Proposed Deep Learning Model Research Articles

Cardiovascular Disease Diagnosis from DXA Scan and Retinal Images Using Deep Learning.

Cardiovascular diseases (CVD) are the leading cause of death worldwide. People affected by CVDs may go undiagnosed until the occurrence of a serious heart failure event such as stroke, heart attack, and myocardial infraction. In Qatar, there is a lack of studies focusing on CVD diagnosis based on non-invasive methods such as retinal image or dual-energy X-ray absorptiometry (DXA). In this study, we aimed at diagnosing CVD using a novel approach integrating information from retinal images and DXA data. We considered an adult Qatari cohort of 500 participants from Qatar Biobank (QBB) with an equal number of participants from the CVD and the control groups. We designed a case-control study with a novel multi-modal (combining data from multiple modalities—DXA and retinal images)—to propose a deep learning (DL)-based technique to distinguish the CVD group from the control group. Uni-modal models based on retinal images and DXA data achieved 75.6% and 77.4% accuracy, respectively. The multi-modal model showed an improved accuracy of 78.3% in classifying CVD group and the control group. We used gradient class activation map (GradCAM) to highlight the areas of interest in the retinal images that influenced the decisions of the proposed DL model most. It was observed that the model focused mostly on the centre of the retinal images where signs of CVD such as hemorrhages were present. This indicates that our model can identify and make use of certain prognosis markers for hypertension and ischemic heart disease. From DXA data, we found higher values for bone mineral density, fat content, muscle mass and bone area across majority of the body parts in CVD group compared to the control group indicating better bone health in the Qatari CVD cohort. This seminal method based on DXA scans and retinal images demonstrate major potentials for the early detection of CVD in a fast and relatively non-invasive manner.

Poly-linear regression with augmented long short term memory neural network: Predicting time series data

Until recently, the supply chain sector, which had been getting by with scattered spreadsheets, phone conversations, and even paper-based records until recently, was exposed for its antiquated methods during the epidemic. As a result, businesses have undergone a decade of digital change in only a few months, with the epidemic driving them to replace antiquated procedures with AI, machine learning, and data science technology. The supply chain sector has reached a point in its AI adoption where the technology is solid and powerful enough to improve decision-making significantly. For example, predictive analytics (e.g., time series forecasting) is already a proven benefit. Such technology is smart enough to recognise irregularities and learn how a stock market will move in real-time. With the advancement of digital innovation, researchers have focused on deep learning (DL) models to get a more accurate and unbiased estimation. Consequently, this paper presents a novel DL approach for time series prediction using a combination of poly-linear regression with Long Short-Term Memory (LSTM) and data augmentation. It is consequently named Poly-linear Regression with Augmented Long Short Term Memory Neural Network (PLR-ALSTM-NN). The proposed DL model can be exploited to predict the future financial markets more accurately than existing state-of-the-art neural networks and machine learning tools. In order to make the model a more generic one, it is first validated on four financial market time-series datasets and then also implemented on a supply chain time-series dataset to predict sales data. LSTM, with its feedback connections, can process an entire series of data as well as single data points and statistical regression establishes the strength and character of the relationship between some dependent and independent variables. After doing experimental validations and based on the long-term and short-term predicted data, the suitability of the proposed PLR-ALSTM-NN is well-grounded against a few recent and advanced state-of-the-art machine learning, and DL approaches.

New Explainable Deep CNN Design for Classifying Breast Tumor Response Over Neoadjuvant Chemotherapy.

To reduce breast tumor size before surgery, Neoadjuvant Chemotherapy (NAC) is applied systematically to patients with local breast cancer. However, with the existing clinical protocols, it is not yet possible to have an early prediction of the effect of chemotherapy on a breast tumor. Predicting the response to chemotherapy could reduce toxicity and delay effective treatment. Computational analysis of Dynamic Contrast-Enhanced Magnetic Resonance Images (DCE-MRI) through Deep Convolution Neural Network (CNN) has proved a significant performance in classifying responders and no responder's patients. This study intends to present a new explainable Deep Learning (DL) model predicting the breast cancer response to chemotherapy based on multiple MRI inputs. In this study, a cohort of 42 breast cancer patients who underwent chemotherapy was used to train and validate the proposed DL model. This dataset was provided by the Jules Bordet institute of radiology in Brussels, Belgium. 14 external subjects were used to validate the DL model to classify responding or non-responding patients on temporal DCE-MRI volumes. The model performance was assessed by the Area Under the receiver operating characteristic Curve (AUC), accuracy, and features map visualization according to pathological complete response (Ground truth). The developed deep learning architecture was able to predict the responding breast tumors to chemotherapy treatment in the external validation dataset with an AUC of 0.93 using parallel learning MRI images acquired at different moments. The visual results showed that the most important extracted features from non-responding tumors are in the peripheral and external tumor regions. The model proposed in this study is more efficient compared to those proposed in the literature. Even with a limited training dataset size, the developed multi-input CNN model using DCE-MR images acquired before and following the first chemotherapy was able to predict responding and non-responding tumors with higher accuracy. Thanks to the visualization of the extracted characteristics by the DL model on the responding and non-responding tumors, the latter could be used henceforth in clinical analysis after its evaluation based on more extra data.

LEMON: A Lightweight Facial Emotion Recognition System for Assistive Robotics Based on Dilated Residual Convolutional Neural Networks

The development of a Social Intelligence System based on artificial intelligence is one of the cutting edge technologies in Assistive Robotics. Such systems need to create an empathic interaction with the users; therefore, it os required to include an Emotion Recognition (ER) framework which has to run, in near real-time, together with several other intelligent services. Most of the low-cost commercial robots, however, although more accessible by users and healthcare facilities, have to balance costs and effectiveness, resulting in under-performing hardware in terms of memory and processing unit. This aspect makes the design of the systems challenging, requiring a trade-off between the accuracy and the complexity of the adopted models. This paper proposes a compact and robust service for Assistive Robotics, called Lightweight EMotion recognitiON (LEMON), which uses image processing, Computer Vision and Deep Learning (DL) algorithms to recognize facial expressions. Specifically, the proposed DL model is based on Residual Convolutional Neural Networks with the combination of Dilated and Standard Convolution Layers. The first remarkable result is the few numbers (i.e., 1.6 Million) of parameters characterizing our model. In addition, Dilated Convolutions expand receptive fields exponentially with preserving resolution, less computation and memory cost to recognize the distinction among facial expressions by capturing the displacement of the pixels. Finally, to reduce the dying ReLU problem and improve the stability of the model, we apply an Exponential Linear Unit (ELU) activation function in the initial layers of the model. We have performed training and evaluation (via one- and five-fold cross validation) of the model with five datasets available in the community and one mixed dataset created by taking samples from all of them. With respect to the other approaches, our model achieves comparable results with a significant reduction in terms of the number of parameters.

Automatic recognition of whole-spine sagittal alignment and curvature analysis through a deep learning technique

PurposeArtificial intelligence based on deep learning (DL) approaches enables the automatic recognition of anatomic landmarks and subsequent estimation of various spinopelvic parameters. The locations of inflection points (IPs) and apices (APs) in whole-spine lateral radiographs could be mathematically determined by a fully automatic spinal sagittal curvature analysis system.MethodsWe developed a DL model for automatic spinal curvature analysis of whole-spine lateral plain radiographs by using 1800 annotated images of various spinal disease etiologies. The DL model comprised a landmark localizer to detect 25 vertebral landmarks and a numerical algorithm for the generation of an individualized spinal sagittal curvature. The characteristics of the spinal curvature, including the IPs, APs, and curvature angle, could thus be analyzed using mathematical definitions. The localization error of each landmark was calculated from the predictions of 300 test images to evaluate the performance of the landmark localizer. The interrater reliability among a senior orthopedic surgeon, a radiologist, and the DL model was assessed using the intraclass correlation coefficient (ICC).ResultsThe accuracy of the landmark localizer was within an acceptable range (median error: 1.7–4.1 mm), and the interrater reliabilities between the proposed DL model and each expert were good to excellent (all ICCs > 0.85) for the measurement of spinal curvature characteristics.ConclusionThe interrater reliability between the proposed DL model and human experts was good to excellent in predicting the locations of IPs, APs, and curvature angles. Future applications should be explored to validate this system and improve its clinical efficiency.

3D k-space reflectance fluorescence tomography via deep learning.

We report on the potential to perform image reconstruction in 3D k-space reflectance fluorescence tomography (FT) using deep learning (DL). Herein, we adopt a modified AUTOMAP architecture and develop a training methodology that leverages an open-source Monte-Carlo-based simulator to generate a large dataset. Using an enhanced EMNIST (EEMNIST) dataset as an embedded contrast function allows us to train the network efficiently. The optical strategy utilizes k-space illumination in a reflectance configuration to probe tissue in the mesoscopic regime with high sensitivity and resolution. The proposed DL model training and validation is performed with both in silico data and a phantom experiment. Overall, our results indicate that the approach can correctly reconstruct both single and multiple fluorescent embedding(s) in a 3D volume. Furthermore, the presented technique is shown to outperform the traditional approaches [least-squares (LSQ) and total-variation minimization (TVAL)], especially at higher depths. We, therefore, expect the proposed computational technique to have future implications in preclinical studies.

Automatic contouring of normal tissues with deep learning for preclinical radiation studies

Objective. Delineation of relevant normal tissues is a bottleneck in image-guided precision radiotherapy workflows for small animals. A deep learning (DL) model for automatic contouring using standardized 3D micro cone-beam CT (μCBCT) volumes as input is proposed, to provide a fully automatic, generalizable method for normal tissue contouring in preclinical studies. Approach. A 3D U-net was trained to contour organs in the head (whole brain, left/right brain hemisphere, left/right eye) and thorax (complete lungs, left/right lung, heart, spinal cord, thorax bone) regions. As an important preprocessing step, Hounsfield units (HUs) were converted to mass density (MD) values, to remove the energy dependency of the μCBCT scanner and improve generalizability of the DL model. Model performance was evaluated quantitatively by Dice similarity coefficient (DSC), mean surface distance (MSD), 95th percentile Hausdorff distance (HD95p), and center of mass displacement (ΔCoM). For qualitative assessment, DL-generated contours (for 40 and 80 kV images) were scored (0: unacceptable, manual re-contouring needed - 5: no adjustments needed). An uncertainty analysis using Monte Carlo dropout uncertainty was performed for delineation of the heart. Main results. The proposed DL model and accompanying preprocessing method provide high quality contours, with in general median DSC > 0.85, MSD < 0.25 mm, HD95p < 1 mm and ΔCoM < 0.5 mm. The qualitative assessment showed very few contours needed manual adaptations (40 kV: 20/155 contours, 80 kV: 3/155 contours). The uncertainty of the DL model is small (within 2%). Significance. A DL-based model dedicated to preclinical studies has been developed for multi-organ segmentation in two body sites. For the first time, a method independent of image acquisition parameters has been quantitatively evaluated, resulting in sub-millimeter performance, while qualitative assessment demonstrated the high quality of the DL-generated contours. The uncertainty analysis additionally showed that inherent model variability is low.

Deep Learning in Prostate Cancer Diagnosis Using Multiparametric Magnetic Resonance Imaging With Whole-Mount Histopathology Referenced Delineations.

Background: Multiparametric magnetic resonance imaging (mpMRI) plays an important role in the diagnosis of prostate cancer (PCa) in the current clinical setting. However, the performance of mpMRI usually varies based on the experience of the radiologists at different levels; thus, the demand for MRI interpretation warrants further analysis. In this study, we developed a deep learning (DL) model to improve PCa diagnostic ability using mpMRI and whole-mount histopathology data.Methods: A total of 739 patients, including 466 with PCa and 273 without PCa, were enrolled from January 2017 to December 2019. The mpMRI (T2 weighted imaging, diffusion weighted imaging, and apparent diffusion coefficient sequences) data were randomly divided into training (n = 659) and validation datasets (n = 80). According to the whole-mount histopathology, a DL model, including independent segmentation and classification networks, was developed to extract the gland and PCa area for PCa diagnosis. The area under the curve (AUC) were used to evaluate the performance of the prostate classification networks. The proposed DL model was subsequently used in clinical practice (independent test dataset; n = 200), and the PCa detective/diagnostic performance between the DL model and different level radiologists was evaluated based on the sensitivity, specificity, precision, and accuracy.Results: The AUC of the prostate classification network was 0.871 in the validation dataset, and it reached 0.797 using the DL model in the test dataset. Furthermore, the sensitivity, specificity, precision, and accuracy of the DL model for diagnosing PCa in the test dataset were 0.710, 0.690, 0.696, and 0.700, respectively. For the junior radiologist without and with DL model assistance, these values were 0.590, 0.700, 0.663, and 0.645 versus 0.790, 0.720, 0.738, and 0.755, respectively. For the senior radiologist, the values were 0.690, 0.770, 0.750, and 0.730 vs. 0.810, 0.840, 0.835, and 0.825, respectively. The diagnosis made with DL model assistance for radiologists were significantly higher than those without assistance (P < 0.05).Conclusion: The diagnostic performance of DL model is higher than that of junior radiologists and can improve PCa diagnostic accuracy in both junior and senior radiologists.

Deep Learning Models to Predict Sea Surface Temperature in Tohoku Region

The prediction of sea surface temperature (SST) is a challenging task, especially for regions with high SST variability. Such predictions are either achieved by physics-based models, which often yield poor predictions and are computationally intensive, or by using data-driven methods, which are skillful and computationally less intensive. However, recent machine learning studies exploring SST prediction have not included the important meteorological parameters governing SST variability. Therefore, in this study, we propose various of deep learning (DL) models trained using past meteorological features to predict day-ahead SST. The proposed models include a deep multilayer perceptron (deep MLP), long short-term memory network (LSTM) and spatial 2-dimensional convolutional neural network (spatial 2D CNN). We explore the potential of the proposed DL models for day-ahead SST prediction across different locations in the Tohoku region (Japan’s east coast), including in situ validation. Evaluation of these DL models’ prediction skills suggests that the spatial 2D CNN’s are highly skillful at coastal locations, whereas at offshore locations, equal prediction skills were noted from the deep MLP and LSTM. We further attempted to improve the spatial 2D CNN by including past SST features, and such improvisation showed very low errors ranging from 0.35°C to 0.75°C and high correlation skill from 0.64 to 0.96. These improved skills were also compared with persistent model (PM) skills using RMSE and Correlation (RC) phase diagram, where we found that improved skills are consistently better than PM skills. In addition, we extracted features from the spatial 2D CNN to understand the reason underlying such improved skills, and we noted that the proposed DL model successfully captured the major meteorological and oceanic features governing SST variability. This led us to conclude that the proposed DL models are capable of producing highly reliable SST predictions, and may be equally applicable to other study regions.

Enhanced Deep Learning Model for Personalized Cancer Treatment

Personalized medicine provides more safe and effective treatment by individualizing the choice of drug and dose based on an individual’s genetic profile. Cancer patients’ response to anti-cancer treatments (drugs) is one of the foremost challenges in personalized medicine that releases the target treatment. Both size and availability of drug sensitivity data have motivated researchers to develop Artificial Intelligence (AI), based models, for predicting drug response to advance cancer treatment. The concerned AI models include Machine Learning (ML) and the recently advanced Deep Learning (DL) based models. This paper introduces both; a data federation method and a DL-based model for predicting drug response. The fundamental goal is to generalize the predictor so it will be able to predict the response to different drugs accurately. As the data has a considerable effect on any AI model, the data federation is utilized to consolidate the data. The proposed consolidation process is carried out to make each cell line contains gene expression data, its mutation profile, and drug response data. ML models such as Support Vector Machine (SVM) and Linear Regression (LR) are used along with Principal Component Analysis (PCA) for feature reduction, and the AI models have been tested with and without data federation. The results show that data federation enhanced the accuracy and decreased the Mean Square Error (MSE) by almost 25%. The proposed DL model uses dimension reduction encoders. The encoder is a DL model that uses unsupervised learning. It is trained by integrating an encoder with a decoder to achieve equality between the input and output. The proposed model has achieved the best accuracy compared to some other recent models in terms of the Pearson correlation coefficient (PCC) as a performance measure. In addition, the results show that the Enhanced Deep Drug Response prediction (Enhanced Deep-DR) model has achieved the best PCC value even with the largest number of genes and drugs, which proves the high capacity and efficiency of the proposed model. Convolutional Neural Network (CNN) based-model is also implemented; it achieves higher accuracy in predicting the drug response than in some other DL-based models but less than the Enhanced Deep learning. The Enhanced Deep-DR achieves better accuracy within the range of 5% to 12% than other DL-models.

Hybrid Deep Learning Model for Fault Detection and Classification of Grid-Connected Photovoltaic System

Effective fault detection and classification play essential roles in reducing the hazards such as electric shocks and fire in photovoltaic (PV) systems. However, the issues of interest in fault detection and classification for PV systems remain an open-ended challenge due to manual and time-consuming processes that require the relevant domain knowledge and experience of fault diagnoses. This paper proposes a hybrid deep-learning (DL) model-based combined architectures as the novel DL approaches to achieve the real-time automatic fault detection and classification of a PV system. This research employed the wavelet packet transform (WPT) as a data preprocessing technique to handle the PV voltage signal collected and feeding them as the inputs for combined DL architectures that consist of the equilibrium optimizer algorithm (EOA) and long short-term memory (LSTM-SAE) approaches. The combined DL architectures are able to extract the fault features automatically from the preprocessed data without requiring any previous knowledge, therefore can override the traditional shortages of manual feature extraction and manual selection of optimal features from the extracted fault features. These desirable features are anticipated to speed up the fault detection and classification capability of the proposed DL model with higher accuracy. In order to determine the performance of the proposed fault model, we carried out a comprehensive evaluation study on a 250-kW grid-connected PV system. In this paper, symmetrical and asymmetrical faults have been studied involving all the phases and ground faults such as single phase to ground, phases to phase, phase to phase to ground, and three-phase to ground. The simulation results validate the efficacy of the proposed model in terms of computation time, accuracy of fault detection, and noise robustness. Comprehensive comparisons between the simulation results and previous studies demonstrate the multidisciplinary applications of the present study.

Use of the deep learning approach to measure alveolar bone level.

The goal was to use a deep convolutional neural network to measure the radiographic alveolar bone level to aid periodontal diagnosis. A deep learning (DL) model was developed by integrating three segmentation networks (bone area, tooth, cemento-enamel junction) and image analysis to measure the radiographic bone level and assign radiographic bone loss (RBL) stages. The percentage of RBL was calculated to determine the stage of RBL for each tooth. A provisional periodontal diagnosis was assigned using the 2018 periodontitis classification. RBL percentage, staging, and presumptive diagnosis were compared with the measurements and diagnoses made by the independent examiners. The average Dice Similarity Coefficient (DSC) for segmentation was over 0.91. There was no significant difference in the RBL percentage measurements determined by DL and examiners ( ). The area under the receiver operating characteristics curve of RBL stage assignment for stages I, II, and III was 0.89, 0.90, and 0.90, respectively. The accuracy of the case diagnosis was 0.85. The proposed DL model provides reliable RBL measurements and image-based periodontal diagnosis using periapical radiographic images. However, this model has to be further optimized and validated by a larger number of images to facilitate its application.

DeepCOVIDNet: Deep Convolutional Neural Network for COVID-19 Detection from Chest Radiographic Images.

The novel Coronavirus Disease 2019 (COVID-19) is a global pandemic that has infected millions of people causing millions of deaths around the world. Reverse Transcription Polymerase Chain Reaction (RT-PCR) is the standard screening method for COVID-19 detection but it requires specific molecular-biology training. Moreover, the general workflow is difficult e.g. sample collection, processing time, and analysis expertise, etc. Chest radiographic image analysis can be a good alternative screening method that is faster, more efficient, and requires minimal clinical or molecular biology trained laboratory personnel. Early studies have shown that abnormalities on the chest radiographic images are likely to be the consequence of COVID-19 infection. In this study, we propose DeepCOVIDNet, a deep learning based COVID-19 detection model. Our proposed deep-learning model is a multiclass classifier that can distinguish COVID-19, viral pneumonia, bacterial pneumonia, and healthy chest X-ray images. Our proposed model classifies radiographic images into four distinct classes and achieves the accuracy of 89.47% along with a high degree of precision, recall and F1 score. On a different dataset setting (COVID-19, bacterial pneumonia, viral pneumonia) our model achieves the maximum accuracy of 98.25%. We demonstrate generalizability of our proposed method using 5-fold cross validation for COVID-19 vs pneumonia and COVID-19 vs healthy classification that also manifests promising results.

A deep-learning model for identifying fresh vertebral compression fractures on digital radiography.

To develop a deep-learning (DL) model for identifying fresh VCFs from digital radiography (DR), with magnetic resonance imaging (MRI) as the reference standard. Patients with lumbar VCFs were retrospectively enrolled from January 2011 to May 2020. All patients underwent DR and MRI scanning. VCFs were categorized as fresh or old according to MRI results, and the VCF grade and type were assessed. The raw DR data were sent to InferScholar Center for annotation. A DL-based prediction model was built, and its diagnostic performance was evaluated. The DeLong test was applied to assess differences in ROC curves between different models. A total of 1877 VCFs in 1099 patients were included in our study and randomly divided into development (n = 824 patients) and test (n = 275 patients) datasets. The ensemble model identified fresh and old VCFs, reaching an AUC of 0.80 (95% confidence interval [CI], 0.77-0.83), an accuracy of 74% (95% CI, 72-77%), a sensitivity of 80% (95% CI, 77-83%), and a specificity of 68% (95% CI, 63-72%). Lateral (AUC, 0.83) views exhibited better performance than anteroposterior views (AUC, 0.77), and the best performance among respective subgroupings was obtained for grade 3 (AUC, 0.89) and crush-type (AUC, 0.87) subgroups. The proposed DL model achieved adequate performance in identifying fresh VCFs from DR. • The ensemble deep-learning model identified fresh VCFs from DR, reaching an AUC of 0.80, an accuracy of 74%, a sensitivity of 80%, and a specificity of 68% with the reference standard of MRI. • The lateral views (AUC, 0.83) exhibited better performance than anteroposterior views (AUC, 0.77). • The grade 3 (AUC, 0.89) and crush-type (AUC, 0.87) subgroups showed the best performance among their respective subgroupings.

Two-Stream Convolutional Long- and Short-Term Memory Model Using Perceptual Loss for Sequence-to-Sequence Arctic Sea Ice Prediction

Arctic sea ice plays a significant role in climate systems, and its prediction is important for coping with global warming. Artificial intelligence (AI) has gained recent attention in various disciplines with the increasing use of big data. In recent years, the use of AI-based sea ice prediction, along with conventional prediction models, has drawn attention. This study proposes a new deep learning (DL)-based Arctic sea ice prediction model with a new perceptual loss function to improve both statistical and visual accuracy. The proposed DL model learned spatiotemporal characteristics of Arctic sea ice for sequence-to-sequence predictions. The convolutional neural network-based perceptual loss function successfully captured unique sea ice patterns, and the widely used loss functions could not use various feature maps. Furthermore, the input variables that are essential to accurately predict Arctic sea ice using various combinations of input variables were identified. The proposed approaches produced statistical outcomes with better accuracy and qualitative agreements with the observed data.

Combining Deep Learning and Graph-Theoretic Brain Features to Detect Posttraumatic Stress Disorder at the Individual Level.

Previous studies using resting-state functional MRI (rs-fMRI) have revealed alterations in graphical metrics in groups of individuals with posttraumatic stress disorder (PTSD). To explore the ability of graph measures to diagnose PTSD and capture its essential features in individual patients, we used a deep learning (DL) model based on a graph-theoretic approach to discriminate PTSD from trauma-exposed non-PTSD at the individual level and to identify its most discriminant features. Our study was performed on rs-fMRI data from 91 individuals with PTSD and 126 trauma-exposed non-PTSD patients. To evaluate our DL method, we used the traditional support vector machine (SVM) classifier as a reference. Our results showed that the proposed DL model allowed single-subject discrimination of PTSD and trauma-exposed non-PTSD individuals with higher accuracy (average: 80%) than the traditional SVM (average: 57.7%). The top 10 DL features were identified within the default mode, central executive, and salience networks; the first two of these networks were also identified in the SVM classification. We also found that nodal efficiency in the left fusiform gyrus was negatively correlated with the Clinician Administered PTSD Scale score. These findings demonstrate that DL based on graphical features is a promising method for assisting in the diagnosis of PTSD.

Towards a dynamic soil survey: Identifying and delineating soil horizons in-situ using deep learning

Soil horizons are the manifestation of pedogenesis and contain the basic morphologic indicators of soil formation. Accurate and quantitative tools for delineating soil horizons in-situ can assist soil scientists towards rapid and dynamic soil survey information. The objective of this study was to develop a deep-learning-based, soil-profile-imaging method for identifying and delineating soil master horizons to assist in digital soil descriptions. A total of 160 soil profile images from four soil orders (Alfisols, Entisols, Inceptisols, and Mollisols) were collected from north China in the Inner Mongolia and Liaoning regions. The 160 profile images were amplified to 2400 individual images for model building using data-augmentation procedures. The augmented profile image dataset was divided into training (70%), validation (15%), and test (15%) datasets. The training and validation datasets were imported into a nested, U-net network for model building. The proposed deep-learning (DL) model classified soil profiles into A, B, and C horizons. The mean pixel accuracy of the DL model was 0.86 with the training dataset, 0.82 with the validation dataset, and 0.83 for the test dataset. Results showed that the DL model was judged to be accurate enough for identifying and delineating soil master horizons from profile images in practice. Based on the proposed DL model, a smartphone application was subsequently developed to digitalize the soil profile and assist field evaluation of soil profile horizonation. The smartphone application, for the Android operating system (version 5.0 and greater), featured a response time of < 5 s. This study demonstrated that the proposed DL model and smartphone application could be a simple, fast, and digital tool for quickly identifying and delineating in-situ soil horizons. These tools allow for rapid data collection, which can be used for future artificial intelligence development and application in soil science towards digital soil profile description and dynamic soil survey.

Computational Intelligence-Based Model for Mortality Rate Prediction in COVID-19 Patients.

The COVID-19 outbreak is currently one of the biggest challenges facing countries around the world. Millions of people have lost their lives due to COVID-19. Therefore, the accurate early detection and identification of severe COVID-19 cases can reduce the mortality rate and the likelihood of further complications. Machine Learning (ML) and Deep Learning (DL) models have been shown to be effective in the detection and diagnosis of several diseases, including COVID-19. This study used ML algorithms, such as Decision Tree (DT), Logistic Regression (LR), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and K-Nearest Neighbor (KNN) and DL model (containing six layers with ReLU and output layer with sigmoid activation), to predict the mortality rate in COVID-19 cases. Models were trained using confirmed COVID-19 patients from 146 countries. Comparative analysis was performed among ML and DL models using a reduced feature set. The best results were achieved using the proposed DL model, with an accuracy of 0.97. Experimental results reveal the significance of the proposed model over the baseline study in the literature with the reduced feature set.

Deep Learning on Enhanced CT Images Can Predict the Muscular Invasiveness of Bladder Cancer.

BackgroundClinical treatment decision making of bladder cancer (BCa) relies on the absence or presence of muscle invasion and tumor staging. Deep learning (DL) is a novel technique in image analysis, but its potential for evaluating the muscular invasiveness of bladder cancer remains unclear. The purpose of this study was to develop and validate a DL model based on computed tomography (CT) images for prediction of muscle-invasive status of BCa.MethodsA total of 441 BCa patients were retrospectively enrolled from two centers and were divided into development (n=183), tuning (n=110), internal validation (n=73) and external validation (n=75) cohorts. The model was built based on nephrographic phase images of preoperative CT urography. Receiver operating characteristic (ROC) curves were performed and the area under the ROC curve (AUC) for discrimination between muscle-invasive BCa and non-muscle-invasive BCa was calculated. The performance of the model was evaluated and compared with that of the subjective assessment by two radiologists.ResultsThe DL model exhibited relatively good performance in all cohorts [AUC: 0.861 in the internal validation cohort, 0.791 in the external validation cohort] and outperformed the two radiologists. The model yielded a sensitivity of 0.733, a specificity of 0.810 in the internal validation cohort and a sensitivity of 0.710 and a specificity of 0.773 in the external validation cohort.ConclusionThe proposed DL model based on CT images exhibited relatively good prediction ability of muscle-invasive status of BCa preoperatively, which may improve individual treatment of BCa.

Advances in Fault Diagnostics and Post‐Fault Operation of Electrical Drives

Advances in Fault Diagnostics and Post‐Fault Operation of Electrical Drives