Utilization of Bioinorganic Nanodrugs and Nanomaterials for the Control of Infectious Diseases Using Deep Learning.

As one of the main causes of morbidity and mortality, viral infections have a major impact on the well-being and economics of every nation in the globe. The ability to predictably diagnose viral infections improves the provision of good healthcare as well as the control and prevention of these conditions. Nanomaterials have gained widespread usage in the medical industry recently due to the rapid advancement of nanotechnology and their exceptional chemical and physical qualities, such as their small size and synthesized surface properties. The utilization of nanoparticles for illness detection, surveillance, control, preventive, and therapy, such as the treatment of bacterial infections, is referred to as nanomedicine. Nanomedicine is a comprehensive discipline that is founded on the usage of nanotechnology for clinical objectives. Nanoparticles, which have a nanoscale dimension and exhibit highly controllable optical and physical characteristics as well as the ability to bind to a large variety of chemicals, are among the most popular nanomaterials in nanomedicine. A deep learning framework of autoencoder for categorization study on viral infections is built based on actual hospital patient history of viral infections from August 2015 to August 2020. The information comprises of 10,950 cases, comprising outpatients and inpatients, encompassing the infectious diseases. Of such 10,950 instances, training set made up 70% or 7665 instances, and testing data made up 30% or 3285 instances. The data processing was done using the presented recurrent neural network-artificial bee colony (RNN-ABC) method. Sparse data densifying processes are done through the autoencoder to enhance the system learning outcome. The suggested autoencoder system was also evaluated to other widely used models, including support vector machine, logistic regression, random forest, and Naïve Bayes. In comparison to other approaches, the study's findings demonstrate how well the suggested autoencoder model can predict viral diseases. The methods used for this research can aid in removing reported lags in current monitoring systems, hence reducing society's expenses.

Automatic detection and recognition of nasopharynx gross tumour volume (GTVnx) by deep learning for nasopharyngeal cancer radiotherapy through magnetic resonance imaging.

BACKGROUND: In this study, we propose the deep learning model-based framework to automatically delineate nasopharynx gross tumor volume (GTVnx) in MRI images. METHODS: MRI images from 200 patients were collected for training-validation and testing set. Three popular deep learning models (FCN, U-Net, Deeplabv3) are proposed to automatically delineate GTVnx. FCN was the first and simplest fully convolutional model. U-Net was proposed specifically for medical image segmentation. In Deeplabv3, the proposed Atrous Spatial Pyramid Pooling (ASPP) block, and fully connected Conditional Random Field(CRF) may improve the detection of the small scattered distributed tumor parts due to its different scale of spatial pyramid layers. The three models are compared under same fair criteria, except the learning rate set for the U-Net. Two widely applied evaluation standards, mIoU and mPA, are employed for the detection result evaluation. RESULTS: The extensive experiments show that the results of FCN and Deeplabv3 are promising as the benchmark of automatic nasopharyngeal cancer detection. Deeplabv3 performs best with the detection of mIoU 0.8529 ± 0.0017 and mPA 0.9103 ± 0.0039. FCN performs slightly worse in term of detection accuracy. However, both consume similar GPU memory and training time. U-Net performs obviously worst in both detection accuracy and memory consumption. Thus U-Net is not suggested for automatic GTVnx delineation. CONCLUSIONS: The proposed framework for automatic target delineation of GTVnx in nasopharynx bring us the desirable and promising results, which could not only be labor-saving, but also make the contour evaluation more objective. This preliminary results provide us with clear directions for further study.

A trial deep learning-based model for four-class histologic classification of colonic tumor from narrow band imaging.

Narrow band imaging (NBI) has been extensively utilized as a diagnostic tool for colorectal neoplastic lesions. This study aimed to develop a trial deep learning (DL) based four-class classification model for low-grade dysplasia (LGD); high-grade dysplasia or mucosal carcinoma (HGD); superficially invasive submucosal carcinoma (SMs) and deeply invasive submucosal carcinomas (SMd) and evaluate its potential as a diagnostic tool. We collected a total of 1,390 NBI images as the dataset, including 53 LGD, 120 HGD, 20 SMs and 17 SMd. A total of 598,801 patches were trimmed from the lesion and background. A patch-based classification model was built by employing a residual convolutional neural network (CNN) and validated by three-fold cross-validation. The patch-based validation accuracy was 0.876, 0.957, 0.907 and 0.929 in LGD, HGD, SMs and SMd, respectively. The image-level classification algorithm was derived from the patch-based mapping across the entire image domain, attaining accuracies of 0.983, 0.990, 0.964, and 0.992 in LGD, HGD, SMs, and SMd, respectively. Our CNN-based model demonstrated high performance for categorizing the histological grade of dysplasia as well as the depth of invasion in routine colonoscopy, suggesting a potential diagnostic tool with minimal human inputs.

Deep learning-based multi-model approach on electron microscopy image of renal biopsy classification.

BACKGROUND: Electron microscopy is important in the diagnosis of renal disease. For immune-mediated renal disease diagnosis, whether the electron-dense granule is present in the electron microscope image is of vital importance. Deep learning methods perform well at feature extraction and assessment of histologic images. However, few studies on deep learning methods for electron microscopy images of renal biopsy have been published. This study aimed to develop a deep learning-based multi-model to automatically detect whether the electron-dense granule is present in the TEM image of renal biopsy, and then help diagnose immune-mediated renal disease. METHODS: Three deep learning models are trained to classify whether the electron-dense granule is present using 910 electron microscopy images of renal biopsies. We proposed two novel methods to improve the model accuracy. One model uses the pre-trained ResNet convolutional layers for feature extraction with transfer learning which was firstly improved with skip architecture, then uses Support Vector Machine as the classifier. We developed a multi-model to combine the traditional ResNet model with the improved one to further improve the accuracy. RESULTS: Deep learning-based multi-model has the highest model accuracy, and the average accuracy is about 88%. The improved ReseNet + SVM model performance is much better than the traditional ResNet model. The average accuracy of the improved ResNet + SVM model is 83%, while the traditional ResNet model accuracy is only 58%. CONCLUSIONS: This study presents the first models for electron microscopy image classification of Renal Biopsy. Identifying whether the electron-dense granule is present plays an important role in the diagnosis of immune complex nephropathy. This study made it possible for Artificial Intelligence models assist to analyze complex electron microscopy images for disease diagnosis.

Quality control system for mammographic breast positioning using deep learning.

This study proposes a deep convolutional neural network (DCNN) classification for the quality control and validation of breast positioning criteria in mammography. A total of 1631 mediolateral oblique mammographic views were collected from an open database. We designed two main steps for mammographic verification: automated detection of the positioning part and classification of three scales that determine the positioning quality using DCNNs. After acquiring labeled mammograms with three scales visually evaluated based on guidelines, the first step was automatically detecting the region of interest of the subject part by image processing. The next step was classifying mammographic positioning accuracy into three scales using four representative DCNNs. The experimental results showed that the DCNN model achieved the best positioning classification accuracy of 0.7836 using VGG16 in the inframammary fold and a classification accuracy of 0.7278 using Xception in the nipple profile. Furthermore, using the softmax function, the breast positioning criteria could be evaluated quantitatively by presenting the predicted value, which is the probability of determining positioning accuracy. The proposed method can be quantitatively evaluated without the need for an individual qualitative evaluation and has the potential to improve the quality control and validation of breast positioning criteria in mammography.

Deep learning radiomics model based on breast ultrasound video to predict HER2 expression status.

Purpose: The detection of human epidermal growth factor receptor 2 (HER2) expression status is essential to determining the chemotherapy regimen for breast cancer patients and to improving their prognosis. We developed a deep learning radiomics (DLR) model combining time-frequency domain features of ultrasound (US) video of breast lesions with clinical parameters for predicting HER2 expression status. Patients and Methods: Data for this research was obtained from 807 breast cancer patients who visited from February 2019 to July 2020. Ultimately, 445 patients were included in the study. Pre-operative breast ultrasound examination videos were collected and split into a training set and a test set. Building a training set of DLR models combining time-frequency domain features and clinical features of ultrasound video of breast lesions based on the training set data to predict HER2 expression status. Test the performance of the model using test set data. The final models integrated with different classifiers are compared, and the best performing model is finally selected. Results: The best diagnostic performance in predicting HER2 expression status is provided by an Extreme Gradient Boosting (XGBoost)-based time-frequency domain feature classifier combined with a logistic regression (LR)-based clinical parameter classifier of clinical parameters combined DLR, particularly with a high specificity of 0.917. The area under the receiver operating characteristic curve (AUC) for the test cohort was 0.810. Conclusion: Our study provides a non-invasive imaging biomarker to predict HER2 expression status in breast cancer patients.

Construction of deep learning-based disease detection model in plants.

Accurately detecting disease occurrences of crops in early stage is essential for quality and yield of crops through the decision of an appropriate treatments. However, detection of disease needs specialized knowledge and long-term experiences in plant pathology. Thus, an automated system for disease detecting in crops will play an important role in agriculture by constructing early detection system of disease. To develop this system, construction of a stepwise disease detection model using images of diseased-healthy plant pairs and a CNN algorithm consisting of five pre-trained models. The disease detection model consists of three step classification models, crop classification, disease detection, and disease classification. The 'unknown' is added into categories to generalize the model for wide application. In the validation test, the disease detection model classified crops and disease types with high accuracy (97.09%). The low accuracy of non-model crops was improved by adding these crops to the training dataset implicating expendability of the model. Our model has the potential to apply to smart farming of Solanaceae crops and will be widely used by adding more various crops as training dataset.

Deep learning applied to EEG source-data reveals both ventral and dorsal visual stream involvement in holistic processing of social stimuli.

Perception of social stimuli (faces and bodies) relies on "holistic" (i.e., global) mechanisms, as supported by picture-plane inversion: perceiving inverted faces/bodies is harder than perceiving their upright counterpart. Albeit neuroimaging evidence suggested involvement of face-specific brain areas in holistic processing, their spatiotemporal dynamics and selectivity for social stimuli is still debated. Here, we investigate the spatiotemporal dynamics of holistic processing for faces, bodies and houses (adopted as control non-social category), by applying deep learning to high-density electroencephalographic signals (EEG) at source-level. Convolutional neural networks were trained to classify cortical EEG responses to stimulus orientation (upright/inverted), separately for each stimulus type (faces, bodies, houses), resulting to perform well above chance for faces and bodies, and close to chance for houses. By explaining network decision, the 150-200 ms time interval and few visual ventral-stream regions were identified as mostly relevant for discriminating face and body orientation (lateral occipital cortex, and for face only, precuneus cortex, fusiform and lingual gyri), together with two additional dorsal-stream areas (superior and inferior parietal cortices). Overall, the proposed approach is sensitive in detecting cortical activity underlying perceptual phenomena, and by maximally exploiting discriminant information contained in data, may reveal spatiotemporal features previously undisclosed, stimulating novel investigations.

Generalising uncertainty improves accuracy and safety of deep learning analytics applied to oncology.

Uncertainty estimation is crucial for understanding the reliability of deep learning (DL) predictions, and critical for deploying DL in the clinic. Differences between training and production datasets can lead to incorrect predictions with underestimated uncertainty. To investigate this pitfall, we benchmarked one pointwise and three approximate Bayesian DL models for predicting cancer of unknown primary, using three RNA-seq datasets with 10,968 samples across 57 cancer types. Our results highlight that simple and scalable Bayesian DL significantly improves the generalisation of uncertainty estimation. Moreover, we designed a prototypical metric-the area between development and production curve (ADP), which evaluates the accuracy loss when deploying models from development to production. Using ADP, we demonstrate that Bayesian DL improves accuracy under data distributional shifts when utilising 'uncertainty thresholding'. In summary, Bayesian DL is a promising approach for generalising uncertainty, improving performance, transparency, and safety of DL models for deployment in the real world.

Explainable semi-supervised deep learning shows that dementia is associated with small, avocado-shaped clocks with irregularly placed hands.

The clock drawing test is a simple and inexpensive method to screen for cognitive frailties, including dementia. In this study, we used the relevance factor variational autoencoder (RF-VAE), a deep generative neural network, to represent digitized clock drawings from multiple institutions using an optimal number of disentangled latent factors. The model identified unique constructional features of clock drawings in a completely unsupervised manner. These factors were examined by domain experts to be novel and not extensively examined in prior research. The features were informative, as they distinguished dementia from non-dementia patients with an area under receiver operating characteristic (AUC) of 0.86 singly, and 0.96 when combined with participants' demographics. The correlation network of the features depicted the "typical dementia clock" as having a small size, a non-circular or "avocado-like" shape, and incorrectly placed hands. In summary, we report a RF-VAE network whose latent space encoded novel constructional features of clocks that classify dementia from non-dementia patients with high performance.

An efficient deep learning based predictor for identifying miRNA-triggered phasiRNA loci in plant.

Phasic small interfering RNAs are plant secondary small interference RNAs that typically generated by the convergence of miRNAs and polyadenylated mRNAs. A growing number of studies have shown that miRNA-initiated phasiRNA plays crucial roles in regulating plant growth and stress responses. Experimental verification of miRNA-initiated phasiRNA loci may take considerable time, energy and labor. Therefore, computational methods capable of processing high throughput data have been proposed one by one. In this work, we proposed a predictor (DIGITAL) for identifying miRNA-initiated phasiRNAs in plant, which combined a multi-scale residual network with a bi-directional long-short term memory network. The negative dataset was constructed based on positive data, through replacing 60% of nucleotides randomly in each positive sample. Our predictor achieved the accuracy of 98.48% and 94.02% respectively on two independent test datasets with different sequence length. These independent testing results indicate the effectiveness of our model. Furthermore, DIGITAL is of robustness and generalization ability, and thus can be easily extended and applied for miRNA target recognition of other species. We provide the source code of DIGITAL, which is freely available at https://github.com/yuanyuanbu/DIGITAL.

Temporal fact extraction of fruit cultivation technologies based on deep learning.

There are great differences in fruit planting techniques due to different regional environments. Farmers can't use the same standard in growing fruit. Most of the information about fruit planting comes from the Internet, which is characterized by complexity and heterogeneous multi-source. How to deal with such information to form the convenient facts becomes an urgent problem. Information extraction could automatically extract fruit cultivation facts from unstructured text. Temporal information is especially crucial for fruit cultivation. Extracting temporal facts from the corpus of cultivation technologies for fruit is also vital to several downstream applications in fruit cultivation. However, the framework of ordinary triplets focuses on handling static facts and ignores the temporal information. Therefore, we propose Basic Fact Extraction and Multi-layer CRFs (BFE-MCRFs), an end-to-end neural network model for the joint extraction of temporal facts. BFE-MCRFs describes temporal knowledge using an improved schema that adds the time dimension. Firstly, the basic facts are extracted from the primary model. Then, multiple temporal relations are added between basic facts and time expressions. Finally, the multi-layer Conditional Random Field are used to detect the objects corresponding to the basic facts under the predefined temporal relationships. Experiments conducted on public and self-constructed datasets show that BFE-MCRFs achieves the best current performance and outperforms the baseline models by a significant margin.

Facial expression recognition using lightweight deep learning modeling.

Facial expression is a type of communication and is useful in many areas of computer vision, including intelligent visual surveillance, human-robot interaction and human behavior analysis. A deep learning approach is presented to classify happy, sad, angry, fearful, contemptuous, surprised and disgusted expressions. Accurate detection and classification of human facial expression is a critical task in image processing due to the inconsistencies amid the complexity, including change in illumination, occlusion, noise and the over-fitting problem. A stacked sparse auto-encoder for facial expression recognition (SSAE-FER) is used for unsupervised pre-training and supervised fine-tuning. SSAE-FER automatically extracts features from input images, and the softmax classifier is used to classify the expressions. Our method achieved an accuracy of 92.50% on the JAFFE dataset and 99.30% on the CK+ dataset. SSAE-FER performs well compared to the other comparative methods in the same domain.

Driver identification and fatigue detection algorithm based on deep learning.

In order to avoid traffic accidents caused by driver fatigue, smoking and talking on the phone, it is necessary to design an effective fatigue detection algorithm. Firstly, this paper studies the detection algorithms of driver fatigue at home and abroad, and analyzes the advantages and disadvantages of the existing algorithms. Secondly, a face recognition module is introduced to crop and align the acquired faces and input them into the Facenet network model for feature extraction, thus completing the identification of drivers. Thirdly, a new driver fatigue detection algorithm based on deep learning is designed based on Single Shot MultiBox Detector (SSD) algorithm, and the additional layer network structure of SSD is redesigned by using the idea of reverse residual. By adding the detection of drivers' smoking and making phone calls, adjusting the size and number of prior boxes of SSD algorithm, improving FPN network and SE network, the identification and verification of drivers can be realized. The experimental results showed that the number of parameters decreased from 96.62 MB to 18.24 MB. The average accuracy rate increased from 89.88% to 95.69%. The projected number of frames per second increased from 51.69 to 71.86. When the confidence threshold was set to 0.5, the recall rate of closed eyes increased from 46.69% to 65.87%, that of yawning increased from 59.72% to 82.72%, and that of smoking increased from 65.87% to 83.09%. These results show that the improved network model has better feature extraction ability for small targets.

An annotated human blastocyst dataset to benchmark deep learning architectures for in vitro fertilization.

Medical Assisted Reproduction proved its efficacy to treat the vast majority forms of infertility. One of the key procedures in this treatment is the selection and transfer of the embryo with the highest developmental potential. To assess this potential, clinical embryologists routinely work with static images (morphological assessment) or short video sequences (time-lapse annotation). Recently, Artificial Intelligence models were utilized to support the embryo selection procedure. Even though they have proven their great potential in different in vitro fertilization settings, there is still considerable room for improvement. To support the advancement of algorithms in this research field, we built a dataset consisting of static blastocyst images and additional annotations. As such, Gardner criteria annotations, depicting a morphological blastocyst rating scheme, and collected clinical parameters are provided. The presented dataset is intended to be used to train deep learning models on static morphological images to predict Gardner's criteria and clinical outcomes such as live birth. A benchmark of human expert's performance in annotating Gardner criteria is provided.

Feasibility of Bone Mineral Density and Bone Microarchitecture Assessment Using Deep Learning With a Convolutional Neural Network.

OBJECTIVES: We evaluated the feasibility of using deep learning with a convolutional neural network for predicting bone mineral density (BMD) and bone microarchitecture from conventional computed tomography (CT) images acquired by multivendor scanners. METHODS: We enrolled 402 patients who underwent noncontrast CT examinations, including L1-L4 vertebrae, and dual-energy x-ray absorptiometry (DXA) examination. Among these, 280 patients (3360 sagittal vertebral images), 70 patients (280 sagittal vertebral images), and 52 patients (208 sagittal vertebral images) were assigned to the training data set for deep learning model development, the validation, and the test data set, respectively. Bone mineral density and the trabecular bone score (TBS), an index of bone microarchitecture, were assessed by DXA. BMDDL and TBSDL were predicted by deep learning with a convolutional neural network (ResNet50). Pearson correlation tests assessed the correlation between BMDDL and BMD, and TBSDL and TBS. The diagnostic performance of BMDDL for osteopenia/osteoporosis and that of TBSDL for bone microarchitecture impairment were evaluated using receiver operating characteristic curve analysis. RESULTS: BMDDL and BMD correlated strongly (r = 0.81, P < 0.01), whereas TBSDL and TBS correlated moderately (r = 0.54, P < 0.01). The sensitivity and specificity of BMDDL for identifying osteopenia or osteoporosis were 93% and 90%, and 100% and 94%, respectively. The sensitivity and specificity of TBSDL for identifying patients with bone microarchitecture impairment were 73% for all values. CONCLUSIONS: The BMDDL and TBSDL derived from conventional CT images could identify patients who should undergo DXA, which could be a gatekeeper tool for detecting latent osteoporosis/osteopenia or bone microarchitecture impairment.

DELMEP: a deep learning algorithm for automated annotation of motor evoked potential latencies.

The analysis of motor evoked potentials (MEPs) generated by transcranial magnetic stimulation (TMS) is crucial in research and clinical medical practice. MEPs are characterized by their latency and the treatment of a single patient may require the characterization of thousands of MEPs. Given the difficulty of developing reliable and accurate algorithms, currently the assessment of MEPs is performed with visual inspection and manual annotation by a medical expert; making it a time-consuming, inaccurate, and error-prone process. In this study, we developed DELMEP, a deep learning-based algorithm to automate the estimation of MEP latency. Our algorithm resulted in a mean absolute error of about 0.5 ms and an accuracy that was practically independent of the MEP amplitude. The low computational cost of the DELMEP algorithm allows employing it in on-the-fly characterization of MEPs for brain-state-dependent and closed-loop brain stimulation protocols. Moreover, its learning ability makes it a particularly promising option for artificial-intelligence-based personalized clinical applications.

Deep learning to detect macular atrophy in wet age-related macular degeneration using optical coherence tomography.

Here, we have developed a deep learning method to fully automatically detect and quantify six main clinically relevant atrophic features associated with macular atrophy (MA) using optical coherence tomography (OCT) analysis of patients with wet age-related macular degeneration (AMD). The development of MA in patients with AMD results in irreversible blindness, and there is currently no effective method of early diagnosis of this condition, despite the recent development of unique treatments. Using OCT dataset of a total of 2211 B-scans from 45 volumetric scans of 8 patients, a convolutional neural network using one-against-all strategy was trained to present all six atrophic features followed by a validation to evaluate the performance of the models. The model predictive performance has achieved a mean dice similarity coefficient score of 0.706 ± 0.039, a mean Precision score of 0.834 ± 0.048, and a mean Sensitivity score of 0.615 ± 0.051. These results show the unique potential of using artificially intelligence-aided methods for early detection and identification of the progression of MA in wet AMD, which can further support and assist clinical decisions.

Deep learning for Mpox: Advances, challenges, and opportunities.

Although deep-learning algorithms in dermatology have shown promise in diagnosing skin cancers, less is known about potential applications for the diagnosis of infectious diseases. In a recent publication in Nature Medicine, Thieme et al. develop a deep-learning algorithm to classify skin lesions from Mpox virus (MPXV) infections.1.

Prediction of transport proteins from sequence information with the deep learning approach.

Transport proteins (TPs) are vital to the growth and life of all living things, especially in fields of microbial pathogenesis and drug resistance of tumor cells. Accurately identifying potential TPs remains an important challenge for the advancement of functional genomics. This study aimed to develop a tool for predicting TPs using the deep learning approach. Here, we proposed DeepTP, a convolutional neural network model that uses parallel subnetworks to extract features from protein sequences and uses fully connected layers for TP classification. To train and evaluate the performance of the developed model, datasets were collected from the UniProtKB/Swiss-Prot database. The test results revealed that the proposed model could successfully identify TPs with the AUCROC, accuracy, F-value, and Matthews correlation coefficient of 0.9719, 0.9513, 0.8982, and 0.8679, respectively. By further comparison, DeepTP achieved better performance than other commonly used methods. Analysis of the gradients of prediction score concerning input suggested that DeepTP makes predictions by recognizing the functional domains of TPs. We anticipate that DeepTP will serve as a useful tool for predicting TPs in large-scale genome projects, which will facilitate the discovery of novel TPs.