Automatic identifying and counting blood cells in smear images by using single shot detector and Taguchi method.

BACKGROUND: Researchers have tried to identify and count different blood cells in microscopic smear images by using deep learning methods of artificial intelligence to solve the highly time-consuming problem. RESULTS: The three types of blood cells are platelets, red blood cells, and white blood cells. This study used the Resnet50 network as a backbone network of the single shot detector (SSD) for automatically identifying and counting different blood cells and, meanwhile, proposed a systematic method to find a better combination of algorithm hyperparameters of the Resnet50 network for promoting accuracy for identifying and counting blood cells. The Resnet50 backbone network of the SSD with its optimized algorithm hyperparameters, which is called the Resnet50-SSD model, was developed to enhance the feature extraction ability for identifying and counting blood cells. Furthermore, the algorithm hyperparameters of Resnet50 backbone networks of the SSD were optimized by the Taguchi experimental method for promoting detection accuracy of the Resnet50-SSD model. The experimental result shows that the detection accuracy of the Resnet50-SSD model with 512 × 512 × 3 input images was better than that of the Resnet50-SSD model with 300 × 300 × 3 input images on the test set of blood cells images. Additionally, the detection accuracy of the Resnet50-SSD model using the combination of algorithm hyperparameters got by the Taguchi method was better than that of the Resnet50-SSD model using the combination of algorithm hyperparameters given by the Matlab example. CONCLUSION: In blood cell images acquired from the BCCD dataset, the proposed Resnet50-SSD model had higher accuracy in identifying and counting blood cells, especially white blood cells and red blood cells.

Classifying microscopic images as acute lymphoblastic leukemia by Resnet ensemble model and Taguchi method.

BACKGROUND: Researchers have attempted to apply deep learning methods of artificial intelligence for rapidly and accurately detecting acute lymphoblastic leukemia (ALL) in microscopic images. RESULTS: A Resnet101-9 ensemble model was developed for classifying ALL in microscopic images. The proposed Resnet101-9 ensemble model combined the use of the nine trained Resnet-101 models with a majority voting strategy. Each trained Resnet-101 model integrated the well-known pre-trained Resnet-101 model and its algorithm hyperparameters by using transfer learning method to classify ALL in microscopic images. The best combination of algorithm hyperparameters for the pre-trained Resnet-101 model was determined by Taguchi experimental method. The microscopic images used for training of the pre-trained Resnet-101 model and for performance tests of the trained Resnet-101 model were obtained from the C-NMC dataset. In experimental tests of performance, the Resnet101-9 ensemble model achieved an accuracy of 85.11% and an F1-score of 88.94 in classifying ALL in microscopic images. The accuracy of the Resnet101-9 ensemble model was superior to that of the nine trained Resnet-101 individual models. All other performance measures (i.e., precision, recall, and specificity) for the Resnet101-9 ensemble model exceeded those for the nine trained Resnet-101 individual models. CONCLUSION: Compared to the nine trained Resnet-101 individual models, the Resnet101-9 ensemble model had superior accuracy in classifying ALL in microscopic images obtained from the C-NMC dataset.

Epidemic prediction of dengue fever based on vector compartment model and Markov chain Monte Carlo method.

BACKGROUND: Dengue epidemics is affected by vector-human interactive dynamics. Infectious disease prevention and control emphasize the timing intervention at the right diffusion phase. In such a way, control measures can be cost-effective, and epidemic incidents can be controlled before devastated consequence occurs. However, timing relations between a measurable signal and the onset of the pandemic are complex to be discovered, and the typical lag period regression is difficult to capture in these complex relations. This study investigates the dynamic diffusion pattern of the disease in terms of a probability distribution. We estimate the parameters of an epidemic compartment model with the cross-infection of patients and mosquitoes in various infection cycles. We comprehensively study the incorporated meteorological and mosquito factors that may affect the epidemic of dengue fever to predict dengue fever epidemics. RESULTS: We develop a dual-parameter estimation algorithm for a composite model of the partial differential equations for vector-susceptible-infectious-recovered with exogeneity compartment model, Markov chain Montel Carlo method, and boundary element method to evaluate the epidemic periodicity under the effect of environmental factors of dengue fever, given the time series data of 2000-2016 from three cities with a population of 4.7 million. The established computer model of "energy accumulation-delayed diffusion-epidemics" is proven to be effective to predict the future trend of reported and unreported infected incidents. Our artificial intelligent algorithm can inform the authority to cease the larvae at the highest vector infection time. We find that the estimated dengue report rate is about 20%, which is close to the number of official announcements, and the percentage of infected vectors increases exponentially yearly. We suggest that the executive authorities should seriously consider the accumulated effect among infected populations. This established epidemic prediction model of dengue fever can be used to simulate and evaluate the best time to prevent and control dengue fever. CONCLUSIONS: Given our developed model, government epidemic prevention teams can apply this platform before they physically carry out the prevention work. The optimal suggestions from these models can be promptly accommodated when real-time data have been continuously corrected from clinics and related agents.

Classifying chest CT images as COVID-19 positive/negative using a convolutional neural network ensemble model and uniform experimental design method.

BACKGROUND: To classify chest computed tomography (CT) images as positive or negative for coronavirus disease 2019 (COVID-19) quickly and accurately, researchers attempted to develop effective models by using medical images. RESULTS: A convolutional neural network (CNN) ensemble model was developed for classifying chest CT images as positive or negative for COVID-19. To classify chest CT images acquired from COVID-19 patients, the proposed COVID19-CNN ensemble model combines the use of multiple trained CNN models with a majority voting strategy. The CNN models were trained to classify chest CT images by transfer learning from well-known pre-trained CNN models and by applying their algorithm hyperparameters as appropriate. The combination of algorithm hyperparameters for a pre-trained CNN model was determined by uniform experimental design. The chest CT images (405 from COVID-19 patients and 397 from healthy patients) used for training and performance testing of the COVID19-CNN ensemble model were obtained from an earlier study by Hu in 2020. Experiments showed that, the COVID19-CNN ensemble model achieved 96.7% accuracy in classifying CT images as COVID-19 positive or negative, which was superior to the accuracies obtained by the individual trained CNN models. Other performance measures (i.e., precision, recall, specificity, and F1-score) obtained bythe COVID19-CNN ensemble model were higher than those obtained by individual trained CNN models. CONCLUSIONS: The COVID19-CNN ensemble model had superior accuracy and excellent capability in classifying chest CT images as COVID-19 positive or negative.

Robust optimization of convolutional neural networks with a uniform experiment design method: a case of phonocardiogram testing in patients with heart diseases.

BACKGROUND: Heart sound measurement is crucial for analyzing and diagnosing patients with heart diseases. This study employed phonocardiogram signals as the input signal for heart disease analysis due to the accessibility of the respective method. This study referenced preprocessing techniques proposed by other researchers for the conversion of phonocardiogram signals into characteristic images composed using frequency subband. Image recognition was then conducted through the use of convolutional neural networks (CNNs), in order to classify the predicted of phonocardiogram signals as normal or abnormal. However, CNN requires the tuning of multiple hyperparameters, which entails an optimization problem for the hyperparameters in the model. To maximize CNN robustness, the uniform experiment design method and a science-based methodical experiment design were used to optimize CNN hyperparameters in this study. RESULTS: An artificial intelligence prediction model was constructed using CNN, and the uniform experiment design method was proposed to acquire hyperparameters for optimal CNN robustness. The results indicate Filters ([Formula: see text]), Stride ([Formula: see text]), Activation functions ([Formula: see text]), and Dropout ([Formula: see text]) to be significant factors considerably influencing the ability of CNN to distinguish among heart sound states. Finally, the confirmation experiment was conducted, and the hyperparameter combination for optimal model robustness was Filters ([Formula: see text]) = 32, Kernel Size ([Formula: see text] = 3 × 3, Stride ([Formula: see text]) = (1,1), Padding ([Formula: see text] as same, Optimizer ([Formula: see text] as the stochastic gradient descent, Activation functions ([Formula: see text]) as relu, and Dropout ([Formula: see text]) = 0.544. With this combination of parameters, the model had an average prediction accuracy rate of 0.787 and standard deviation of 0. CONCLUSION: In this study, phonocardiogram signals were used for the early prediction of heart diseases. The science-based and methodical uniform experiment design was used for the optimization of CNN hyperparameters to construct a CNN with optimal robustness. The results revealed that the constructed model exhibited robustness and an acceptable accuracy rate. Other literature has failed to address hyperparameter optimization problems in CNN; a method is subsequently proposed for robust CNN optimization, thereby solving this problem.

Artificial intelligence classification model for macular degeneration images: a robust optimization framework for residual neural networks.

BACKGROUND: The prevalence of chronic disease is growing in aging societies, and artificial-intelligence-assisted interpretation of macular degeneration images is a topic that merits research. This study proposes a residual neural network (ResNet) model constructed using uniform design. The ResNet model is an artificial intelligence model that classifies macular degeneration images and can assist medical professionals in related tests and classification tasks, enhance confidence in making diagnoses, and reassure patients. However, the various hyperparameters in a ResNet lead to the problem of hyperparameter optimization in the model. This study employed uniform design-a systematic, scientific experimental design-to optimize the hyperparameters of the ResNet and establish a ResNet with optimal robustness. RESULTS: An open dataset of macular degeneration images ( https://data.mendeley.com/datasets/rscbjbr9sj/3 ) was divided into training, validation, and test datasets. According to accuracy, false negative rate, and signal-to-noise ratio, this study used uniform design to determine the optimal combination of ResNet hyperparameters. The ResNet model was tested and the results compared with results obtained in a previous study using the same dataset. The ResNet model achieved higher optimal accuracy (0.9907), higher mean accuracy (0.9848), and a lower mean false negative rate (0.015) than did the model previously reported. The optimal ResNet hyperparameter combination identified using the uniform design method exhibited excellent performance. CONCLUSION: The high stability of the ResNet model established using uniform design is attributable to the study's strict focus on achieving both high accuracy and low standard deviation. This study optimized the hyperparameters of the ResNet model by using uniform design because the design features uniform distribution of experimental points and facilitates effective determination of the representative parameter combination, reducing the time required for parameter design and fulfilling the requirements of a systematic parameter design process.

Classification of age-related macular degeneration using convolutional-neural-network-based transfer learning.

BACKGROUND: To diagnose key pathologies of age-related macular degeneration (AMD) and diabetic macular edema (DME) quickly and accurately, researchers attempted to develop effective artificial intelligence methods by using medical images. RESULTS: A convolutional neural network (CNN) with transfer learning capability is proposed and appropriate hyperparameters are selected for classifying optical coherence tomography (OCT) images of AMD and DME. To perform transfer learning, a pre-trained CNN model is used as the starting point for a new CNN model for solving related problems. The hyperparameters (parameters that have set values before the learning process begins) in this study were algorithm hyperparameters that affect learning speed and quality. During training, different CNN-based models require different algorithm hyperparameters (e.g., optimizer, learning rate, and mini-batch size). Experiments showed that, after transfer learning, the CNN models (8-layer Alexnet, 22-layer Googlenet, 16-layer VGG, 19-layer VGG, 18-layer Resnet, 50-layer Resnet, and a 101-layer Resnet) successfully classified OCT images of AMD and DME. CONCLUSIONS: The experimental results further showed that, after transfer learning, the VGG19, Resnet101, and Resnet50 models with appropriate algorithm hyperparameters had excellent capability and performance in classifying OCT images of AMD and DME.

Fuzzy logic and Gagné learning hierarchy for assessing mathematics skills.

This study developed a fuzzy logic and Gagné learning hierarchy (FL-GLH) for assessing mathematics skills and identifying learning barrier points. Fuzzy logic was used to model the human reasoning process in linguistic terms. Specifically, fuzzy logic was used to build relationships between skill level concepts as inputs and learning achievement as an output. Gagné learning hierarchy was used to develop a learning hierarchy diagram, which included learning paths and test questions for assessing mathematics skills. First, the Gagné learning hierarchy was used to generate learning path diagrams and test questions. In the second step, skill level concepts were grouped, and their membership functions were established to fuzzify the input parameters and to build membership functions of learning achievement as an output. Third, the inference engine generated fuzzy values by applying fuzzy rules based on fuzzy reasoning. Finally, the defuzzifier converted fuzzy values to crisp output values for learning achievement. Practical applications of the FL-GLH confirmed its effectiveness for evaluating student learning achievement, for finding student learning barrier points, and for providing teachers with guidelines for improving learning efficiency in students.

Non-destructive acoustic screening of pineapple ripeness by unsupervised machine learning and Wavelet Kernel methods.

In a pineapple exporting factory, manual lines are usually built to screen fruits of non-ripen hitting sounds from millions of undecided fruits for long-haul transportation. However, human workers cannot concentratedly listen and make consistent judgments over long hours. Pineapple screening becomes arbitrary after approximately an hour. We developed a non-destructive screening device aside from the conveyor sorter to classify pineapples automatically. The device makes intelligent judgments by tapping a sound source to the skin of pineapples and analyzing the penetrated sounds by wavelet kernel decomposition and unsupervised machine learning (ML). The sound tapping relies on the well-touch of the skin. We also design several acoustic couplers to adapt the vibrator to the skin and pick high-quality penetrated sounds. A Taguchi experiment design was used to determine the most suitable coupler. We found that our unsupervised ML method achieves 98.56% accuracy and 0.93 F1-score by using a specially designed thorn-board for assisting tapping sound to fruit skin.

Predictive model for 5-year mortality after breast cancer surgery in Taiwan residents.

BACKGROUND: Few studies of breast cancer surgery outcomes have used longitudinal data for more than 2 years. This study aimed to validate the use of the artificial neural network (ANN) model to predict the 5-year mortality of breast cancer patients after surgery and compare predictive accuracy between the ANN model, multiple logistic regression (MLR) model, and Cox regression model. METHODS: This study compared the MLR, Cox, and ANN models based on clinical data of 3632 breast cancer patients who underwent surgery between 1996 and 2010. An estimation dataset was used to train the model, and a validation dataset was used to evaluate model performance. The sensitivity analysis was also used to assess the relative significance of input variables in the prediction model. RESULTS: The ANN model significantly outperformed the MLR and Cox models in predicting 5-year mortality, with higher overall performance indices. The results indicated that the 5-year postoperative mortality of breast cancer patients was significantly associated with age, Charlson comorbidity index (CCI), chemotherapy, radiotherapy, hormone therapy, and breast cancer surgery volumes of hospital and surgeon (all P < 0.05). Breast cancer surgery volume of surgeon was the most influential (sensitive) variable affecting 5-year mortality, followed by breast cancer surgery volume of hospital, age, and CCI. CONCLUSIONS: Compared with the conventional MLR and Cox models, the ANN model was more accurate in predicting 5-year mortality of breast cancer patients who underwent surgery. The mortality predictors identified in this study can also be used to educate candidates for breast cancer surgery with respect to the course of recovery and health outcomes.

Predicting quality of life after breast cancer surgery using ANN-based models: performance comparison with MR.

PURPOSE: The goal was to develop models for predicting long-term quality of life (QOL) after breast cancer surgery. METHODS: Data were obtained from 203 breast cancer patients who completed the SF-36 health survey before and 2 years after surgery. Two of the models used to predict QOL after surgery were artificial neural networks (ANNs), which included one multilayer perceptron (MLP) network and one radial basis function (RBF) network. The third model was a multiple regression (MR) model. The criteria for evaluating the accuracy of the system models were mean square error (MSE) and mean absolute percentage error (MAPE). RESULTS: Compared to the MR model, the ANN-based models generally had smaller MSE values and smaller MAPE values in the test data set. One exception was the second year MSE for the test value. Most MAPE values for the ANN models ranged from 10 to 20 %. The one exception was the 6-month physical component summary score (PCS), which ranged from 23.19 to 26.86 %. Comparison of criteria for evaluating system performance showed that the ANN-based systems outperformed the MR system in terms of prediction accuracy. In both the MLP and RBF networks, surgical procedure type was the most sensitive parameter affecting PCS, and preoperative functional status was the most sensitive parameter affecting mental component summary score. CONCLUSION: The three systems can be combined to obtain a conservative prediction, and a combined approach is a potential supplemental tool for predicting long-term QOL after surgical treatment for breast cancer. RELEVANCE: Patients should also be advised that their postoperative QOL might depend not only on the success of their operations but also on their preoperative functional status.

Predicting two-year quality of life after breast cancer surgery using artificial neural network and linear regression models.

The purpose of this study was to validate the use of artificial neural network (ANN) models for predicting quality of life (QOL) after breast cancer surgery and to compare the predictive capability of ANNs with that of linear regression (LR) models. The European Organization for Research and Treatment of Cancer Quality of Life Questionnaire and its supplementary breast cancer measure were completed by 402 breast cancer patients at baseline and at 2 years postoperatively. The accuracy of the system models were evaluated in terms of mean square error (MSE) and mean absolute percentage error (MAPE). A global sensitivity analysis was also performed to assess the relative significance of input parameters in the system model and to rank the variables in order of importance. Compared to the LR model, the ANN model generally had smaller MSE and MAPE values in both the training and testing datasets. Most ANN models had MAPE values ranging from 4.70 to 19.96 %, and most had high prediction accuracy. The ANN model also outperformed the LR model in terms of prediction accuracy. According to global sensitivity analysis, pre-operative functional status was the best predictor of QOL after surgery. Compared with the conventional LR model, the ANN model in the study was more accurate for predicting patient-reported QOL and had higher overall performance indices. Further refinements are expected to obtain sufficient performance improvements for its routine use in clinical practice as an adjunctive decision-making tool.

Comparisons of prediction models of quality of life after laparoscopic cholecystectomy: a longitudinal prospective study.

BACKGROUND: Few studies of laparoscopic cholecystectomy (LC) outcome have used longitudinal data for more than two years. Moreover, no studies have considered group differences in factors other than outcome such as age and nonsurgical treatment. Additionally, almost all published articles agree that the essential issue of the internal validity (reproducibility) of the artificial neural network (ANN), support vector machine (SVM), Gaussian process regression (GPR) and multiple linear regression (MLR) models has not been adequately addressed. This study proposed to validate the use of these models for predicting quality of life (QOL) after LC and to compare the predictive capability of ANNs with that of SVM, GPR and MLR. METHODOLOGY/PRINCIPAL FINDINGS: A total of 400 LC patients completed the SF-36 and the Gastrointestinal Quality of Life Index at baseline and at 2 years postoperatively. The criteria for evaluating the accuracy of the system models were mean square error (MSE) and mean absolute percentage error (MAPE). A global sensitivity analysis was also performed to assess the relative significance of input parameters in the system model and to rank the variables in order of importance. Compared to SVM, GPR and MLR models, the ANN model generally had smaller MSE and MAPE values in the training data set and test data set. Most ANN models had MAPE values ranging from 4.20% to 8.60%, and most had high prediction accuracy. The global sensitivity analysis also showed that preoperative functional status was the best parameter for predicting QOL after LC. CONCLUSIONS/SIGNIFICANCE: Compared with SVM, GPR and MLR models, the ANN model in this study was more accurate in predicting patient-reported QOL and had higher overall performance indices. Further studies of this model may consider the effect of a more detailed database that includes complications and clinical examination findings as well as more detailed outcome data.

Post-cholecystectomy quality of life: a prospective multicenter cohort study of its associations with preoperative functional status and patient demographics.

PURPOSE: This study analyzed patient demographics and preoperative functional status for associations with post-cholecystectomy quality of life (QOL). METHODS: This prospective study analyzed 159 cholecystectomy patients at two tertiary academic hospitals. All patients completed the SF-36 and the gastrointestinal quality of life index (GIQLI) at baseline and at 3 and 6 months postoperatively. The 95% confidence intervals for differences in responsiveness estimates were derived by bootstrap estimation. Scores derived by these instruments were interpreted by generalized estimating equation (GEE) before and after cholecystectomy. RESULTS: The examined population significantly (p < 0.05) improved in both SF-36 subscales and GIQLI subscales. After adjusting for time effects (time, and time(2)) and baseline predictors, GEE approaches revealed the following explanatory variables for QOL: time, time(2), age, gender, preoperative GIQLI score, body mass index, and number of comorbidities. CONCLUSION: The data revealed dramatically improved post-cholecystectomy QOL. However, QOL change was simultaneously associated with preoperative functional status and demographic characteristics.

Tuning the structure and parameters of a neural network by using hybrid Taguchi-genetic algorithm.

In this paper, a hybrid Taguchi-genetic algorithm (HTGA) is applied to solve the problem of tuning both network structure and parameters of a feedforward neural network. The HTGA approach is a method of combining the traditional genetic algorithm (TGA), which has a powerful global exploration capability, with the Taguchi method, which can exploit the optimum offspring. The Taguchi method is inserted between crossover and mutation operations of a TGA. Then, the systematic reasoning ability of the Taguchi method is incorporated in the crossover operations to select the better genes to achieve crossover, and consequently enhance the genetic algorithms. Therefore, the HTGA approach can be more robust, statistically sound, and quickly convergent. First, the authors evaluate the performance of the presented HTGA approach by studying some global numerical optimization problems. Then, the presented HTGA approach is effectively applied to solve three examples on forecasting the sunspot numbers, tuning the associative memory, and solving the XOR problem. The numbers of hidden nodes and the links of the feedforward neural network are chosen by increasing them from small numbers until the learning performance is good enough. As a result, a partially connected feedforward neural network can be obtained after tuning. This implies that the cost of implementation of the neural network can be reduced. In these studied problems of tuning both network structure and parameters of a feedforward neural network, there are many parameters and numerous local optima so that these studied problems are challenging enough for evaluating the performances of any proposed GA-based approaches. The computational experiments show that the presented HTGA approach can obtain better results than the existing method reported recently in the literature.