Search

As the demand for health grows, the increase in medical waste generation is gradually outstripping the load. In this paper, we propose a deep learning approach for identification and classification of medical waste. Deep learning is currently the most popular technique in image classification, but its need for large amounts of data limits its usage. In this scenario, we propose a deep learning-based classification method, in which ResNeXt is a suitable deep neural network for practical implementation, followed by transfer learning methods to improve classification results. We pay special attention to the problem of medical waste classification, which needs to be solved urgently in the current environmental protection context. We applied the technique to 3480 images and succeeded in correctly identifying 8 kinds of medical waste with an accuracy of 97.2%; the average F1-score of five-fold cross-validation was 97.2%. This study provided a deep learning-based method for automatic detection and classification of 8 kinds of medical waste with high accuracy and average precision. We believe that the power of artificial intelligence could be harnessed in products that would facilitate medical waste classification and could become widely available throughout China. [ABSTRACT FROM AUTHOR]

Point cloud processing is a highly challenging task in 3D vision because it is unstructured and unordered. Recently, deep learning has been proven to be quite successful in point cloud recognition, registration, segmentation, etc. Neighborhood search operation is an important component of point cloud deep learning models, and directly affects the performance of the model. In this paper, we propose a learnable neighborhood search method. This method adaptively chooses an appropriate search method based on the characteristics of each point, thus avoiding the disadvantage of selecting the search method manually. We validate the proposed methods on ModelNet40 dataset and ShapeNetPart dataset, and all the chosen models achieved a performance improvement with a maximum improvement of 1.1%. The proposed method is a plug-and-play technique and can be easily integrated into existing methods. [ABSTRACT FROM AUTHOR]

Many pore-forming proteins originating from pathogenic bacteria are toxic against agricultural pests. They are the key ingredients in several pesticidal products for agricultural use, including transgenic crops. There is an urgent need to identify novel pore-forming proteins to combat development of resistance in pests to existing products, and to develop products that are effective against a broader range of pests. Existing computational methodologies to search for these proteins rely on sequence homology-based approaches. These approaches are based on similarities between protein sequences, and thus are limited in their usefulness for discovering novel proteins. In this paper, we outline a novel deep learning model trained on pore-forming proteins from the public domain. We compare different ways of encoding protein information during training, and contrast it with traditional approaches. We show that our model is capable of identifying known pore formers with no sequence similarity to the proteins used to train the model, and therefore holds promise for identifying novel pore formers. [ABSTRACT FROM AUTHOR]

India is a hotspot of the COVID-19 crisis. During the first wave, several lockdowns (L) and gradual unlock (UL) phases were implemented by the government of India (GOI) to curb the virus spread. These phases witnessed many challenges and various day-to-day developments such as virus spread and resource management. Twitter, a social media platform, was extensively used by citizens to react to these events and related topics that varied temporally and geographically. Analyzing these variations can be a potent tool for informed decision-making. This paper attempts to capture these spatiotemporal variations of citizen reactions by predicting and analyzing the sentiments of geotagged tweets during L and UL phases. Various sentiment analysis based studies on the related subject have been done; however, its integration with location intelligence for decision making remains a research gap. The sentiments were predicted through a proposed hybrid Deep Learning (DL) model which leverages the strengths of BiLSTM and CNN model classes. The model was trained on a freely available Sentiment140 dataset and was tested over manually annotated COVID-19 related tweets from India. The model classified the tweets with high accuracy of around 90%, and analysis of geotagged tweets during L and UL phases reveal significant geographical variations. The findings as a decision support system can aid in analyzing citizen reactions toward the resources and events during an ongoing pandemic. The system can have various applications such as resource planning, crowd management, policy formulation, vaccination, prompt response, etc. [ABSTRACT FROM AUTHOR]

Rock mass condition assessment during tunnel excavation is a critical step for the intelligent control of tunnel boring machine (TBM). To address this and achieve automatic detection, a visual assessment system is installed to the TBM and a lager in-situ rock mass image dataset is collected from the water conveyance channel project. The rock mass condition assessment task is transformed into a fine-grain classification task. To fulfill the task, a self-convolution based attention fusion network (SAFN) is designed in this paper. The core of our method is the discovery and fusion of the object attention map within a deep neural network. The network consists of two novel modules, the self-convolution based attention extractor (SAE) module and the self-convolution based attention pooling algorithm (SAP) module. The former is designed to detect the intact rock regions generating the attention map, and the latter is designed to improve the performance of classifier by fusing the attention map that focuses on the intact rock regions. The results of SAFN are evaluated from aspects of interpretability, ablation, accuracy and cross-validation, and it outperforms state-of-the-art models in the rock mass assessment dataset. Furthermore, the dynamic filed test show that our assessment system based on the SAFN model is accurate and efficient for automated classification of rock mass. [ABSTRACT FROM AUTHOR]

It seems as though progressively more people are in the race to upload content, data, and information online; and hospitals haven't neglected this trend either. Hospitals are now at the forefront for multi-site medical data sharing to provide ground-breaking advancements in the way health records are shared and patients are diagnosed. Sharing of medical data is essential in modern medical research. Yet, as with all data sharing technology, the challenge is to balance improved treatment with protecting patient's personal information. This paper provides a novel split learning algorithm coined the term, "multi-site split learning", which enables a secure transfer of medical data between multiple hospitals without fear of exposing personal data contained in patient records. It also explores the effects of varying the number of end-systems and the ratio of data-imbalance on the deep learning performance. A guideline for the most optimal configuration of split learning that ensures privacy of patient data whilst achieving performance is empirically given. We argue the benefits of our multi-site split learning algorithm, especially regarding the privacy preserving factor, using CT scans of COVID-19 patients, X-ray bone scans, and cholesterol level medical data. [ABSTRACT FROM AUTHOR]

A brain tumour is a mass or cluster of abnormal cells in the brain, which has the possibility of becoming life-threatening because of its ability to invade neighbouring tissues and also form metastases. An accurate diagnosis is essential for successful treatment planning, and magnetic resonance imaging is the principal imaging modality for diagnosing brain tumours and their extent. Deep Learning methods in computer vision applications have shown significant improvement in recent years, most of which can be credited to the fact that a sizeable amount of data is available to train models, and the improvements in the model architectures yield better approximations in a supervised setting. Classifying tumours using such deep learning methods has made significant progress with the availability of open datasets with reliable annotations. Typically those methods are either 3D models, which use 3D volumetric MRIs or even 2D models considering each slice separately. However, by treating one spatial dimension separately or by considering the slices as a sequence of images over time, spatiotemporal models can be employed as "spatiospatial" models for this task. These models have the capabilities of learning specific spatial and temporal relationships while reducing computational costs. This paper uses two spatiotemporal models, ResNet (2+1)D and ResNet Mixed Convolution, to classify different types of brain tumours. It was observed that both these models performed superior to the pure 3D convolutional model, ResNet18. Furthermore, it was also observed that pre-training the models on a different, even unrelated dataset before training them for the task of tumour classification improves the performance. Finally, Pre-trained ResNet Mixed Convolution was observed to be the best model in these experiments, achieving a macro F1-score of 0.9345 and a test accuracy of 96.98%, while at the same time being the model with the least computational cost. [ABSTRACT FROM AUTHOR]

In recent years, more and more deep learning frameworks are being applied to hyperspectral image classification tasks and have achieved great results. However, the existing network models have higher model complexity and require more time consumption. Traditional hyperspectral image classification methods tend to ignore the correlation between local spatial features. In this paper, a new hyperspectral image classification method is proposed, which combines two-dimensional Gabor filter with random patch convolution (GRPC) feature extraction to obtain spatial-spectral feature information. The method firstly performs dimensionality reduction through principal component analysis and linear discriminant analysis and extracts the edge texture and spatial information of the image using a Gabor filter for the reduced-dimensional image. Next, the extracted information is convolved with random patches to extract spectral features. Finally, the spatial features and multi-level spectral features are fused to classify the images using the Support Vector Machine classifier. In order to verify the performance of this method, experiments were conducted on three widely used datasets of Indian Pines, Pavia University and Kennedy Space Center. The overall classification accuracy reached 98.09%, 99.64% and 96.53%, which are all higher than other comparison methods. The experimental results reveal the superiority of the proposed method in classification accuracy. [ABSTRACT FROM AUTHOR]

Governments pay agencies to control the activities of farmers who receive governmental support. Field visits are costly and highly time-consuming; hence remote sensing is widely used for monitoring farmers' activities. Nowadays, a vast amount of available data from the Sentinel mission significantly boosted research in agriculture. Estonia is among the first countries to take advantage of this data source to automate mowing and ploughing events detection across the country. Although techniques that rely on optical data for monitoring agriculture events are favourable, the availability of such data during the growing season is limited. Thus, alternative data sources have to be evaluated. In this paper, we developed a deep learning model with an integrated reject option for detecting grassland mowing events using time series of Sentinel-1 and Sentinel-2 optical images acquired from 2000 fields in Estonia in 2018 during the vegetative season. The rejection mechanism is based on a threshold over the prediction confidence of the proposed model. The proposed model significantly outperforms the state-of-the-art technique and achieves event accuracy of 73.3% and end of season accuracy of 94.8%. [ABSTRACT FROM AUTHOR]

The rapid adoption of artificial intelligence methods in healthcare is coupled with the critical need for techniques to rigorously introspect models and thereby ensure that they behave reliably. This has led to the design of explainable AI techniques that uncover the relationships between discernible data signatures and model predictions. In this context, counterfactual explanations that synthesize small, interpretable changes to a given query while producing desired changes in model predictions have become popular. This under-constrained, inverse problem is vulnerable to introducing irrelevant feature manipulations, particularly when the model's predictions are not well-calibrated. Hence, in this paper, we propose the TraCE (training calibration-based explainers) technique, which utilizes a novel uncertainty-based interval calibration strategy for reliably synthesizing counterfactuals. Given the wide-spread adoption of machine-learned solutions in radiology, our study focuses on deep models used for identifying anomalies in chest X-ray images. Using rigorous empirical studies, we demonstrate the superiority of TraCE explanations over several state-of-the-art baseline approaches, in terms of several widely adopted evaluation metrics. Our findings show that TraCE can be used to obtain a holistic understanding of deep models by enabling progressive exploration of decision boundaries, to detect shortcuts, and to infer relationships between patient attributes and disease severity. [ABSTRACT FROM AUTHOR]

Considerable attention has been given to deep-learning and machine-learning techniques in an effort to reduce the computational cost of computational fluid dynamics simulation. The present paper addresses the prediction of steady flows passing many fixed cylinders using a deep-learning model and investigates the accuracy of the predicted velocity field. The deep-learning model outputs the x- and y-components of the flow velocity field when the cylinder arrangement is input. The accuracy of the predicted velocity field is investigated, focusing on the velocity profile of the fluid flow and the fluid force acting on the cylinders. The present model accurately predicts the flow when the number of cylinders is equal to or close to that set in the training dataset. The extrapolation of the prediction to a smaller number of cylinders results in error, which can be interpreted as internal friction of the fluid. The results of the fluid force acting on the cylinders suggest that the present deep-learning model has good generalization performance for systems with a larger number of cylinders. [ABSTRACT FROM AUTHOR]

Long short-term memory (LSTM) models provide high predictive performance through their ability to recognize longer sequences of time series data. More recently, bidirectional deep learning models (BiLSTM) have extended the LSTM capabilities by training the input data twice in forward and backward directions. In this paper, BiLSTM short term traffic forecasting models have been developed and evaluated using data from a calibrated micro-simulation model for a congested freeway in Melbourne, Australia. The simulation model was extensively calibrated and validated to a high degree of accuracy using field data collected from 55 detectors on the freeway. The base year simulation model was then used to generate loop detector data including speed, flow and occupancy which were used to develop and compare a number of LSTM models for short-term traffic prediction up to 60 min into the future. The modelling results showed that BiLSTM outperformed other predictive models for multiple prediction horizons for base year conditions. The simulation model was then adapted for future year scenarios where the traffic demand was increased by 25–100 percent to reflect potential future increases in traffic demands. The results showed superior performance of BiLSTM for multiple prediction horizons for all traffic variables. [ABSTRACT FROM AUTHOR]

Recently, Raman Spectroscopy (RS) was demonstrated to be a non-destructive way of cancer diagnosis, due to the uniqueness of RS measurements in revealing molecular biochemical changes between cancerous vs. normal tissues and cells. In order to design computational approaches for cancer detection, the quality and quantity of tissue samples for RS are important for accurate prediction. In reality, however, obtaining skin cancer samples is difficult and expensive due to privacy and other constraints. With a small number of samples, the training of the classifier is difficult, and often results in overfitting. Therefore, it is important to have more samples to better train classifiers for accurate cancer tissue classification. To overcome these limitations, this paper presents a novel generative adversarial network based skin cancer tissue classification framework. Specifically, we design a data augmentation module that employs a Generative Adversarial Network (GAN) to generate synthetic RS data resembling the training data classes. The original tissue samples and the generated data are concatenated to train classification modules. Experiments on real-world RS data demonstrate that (1) data augmentation can help improve skin cancer tissue classification accuracy, and (2) generative adversarial network can be used to generate reliable synthetic Raman spectroscopic data. [ABSTRACT FROM AUTHOR]

This paper proposes a method that automatically measures non-invasive blood pressure (BP) based on an auscultatory approach using Korotkoff sounds (K-sounds). There have been methods utilizing K-sounds that were more accurate in general than those using cuff pressure signals only under well-controlled environments, but most were vulnerable to the measurement conditions and to external noise because blood pressure is simply determined based on threshold values in the sound signal. The proposed method enables robust and precise BP measurements by evaluating the probability that each sound pulse is an audible K-sound based on a deep learning using a convolutional neural network (CNN). Instead of classifying sound pulses into two categories, audible K-sounds and others, the proposed CNN model outputs probability values. These values in a Korotkoff cycle are arranged in time order, and the blood pressure is determined. The proposed method was tested with a dataset acquired in practice that occasionally contains considerable noise, which can degrade the performance of the threshold-based methods. The results demonstrate that the proposed method outperforms a previously reported CNN-based classification method using K-sounds. With larger amounts of various types of data, the proposed method can potentially achieve more precise and robust results. [ABSTRACT FROM AUTHOR]

Applied Current Thermoacoustic Imaging (ACTAI) is a new imaging method which combines electromagnetic excitation with ultrasound imaging, and takes ultrasonic signal as medium and biological tissue conductivity as detection target. Taking the high contrast advantage of Electrical Impedance Tomography (EIT) and high resolution advantage of ultrasound imaging, ACTAI has broad application prospects in the field of biomedical imaging. Although ACTAI has high excitation efficiency and strong detectable Signal-to-Noise Ratio, yet while under low frequency electromagnetic excitation, it is still a big challenge to reconstruct a high-resolution image of target conductivity. This paper proposes a new method for reconstructing conductivity based on Generative Adversarial Network, and it consists of three main steps: firstly, use Wiener filtering deconvolution to restore the electrical signal output by the ultrasonic probe to a real acoustic signal. Then obtain the initial acoustic source image with filtered backprojection technology. Finally, match the conductivity image with the initial sound source image, which are used as training samples for generating the adversarial network to establish a deep learning model for conductivity reconstruction. After theoretical analysis and simulation research, it is found that by introducing machine learning, the new method can dig out the inverse problem solving model contained in the data, which further reconstruct a high-resolution conductivity image and has strong anti-interference characteristics. The new method provides a new way to solve the problem of conductivity reconstruction in Applied Current Thermoacoustic Imaging. [ABSTRACT FROM AUTHOR]

The analysis of human facial expressions from the thermal images captured by the Infrared Thermal Imaging (IRTI) cameras has recently gained importance compared to images captured by the standard cameras using light having a wavelength in the visible spectrum. It is because infrared cameras work well in low-light conditions and also infrared spectrum captures thermal distribution that is very useful for building systems like Robot interaction systems, quantifying the cognitive responses from facial expressions, disease control, etc. In this paper, a deep learning model called IRFacExNet (InfraRed Facial Expression Network) has been proposed for facial expression recognition (FER) from infrared images. It utilizes two building blocks namely Residual unit and Transformation unit which extract dominant features from the input images specific to the expressions. The extracted features help to detect the emotion of the subjects in consideration accurately. The Snapshot ensemble technique is adopted with a Cosine annealing learning rate scheduler to improve the overall performance. The performance of the proposed model has been evaluated on a publicly available dataset, namely IRDatabase developed by RWTH Aachen University. The facial expressions present in the dataset are Fear, Anger, Contempt, Disgust, Happy, Neutral, Sad, and Surprise. The proposed model produces 88.43% recognition accuracy, better than some state-of-the-art methods considered here for comparison. Our model provides a robust framework for the detection of accurate expression in the absence of visible light. [ABSTRACT FROM AUTHOR]

One major impediment to the wider use of deep learning for clinical decision making is the difficulty of assigning a level of confidence to model predictions. Currently, deep Bayesian neural networks and sparse Gaussian processes are the main two scalable uncertainty estimation methods. However, deep Bayesian neural networks suffer from lack of expressiveness, and more expressive models such as deep kernel learning, which is an extension of sparse Gaussian process, captures only the uncertainty from the higher-level latent space. Therefore, the deep learning model under it lacks interpretability and ignores uncertainty from the raw data. In this paper, we merge features of the deep Bayesian learning framework with deep kernel learning to leverage the strengths of both methods for a more comprehensive uncertainty estimation. Through a series of experiments on predicting the first incidence of heart failure, diabetes and depression applied to large-scale electronic medical records, we demonstrate that our method is better at capturing uncertainty than both Gaussian processes and deep Bayesian neural networks in terms of indicating data insufficiency and identifying misclassifications, with a comparable generalization performance. Furthermore, by assessing the accuracy and area under the receiver operating characteristic curve over the predictive probability, we show that our method is less susceptible to making overconfident predictions, especially for the minority class in imbalanced datasets. Finally, we demonstrate how uncertainty information derived by the model can inform risk factor analysis towards model interpretability. [ABSTRACT FROM AUTHOR]

Medical images are difficult to comprehend for a person without expertise. The scarcity of medical practitioners across the globe often face the issue of physical and mental fatigue due to the high number of cases, inducing human errors during the diagnosis. In such scenarios, having an additional opinion can be helpful in boosting the confidence of the decision maker. Thus, it becomes crucial to have a reliable visual question answering (VQA) system to provide a 'second opinion' on medical cases. However, most of the VQA systems that work today cater to real-world problems and are not specifically tailored for handling medical images. Moreover, the VQA system for medical images needs to consider a limited amount of training data available in this domain. In this paper, we develop MedFuseNet, an attention-based multimodal deep learning model, for VQA on medical images taking the associated challenges into account. Our MedFuseNet aims at maximizing the learning with minimal complexity by breaking the problem statement into simpler tasks and predicting the answer. We tackle two types of answer prediction—categorization and generation. We conducted an extensive set of quantitative and qualitative analyses to evaluate the performance of MedFuseNet. Our experiments demonstrate that MedFuseNet outperforms the state-of-the-art VQA methods, and that visualization of the captured attentions showcases the intepretability of our model's predicted results. [ABSTRACT FROM AUTHOR]

By emulating biological features in brain, Spiking Neural Networks (SNNs) offer an energy-efficient alternative to conventional deep learning. To make SNNs ubiquitous, a 'visual explanation' technique for analysing and explaining the internal spike behavior of such temporal deep SNNs is crucial. Explaining SNNs visually will make the network more transparent giving the end-user a tool to understand how SNNs make temporal predictions and why they make a certain decision. In this paper, we propose a bio-plausible visual explanation tool for SNNs, called Spike Activation Map (SAM). SAM yields a heatmap (i.e., localization map) corresponding to each time-step of input data by highlighting neurons with short inter-spike interval activity. Interestingly, without the use of gradients and ground truth, SAM produces a temporal localization map highlighting the region of interest in an image attributed to an SNN's prediction at each time-step. Overall, SAM outsets the beginning of a new research area 'explainable neuromorphic computing' that will ultimately allow end-users to establish appropriate trust in predictions from SNNs. [ABSTRACT FROM AUTHOR]

With the presence of novel coronavirus disease at the end of 2019, several approaches were proposed to help physicians detect the disease, such as using deep learning to recognize lung involvement based on the pattern of pneumonia. These approaches rely on analyzing the CT images and exploring the COVID-19 pathologies in the lung. Most of the successful methods are based on the deep learning technique, which is state-of-the-art. Nevertheless, the big drawback of the deep approaches is their need for many samples, which is not always possible. This work proposes a combined deep architecture that benefits both employed architectures of DenseNet and CapsNet. To more generalize the deep model, we propose a regularization term with much fewer parameters. The network convergence significantly improved, especially when the number of training data is small. We also propose a novel Cost-sensitive loss function for imbalanced data that makes our model feasible for the condition with a limited number of positive data. Our novelties make our approach more intelligent and potent in real-world situations with imbalanced data, popular in hospitals. We analyzed our approach on two publicly available datasets, HUST and COVID-CT, with different protocols. In the first protocol of HUST, we followed the original paper setup and outperformed it. With the second protocol of HUST, we show our approach superiority concerning imbalanced data. Finally, with three different validations of the COVID-CT, we provide evaluations in the presence of a low number of data along with a comparison with state-of-the-art. [ABSTRACT FROM AUTHOR]

Craniofacial anomaly including deformational plagiocephaly as a result of deformities in head and facial bones evolution is a serious health problem in newbies. The impact of such condition on the affected infants is profound from both medical and social viewpoint. Indeed, timely diagnosing through different medical examinations like anthropometric measurements of the skull or even Computer Tomography (CT) image modality followed by a periodical screening and monitoring plays a vital role in treatment phase. In this paper, a classification model for detecting and monitoring deformational plagiocephaly in affected infants is presented. The presented model is based on a deep learning network architecture. The given model achieves high accuracy of 99.01% with other classification parameters. The input to the model are the images captured by commonly used smartphone cameras which waives the requirement to sophisticated medical imaging modalities. The method is deployed into a mobile application which enables the parents/caregivers and non-clinical experts to monitor and report the treatment progress at home. [ABSTRACT FROM AUTHOR]

In recent years, the hyperspectral classification algorithm based on deep learning has received widespread attention, but the existing network models have higher model complexity and require more time consumption. In order to further improve the accuracy of hyperspectral image classification and reduce model complexity, this paper proposes an asymmetric coordinate attention spectral-spatial feature fusion network (ACAS2F2N) to capture distinguishing hyperspectral features. Specifically, adaptive asymmetric iterative attention was proposed to obtain the discriminative spectral-spatial features. Different from the common feature fusion method, this feature fusion method can adapt to most skip connection tasks. In addition, there is no manual parameter setting. Coordinate attention is used to obtain accurate coordinate information and channel relationship. The strip pooling module was introduced to increase the network's receptive field and avoid irrelevant information brought by conventional convolution kernels. The proposed algorithm is tested on the mainstream hyperspectral datasets (IP, KSC, and Botswana), experimental results show that the proposed ACAS2F2N can achieve state-of-the-art performance with lower time complexity. [ABSTRACT FROM AUTHOR]

Among the most leading causes of mortality across the globe are infectious diseases which have cost tremendous lives with the latest being coronavirus (COVID-19) that has become the most recent challenging issue. The extreme nature of this infectious virus and its ability to spread without control has made it mandatory to find an efficient auto-diagnosis system to assist the people who work in touch with the patients. As fuzzy logic is considered a powerful technique for modeling vagueness in medical practice, an Adaptive Neuro-Fuzzy Inference System (ANFIS) was proposed in this paper as a key rule for automatic COVID-19 detection from chest X-ray images based on the characteristics derived by texture analysis using gray level co-occurrence matrix (GLCM) technique. Unlike the proposed method, especially deep learning-based approaches, the proposed ANFIS-based method can work on small datasets. The results were promising performance accuracy, and compared with the other state-of-the-art techniques, the proposed method gives the same performance as the deep learning with complex architectures using many backbone. [ABSTRACT FROM AUTHOR]

Adaptive optics flood illumination ophthalmoscopy (AO-FIO) is an established imaging tool in the investigation of retinal diseases. However, the clinical interpretation of AO-FIO images can be challenging due to varied image quality. Therefore, image quality assessment is essential before interpretation. An image assessment tool will also assist further work on improving the image quality, either during acquisition or post processing. In this paper, we describe, validate and compare two automated image quality assessment methods; the energy of Laplacian focus operator (LAPE; not commonly used but easily implemented) and convolutional neural network (CNN; effective but more complex approach). We also evaluate the effects of subject age, axial length, refractive error, fixation stability, disease status and retinal location on AO-FIO image quality. Based on analysis of 10,250 images of 50 × 50 μm size, at 41 retinal locations, from 50 subjects we demonstrate that CNN slightly outperforms LAPE in image quality assessment. CNN achieves accuracy of 89%, whereas LAPE metric achieves 73% and 80% (for a linear regression and random forest multiclass classifier methods, respectively) compared to ground truth. Furthermore, the retinal location, age and disease are factors that can influence the likelihood of poor image quality. [ABSTRACT FROM AUTHOR]

COVID-19 is a serious ongoing worldwide pandemic. Using X-ray chest radiography images for automatically diagnosing COVID-19 is an effective and convenient means of providing diagnostic assistance to clinicians in practice. This paper proposes a bagging dynamic deep learning network (B-DDLN) for diagnosing COVID-19 by intelligently recognizing its symptoms in X-ray chest radiography images. After a series of preprocessing steps for images, we pre-train convolution blocks as a feature extractor. For the extracted features, a bagging dynamic learning network classifier is trained based on neural dynamic learning algorithm and bagging algorithm. B-DDLN connects the feature extractor and bagging classifier in series. Experimental results verify that the proposed B-DDLN achieves 98.8889% testing accuracy, which shows the best diagnosis performance among the existing state-of-the-art methods on the open image set. It also provides evidence for further detection and treatment. [ABSTRACT FROM AUTHOR]

The new coronavirus unleashed a worldwide pandemic in early 2020, and a fatality rate several times that of the flu. As the number of infections soared, and capabilities for testing lagged behind, chest X-ray (CXR) imaging became more relevant in the early diagnosis and treatment planning for patients with suspected or confirmed COVID-19 infection. In a few weeks, proposed new methods for lung screening using deep learning rapidly appeared, while quality assurance discussions lagged behind. This paper proposes a set of protocols to validate deep learning algorithms, including our ROI Hide-and-Seek protocol, which emphasizes or hides key regions of interest from CXR data. Our protocol allows assessing the classification performance for anomaly detection and its correlation to radiological signatures, an important issue overlooked in several deep learning approaches proposed so far. By running a set of systematic tests over CXR representations using public image datasets, we demonstrate the weaknesses of current techniques and offer perspectives on the advantages and limitations of automated radiography analysis when using heterogeneous data sources. [ABSTRACT FROM AUTHOR]

Cancer tumor classification based on morphological characteristics alone has been shown to have serious limitations. Breast, lung, colorectal, thyroid, and ovarian are the most commonly diagnosed cancers among women. Precise classification of cancers into their types is considered a vital problem for cancer diagnosis and therapy. In this paper, we proposed a stacking ensemble deep learning model based on one-dimensional convolutional neural network (1D-CNN) to perform a multi-class classification on the five common cancers among women based on RNASeq data. The RNASeq gene expression data was downloaded from Pan-Cancer Atlas using GDCquery function of the TCGAbiolinks package in the R software. We used least absolute shrinkage and selection operator (LASSO) as feature selection method. We compared the results of the new proposed model with and without LASSO with the results of the single 1D-CNN and machine learning methods which include support vector machines with radial basis function, linear, and polynomial kernels; artificial neural networks; k-nearest neighbors; bagging trees. The results show that the proposed model with and without LASSO has a better performance compared to other classifiers. Also, the results show that the machine learning methods (SVM-R, SVM-L, SVM-P, ANN, KNN, and bagging trees) with under-sampling have better performance than with over-sampling techniques. This is supported by the statistical significance test of accuracy where the p-values for differences between the SVM-R and SVM-P, SVM-R and ANN, SVM-R and KNN are found to be p = 0.003, p = < 0.001, and p = < 0.001, respectively. Also, SVM-L had a significant difference compared to ANN p = 0.009. Moreover, SVM-P and ANN, SVM-P and KNN are found to be significantly different with p-values p = < 0.001 and p = < 0.001, respectively. In addition, ANN and bagging trees, ANN and KNN were found to be significantly different with p-values p = < 0.001 and p = 0.004, respectively. Thus, the proposed model can help in the early detection and diagnosis of cancer in women, and hence aid in designing early treatment strategies to improve survival. [ABSTRACT FROM AUTHOR]

The cocktail party phenomenon describes the ability of the human brain to focus auditory attention on a particular stimulus while ignoring other acoustic events. Selective auditory attention detection (SAAD) is an important issue in the development of brain-computer interface systems and cocktail party processors. This paper proposes a new dynamic attention detection system to process the temporal evolution of the input signal. The proposed dynamic SAAD is modeled as a sequential decision-making problem, which is solved by recurrent neural network (RNN) and reinforcement learning methods of Q-learning and deep Q-learning. Among different dynamic learning approaches, the evaluation results show that the deep Q-learning approach with RNN as agent provides the highest classification accuracy (94.2%) with the least detection delay. The proposed SAAD system is advantageous, in the sense that the detection of attention is performed dynamically for the sequential inputs. Also, the system has the potential to be used in scenarios, where the attention of the listener might be switched in time in the presence of various acoustic events. [ABSTRACT FROM AUTHOR]

COVID-19 has crippled the world's healthcare systems, setting back the economy and taking the lives of several people. Although potential vaccines are being tested and supplied around the world, it will take a long time to reach every human being, more so with new variants of the virus emerging, enforcing a lockdown-like situation on parts of the world. Thus, there is a dire need for early and accurate detection of COVID-19 to prevent the spread of the disease, even more. The current gold-standard RT-PCR test is only 71% sensitive and is a laborious test to perform, leading to the incapability of conducting the population-wide screening. To this end, in this paper, we propose an automated COVID-19 detection system that uses CT-scan images of the lungs for classifying the same into COVID and Non-COVID cases. The proposed method applies an ensemble strategy that generates fuzzy ranks of the base classification models using the Gompertz function and fuses the decision scores of the base models adaptively to make the final predictions on the test cases. Three transfer learning-based convolutional neural network models are used, namely VGG-11, Wide ResNet-50-2, and Inception v3, to generate the decision scores to be fused by the proposed ensemble model. The framework has been evaluated on two publicly available chest CT scan datasets achieving state-of-the-art performance, justifying the reliability of the model. The relevant source codes related to the present work is available in: GitHub. [ABSTRACT FROM AUTHOR]

This paper proposes a fully automatic method to segment the inner boundary of the bony orbit in two different image modalities: magnetic resonance imaging (MRI) and computed tomography (CT). The method, based on a deep learning architecture, uses two fully convolutional neural networks in series followed by a graph-search method to generate a boundary for the orbit. When compared to human performance for segmentation of both CT and MRI data, the proposed method achieves high Dice coefficients on both orbit and background, with scores of 0.813 and 0.975 in CT images and 0.930 and 0.995 in MRI images, showing a high degree of agreement with a manual segmentation by a human expert. Given the volumetric characteristics of these imaging modalities and the complexity and time-consuming nature of the segmentation of the orbital region in the human skull, it is often impractical to manually segment these images. Thus, the proposed method provides a valid clinical and research tool that performs similarly to the human observer. [ABSTRACT FROM AUTHOR]

An amendment to this paper has been published and can be accessed via a link at the top of the paper. [ABSTRACT FROM AUTHOR]

The pulse arrival time (PAT), the difference between the R-peak time of electrocardiogram (ECG) signal and the systolic peak of photoplethysmography (PPG) signal, is an indicator that enables noninvasive and continuous blood pressure estimation. However, it is difficult to accurately measure PAT from ECG and PPG signals because they have inconsistent shapes owing to patient-specific physical characteristics, pathological conditions, and movements. Accordingly, complex preprocessing is required to estimate blood pressure based on PAT. In this paper, as an alternative solution, we propose a noninvasive continuous algorithm using the difference between ECG and PPG as a new feature that can include PAT information. The proposed algorithm is a deep CNN–LSTM-based multitasking machine learning model that outputs simultaneous prediction results of systolic (SBP) and diastolic blood pressures (DBP). We used a total of 48 patients on the PhysioNet website by splitting them into 38 patients for training and 10 patients for testing. The prediction accuracies of SBP and DBP were 0.0 ± 1.6 mmHg and 0.2 ± 1.3 mmHg, respectively. Even though the proposed model was assessed with only 10 patients, this result was satisfied with three guidelines, which are the BHS, AAMI, and IEEE standards for blood pressure measurement devices. [ABSTRACT FROM AUTHOR]

Protein structure prediction is an important problem in bioinformatics and has been studied for decades. However, there are still few open-source comprehensive protein structure prediction packages publicly available in the field. In this paper, we present our latest open-source protein tertiary structure prediction system—MULTICOM2, an integration of template-based modeling (TBM) and template-free modeling (FM) methods. The template-based modeling uses sequence alignment tools with deep multiple sequence alignments to search for structural templates, which are much faster and more accurate than MULTICOM1. The template-free (ab initio or de novo) modeling uses the inter-residue distances predicted by DeepDist to reconstruct tertiary structure models without using any known structure as template. In the blind CASP14 experiment, the average TM-score of the models predicted by our server predictor based on the MULTICOM2 system is 0.720 for 58 TBM (regular) domains and 0.514 for 38 FM and FM/TBM (hard) domains, indicating that MULTICOM2 is capable of predicting good tertiary structures across the board. It can predict the correct fold for 76 CASP14 domains (95% regular domains and 55% hard domains) if only one prediction is made for a domain. The success rate is increased to 3% for both regular and hard domains if five predictions are made per domain. Moreover, the prediction accuracy of the pure template-free structure modeling method on both TBM and FM targets is very close to the combination of template-based and template-free modeling methods. This demonstrates that the distance-based template-free modeling method powered by deep learning can largely replace the traditional template-based modeling method even on TBM targets that TBM methods used to dominate and therefore provides a uniform structure modeling approach to any protein. Finally, on the 38 CASP14 FM and FM/TBM hard domains, MULTICOM2 server predictors (MULTICOM-HYBRID, MULTICOM-DEEP, MULTICOM-DIST) were ranked among the top 20 automated server predictors in the CASP14 experiment. After combining multiple predictors from the same research group as one entry, MULTICOM-HYBRID was ranked no. 5. The source code of MULTICOM2 is freely available at https://github.com/multicom-toolbox/multicom/tree/multicom_v2.0. [ABSTRACT FROM AUTHOR]

In this paper, a new powerful deep learning framework, named as DENTECT, is developed in order to instantly detect five different dental treatment approaches and simultaneously number the dentition based on the FDI notation on panoramic X-ray images. This makes DENTECT the first system that focuses on identification of multiple dental treatments; namely periapical lesion therapy, fillings, root canal treatment (RCT), surgical extraction, and conventional extraction all of which are accurately located within their corresponding borders and tooth numbers. Although DENTECT is trained on only 1005 images, the annotations supplied by experts provide satisfactory results for both treatment and enumeration detection. This framework carries out enumeration with an average precision (AP) score of 89.4% and performs treatment identification with a 59.0% AP score. Clinically, DENTECT is a practical and adoptable tool that accelerates the process of treatment planning with a level of accuracy which could compete with that of dental clinicians. [ABSTRACT FROM AUTHOR]

The volume of labeled data is often the primary determinant of success in developing machine learning algorithms. This has increased interest in methods for leveraging crowds to scale data labeling efforts, and methods to learn from noisy crowd-sourced labels. The need to scale labeling is acute but particularly challenging in medical applications like pathology, due to the expertise required to generate quality labels and the limited availability of qualified experts. In this paper we investigate the application of Scalable Variational Gaussian Processes for Crowdsourcing (SVGPCR) in digital pathology. We compare SVGPCR with other crowdsourcing methods using a large multi-rater dataset where pathologists, pathology residents, and medical students annotated tissue regions breast cancer. Our study shows that SVGPCR is competitive with equivalent methods trained using gold-standard pathologist generated labels, and that SVGPCR meets or exceeds the performance of other crowdsourcing methods based on deep learning. We also show how SVGPCR can effectively learn the class-conditional reliabilities of individual annotators and demonstrate that Gaussian-process classifiers have comparable performance to similar deep learning methods. These results suggest that SVGPCR can meaningfully engage non-experts in pathology labeling tasks, and that the class-conditional reliabilities estimated by SVGPCR may assist in matching annotators to tasks where they perform well. [ABSTRACT FROM AUTHOR]

Myoelectric hand prostheses offer a way for upper-limb amputees to recover gesture and prehensile abilities to ease rehabilitation and daily life activities. However, studies with prosthesis users found that a lack of intuitiveness and ease-of-use in the human-machine control interface are among the main driving factors in the low user acceptance of these devices. This paper proposes a highly intuitive, responsive and reliable real-time myoelectric hand prosthesis control strategy with an emphasis on the demonstration and report of real-time evaluation metrics. The presented solution leverages surface high-density electromyography (HD-EMG) and a convolutional neural network (CNN) to adapt itself to each unique user and his/her specific voluntary muscle contraction patterns. Furthermore, a transfer learning approach is presented to drastically reduce the training time and allow for easy installation and calibration processes. The CNN-based gesture recognition system was evaluated in real-time with a group of 12 able-bodied users. A real-time test for 6 classes/grip modes resulted in mean and median positive predictive values (PPV) of 93.43% and 100%, respectively. Each gesture state is instantly accessible from any other state, with no mode switching required for increased responsiveness and natural seamless control. The system is able to output a correct prediction within less than 116 ms latency. 100% PPV has been attained in many trials and is realistically achievable consistently with user practice and/or employing a thresholded majority vote inference. Using transfer learning, these results are achievable after a sensor installation, data recording and network training/fine-tuning routine taking less than 10 min to complete, a reduction of 89.4% in the setup time of the traditional, non-transfer learning approach. [ABSTRACT FROM AUTHOR]

Coronary calcifications are an obstacle for successful percutaneous treatment of coronary artery disease patients. The optimal method for delineating calcifications extent is coronary optical coherence tomography (OCT). To identify calcification on OCT and subsequently tailor the appropriate treatment, requires expertise in both image acquisition and interpretation. Image acquisition consists from system calibration, blood clearance by a contrast agent along with synchronization of the pullback process. Accurate interpretation demands careful review by the operator of a segment of 50–75 mm of the coronary vessel at steps of 5–10 frames per mm accounting for 375–540 images in each OCT run, which is time consuming and necessitates some expertise in OCT analysis. In this paper we developed a new deep learning algorithm to assist the physician to identify and quantify coronary calcifications promptly, efficiently and accurately. Our algorithm achieves an accuracy of 0.9903 ± 0.009 over the test set at size of 1500 frames and even managed to find calcifications that were not recognized manually by the physician. For the best knowledge of the authors our algorithm achieves high accuracy which was never achieved in the past. [ABSTRACT FROM AUTHOR]

Deep learning has brought a dramatic development in molecular property prediction that is crucial in the field of drug discovery using various representations such as fingerprints, SMILES, and graphs. In particular, SMILES is used in various deep learning models via character-based approaches. However, SMILES has a limitation in that it is hard to reflect chemical properties. In this paper, we propose a new self-supervised method to learn SMILES and chemical contexts of molecules simultaneously in pre-training the Transformer. The key of our model is learning structures with adjacency matrix embedding and learning logics that can infer descriptors via Quantitative Estimation of Drug-likeness prediction in pre-training. As a result, our method improves the generalization of the data and achieves the best average performance by benchmarking downstream tasks. Moreover, we develop a web-based fine-tuning service to utilize our model on various tasks. [ABSTRACT FROM AUTHOR]

Deep learning-based tools may annotate and interpret medical data more quickly, consistently, and accurately than medical doctors. However, as medical doctors are ultimately responsible for clinical decision-making, any deep learning-based prediction should be accompanied by an explanation that a human can understand. We present an approach called electrocardiogram gradient class activation map (ECGradCAM), which is used to generate attention maps and explain the reasoning behind deep learning-based decision-making in ECG analysis. Attention maps may be used in the clinic to aid diagnosis, discover new medical knowledge, and identify novel features and characteristics of medical tests. In this paper, we showcase how ECGradCAM attention maps can unmask how a novel deep learning model measures both amplitudes and intervals in 12-lead electrocardiograms, and we show an example of how attention maps may be used to develop novel ECG features. [ABSTRACT FROM AUTHOR]

Brain tumor localization and segmentation from magnetic resonance imaging (MRI) are hard and important tasks for several applications in the field of medical analysis. As each brain imaging modality gives unique and key details related to each part of the tumor, many recent approaches used four modalities T1, T1c, T2, and FLAIR. Although many of them obtained a promising segmentation result on the BRATS 2018 dataset, they suffer from a complex structure that needs more time to train and test. So, in this paper, to obtain a flexible and effective brain tumor segmentation system, first, we propose a preprocessing approach to work only on a small part of the image rather than the whole part of the image. This method leads to a decrease in computing time and overcomes the overfitting problems in a Cascade Deep Learning model. In the second step, as we are dealing with a smaller part of brain images in each slice, a simple and efficient Cascade Convolutional Neural Network (C-ConvNet/C-CNN) is proposed. This C-CNN model mines both local and global features in two different routes. Also, to improve the brain tumor segmentation accuracy compared with the state-of-the-art models, a novel Distance-Wise Attention (DWA) mechanism is introduced. The DWA mechanism considers the effect of the center location of the tumor and the brain inside the model. Comprehensive experiments are conducted on the BRATS 2018 dataset and show that the proposed model obtains competitive results: the proposed method achieves a mean whole tumor, enhancing tumor, and tumor core dice scores of 0.9203, 0.9113 and 0.8726 respectively. Other quantitative and qualitative assessments are presented and discussed. [ABSTRACT FROM AUTHOR]

Early detection and appropriate medical treatment are of great use for ear disease. However, a new diagnostic strategy is necessary for the absence of experts and relatively low diagnostic accuracy, in which deep learning plays an important role. This paper puts forward a mechanic learning model which uses abundant otoscope image data gained in clinical cases to achieve an automatic diagnosis of ear diseases in real time. A total of 20,542 endoscopic images were employed to train nine common deep convolution neural networks. According to the characteristics of the eardrum and external auditory canal, eight kinds of ear diseases were classified, involving the majority of ear diseases, such as normal, Cholestestoma of the middle ear, Chronic suppurative otitis media, External auditory cana bleeding, Impacted cerumen, Otomycosis external, Secretory otitis media, Tympanic membrane calcification. After we evaluate these optimization schemes, two best performance models are selected to combine the ensemble classifiers with real-time automatic classification. Based on accuracy and training time, we choose a transferring learning model based on DensNet-BC169 and DensNet-BC1615, getting a result that each model has obvious improvement by using these two ensemble classifiers, and has an average accuracy of 95.59%. Considering the dependence of classifier performance on data size in transfer learning, we evaluate the high accuracy of the current model that can be attributed to large databases. Current studies are unparalleled regarding disease diversity and diagnostic precision. The real-time classifier trains the data under different acquisition conditions, which is suitable for real cases. According to this study, in the clinical case, the deep learning model is of great use in the early detection and remedy of ear diseases. [ABSTRACT FROM AUTHOR]

Training machine learning models on classical computers is usually a time and compute intensive process. With Moore's law nearing its inevitable end and an ever-increasing demand for large-scale data analysis using machine learning, we must leverage non-conventional computing paradigms like quantum computing to train machine learning models efficiently. Adiabatic quantum computers can approximately solve NP-hard problems, such as the quadratic unconstrained binary optimization (QUBO), faster than classical computers. Since many machine learning problems are also NP-hard, we believe adiabatic quantum computers might be instrumental in training machine learning models efficiently in the post Moore's law era. In order to solve problems on adiabatic quantum computers, they must be formulated as QUBO problems, which is very challenging. In this paper, we formulate the training problems of three machine learning models—linear regression, support vector machine (SVM) and balanced k-means clustering—as QUBO problems, making them conducive to be trained on adiabatic quantum computers. We also analyze the computational complexities of our formulations and compare them to corresponding state-of-the-art classical approaches. We show that the time and space complexities of our formulations are better (in case of SVM and balanced k-means clustering) or equivalent (in case of linear regression) to their classical counterparts. [ABSTRACT FROM AUTHOR]

Whole slide images (WSIs) pose unique challenges when training deep learning models. They are very large which makes it necessary to break each image down into smaller patches for analysis, image features have to be extracted at multiple scales in order to capture both detail and context, and extreme class imbalances may exist. Significant progress has been made in the analysis of these images, thanks largely due to the availability of public annotated datasets. We postulate, however, that even if a method scores well on a challenge task, this success may not translate to good performance in a more clinically relevant workflow. Many datasets consist of image patches which may suffer from data curation bias; other datasets are only labelled at the whole slide level and the lack of annotations across an image may mask erroneous local predictions so long as the final decision is correct. In this paper, we outline the differences between patch or slide-level classification versus methods that need to localize or segment cancer accurately across the whole slide, and we experimentally verify that best practices differ in both cases. We apply a binary cancer detection network on post neoadjuvant therapy breast cancer WSIs to find the tumor bed outlining the extent of cancer, a task which requires sensitivity and precision across the whole slide. We extensively study multiple design choices and their effects on the outcome, including architectures and augmentations. We propose a negative data sampling strategy, which drastically reduces the false positive rate (25% of false positives versus 62.5%) and improves each metric pertinent to our problem, with a 53% reduction in the error of tumor extent. Our results indicate classification performances of image patches versus WSIs are inversely related when the same negative data sampling strategy is used. Specifically, injection of negatives into training data for image patch classification degrades the performance, whereas the performance is improved for slide and pixel-level WSI classification tasks. Furthermore, we find applying extensive augmentations helps more in WSI-based tasks compared to patch-level image classification. [ABSTRACT FROM AUTHOR]

In the last 20 years, terrorism has led to hundreds of thousands of deaths and massive economic, political, and humanitarian crises in several regions of the world. Using real-world data on attacks occurred in Afghanistan and Iraq from 2001 to 2018, we propose the use of temporal meta-graphs and deep learning to forecast future terrorist targets. Focusing on three event dimensions, i.e., employed weapons, deployed tactics and chosen targets, meta-graphs map the connections among temporally close attacks, capturing their operational similarities and dependencies. From these temporal meta-graphs, we derive 2-day-based time series that measure the centrality of each feature within each dimension over time. Formulating the problem in the context of the strategic behavior of terrorist actors, these multivariate temporal sequences are then utilized to learn what target types are at the highest risk of being chosen. The paper makes two contributions. First, it demonstrates that engineering the feature space via temporal meta-graphs produces richer knowledge than shallow time-series that only rely on frequency of feature occurrences. Second, the performed experiments reveal that bi-directional LSTM networks achieve superior forecasting performance compared to other algorithms, calling for future research aiming at fully discovering the potential of artificial intelligence to counter terrorist violence. [ABSTRACT FROM AUTHOR]

Image compression is used in several clinical organizations to help address the overhead associated with medical imaging. These methods reduce file size by using a compact representation of the original image. This study aimed to analyze the impact of image compression on the performance of deep learning-based models in classifying mammograms as "malignant"—cases that lead to a cancer diagnosis and treatment—or "normal" and "benign," non-malignant cases that do not require immediate medical intervention. In this retrospective study, 9111 unique mammograms–5672 normal, 1686 benign, and 1754 malignant cases were collected from the National Cancer Center in the Republic of Korea. Image compression was applied to mammograms with compression ratios (CRs) ranging from 15 to 11 K. Convolutional neural networks (CNNs) with three convolutional layers and three fully-connected layers were trained using these images to classify a mammogram as malignant or not malignant across a range of CRs using five-fold cross-validation. Models trained on images with maximum CRs of 5 K had an average area under the receiver operating characteristic curve (AUROC) of 0.87 and area under the precision-recall curve (AUPRC) of 0.75 across the five folds and compression ratios. For images compressed with CRs of 10 K and 11 K, model performance decreased (average 0.79 in AUROC and 0.49 in AUPRC). Upon generating saliency maps that visualize the areas each model views as significant for prediction, models trained on less compressed (CR < = 5 K) images had maps encapsulating a radiologist's label, while models trained on images with higher amounts of compression had maps that missed the ground truth completely. In addition, base ResNet18 models pre-trained on ImageNet and trained using compressed mammograms did not show performance improvements over our CNN model, with AUROC and AUPRC values ranging from 0.77 to 0.87 and 0.52 to 0.71 respectively when trained and tested on images with maximum CRs of 5 K. This paper finds that while training models on images with increased the robustness of the models when tested on compressed data, moderate image compression did not substantially impact the classification performance of DL-based models. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have achieved state-of-the-art performance in many important domains, including medical diagnosis, security, and autonomous driving. In domains where safety is highly critical, an erroneous decision can result in serious consequences. While a perfect prediction accuracy is not always achievable, recent work on Bayesian deep networks shows that it is possible to know when DNNs are more likely to make mistakes. Knowing what DNNs do not know is desirable to increase the safety of deep learning technology in sensitive applications; Bayesian neural networks attempt to address this challenge. Traditional approaches are computationally intractable and do not scale well to large, complex neural network architectures. In this paper, we develop a theoretical framework to approximate Bayesian inference for DNNs by imposing a Bernoulli distribution on the model weights. This method called Monte Carlo DropConnect (MC-DropConnect) gives us a tool to represent the model uncertainty with little change in the overall model structure or computational cost. We extensively validate the proposed algorithm on multiple network architectures and datasets for classification and semantic segmentation tasks. We also propose new metrics to quantify uncertainty estimates. This enables an objective comparison between MC-DropConnect and prior approaches. Our empirical results demonstrate that the proposed framework yields significant improvement in both prediction accuracy and uncertainty estimation quality compared to the state of the art. [ABSTRACT FROM AUTHOR]

Global monitoring of disease vectors is undoubtedly becoming an urgent need as the human population rises and becomes increasingly mobile, international commercial exchanges increase, and climate change expands the habitats of many vector species. Traditional surveillance of mosquitoes, vectors of many diseases, relies on catches, which requires regular manual inspection and reporting, and dedicated personnel, making large-scale monitoring difficult and expensive. New approaches are solving the problem of scalability by relying on smartphones and the Internet to enable novel community-based and digital observatories, where people can upload pictures of mosquitoes whenever they encounter them. An example is the Mosquito Alert citizen science system, which includes a dedicated mobile phone app through which geotagged images are collected. This system provides a viable option for monitoring the spread of various mosquito species across the globe, although it is partly limited by the quality of the citizen scientists' photos. To make the system useful for public health agencies, and to give feedback to the volunteering citizens, the submitted images are inspected and labeled by entomology experts. Although citizen-based data collection can greatly broaden disease-vector monitoring scales, manual inspection of each image is not an easily scalable option in the long run, and the system could be improved through automation. Based on Mosquito Alert's curated database of expert-validated mosquito photos, we trained a deep learning model to find tiger mosquitoes (Aedes albopictus), a species that is responsible for spreading chikungunya, dengue, and Zika among other diseases. The highly accurate 0.96 area under the receiver operating characteristic curve score promises not only a helpful pre-selector for the expert validation process but also an automated classifier giving quick feedback to the app participants, which may help to keep them motivated. In the paper, we also explored the possibilities of using the model to improve future data collection quality as a feedback loop. [ABSTRACT FROM AUTHOR]

The application of machine learning (ML) techniques in materials science has attracted significant attention in recent years, due to their impressive ability to efficiently extract data-driven linkages from various input materials representations to their output properties. While the application of traditional ML techniques has become quite ubiquitous, there have been limited applications of more advanced deep learning (DL) techniques, primarily because big materials datasets are relatively rare. Given the demonstrated potential and advantages of DL and the increasing availability of big materials datasets, it is attractive to go for deeper neural networks in a bid to boost model performance, but in reality, it leads to performance degradation due to the vanishing gradient problem. In this paper, we address the question of how to enable deeper learning for cases where big materials data is available. Here, we present a general deep learning framework based on Individual Residual learning (IRNet) composed of very deep neural networks that can work with any vector-based materials representation as input to build accurate property prediction models. We find that the proposed IRNet models can not only successfully alleviate the vanishing gradient problem and enable deeper learning, but also lead to significantly (up to 47%) better model accuracy as compared to plain deep neural networks and traditional ML techniques for a given input materials representation in the presence of big data. [ABSTRACT FROM AUTHOR]

SPECT nuclear medicine imaging is widely used for treating, diagnosing, evaluating and preventing various serious diseases. The automated classification of medical images is becoming increasingly important in developing computer-aided diagnosis systems. Deep learning, particularly for the convolutional neural networks, has been widely applied to the classification of medical images. In order to reliably classify SPECT bone images for the automated diagnosis of metastasis on which the SPECT imaging solely focuses, in this paper, we present several deep classifiers based on the deep networks. Specifically, original SPECT images are cropped to extract the thoracic region, followed by a geometric transformation that contributes to augment the original data. We then construct deep classifiers based on the widely used deep networks including VGG, ResNet and DenseNet by fine-tuning their parameters and structures or self-defining new network structures. Experiments on a set of real-world SPECT bone images show that the proposed classifiers perform well in identifying bone metastasis with SPECT imaging. It achieves 0.9807, 0.9900, 0.9830, 0.9890, 0.9802 and 0.9933 for accuracy, precision, recall, specificity, F-1 score and AUC, respectively, on the test samples from the augmented dataset without normalization. [ABSTRACT FROM AUTHOR]

Texture features are designed to quantitatively evaluate patterns of spatial distribution of image pixels for purposes of image analysis and interpretation. Unexplained variations in the texture patterns often lead to misinterpretation and undesirable consequences in medical image analysis. In this paper we explore the ability of machine learning (ML) methods to design a radiology test of Osteoarthritis (OA) at early stage when the number of patients' cases is small. In our experiments we use high-resolution X-ray images of knees in patients which were identified with Kellgren–Lawrence scores progressing from 1. The existing ML methods have provided a limited diagnostic accuracy, whilst the proposed Group Method of Data Handling strategy of Deep Learning has significantly extended the diagnostic test. The comparative experiments demonstrate that the proposed framework using the Zernike-based texture features has significantly improved the diagnostic accuracy on average by 11%. This allows us to conclude that the designed model for early diagnostic of OA will provide more accurate radiology tests, although new study is required when a large number of patients' cases will be available. [ABSTRACT FROM AUTHOR]