Enhancing genome-wide populus trait prediction through deep convolutional neural networks.

As a promising model, genome-based plant breeding has greatly promoted the improvement of agronomic traits. Traditional methods typically adopt linear regression models with clear assumptions, neither obtaining the linkage between phenotype and genotype nor providing good ideas for modification. Nonlinear models are well characterized in capturing complex nonadditive effects, filling this gap under traditional methods. Taking populus as the research object, this paper constructs a deep learning method, DCNGP, which can effectively predict the traits including 65 phenotypes. The method was trained on three datasets, and compared with other four classic models-Bayesian ridge regression (BRR), Elastic Net, support vector regression, and dualCNN. The results show that DCNGP has five typical advantages in performance: strong prediction ability on multiple experimental datasets; the incorporation of batch normalization layers and Early-Stopping technology enhancing the generalization capabilities and prediction stability on test data; learning potent features from the data and thus circumventing the tedious steps of manual production; the introduction of a Gaussian Noise layer enhancing predictive capabilities in the case of inherent uncertainties or perturbations; fewer hyperparameters aiding to reduce tuning time across datasets and improve auto-search efficiency. In this way, DCNGP shows powerful predictive ability from genotype to phenotype, which provide an important theoretical reference for building more robust populus breeding programs.

Forensic bone age assessment of hand and wrist joint MRI images in Chinese han male adolescents based on deep convolutional neural networks.

In Chinese criminal law, the ages of 12, 14, 16, and 18 years old play a significant role in the determination of criminal responsibility. In this study, we developed an epiphyseal grading system based on magnetic resonance image (MRI) of the hand and wrist for the Chinese Han population and explored the feasibility of employing deep learning techniques for bone age assessment based on MRI of the hand and wrist. This study selected 282 Chinese Han Chinese males aged 6.0-21.0 years old. In the course of our study, we proposed a novel deep learning model for extracting and enhancing MRI hand and wrist bone features to enhance the prediction of target MRI hand and wrist bone age and achieve precise classification of the target MRI and regression of bone age. The evaluation metric for the classification model including precision, specificity, sensitivity, and accuracy, while the evaluation metrics chosen for the regression model are MAE. The epiphyseal grading was used as a supervised method, which effectively solved the problem of unbalanced sample distribution, and the two experts showed strong consistency in the epiphyseal plate grading process. In the classification results, the accuracy in distinguishing between adults and minors was 91.1%, and the lowest accuracy in the three minor classifications (12, 14, and 16 years of age) was 94.6%, 91.1% and 96.4%, respectively. The MAE of the regression results was 1.24 years. In conclusion, the deep learning model proposed enabled the age assessment of hand and wrist bones based on MRI.

Deep Learning and Histogram-Based Grain Size Analysis of Images.

Grain size analysis is used to study grain size and distribution. It is a critical indicator in sedimentary simulation experiments (SSEs), which aids in understanding hydrodynamic conditions and identifying the features of sedimentary environments. Existing methods for grain size analysis based on images primarily focus on scenarios where grain edges are distinct or grain arrangements are regular. However, these methods are not suitable for images from SSEs. We proposed a deep learning model incorporating histogram layers for the analysis of SSE images with fuzzy grain edges and irregular arrangements. Firstly, ResNet18 was used to extract features from SSE images. These features were then input into the histogram layer to obtain local histogram features, which were concatenated to form comprehensive histogram features for the entire image. Finally, the histogram features were connected to a fully connected layer to estimate the grain size corresponding to the cumulative volume percentage. In addition, an applied workflow was developed. The results demonstrate that the proposed method achieved higher accuracy than the eight other models and was highly consistent with manual results in practice. The proposed method enhances the efficiency and accuracy of grain size analysis for images with irregular grain distribution and improves the quantification and automation of grain size analysis in SSEs. It can also be applied for grain size analysis in fields such as soil and geotechnical engineering.

Refactoring and performance analysis of the main CNN architectures: using false negative rate minimization to solve the clinical images melanoma detection problem.

BACKGROUND: Melanoma is one of the deadliest tumors in the world. Early detection is critical for first-line therapy in this tumor pathology and it remains challenging due to the need for histological analysis to ensure correctness in diagnosis. Therefore, multiple computer-aided diagnosis (CAD) systems working on melanoma images were proposed to mitigate the need of a biopsy. However, although the high global accuracy is declared in literature results, the CAD systems for the health fields must focus on the lowest false negative rate (FNR) possible to qualify as a diagnosis support system. The final goal must be to avoid classification type 2 errors to prevent life-threatening situations. Another goal could be to create an easy-to-use system for both physicians and patients. RESULTS: To achieve the minimization of type 2 error, we performed a wide exploratory analysis of the principal convolutional neural network (CNN) architectures published for the multiple image classification problem; we adapted these networks to the melanoma clinical image binary classification problem (MCIBCP). We collected and analyzed performance data to identify the best CNN architecture, in terms of FNR, usable for solving the MCIBCP problem. Then, to provide a starting point for an easy-to-use CAD system, we used a clinical image dataset (MED-NODE) because clinical images are easier to access: they can be taken by a smartphone or other hand-size devices. Despite the lower resolution than dermoscopic images, the results in the literature would suggest that it would be possible to achieve high classification performance by using clinical images. In this work, we used MED-NODE, which consists of 170 clinical images (70 images of melanoma and 100 images of naevi). We optimized the following CNNs for the MCIBCP problem: Alexnet, DenseNet, GoogleNet Inception V3, GoogleNet, MobileNet, ShuffleNet, SqueezeNet, and VGG16. CONCLUSIONS: The results suggest that a CNN built on the VGG or AlexNet structure can ensure the lowest FNR (0.07) and (0.13), respectively. In both cases, discrete global performance is ensured: 73% (accuracy), 82% (sensitivity) and 59% (specificity) for VGG; 89% (accuracy), 87% (sensitivity) and 90% (specificity) for AlexNet.

Liver PDFF estimation using a multi-decoder water-fat separation neural network with a reduced number of echoes.

OBJECTIVE: To accurately estimate liver PDFF from chemical shift-encoded (CSE) MRI using a deep learning (DL)-based Multi-Decoder Water-Fat separation Network (MDWF-Net), that operates over complex-valued CSE-MR images with only 3 echoes. METHODS: The proposed MDWF-Net and a U-Net model were independently trained using the first 3 echoes of MRI data from 134 subjects, acquired with conventional 6-echoes abdomen protocol at 1.5 T. Resulting models were then evaluated using unseen CSE-MR images obtained from 14 subjects that were acquired with a 3-echoes CSE-MR pulse sequence with a shorter duration compared to the standard protocol. Resulting PDFF maps were qualitatively assessed by two radiologists, and quantitatively assessed at two corresponding liver ROIs, using Bland Altman and regression analysis for mean values, and ANOVA testing for standard deviation (STD) (significance level: .05). A 6-echo graph cut was considered ground truth. RESULTS: Assessment of radiologists demonstrated that, unlike U-Net, MDWF-Net had a similar quality to the ground truth, despite it considered half of the information. Regarding PDFF mean values at ROIs, MDWF-Net showed a better agreement with ground truth (regression slope = 0.94, R2 = 0.97) than U-Net (regression slope = 0.86, R2 = 0.93). Moreover, ANOVA post hoc analysis of STDs showed a statistical difference between graph cuts and U-Net (p < .05), unlike MDWF-Net (p = .53). CONCLUSION: MDWF-Net showed a liver PDFF accuracy comparable to the reference graph cut method, using only 3 echoes and thus allowing a reduction in the acquisition times. CLINICAL RELEVANCE STATEMENT: We have prospectively validated that the use of a multi-decoder convolutional neural network to estimate liver proton density fat fraction allows a significant reduction in MR scan time by reducing the number of echoes required by 50%. KEY POINTS: • Novel water-fat separation neural network allows for liver PDFF estimation by using multi-echo MR images with a reduced number of echoes. • Prospective single-center validation demonstrated that echo reduction leads to a significant shortening of the scan time, compared to standard 6-echo acquisition. • Qualitative and quantitative performance of the proposed method showed no significant differences in PDFF estimation with respect to the reference technique.

An Intelligent Sensor Based Decision Support System for Diagnosing Pulmonary Ailment through Standardized Chest X-ray Scans.

Academics and the health community are paying much attention to developing smart remote patient monitoring, sensors, and healthcare technology. For the analysis of medical scans, various studies integrate sophisticated deep learning strategies. A smart monitoring system is needed as a proactive diagnostic solution that may be employed in an epidemiological scenario such as COVID-19. Consequently, this work offers an intelligent medicare system that is an IoT-empowered, deep learning-based decision support system (DSS) for the automated detection and categorization of infectious diseases (COVID-19 and pneumothorax). The proposed DSS system was evaluated using three independent standard-based chest X-ray scans. The suggested DSS predictor has been used to identify and classify areas on whole X-ray scans with abnormalities thought to be attributable to COVID-19, reaching an identification and classification accuracy rate of 89.58% for normal images and 89.13% for COVID-19 and pneumothorax. With the suggested DSS system, a judgment depending on individual chest X-ray scans may be made in approximately 0.01 s. As a result, the DSS system described in this study can forecast at a pace of 95 frames per second (FPS) for both models, which is near to real-time.

Automatic model for cervical cancer screening based on convolutional neural network: a retrospective, multicohort, multicenter study.

BACKGROUND: The incidence rates of cervical cancer in developing countries have been steeply increasing while the medical resources for prevention, detection, and treatment are still quite limited. Computer-based deep learning methods can achieve high-accuracy fast cancer screening. Such methods can lead to early diagnosis, effective treatment, and hopefully successful prevention of cervical cancer. In this work, we seek to construct a robust deep convolutional neural network (DCNN) model that can assist pathologists in screening cervical cancer. METHODS: ThinPrep cytologic test (TCT) images diagnosed by pathologists from many collaborating hospitals in different regions were collected. The images were divided into a training dataset (13,775 images), validation dataset (2301 images), and test dataset (408,030 images from 290 scanned copies) for training and effect evaluation of a faster region convolutional neural network (Faster R-CNN) system. RESULTS: The sensitivity and specificity of the proposed cervical cancer screening system was 99.4 and 34.8%, respectively, with an area under the curve (AUC) of 0.67. The model could also distinguish between negative and positive cells. The sensitivity values of the atypical squamous cells of undetermined significance (ASCUS), the low-grade squamous intraepithelial lesion (LSIL), and the high-grade squamous intraepithelial lesions (HSIL) were 89.3, 71.5, and 73.9%, respectively. This system could quickly classify the images and generate a test report in about 3 minutes. Hence, the system can reduce the burden on the pathologists and saves them valuable time to analyze more complex cases. CONCLUSIONS: In our study, a CNN-based TCT cervical-cancer screening model was established through a retrospective study of multicenter TCT images. This model shows improved speed and accuracy for cervical cancer screening, and helps overcome the shortage of medical resources required for cervical cancer screening.

Simultaneously Improve Transferability and Discriminability for Adversarial Domain Adaptation.

Although adversarial domain adaptation enhances feature transferability, the feature discriminability will be degraded in the process of adversarial learning. Moreover, most domain adaptation methods only focus on distribution matching in the feature space; however, shifts in the joint distributions of input features and output labels linger in the network, and thus, the transferability is not fully exploited. In this paper, we propose a matrix rank embedding (MRE) method to enhance feature discriminability and transferability simultaneously. MRE restores a low-rank structure for data in the same class and enforces a maximum separation structure for data in different classes. In this manner, the variations within the subspace are reduced, and the separation between the subspaces is increased, resulting in improved discriminability. In addition to statistically aligning the class-conditional distribution in the feature space, MRE forces the data of the same class in different domains to exhibit an approximate low-rank structure, thereby aligning the class-conditional distribution in the label space, resulting in improved transferability. MRE is computationally efficient and can be used as a plug-and-play term for other adversarial domain adaptation networks. Comprehensive experiments demonstrate that MRE can advance state-of-the-art domain adaptation methods.

Deep Learning for Lesion Detection, Progression, and Prediction of Musculoskeletal Disease.

Deep learning is one of the most exciting new areas in medical imaging. This review article provides a summary of the current clinical applications of deep learning for lesion detection, progression, and prediction of musculoskeletal disease on radiographs, computed tomography (CT), magnetic resonance imaging (MRI), and nuclear medicine. Deep-learning methods have shown success for estimating pediatric bone age, detecting fractures, and assessing the severity of osteoarthritis on radiographs. In particular, the high diagnostic performance of deep-learning approaches for estimating pediatric bone age and detecting fractures suggests that the new technology may soon become available for use in clinical practice. Recent studies have also documented the feasibility of using deep-learning methods for identifying a wide variety of pathologic abnormalities on CT and MRI including internal derangement, metastatic disease, infection, fractures, and joint degeneration. However, the detection of musculoskeletal disease on CT and especially MRI is challenging, as it often requires analyzing complex abnormalities on multiple slices of image datasets with different tissue contrasts. Thus, additional technical development is needed to create deep-learning methods for reliable and repeatable interpretation of musculoskeletal CT and MRI examinations. Furthermore, the diagnostic performance of all deep-learning methods for detecting and characterizing musculoskeletal disease must be evaluated in prospective studies using large image datasets acquired at different institutions with different imaging parameters and different imaging hardware before they can be implemented in clinical practice. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY STAGE: 2 J. MAGN. RESON. IMAGING 2020;52:1607-1619.

Breast cancer pathological image classification based on deep learning.

The automatic classification of breast cancer pathological images has important clinical application value. However, to develop the classification algorithm using the artificially extracted image features faces several challenges including the requirement of professional domain knowledge to extract and compute highiquality image features, which are often time-consuming, laborious, and difficult. For overcoming these challenges, this study developed and applied an improved deep convolutional neural network model to perform automatic classification of breast cancer using pathological images. Specifically, in this study, data enhancement and migration learning methods are used to effectively avoid the overfitting problems with deep learning models when they are limited by training image sample size. Experimental results show that a 91% recognition rate or accuracy when applying this improved deep learning model to a publicly available dataset of BreaKHis. Comparing with other previously used models, the new model yields good robustness and generalization.

Cortical signals analysis to recognize intralimb mobility using modified RNN and various EEG quantities.

Electroencephalogram (EEG) signals are critical in interpreting sensorimotor activities for predicting body movements. However, their efficacy in identifying intralimb movements, such as the dorsiflexion and plantar flexion of the foot, remains suboptimal. This study aims to explore whether various EEG signal quantities can effectively recognize intralimb movements to facilitate the development of Brain-Computer Interface (BCI) devices for foot rehabilitation. This research involved twenty-two healthy, right-handed participants. EEG data were collected using 21 electrodes positioned over the motor cortex, while two electromyography (EMG) electrodes recorded the onset of ankle joint movements. The study focused on analyzing slow cortical potential (SCP) and sensorimotor rhythms (SMR) in alpha and beta bands from the EEG. Five key features-fourth-order Autoregressive feature, variance, waveform length, standard deviation, and permutation entropy-were extracted. A modified Recurrent Neural Network (RNN) including Long Short-term Memory (LSTM) and Gated Recurrent Unit (GRU) algorithms was developed for movement recognition. These were compared against conventional machine learning algorithms, including nonlinear Support Vector Machine (SVM) and k Nearest Neighbourhood (kNN) classifiers. The performance of the proposed models was assessed using two data schemes: within-subject and across-subjects. The findings demonstrated that the GRU and LSTM models significantly outperformed traditional machine learning algorithms in recognizing different EEG signal quantities for intralimb movement. The study indicates that deep learning models, particularly GRU and LSTM, hold superior potential over standard machine learning techniques in identifying intralimb movements using EEG signals. Where the accuracies of LSTM for within and across subjects were 98.87 ± 1.80 % and 87.38 ± 0.86 % respectively. Whereas the accuracy of GRU within and across subjects were 99.18 ± 1.28 % and 86.44 ± 0.69 % respectively. This advancement could significantly benefit the development of BCI devices aimed at foot rehabilitation, suggesting a new avenue for enhancing physical therapy outcomes.

Microstrip isoelectric focusing with deep learning for simultaneous screening of diabetes, anemia, and thalassemia.

BACKGROUND: Hemoglobin (Hb) is an important protein in red blood cells and a crucial diagnostic indicator of diseases, e.g., diabetes, thalassemia, and anemia. However, there is a rare report on methods for the simultaneous screening of diabetes, anemia, and thalassemia. Isoelectric focusing (IEF) is a common separative tool for the separation and analysis of Hb. However, the current analysis of IEF images is time-consuming and cannot be used for simultaneous screening. Therefore, an artificial intelligence (AI) of IEF image recognition is desirable for accurate, sensitive, and low-cost screening. RESULTS: Herein, we proposed a novel comprehensive method based on microstrip isoelectric focusing (mIEF) for detecting the relative content of Hb species. There was a good coincidence between the quantitation of Hb via a conventional automated hematology analyzer and the one via mIEF with R2 = 0.9898. Nevertheless, our results showed that the accuracy of disease diagnosis based on the quantification of Hb species alone is as low as 69.33 %, especially for the simultaneous screening of multiple diseases of diabetes, anemia, alpha-thalassemia, and beta-thalassemia. Therefore, we introduced a ResNet1D-based diagnosis model for the improvement of screening accuracy of multiple diseases. The results showed that the proposed model could achieve a high accuracy of more than 90 % and a good sensitivity of more than 96 % for each disease, indicating the overwhelming advantage of the mIEF method combined with deep learning in contrast to the pure mIEF method. SIGNIFICANCE: Overall, the presented method of mIEF with deep learning enabled, for the first time, the absolute quantitative detection of Hb, relative quantitation of Hb species, and simultaneous screening of diabetes, anemia, alpha-thalassemia, and beta-thalassemia. The AI-based diagnosis assistant system combined with mIEF, we believe, will help doctors and specialists perform fast and precise disease screening in the future.

Identification of autism spectrum disorder based on electroencephalography: A systematic review.

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by difficulties in social communication and repetitive and stereotyped behaviors. According to the World Health Organization, about 1 in 100 children worldwide has autism. With the global prevalence of ASD, timely and accurate diagnosis has been essential in enhancing the intervention effectiveness for ASD children. Traditional ASD diagnostic methods rely on clinical observations and behavioral assessment, with the disadvantages of time-consuming and lack of objective biological indicators. Therefore, automated diagnostic methods based on machine learning and deep learning technologies have emerged and become significant since they can achieve more objective, efficient, and accurate ASD diagnosis. Electroencephalography (EEG) is an electrophysiological monitoring method that records changes in brain spontaneous potential activity, which is of great significance for identifying ASD children. By analyzing EEG data, it is possible to detect abnormal synchronous neuronal activity of ASD children. This paper gives a comprehensive review of the EEG-based ASD identification using traditional machine learning methods and deep learning approaches, including their merits and potential pitfalls. Additionally, it highlights the challenges and the opportunities ahead in search of more effective and efficient methods to automatically diagnose autism based on EEG signals, which aims to facilitate automated ASD identification.

Strong Diagnostic Performance of Single Energy 256-row Multidetector Computed Tomography with Deep Learning Image Reconstruction in the Assessment of Myocardial Fibrosis.

Objective Although magnetic resonance imaging (MRI) is the gold standard for evaluating abnormal myocardial fibrosis and extracellular volume (ECV) of the left ventricular myocardium (LVM), a similar evaluation has recently become possible using computed tomography (CT). In this study, we investigated the diagnostic accuracy of a new 256-row multidetector CT with a low tube-voltage single energy scan and deep-learning-image reconstruction (DLIR) in detecting abnormal late enhancement (LE) in LVM. Methods We evaluated the diagnostic performance of CT for detecting LE in LVM and compared the results with those of MRI as a reference. We also measured the ECV of the LVM on CT and compared the results with those on MRI. Materials We analyzed 50 consecutive patients who underwent cardiac CT, including a late-phase scan and MRI, within three months of suspected cardiomyopathy. All patients underwent 256-slice CT (Revolution APEX; GE Healthcare, Waukesha, USA) with a low tube-voltage (70 kV) single energy scan and DLIR for a late-phase scan. Results In patient- and segment-based analyses, the sensitivity, specificity, and accuracy of detection of LE on CT were 94% and 85%, 100% and 95%, and 96% and 93%, respectively. The ECV of LVM per patient on CT and MRI was 33.0±6.2% and 35.9±6.1%, respectively. These findings were extremely strongly correlated, with a correlation coefficient of 0.87 (p<0.0001). The effective radiation dose on late-phase scanning was 2.4±0.9 mSv. Conclusion The diagnostic performance of 256-row multislice CT with a low tube voltage and DLIR for detecting LE and measuring ECV in LVM is credible.

A novel hierarchical framework for plant leaf disease detection using residual vision transformer.

Early detection of plant leaf diseases accurately and promptly is very crucial for safeguarding agricultural crop productivity and ensuring food security. During their life cycle, plant leaves get diseased because of multiple factors like bacteria, fungi, weather conditions, etc. In this work, the authors propose a model that aids in the early detection of leaf diseases using a novel hierarchical residual vision transformer using improved Vision Transformer and ResNet9 models. The proposed model can extract more meaningful and discriminating details by reducing the number of trainable parameters with a smaller number of computations. The proposed method is evaluated on the Local Crop dataset, Plant Village dataset, and Extended Plant Village Dataset with 13, 38, and 51 different leaf disease classes. The proposed model is trained using the best trail parameters of Improved Vision Transformer and classified the features using ResNet 9. Performance evaluation is carried out on a wide aspects over the aforementioned datasets and results revealed that the proposed model outperforms other models such as InceptionV3, MobileNetV2, and ResNet50.

Utilizing deep learning models in an intelligent eye-tracking system for autism spectrum disorder diagnosis.

Timely and unbiased evaluation of Autism Spectrum Disorder (ASD) is essential for providing lasting benefits to affected individuals. However, conventional ASD assessment heavily relies on subjective criteria, lacking objectivity. Recent advancements propose the integration of modern processes, including artificial intelligence-based eye-tracking technology, for early ASD assessment. Nonetheless, the current diagnostic procedures for ASD often involve specialized investigations that are both time-consuming and costly, heavily reliant on the proficiency of specialists and employed techniques. To address the pressing need for prompt, efficient, and precise ASD diagnosis, an exploration of sophisticated intelligent techniques capable of automating disease categorization was presented. This study has utilized a freely accessible dataset comprising 547 eye-tracking systems that can be used to scan pathways obtained from 328 characteristically emerging children and 219 children with autism. To counter overfitting, state-of-the-art image resampling approaches to expand the training dataset were employed. Leveraging deep learning algorithms, specifically MobileNet, VGG19, DenseNet169, and a hybrid of MobileNet-VGG19, automated classifiers, that hold promise for enhancing diagnostic precision and effectiveness, was developed. The MobileNet model demonstrated superior performance compared to existing systems, achieving an impressive accuracy of 100%, while the VGG19 model achieved 92% accuracy. These findings demonstrate the potential of eye-tracking data to aid physicians in efficiently and accurately screening for autism. Moreover, the reported results suggest that deep learning approaches outperform existing event detection algorithms, achieving a similar level of accuracy as manual coding. Users and healthcare professionals can utilize these classifiers to enhance the accuracy rate of ASD diagnosis. The development of these automated classifiers based on deep learning algorithms holds promise for enhancing the diagnostic precision and effectiveness of ASD assessment, addressing the pressing need for prompt, efficient, and precise ASD diagnosis.

Advances in machine learning-based bacteria analysis for forensic identification: identity, ethnicity, and site of occurrence.

When faced with an unidentified body, identifying the victim can be challenging, particularly if physical characteristics are obscured or masked. In recent years, microbiological analysis in forensic science has emerged as a cutting-edge technology. It not only exhibits individual specificity, distinguishing different human biotraces from various sites of occurrence (e.g., gastrointestinal, oral, skin, respiratory, and genitourinary tracts), each hosting distinct bacterial species, but also offers insights into the accident's location and the surrounding environment. The integration of machine learning with microbiomics provides a substantial improvement in classifying bacterial species compares to traditional sequencing techniques. This review discusses the use of machine learning algorithms such as RF, SVM, ANN, DNN, regression, and BN for the detection and identification of various bacteria, including Bacillus anthracis, Acetobacter aceti, Staphylococcus aureus, and Streptococcus, among others. Deep leaning techniques, such as Convolutional Neural Networks (CNN) models and derivatives, are also employed to predict the victim's age, gender, lifestyle, and racial characteristics. It is anticipated that big data analytics and artificial intelligence will play a pivotal role in advancing forensic microbiology in the future.

Assembling High-Quality Lymph Node Clinical Target Volumes for Cervical Cancer Radiotherapy Using a Deep Learning-Based Approach.

AIM: The study aimed to explore an approach for accurately assembling high-quality lymph node clinical target volumes (CTV) on CT images in cervical cancer radiotherapy with the encoder-decoder 3D network. METHODS: 216 cases of CT images treated at our center between 2017 and 2020 were included as a sample, which were divided into two cohorts, including 152 cases and 64 controls, respectively. Para-aortic lymph node, common iliac, external iliac, internal iliac, obturator, presacral, and groin nodal regions were delineated as sub-CTV manually in the cohort including 152 cases. Then, the 152 cases were randomly divided into training (96 cases), validation (36 cases), and test (20 cases) groups for the training process. Each structure was individually trained and optimized through a deep learning model. An additional 64 cases with 6 different clinical conditions were taken as examples to verify the feasibility of CTV generation based on our model. Dice similarity coefficient (DSC) and Hausdorff distance (HD) metrics were both used for quantitative evaluation. RESULTS: Comparing auto-segmentation results to ground truth, the mean DSC value/HD was 0.838/7.7mm, 0.853/4.7mm, 0.855/4.7mm, 0.844/4.7mm, 0.784/5.2mm, 0.826/4.8mm and 0.874/4.8mm for CTV_PAN, CTV_common iliac, CTV_internal iliac, CTV_external iliac, CTV_obturator, CTV_presacral, and CTV_groin, respectively. The similarity comparison results of six different clinical situations were 0.877/4.4mm, 0.879/4.6mm, 0.881/4.2mm, 0.882/4.3mm, 0.872/6.0mm, and 0.875/4.9mm for DSC value/HD, respectively. CONCLUSION: We have developed a deep learning-based approach to segmenting lymph node sub-regions automatically and assembling high-quality CTVs according to clinical needs in cervical cancer radiotherapy. This work can increase the efficiency of the process of cervical cancer detection and treatment.

Deep efficient-nets with transfer learning assisted detection of COVID-19 using chest X-ray radiology imaging.

Corona Virus (COVID-19) could be considered as one of the most devastating pandemics of the twenty-first century. The effective and the rapid screening of infected patients could reduce the mortality and even the contagion rate. Chest X-ray radiology could be designed as one of the effective screening techniques for COVID-19 exploration. In this paper, we propose an advanced approach based on deep learning architecture to automatic and effective screening techniques dedicated to the COVID-19 exploration through chest X-ray (CXR) imaging. Despite the success of state-of-the-art deep learning-based models for COVID-19 detection, they might suffer from several problems such as the huge memory and the computational requirement, the overfitting effect, and the high variance. To alleviate these issues, we investigate the Transfer Learning to the Efficient-Nets models. Next, we fine-tuned the whole network to select the optimal hyperparameters. Furthermore, in the preprocessing step, we consider an intensity-normalization method succeeded by some data augmentation techniques to solve the imbalanced dataset classes' issues. The proposed approach has presented a good performance in detecting patients attained by COVID-19 achieving an accuracy rate of 99.0% and 98% respectively using training and testing datasets. A comparative study over a publicly available dataset with the recently published deep-learning-based architectures could attest the proposed approach's performance.

A Pretrained ELECTRA Model for Kinase-Specific Phosphorylation Site Prediction.

Phosphorylation plays a vital role in signal transduction and cell cycle. Identifying and understanding phosphorylation through machine-learning methods has a long history. However, existing methods only learn representations of a protein sequence segment from a labeled dataset itself, which could result in biased or incomplete features, especially for kinase-specific phosphorylation site prediction in which training data are typically sparse. To learn a comprehensive contextual representation of a protein sequence segment for kinase-specific phosphorylation site prediction, we pretrained our model from over 24 million unlabeled sequence fragments using ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately). The pretrained model was applied to kinase-specific site prediction of kinases CDK, PKA, CK2, MAPK, and PKC. The pretrained ELECTRA model achieves 9.02% improvement over BERT and 11.10% improvement over MusiteDeep in the area under the precision-recall curve on the benchmark data.