Using global feedback to induce learning of gist of abnormality in mammograms

Extraction of global structural regularities provides general 'gist' of our everyday visual environment as it does the gist of abnormality for medical experts reviewing medical images. We investigated whether naïve observers could learn this gist of medical abnormality. Fifteen participants completed nine adaptive training sessions viewing four categories of unilateral mammograms: normal, obvious-abnormal, subtle-abnormal, and global signals of abnormality (mammograms with no visible lesions but from breasts contralateral to or years prior to the development of cancer) and receiving only categorical feedback. Performance was tested pre-training, post-training, and after a week's retention on 200 mammograms viewed for 500 ms without feedback. Performance measured as d' was modulated by mammogram category, with the highest performance for mammograms with visible lesions. Post-training, twelve observed showed increased d' for all mammogram categories but a subset of nine, labelled learners also showed a positive correlation of d' across training. Critically, learners learned to detect abnormality in mammograms with only the global signals, but improvements were poorly retained. A state-of-the-art breast cancer classifier detected mammograms with lesions but struggled to detect cancer in mammograms with the global signal of abnormality. The gist of abnormality can be learned through perceptual/incidental learning in mammograms both with and without visible lesions, subject to individual differences. Poor retention suggests perceptual tuning to gist needs maintenance, converging with findings that radiologists' gist performance correlates with the number of cases reviewed per year, not years of experience. The human visual system can tune itself to complex global signals not easily captured by current deep neural networks.

Water demand in watershed forecasting using a hybrid model based on autoregressive moving average and deep neural networks

Increasing water demand is exacerbating water shortages in water-scarce regions (such as India, China, and Iran). Effective water demand forecasting is essential for the sustainable management of water supply systems in watersheds. To alleviate the contradiction between water supply and demand in the basin, with water demand for economic growth as the main target, a hybrid moving autoregressive and deep neural network model (ARMA-DNN) was developed in this study, and four commonly used statistical indicators (MAE, RMSE, MSE, and R²) were selected to evaluate the performance of the model. Finally, the validity and practicality of the model were verified by taking the Minjiang River basin in China as an example. The results show that (a) the model can predict future water demand more accurately under the conditions of actual water consumption changes, (b) the ideal agricultural production in the Minjiang River Basin is predicted to be reached 2.26 × 10⁹t in 2021, and (c) the highest industrial economic efficiency in Chengdu is 1.51 × 10⁹yuan, while water satisfaction reaches 102%. This means that effective water demand forecasting can alleviate water demand conflicts under climate change conditions to a certain extent. At the same time, watershed managers can develop different water allocation schemes based on the prediction results of the hybrid ARMA-DNN model.

HD2A-Net: A novel dual gated attention network using comprehensive hybrid dilated convolutions for medical image segmentation

The convolutional neural networks (CNNs) have been widely proposed in the medical image analysis tasks, especially in the image segmentations. In recent years, the encoder-decoder structures, such as the U-Net, were rendered. However, the multi-scale information transmission and effective modeling for long-range feature dependencies in these structures were not sufficiently considered. To improve the performance of the existing methods, we propose a novel hybrid dual dilated attention network (HD²A-Net) to conduct the lesion region segmentations. In the proposed network, we innovatively present the comprehensive hybrid dilated convolution (CHDC) module, which facilitates the transmission of the multi-scale information. Based on the CHDC module and the attention mechanisms, we design a novel dual dilated gated attention (DDGA) block to enhance the saliency of related regions from the multi-scale aspect. Besides, a dilated dense (DD) block is designed to expand the receptive fields. The ablation studies were performed to verify our proposed blocks. Besides, the interpretability of the HD²A-Net was analyzed through the visualization of the attention weight maps from the key blocks. Compared to the state-of-the-art methods including CA-Net, DeepLabV3+, and Attention U-Net, the HD²A-Net outperforms significantly, with the metrics of Dice, Average Symmetric Surface Distance (ASSD), and mean Intersection-over-Union (mIoU) reaching 93.16%, 93.63%, and 94.72%, 0.36 pix, 0.69 pix, and 0.52 pix, and 88.03%, 88.67%, and 90.33% on three publicly available medical image datasets: MAEDE-MAFTOUNI (COVID-19 CT), ISIC-2018 (Melanoma Dermoscopy), and Kvasir-SEG (Gastrointestinal Disease Polyp), respectively.

Symmetry-based regularization in deep breast cancer screening

Breast cancer is the most common and lethal form of cancer in women. Recent efforts have focused on developing accurate neural network-based computer-aided diagnosis systems for screening to help anticipate this disease. The ultimate goal is to reduce mortality and improve quality of life after treatment. Due to the difficulty in collecting and annotating data in this domain, data scarcity is - and will continue to be - a limiting factor. In this work, we present a unified view of different regularization methods that incorporate domain-known symmetries in the model. Three general strategies were followed: (i) data augmentation, (ii) invariance promotion in the loss function, and (iii) the use of equivariant architectures. Each of these strategies encodes different priors on the functions learned by the model and can be readily introduced in most settings. Empirically we show that the proposed symmetry-based regularization procedures improve generalization to unseen examples. This advantage is verified in different scenarios, datasets and model architectures. We hope that both the principle of symmetry-based regularization and the concrete methods presented can guide development towards more data-efficient methods for breast cancer screening as well as other medical imaging domains.

Applications of artificial neural networks in microorganism image analysis: a comprehensive review from conventional multilayer perceptron to popular convolutional neural network and potential visual transformer

Microorganisms are widely distributed in the human daily living environment. They play an essential role in environmental pollution control, disease prevention and treatment, and food and drug production. The analysis of microorganisms is essential for making full use of different microorganisms. The conventional analysis methods are laborious and time-consuming. Therefore, the automatic image analysis based on artificial neural networks is introduced to optimize it. However, the automatic microorganism image analysis faces many challenges, such as the requirement of a robust algorithm caused by various application occasions, insignificant features and easy under-segmentation caused by the image characteristic, and various analysis tasks. Therefore, we conduct this review to comprehensively discuss the characteristics of microorganism image analysis based on artificial neural networks. In this review, the background and motivation are introduced first. Then, the development of artificial neural networks and representative networks are presented. After that, the papers related to microorganism image analysis based on classical and deep neural networks are reviewed from the perspectives of different tasks. In the end, the methodology analysis and potential direction are discussed.

Extension-contraction transformation network for pancreas segmentation in abdominal CT scans

Accurate and automatic pancreas segmentation from abdominal computed tomography (CT) scans is crucial for the diagnosis and prognosis of pancreatic diseases. However, the pancreas accounts for a relatively small portion of the scan and presents high anatomical variability and low contrast, making traditional automated segmentation methods fail to generate satisfactory results. In this paper, we propose an extension-contraction transformation network (ECTN) and deploy it into a cascaded two-stage segmentation framework for accurate pancreas segmenting. This model can enhance the perception of 3D context by distinguishing and exploiting the extension and contraction transformation of the pancreas between slices. It consists of an encoder, a segmentation decoder, and an extension-contraction (EC) decoder. The EC decoder is responsible for predicting the inter-slice extension and contraction transformation of the pancreas by feeding the extension and contraction information generated by the segmentation decoder; meanwhile, its output is combined with the output of the segmentation decoder to reconstruct and refine the segmentation results. Quantitative evaluation is performed on NIH Pancreas Segmentation (Pancreas-CT) dataset using 4-fold cross-validation. We obtained average Precision of 86.59±6.14% , Recall of 85.11±5.96%, Dice similarity coefficient (DSC) of 85.58±3.98%. and Jaccard Index (JI) of 74.99±5.86%. The performance of our method outperforms several baseline and state-of-the-art methods.

Hierarchical attention network for multivariate time series long-term forecasting

Multivariate time series long-term forecasting has always been the subject of research in various fields such as economics, finance, and traffic. In recent years, attention-based recurrent neural networks (RNNs) have received attention due to their ability of reducing error accumulation. However, the existing attention-based RNNs fail to eliminate the negative influence of irrelevant factors on prediction, and ignore the conflict between exogenous factors and target factor. To tackle these problems, we propose a novel Hierarchical Attention Network (HANet) for multivariate time series long-term forecasting. At first, HANet designs a factor-aware attention network (FAN) and uses it as the first component of the encoder. FAN weakens the negative impact of irrelevant exogenous factors on predictions by assigning small weights to them. Then HANet proposes a multi-modal fusion network (MFN) as the second component of the encoder. MFN employs a specially designed multi-modal fusion gate to adaptively select how much information about the expression of current time come from target and exogenous factors. Experiments on two real-world datasets reveal that HANet not only outperforms state-of-the-art methods, but also provides interpretability for prediction.

Deep Neuro-Fuzzy System application trends, challenges, and future perspectives: a systematic survey

Deep neural networks (DNN) have remarkably progressed in applications involving large and complex datasets but have been criticized as a black-box. This downside has recently become a motivation for the research community to pursue the ideas of hybrid approaches, resulting in novel hybrid systems classified as deep neuro-fuzzy systems (DNFS). Studies regarding the implementation of DNFS have rapidly increased in the domains of computing, healthcare, transportation, and finance with high interpretability and reasonable accuracy. However, relatively few survey studies have been found in the literature to provide a comprehensive insight into this domain. Therefore, this study aims to perform a systematic review to evaluate the current progress, trends, arising issues, research gaps, challenges, and future scope related to DNFS studies. A study mapping process was prepared to guide a systematic search for publications related to DNFS published between 2015 and 2020 using five established scientific directories. As a result, a total of 105 studies were identified and critically analyzed to address research questions with the objectives: (i) to understand the concept of DNFS; (ii) to find out DNFS optimization methods; (iii) to visualize the intensity of work carried out in DNFS domain; and (iv) to highlight DNFS application subjects and domains. We believe that this study provides up-to-date guidance for future research in the DNFS domain, allowing for more effective advancement in techniques and processes. The analysis made in this review proves that DNFS-based research is actively growing with a substantial implementation and application scope in the future.

On the ability of machine learning methods to discover novel scaffolds

The recent advances in the application of machine learning to drug discovery have made it a 'hot topic' for research, with hundreds of academic groups and companies integrating machine learning into their drug discovery projects. Nevertheless, there remains great uncertainty regarding the most appropriate ways to evaluate the relative performance of these powerful methods against more traditional cheminformatics approaches, and many pitfalls remain for the unwary. In 2020, researchers at MIT (Stokes et al., Cell 180(4), 688-702, 2020) reported the discovery of a new compound with antibacterial activity, halicin, through the use of a neural network machine learning method. A robust ability to identify new active chemotypes through computational methods would be very useful. In this study, we have used the Stokes et al. dataset to compare the performance of this method to two other approaches, Mapping of Activity Through Dichotomic Scores (MADS) by Todeschini et al. (J Chemom 32(4):e2994, 2018) and Random Matrix Theory (RMT) by Lee et al. (Proc Natl Acad Sci 116(9):3373-3378, 2019). Our results demonstrate that all three methods are capable of predicting halicin as an active antibacterial compound, but that this result is dependent on the dataset composition, pre-processing and the molecular fingerprint used. We have further assessed overall performance as determined by several performance metrics. We also investigated the scaffold hopping potential of the methods by modifying the dataset by removal of the β-lactam and fluoroquinolone chemotypes. MADS and RMT are able to identify actives in the test set that contained these substructures. This ability arises because of high scoring fragments of the withheld chemotypes that are in common with other active antibiotic classes. Interestingly, MADS is relatively better compared to the other two methods based on general predictive performance.

Structural analysis of melanosomes in living mammalian cells using scanning electron-assisted dielectric microscopy with deep neural network

Melanins are the main pigments found in mammals. Their synthesis and transfer to keratinocytes have been widely investigated for many years. However, analysis has been mainly carried out using fixed rather than live cells. In this study, we have analysed the melanosomes in living mammalian cells using newly developed scanning electron-assisted dielectric microscopy (SE-ADM). The melanosomes in human melanoma MNT-1 cells were observed as clear black particles in SE-ADM. The main structure of melanosomes was toroidal while that of normal melanocytes was ellipsoidal. In tyrosinase knockout MNT-1 cells, not only the black particles in the SE-ADM images but also the Raman shift of melanin peaks completely disappeared suggesting that the black particles were really melanosomes. We developed a deep neural network (DNN) system to automatically detect melanosomes in cells and analysed their diameter and roundness. In terms of melanosome morphology, the diameter of melanosomes in melanoma cells did not change while that in normal melanocytes increased during culture. The established DNN analysis system with SE-ADM can be used for other particles, e.g. exosomes, lysosomes, and other biological particles.

LWSNet - a novel deep-learning architecture to segregate Covid-19 and pneumonia from x-ray imagery

Automatic detection of lung diseases using AI-based tools became very much necessary to handle the huge number of cases occurring across the globe and support the doctors. This paper proposed a novel deep learning architecture named LWSNet (Light Weight Stacking Network) to separate Covid-19, cold pneumonia, and normal chest x-ray images. This framework is based on single, double, triple, and quadruple stack mechanisms to address the above-mentioned tri-class problem. In this framework, a truncated version of standard deep learning models and a lightweight CNN model was considered to conviniently deploy in resource-constraint devices. An evaluation was conducted on three publicly available datasets alongwith their combination. We received 97.28%, 96.50%, 97.41%, and 98.54% highest classification accuracies using quadruple stack. On further investigation, we found, using LWSNet, the average accuracy got improved from individual model to quadruple model by 2.31%, 2.55%, 2.88%, and 2.26% on four respective datasets.

LWSNet - a novel deep-learning architecture to segregate Covid-19 and pneumonia from x-ray imagery

Automatic detection of lung diseases using AI-based tools became very much necessary to handle the huge number of cases occurring across the globe and support the doctors. This paper proposed a novel deep learning architecture named LWSNet (Light Weight Stacking Network) to separate Covid-19, cold pneumonia, and normal chest x-ray images. This framework is based on single, double, triple, and quadruple stack mechanisms to address the above-mentioned tri-class problem. In this framework, a truncated version of standard deep learning models and a lightweight CNN model was considered to conviniently deploy in resource-constraint devices. An evaluation was conducted on three publicly available datasets alongwith their combination. We received 97.28%, 96.50%, 97.41%, and 98.54% highest classification accuracies using quadruple stack. On further investigation, we found, using LWSNet, the average accuracy got improved from individual model to quadruple model by 2.31%, 2.55%, 2.88%, and 2.26% on four respective datasets.

Pathological Voice Detection and Classification Based on Multimodal Transmission Network

OBJECTIVES

Describing pronunciation features from multiple perspectives can help doctors accurately diagnose the pathological type of a patient's voice. According to the two modal information of sound signal and electroglottography (EGG) signal, this paper proposes a pathological voice detection and classification algorithm based on multimodal transmission network.

METHODS

Firstly, we used the short-time Fourier transform (STFT) to map the features of the two signals, and designed the Mel filter to obtain the Mel spectogram. Then, the constructed multimodal transmission network extracted features from Mel spectogram and applied Multimodal Transfer Module (MMTM) module. Finally, the fusion layer can integrate multimodal information, and the full connection layer diagnoses and classifies voice pathology according to the fused features.

RESULTS

The experiment was based on 1179 subjects in Saarbrücken voice database (SVD), and the average accuracy, recall, specificity and F1 score of pathological voice classification reached 98.02%, 98.23%, 97.82% and 97.95% respectively. Compared with other algorithms, the classification accuracy is significantly improved.

CONCLUSIONS

The proposed model can integrate multiple modal information to obtain more comprehensive and stable voice features and improve the accuracy of pathological voice classification. Future research will further explore in reducing the time-consuming and complexity of the model.

Deep neural network prediction of modified stepped double-slope solar still with a cotton wick and cobalt oxide nanofluid

This research work intends to enhance the stepped double-slope solar still performance through an experimental assessment of combining linen wicks and cobalt oxide nanoparticles to the stepped double-slope solar still to improve the water evaporation and water production. The results illustrated that the cotton wicks and cobalt oxide (Co₃O₄) nanofluid with 1wt% increased the hourly freshwater output (HP) and instantaneous thermal efficiency (ITE). On the other hand, this study compares four machine learning methods to create a prediction model of tubular solar still performance. The methods developed and compared are support vector regressor (SVR), decision tree regressor, neural network, and deep neural network based on experimental data. This problem is a multi-output prediction problem which is HP and ITE. The prediction performance for the SVR was the lowest, with 70 (ml/m² h) mean absolute error (MAE) for HP and 4.5% for ITE. Decision tree regressor has a better prediction for HP with 33 (ml/m² h) MAE and almost the same MAE for ITE. Neural network has a better prediction for HP with 28 (ml/m² h) MAE and a bit worse prediction for ITE with 5.7%. The best model used the deep neural network with 1.94 (ml/m² h) MAE for HP and 0.67% MAE for ITE.

Adaptive beamforming based on minimum variance (ABF-MV) using deep neural network for ultrafast ultrasound imaging

Ultrafast ultrasound imaging can achieve high frame rate by emitting planewave (PW). However, the image quality is drastically degraded in comparison with traditional scanline focused imaging. Using adaptive beamforming techniques can improve image quality at cost of real-time performance. In this work, an adaptive beamforming based on minimum variance (ABF-MV) with deep neural network (DNN) is proposed to improve the image performance and to speed up the beamforming process of ultrafast ultrasound imaging. In particular, a DNN, with a combination architecture of fully-connected network (FCN) and convolutional autoencoder (CAE), is trained with channel radio-frequency (RF) data as input while minimum variance (MV) beamformed data as ground truth. Conventional delay-and-sum (DAS) beamformer and MV beamformer are utilized for comparison to evaluate the performance of the proposed method with simulations, phantom experiments, and in-vivo experiments. The results show that the proposed method can achieve superior resolution and contrast performance, compared with DAS. Moreover, it is remarkable that both in theoretical analysis and implementation, our proposed method has comparable image quality, lower computational complexity, and faster frame rate, compared with MV. In conclusion, the proposed method has the potential to be deployed in ultrafast ultrasound imaging systems in terms of imaging performance and processing time.

Perturbation of deep autoencoder weights for model compression and classification of tabular data

Fully connected deep neural networks (DNN) often include redundant weights leading to overfitting and high memory requirements. Additionally, in tabular data classification, DNNs are challenged by the often superior performance of traditional machine learning models. This paper proposes periodic perturbations (prune and regrow) of DNN weights, especially at the self-supervised pre-training stage of deep autoencoders. The proposed weight perturbation strategy outperforms dropout learning or weight regularization (L1 or L2) for four out of six tabular data sets in downstream classification tasks. Unlike dropout learning, the proposed weight perturbation routine additionally achieves 15% to 40% sparsity across six tabular data sets, resulting in compressed pretrained models. The proposed pretrained model compression improves the accuracy of downstream classification, unlike traditional weight pruning methods that trade off performance for model compression. Our experiments reveal that a pretrained deep autoencoder with weight perturbation can outperform traditional machine learning in tabular data classification, whereas baseline fully-connected DNNs yield the worst classification accuracy. However, traditional machine learning models are superior to any deep model when a tabular data set contains uncorrelated variables. Therefore, the performance of deep models with tabular data is contingent on the types and statistics of constituent variables.

Combining novel feature selection strategy and hyperspectral vegetation indices to predict crop yield

BACKGROUND

Wheat is an important food crop globally, and timely prediction of wheat yield in breeding efforts can improve selection efficiency. Traditional yield prediction method based on secondary traits is time-consuming, costly, and destructive. It is urgent to develop innovative methods to improve selection efficiency and accelerate genetic gains in the breeding cycle.

RESULTS

Crop yield prediction using remote sensing has gained popularity in recent years. This paper proposed a novel ensemble feature selection (EFS) method to improve yield prediction from hyperspectral data. For this, 207 wheat cultivars and breeding lines were grown under full and limited irrigation treatments respectively, and their canopy hyperspectral reflectance was measured at the flowering, early grain filling (EGF), mid grain filling (MGF), and late grain filling (LGF) stages. Then, 115 vegetation indices were extracted from the hyperspectral reflectance and combined with four feature selection methods, i.e., mean decrease impurity (MDI), Boruta, FeaLect, and RReliefF to train deep neural network (DNN) models for yield prediction. Next, a learning framework was developed by combining the predicted values of the selected and the full features using multiple linear regression (MLR). The results show that the selected features contributed to higher yield prediction accuracy than the full features, and the MDI method performed well across growth stages, with a mean R² ranging from 0.634 to 0.666 (mean RMSE = 0.926-0.967 t ha^-1). Also, the proposed EFS method outperformed all the individual feature selection methods across growth stages, with a mean R² ranging from 0.648 to 0.679 (mean RMSE = 0.911-0.950 t ha^-1).

CONCLUSIONS

The proposed EFS method can improve grain yield prediction from hyperspectral data and can be used to assist wheat breeders in earlier decision-making.

A self-supervised COVID-19 CT recognition system with multiple regularizations

The diagnosis of Coronavirus Disease 2019 (COVID-19) exploiting machine learning algorithms based on chest computed tomography (CT) images has become an important technology. Though many excellent computer-aided methods leveraging CT images have been designed, they do not possess sufficiently high recognition accuracy. Besides, these methods entail vast amounts of training data, which might be difficult to be satisfied in some real-world applications. To address these two issues, this paper proposes a novel COVID-19 recognition system based on CT images, which has high recognition accuracy, while only requiring a small amount of training data. Specifically, the system possesses the following three improvements: 1) Data: a novel redesigned BCELoss that incorporates Label Smoothing, Focal Loss, and Label Weighting Regularization (LSFLLW-R) technique for optimizing the solution space and preventing overfitting, 2) Model: a backbone network processed by two-phase contrastive self-supervised learning for classifying multiple labels, and 3) Method: a decision-fusing ensemble learning method for getting a more stable system, with balanced metric values. Our proposed system is evaluated on the small-scale expanded COVID-CT dataset, achieving an accuracy of 94.3%, a precision of 94.1%, a recall (sensitivity) of 93.4%, an F1-score of 94.7%, and an Area Under the Curve (AUC) of 98.9%, for COVID-19 diagnosis, respectively. These experimental results verify that our system can not only identify pathological locations effectively, but also achieve better performance in terms of accuracy, generalizability, and stability, compared with several other state-of-the-art COVID-19 diagnosis methods.

MCA-net: A multi-task channel attention network for Myocardial infarction detection and location using 12-lead ECGs

PROBLEM

Myocardial infarction (MI) is a classic cardiovascular disease (CVD) that requires prompt diagnosis. However, due to the complexity of its pathology, it is difficult for cardiologists to make an accurate diagnosis in a short period.

AIM

In the clinical, MI can be detected and located by the morphological changes on a 12-lead electrocardiogram (ECG). Therefore, we need to develop an automatic, high-performance, and easily scalable algorithm for MI detection and location using 12-lead ECGs to effectively reduce the burden on cardiologists.

METHODS

This paper proposes a multi-task channel attention network (MCA-net) for MI detection and location using 12-lead ECGs. It employs a channel attention network based on a residual structure to efficiently capture and integrate features from different leads. On top of this, a multi-task framework is used to additionally introduce the shared and complementary information between MI detection and location tasks to further enhance the model performance.

RESULTS

Our method is evaluated on two datasets (The PTB and PTBXL datasets). It achieved more than 90% accuracy for MI detection task on both datasets. For MI location tasks, we achieved 68.90% and 49.18% accuracy on the PTB dataset, respectively. And on the PTBXL dataset, we achieved more than 80% accuracy.

CONCLUSION

Numerous comparison experiments demonstrate that MCA-net outperforms the state-of-the-art methods and has a better generalization. Therefore, it can effectively assist cardiologists to detect and locate MI and has important implications for the early diagnosis of MI and patient prognosis.

Defending against adversarial attacks on Covid-19 classifier: A denoiser-based approach

Covid-19 has posed a serious threat to the existence of the human race. Early detection of the virus is vital to effectively containing the virus and treating the patients. Profound testing methods such as the Real-time reverse transcription-polymerase chain reaction (RT-PCR) test and the Rapid Antigen Test (RAT) are being used for detection, but they have their limitations. The need for early detection has led researchers to explore other testing techniques. Deep Neural Network (DNN) models have shown high potential in medical image classification and various models have been built by researchers which exhibit high accuracy for the task of Covid-19 detection using chest X-ray images. However, it is proven that DNNs are inherently susceptible to adversarial inputs, which can compromise the results of the models. In this paper, the adversarial robustness of such Covid-19 classifiers is evaluated by performing common adversarial attacks, which include the Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD). Using these attacks, it is found that the accuracy of the models for Covid-19 samples decreases drastically. In the medical domain, adversarial training is the most widely explored technique to defend against adversarial attacks. However, using this technique requires replacing the original model and retraining it by including adversarial samples. Another defensive technique, High-Level Representation Guided Denoiser (HGD), overcomes this limitation by employing an adversarial filter which is also transferable across models. Moreover, the HGD architecture, being suitable for high-resolution images, makes it a good candidate for medical image applications. In this paper, the HGD architecture has been evaluated as a potential defensive technique for the task of medical image analysis. Experiments carried out show an increased accuracy of up to 82% in the white box setting. However, in the black box setting, the defense completely fails to defend against adversarial samples.

•

The current methods of testing for the virus are RT-PCR and RAT. These test results may take up to 24 h. Recent studies and research have shown that lung images show the presence or damage caused by the virus using machine learning techniques.

•

Adversarial Attack is a major security threat in the domain of machine learning. Adversarial training is the most widely explored technique to defend against adversarial attacks.

•

High-level representation Guided Denoiser (HGD) architecture, another defensive technique, being suitable for high-resolution images, makes it a good candidate for medical image applications.

•

HGD architecture has been evaluated as a potential defensive technique for the task of medical image analysis with a new loss function.

•

In a White box scenario considerable increase in accuracy is seen. However, in the black box setting, the defense fails to defend against adversarial samples.

A fingerprints based molecular property prediction method using the BERT model

Molecular property prediction (MPP) is vital in drug discovery and drug reposition. Deep learning-based MPP models capture molecular property-related features from various molecule representations. In this paper, we propose a molecule sequence embedding and prediction model facing with MPP task. We pre-trained a bi-directional encoder representations from Transformers (BERT) encoder to obtain the semantic representation of compound fingerprints, called Fingerprints-BERT (FP-BERT), in a self-supervised learning manner. Then, the encoded molecular representation by the FP-BERT is input to the convolutional neural network (CNN) to extract higher-level abstract features, and the predicted properties of the molecule are finally obtained through fully connected layer for distinct classification or regression MPP tasks. Comparison with the baselines shows that the proposed model achieves high prediction performance on all of the classification tasks and regression tasks.

Species level mapping of a seagrass bed using an unmanned aerial vehicle and deep learning technique

Background

Seagrass beds are essential habitats in coastal ecosystems, providing valuable ecosystem services, but are threatened by various climate change and human activities. Seagrass monitoring by remote sensing have been conducted over past decades using satellite and aerial images, which have low resolution to analyze changes in the composition of different seagrass species in the meadows. Recently, unmanned aerial vehicles (UAVs) have allowed us to obtain much higher resolution images, which is promising in observing fine-scale changes in seagrass species composition. Furthermore, image processing techniques based on deep learning can be applied to the discrimination of seagrass species that were difficult based only on color variation. In this study, we conducted mapping of a multispecific seagrass bed in Saroma-ko Lagoon, Hokkaido, Japan, and compared the accuracy of the three discrimination methods of seagrass bed areas and species composition, i.e., pixel-based classification, object-based classification, and the application of deep neural network.

Methods

We set five benthic classes, two seagrass species (Zostera marina and Z. japonica), brown and green macroalgae, and no vegetation for creating a benthic cover map. High-resolution images by UAV photography enabled us to produce a map at fine scales (<1 cm resolution).

Results

The application of a deep neural network successfully classified the two seagrass species. The accuracy of seagrass bed classification was the highest (82%) when the deep neural network was applied.

Conclusion

Our results highlighted that a combination of UAV mapping and deep learning could help monitor the spatial extent of seagrass beds and classify their species composition at very fine scales.

DNN based reliability evaluation for telemedicine data

Telemedicine data are measured directly by untrained patients, which may cause problems in data reliability. Many deep learning-based studies have been conducted to improve the quality of measurement data. However, they could not provide an accurate basis for judgment. Therefore, this study proposed a deep neural network filter-based reliability evaluation system that could present an accurate basis for judgment and verified its reliability by evaluating photoplethysmography signal and change in data quality according to judgment criteria through clinical trials. In the results, the deviation of 3% or more when the oxygen saturation was judged as normal according to each criterion was 0.3% and 0.82% for criteria 1 and 2, respectively, which was very low compared to the abnormal judgment (3.86%). The deviation of diastolic blood pressure (≥ 10 mmHg) according to criterion 3 was reduced by about 4% in the normal judgment compared to the abnormal. In addition, when multiple judgment conditions were satisfied, abnormal data were better discriminated than when only one criterion was satisfied. Therefore, the basis for judging abnormal data can be presented with the system proposed in this study, and the quality of telemedicine data can be improved according to the judgment result.

Detection of Common Cold from Speech Signals using Deep Neural Network

This paper presents a deep learning-based analysis and classification of cold speech observed when a person is diagnosed with the common cold. The common cold is a viral infectious disease that affects the throat and the nose. Since speech is produced by the vocal tract after linear filtering of excitation source information, during a common cold, its attributes are impacted by the throat and the nose. The proposed study attempts to develop a deep learning-based classification model that can accurately predict whether a person has a cold or not based on their speech. The common cold-related information is captured using Mel-frequency cepstral coefficients (MFCC) and linear predictive coding (LPC) from the speech signal. The data imbalance is handled using the sampling strategy, SMOTE-Tomek links. Then, utilizing MFCC and LPC features, a deep learning-based model is trained and then used to categorize cold speech. The performance of a deep learning-based method is compared to logistic regression, random forest, and gradient boosted tree classifiers. The proposed model is less complex and uses a smaller feature set while giving comparable results to other state-of-the-art methods. The proposed method gives an UAR of 67.71 % , higher than the benchmark OpenSMILE SVM result of 64 % . The study's success will yield a noninvasive method for cold detection, which can further be extended to detect other speech-affecting pathologies.

Application of Deep Learning on Single-cell RNA Sequencing Data Analysis: A Review

Single-cell RNA sequencing (scRNA-seq) has become a routinely used technique to quantify the gene expression profile of thousands of single cells simultaneously. Analysis of scRNA-seq data plays an important role in the study of cell states and phenotypes, and has helped elucidate biological processes, such as those occurring during the development of complex organisms, and improved our understanding of disease states, such as cancer, diabetes, and coronavirus disease 2019 (COVID-19). Deep learning, a recent advance of artificial intelligence that has been used to address many problems involving large datasets, has also emerged as a promising tool for scRNA-seq data analysis, as it has a capacity to extract informative and compact features from noisy, heterogeneous, and high-dimensional scRNA-seq data to improve downstream analysis. The present review aims at surveying recently developed deep learning techniques in scRNA-seq data analysis, identifying key steps within the scRNA-seq data analysis pipeline that have been advanced by deep learning, and explaining the benefits of deep learning over more conventional analytic tools. Finally, we summarize the challenges in current deep learning approaches faced within scRNA-seq data and discuss potential directions for improvements in deep learning algorithms for scRNA-seq data analysis.