanoLC-MS2-product Dependent-MS3 Analysis of Permethylated Glycans.

The intrinsic nature of glycosylation, namely nontemplate encoded, stepwise elongation and termination with a diverse range of isomeric glyco-epitopes (glycotopes), translates into ambiguity in most cases of mass spectrometry (MS)-based glycomic mapping. It is arguable that whether one needs to delineate every single glycomic entity, which may be counterproductive. Instead, one should focus on identifying as many structural features as possible that would collectively define the glycomic characteristics of a cell or tissue, and how these may change in response to self-programmed development, immuno-activation, and malignant transformation. We have been pursuing this line of analytical strategy that homes in on identifying the terminal sulfo-, sialyl, and/or fucosylated glycotopes by comprehensive nanoLC-MS2-product dependent MS3 analysis of permethylated glycans, in conjunction with development of a data mining computational tool, GlyPick, to enable an automated, high throughput, semi-quantitative glycotope-centric glycomic mapping amenable to even nonexperts. We demonstrate in this work that diagnostic MS2 ions can be relied on to inform the presence of specific glycotopes, whereas their possible isomeric identities can be resolved at MS3 level. Both MS2 and associated MS3 data can be acquired exhaustively and processed automatically by GlyPick. The high acquisition speed, resolution, and mass accuracy afforded by top-notch Orbitrap Fusion MS system now allow a sensible spectral count and/or summed ion intensity-based glycome-wide glycotope quantification. We report here the technical aspects, reproducibility and optimization of such an analytical approach that uses the same acidic reverse phase C18 nanoLC conditions fully compatible with proteomic analysis to allow rapid hassle-free switching. We further show how this workflow is particularly effective when applied to larger, multiply sialylated and fucosylated N-glycans derived from mouse brain. The complexity of their terminal glycotopes including variants of fucosylated and disialylated type 1 and 2 chains would otherwise not be adequately delineated by any conventional LC-MS/MS analysis.

Author Correction: Three-Category Classification of Magnetic Resonance Hearing Loss Images Based on Deep Autoencoder.

The original version of this article unfortunately contained a mistake. The reference #27 in the reference list is incorrect in that the individual chapter should be cited instead of the whole book.

Classification of Alzheimer's Disease Based on Eight-Layer Convolutional Neural Network with Leaky Rectified Linear Unit and Max Pooling.

Alzheimer's disease (AD) is a progressive brain disease. The goal of this study is to provide a new computer-vision based technique to detect it in an efficient way. The brain-imaging data of 98 AD patients and 98 healthy controls was collected using data augmentation method. Then, convolutional neural network (CNN) was used, CNN is the most successful tool in deep learning. An 8-layer CNN was created with optimal structure obtained by experiences. Three activation functions (AFs): sigmoid, rectified linear unit (ReLU), and leaky ReLU. The three pooling-functions were also tested: average pooling, max pooling, and stochastic pooling. The numerical experiments demonstrated that leaky ReLU and max pooling gave the greatest result in terms of performance. It achieved a sensitivity of 97.96%, a specificity of 97.35%, and an accuracy of 97.65%, respectively. In addition, the proposed approach was compared with eight state-of-the-art approaches. The method increased the classification accuracy by approximately 5% compared to state-of-the-art methods.

Multiple Sclerosis Identification Based on Fractional Fourier Entropy and a Modified Jaya Algorithm.

Aim: Currently, identifying multiple sclerosis (MS) by human experts may come across the problem of "normal-appearing white matter", which causes a low sensitivity. Methods: In this study, we presented a computer vision based approached to identify MS in an automatic way. This proposed method first extracted the fractional Fourier entropy map from a specified brain image. Afterwards, it sent the features to a multilayer perceptron trained by a proposed improved parameter-free Jaya algorithm. We used cost-sensitivity learning to handle the imbalanced data problem. Results: The 10 × 10-fold cross validation showed our method yielded a sensitivity of 97.40 ± 0.60%, a specificity of 97.39 ± 0.65%, and an accuracy of 97.39 ± 0.59%. Conclusions: We validated by experiments that the proposed improved Jaya performs better than plain Jaya algorithm and other latest bioinspired algorithms in terms of classification performance and training speed. In addition, our method is superior to four state-of-the-art MS identification approaches.

Three-Category Classification of Magnetic Resonance Hearing Loss Images Based on Deep Autoencoder.

Hearing loss, a partial or total inability to hear, is known as hearing impairment. Untreated hearing loss can have a bad effect on normal social communication, and it can cause psychological problems in patients. Therefore, we design a three-category classification system to detect the specific category of hearing loss, which is beneficial to be treated in time for patients. Before the training and test stages, we use the technology of data augmentation to produce a balanced dataset. Then we use deep autoencoder neural network to classify the magnetic resonance brain images. In the stage of deep autoencoder, we use stacked sparse autoencoder to generate visual features, and softmax layer to classify the different brain images into three categories of hearing loss. Our method can obtain good experimental results. The overall accuracy of our method is 99.5%, and the time consuming is 0.078 s per brain image. Our proposed method based on stacked sparse autoencoder works well in classification of hearing loss images. The overall accuracy of our method is 4% higher than the best of state-of-the-art approaches.

Alcoholism Detection by Data Augmentation and Convolutional Neural Network with Stochastic Pooling.

Alcohol use disorder (AUD) is an important brain disease. It alters the brain structure. Recently, scholars tend to use computer vision based techniques to detect AUD. We collected 235 subjects, 114 alcoholic and 121 non-alcoholic. Among the 235 image, 100 images were used as training set, and data augmentation method was used. The rest 135 images were used as test set. Further, we chose the latest powerful technique-convolutional neural network (CNN) based on convolutional layer, rectified linear unit layer, pooling layer, fully connected layer, and softmax layer. We also compared three different pooling techniques: max pooling, average pooling, and stochastic pooling. The results showed that our method achieved a sensitivity of 96.88%, a specificity of 97.18%, and an accuracy of 97.04%. Our method was better than three state-of-the-art approaches. Besides, stochastic pooling performed better than other max pooling and average pooling. We validated CNN with five convolution layers and two fully connected layers performed the best. The GPU yielded a 149× acceleration in training and a 166× acceleration in test, compared to CPU.