Periapical Lesions in Panoramic Radiography and CBCT Imaging-Assessment of AI's Diagnostic Accuracy

Background/Objectives: Periapical lesions (PLs) are frequently detected in dental radiology. Accurate diagnosis of these lesions is essential for proper treatment planning. Imaging techniques such as orthopantomogram (OPG) and cone-beam CT (CBCT) imaging are used to identify PLs. The aim of this study was to assess the diagnostic accuracy of artificial intelligence (AI) software Diagnocat for PL detection in OPG and CBCT images. Methods: The study included 49 patients, totaling 1223 teeth. Both OPG and CBCT images were analyzed by AI software and by three experienced clinicians. All the images were obtained in one patient cohort, and findings were compared to the consensus of human readers using CBCT. The AI's diagnostic accuracy was compared to a reference method, calculating sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), and F1 score. Results: The AI's sensitivity for OPG images was 33.33% with an F1 score of 32.73%. For CBCT images, the AI's sensitivity was 77.78% with an F1 score of 84.00%. The AI's specificity was over 98% for both OPG and CBCT images. Conclusions: The AI demonstrated high sensitivity and high specificity in detecting PLs in CBCT images but lower sensitivity in OPG images.

[A Review on Automatic Detection Algorithm for Patient-Ventilator Asynchrony during Mechanical Ventilation]

This study summarizes the application of automatic recognition technologies for patient-ventilator asynchrony (PVA) during mechanical ventilation. In the early stages, the method of setting rules and thresholds relied on manual interpretation of ventilator parameters and waveforms. While these methods were intuitive and easy to operate, they were relatively sensitive in threshold setting and rule selection and could not adapt well to minor changes in patient status. Subsequently, machine learning and deep learning technologies began to emerge and develop. These technologies automatically extract and learn data characteristics through algorithms, making PVA detection more robust and universal. Among them, logistic regression, support vector machines, random forest, hidden Markov models, convolutional autoencoders, long short-term memory networks, one-dimensional convolutional neural networks, etc., have all been successfully used for PVA recognition. Despite the significant advancements in feature extraction through deep learning methods, their demand for labelled data is high, potentially consuming significant medical resources. Therefore, the combination of reinforcement learning and self-supervised learning may be a viable solution. In addition, most algorithm validations are based on a single dataset, so the need for cross-dataset validation in the future will be an important and challenging direction for development.

An approach to the diagnosis of lumbar disc herniation using deep learning models

Background: In magnetic resonance imaging (MRI), lumbar disc herniation (LDH) detection is challenging due to the various shapes, sizes, angles, and regions associated with bulges, protrusions, extrusions, and sequestrations. Lumbar abnormalities in MRI can be detected automatically by using deep learning methods. As deep learning models gain recognition, they may assist in diagnosing LDH with MRI images and provide initial interpretation in clinical settings. YOU ONLY LOOK ONCE (YOLO) model series are often used to train deep learning algorithms for real-time biomedical image detection and prediction. This study aims to confirm which YOLO models (YOLOv5, YOLOv6, and YOLOv7) perform well in detecting LDH in different regions of the lumbar intervertebral disc. Materials and methods: The methodology involves several steps, including converting DICOM images to JPEG, reviewing and selecting MRI slices for labeling and augmentation using ROBOFLOW, and constructing YOLOv5x, YOLOv6, and YOLOv7 models based on the dataset. The training dataset was combined with the radiologist's labeling and annotation, and then the deep learning models were trained using the training/validation dataset. Results: Our result showed that the 550-dataset with augmentation (AUG) or without augmentation (non-AUG) in YOLOv5x generates satisfactory training performance in LDH detection. The AUG dataset overall performance provides slightly higher accuracy than the non-AUG. YOLOv5x showed the highest performance with 89.30% mAP compared to YOLOv6, and YOLOv7. Also, YOLOv5x in non-AUG dataset showed the balance LDH region detections in L2-L3, L3-L4, L4-L5, and L5-S1 with above 90%. And this illustrates the competitiveness of using non-AUG dataset to detect LDH. Conclusion: Using YOLOv5x and the 550 augmented dataset, LDH can be detected with promising both in non-AUG and AUG dataset. By utilizing the most appropriate YOLO model, clinicians have a greater chance of diagnosing LDH early and preventing adverse effects for their patients.

Deep Learning-Based Precision Analysis for Acrosome Reaction by Modification of Plasma Membrane in Boar Sperm

The analysis of AR is widely used to detect loss of acrosome in sperm, but the subjective decisions of experts affect the accuracy of the examination. Therefore, we develop an ARCS for objectivity and consistency of analysis using convolutional neural networks (CNNs) trained with various magnification images. Our models were trained on 215 microscopic images at 400× and 438 images at 1000× magnification using the ResNet 50 and Inception-ResNet v2 architectures. These models distinctly recognized micro-changes in the PM of AR sperms. Moreover, the Inception-ResNet v2-based ARCS achieved a mean average precision of over 97%. Our system's calculation of the AR ratio on the test dataset produced results similar to the work of the three experts and could do so more quickly. Our model streamlines sperm detection and AR status determination using a CNN-based approach, replacing laborious tasks and expert assessments. The ARCS offers consistent AR sperm detection, reduced human error, and decreased working time. In conclusion, our study suggests the feasibility and benefits of using a sperm diagnosis artificial intelligence assistance system in routine practice scenarios.

Utilizing CNN-LSTM techniques for the enhancement of medical systems

COVID-19 is one of the most chronic and serious infections of recent years due to its worldwide spread. Determining who was genuinely affected when the disease spreads more widely is challenging. More than 60% of affected individuals report having a dry cough. In many recent studies, diagnostic models were developed using coughing and other breathing sounds. With the development of technology, body sounds are now collected using digital techniques for respiratory and cardiovascular tests. Early research on identifying COVID-19 utilizing speech and diagnosing signs yielded encouraging findings. The gathering of extensive, multi-group, airborne acoustical sound data is used in the developed framework to conduct an efficient assessment to test for COVID-19. An effective classification model is created to assess COVID-19 utilizing deep learning methods. The MIT-Covid-19 dataset is used as the input, and the Weiner filter is used for pre-processing. Following feature extraction done by Mel-frequency cepstral coefficients, the classification is performed using the CNN-LSTM approach. The study compared the performance of the developed framework with other techniques such as CNN, GRU, and LSTM. Study results revealed that CNN-LSTM outperformed other existing approaches by 97.7%.

Alpha2 Adrenergic Modulation of Spike-Wave Epilepsy: Experimental Study of Pro-Epileptic and Sedative Effects of Dexmedetomidine

In the present report, we evaluated adrenergic mechanisms of generalized spike-wave epileptic discharges (SWDs), which are the encephalographic hallmarks of idiopathic generalized epilepsies. SWDs link to a hyper-synchronization in the thalamocortical neuronal activity. We unclosed some alpha2-adrenergic mechanisms of sedation and provocation of SWDs in rats with spontaneous spike-wave epilepsy (WAG/Rij and Wistar) and in control non-epileptic rats (NEW) of both sexes. Dexmedetomidine (Dex) was a highly selective alpha-2 agonist (0.003-0.049 mg/kg, i.p.). Injections of Dex did not elicit de novo SWDs in non-epileptic rats. Dex can be used to disclose the latent form of spike-wave epilepsy. Subjects with long-lasting SWDs at baseline were at high risk of absence status after activation of alpha2- adrenergic receptors. We create the concept of alpha1- and alpha2-ARs regulation of SWDs via modulation of thalamocortical network activity. Dex induced the specific abnormal state favorable for SWDs-"alpha2 wakefulness". Dex is regularly used in clinical practice. EEG examination in patients using low doses of Dex might help to diagnose the latent forms of absence epilepsy (or pathology of cortico-thalamo-cortical circuitry).

Diagnostic Test Accuracy of Artificial Intelligence in Detecting Periapical Periodontitis on Two-Dimensional Radiographs: A Retrospective Study and Literature Review

This study aims to evaluate the diagnostic accuracy of artificial intelligence in detecting apical pathosis on periapical radiographs. A total of twenty anonymized periapical radiographs were retrieved from the database of Poznan University of Medical Sciences. These radiographs displayed a sequence of 60 visible teeth. The evaluation of the radiographs was conducted using two methods (manual and automatic), and the results obtained from each technique were afterward compared. For the ground-truth method, one oral and maxillofacial radiology expert with more than ten years of experience and one trainee in oral and maxillofacial radiology evaluated the radiographs by classifying teeth as healthy and unhealthy. A tooth was considered unhealthy when periapical periodontitis related to this tooth had been detected on the radiograph. At the same time, a tooth was classified as healthy when no periapical radiolucency was detected on the periapical radiographs. Then, the same radiographs were evaluated by artificial intelligence, Diagnocat (Diagnocat Ltd., San Francisco, CA, USA). Diagnocat (Diagnocat Ltd., San Francisco, CA, USA) correctly identified periapical lesions on periapical radiographs with a sensitivity of 92.30% and identified healthy teeth with a specificity of 97.87%. The recorded accuracy and F1 score were 96.66% and 0.92, respectively. The artificial intelligence algorithm misdiagnosed one unhealthy tooth (false negative) and over-diagnosed one healthy tooth (false positive) compared to the ground-truth results. Diagnocat (Diagnocat Ltd., San Francisco, CA, USA) showed an optimum accuracy for detecting periapical periodontitis on periapical radiographs. However, more research is needed to assess the diagnostic accuracy of artificial intelligence-based algorithms in dentistry.

MyI-Net: Fully Automatic Detection and Quantification of Myocardial Infarction from Cardiovascular MRI Images

Myocardial infarction (MI) occurs when an artery supplying blood to the heart is abruptly occluded. The "gold standard" method for imaging MI is cardiovascular magnetic resonance imaging (MRI) with intravenously administered gadolinium-based contrast (with damaged areas apparent as late gadolinium enhancement [LGE]). However, no "gold standard" fully automated method for the quantification of MI exists. In this work, we propose an end-to-end fully automatic system (MyI-Net) for the detection and quantification of MI in MRI images. It has the potential to reduce uncertainty due to technical variability across labs and the inherent problems of data and labels. Our system consists of four processing stages designed to maintain the flow of information across scales. First, features from raw MRI images are generated using feature extractors built on ResNet and MoblieNet architectures. This is followed by atrous spatial pyramid pooling (ASPP) to produce spatial information at different scales to preserve more image context. High-level features from ASPP and initial low-level features are concatenated at the third stage and then passed to the fourth stage where spatial information is recovered via up-sampling to produce final image segmentation output into: (i) background, (ii) heart muscle, (iii) blood and (iv) LGE areas. Our experiments show that the model named MI-ResNet50-AC provides the best global accuracy (97.38%), mean accuracy (86.01%), weighted intersection over union (IoU) of 96.47%, and bfscore of 64.46% for the global segmentation. However, in detecting only LGE tissue, a smaller model, MI-ResNet18-AC, exhibited higher accuracy (74.41%) than MI-ResNet50-AC (64.29%). New models were compared with state-of-the-art models and manual quantification. Our models demonstrated favorable performance in global segmentation and LGE detection relative to the state-of-the-art, including a four-fold better performance in matching LGE pixels to contours produced by clinicians.

Sleep Apnea Detection Using Wavelet Scattering Transformation and Random Forest Classifier

Obstructive Sleep Apnea (OSA) is a common sleep-breathing disorder that highly reduces the quality of human life. The most powerful method for the detection and classification of sleep apnea is the Polysomnogram. However, this method is time-consuming and cost-inefficient. Therefore, several methods focus on using electrocardiogram (ECG) signals to detect sleep apnea. This paper proposed a novel automated approach to detect and classify apneic events from single-lead ECG signals. Wavelet Scattering Transformation (WST) was applied to the ECG signals to decompose the signal into smaller segments. Then, a set of features, including higher-order statistics and entropy-based features, was extracted from the WST coefficients to formulate a search space. The obtained features were fed to a random forest classifier to classify the ECG segments. The experiment was validated using the 10-fold and hold-out cross-validation methods, which resulted in an accuracy of 91.65% and 90.35%, respectively. The findings were compared with different classifiers to show the significance of the proposed approach. The proposed approach achieved better performance measures than most of the existing methodologies.

Automatic Thinning Detection through Image Segmentation Using Equivalent Array-Type Lamp-Based Lock-in Thermography

Among the non-destructive testing (NDT) techniques, infrared thermography (IRT) is an attractive and highly reliable technology that can measure the thermal response of a wide area in real-time. In this study, thinning defects in S275 specimens were detected using lock-in thermography (LIT). After acquiring phase and amplitude images using four-point signal processing, the optimal excitation frequency was calculated. After segmentation was performed on each defect area, binarization was performed using the Otsu algorithm. For automated detection, the boundary tracking algorithm was used. The number of pixels was calculated and the detectability using RMSE was evaluated. Clarification of defective objects using image segmentation detectability evaluation technique using RMSE was presented.

Automatic Identification of Involuntary Muscle Activity in Subacute Patients with Upper Motor Neuron Lesion at Rest-A Validation Study

Sustained involuntary muscle activity (IMA) is a highly disabling phenomenon that arises in the acute phase of an upper motor neuron lesion (UMNL). Wearable probes for long-lasting surface EMG (sEMG) recordings have been recently recommended to detect IMA insurgence and to quantify its evolution over time, in conjunction with a complex algorithm for IMA automatic identification and classification. In this study, we computed sensitivity (Se), specificity (Sp), and overall accuracy (Acc) of this algorithm by comparing it with the classification provided by two expert assessors. Based on sample size estimation, 6020 10 s-long sEMG epochs were classified by both the algorithm and the assessors. Epochs were randomly extracted from long-lasting sEMG signals collected in-field from 14 biceps brachii (BB) muscles of 10 patients (5F, age range 50-71 years) hospitalized in an acute rehabilitation ward following a stroke or a post-anoxic coma and complete upper limb (UL) paralysis. Among the 14 BB muscles assessed, Se was 85.6% (83.6-87.4%); Sp was 89.7% (88.6-90.7%), and overall Acc was 88.5% (87.6-89.4%) and ranged between 78.6% and 98.7%. The presence of IMA was detected correctly in all patients. These results support the algorithm's use for in-field IMA assessment based on data acquired with wearable sensors. The assessment and monitoring of IMA in acute and subacute patients with UMNL could improve the quality of care needed by triggering early treatments to lessen long-term complications.

Automatic detection of Gibbs artefact in MR images with transfer learning approach

BACKGROUND

Quality control of magnetic resonance imaging includes image validation, which covers also artefact detection. The daily manual review of magnetic resonance images for possible artefacts can be time-consuming, so automated methods for computer-assisted quality assessment of magnetic resonance imaging need to be developed.

OBJECTIVE

The aim of this study was to develop automatic detection of Gibbs artefacts in magnetic resonance imaging using a deep learning method called transfer learning, and to demonstrate the potential of this approach for the development of an automatic quality control tool for the detection of such artefacts in magnetic resonance imaging.

METHODS

The magnetic resonance image dataset of the scanned phantom for quality assurance was created using a turbo spin-echo pulse sequence in the transverse plane. Images were created to include Gibbs artefacts of varying intensities. The images were annotated by two independent reviewers. The annotated dataset was used to develop a method for Gibbs artefact detection using the transfer learning approach. The VGG-16, VGG-19, and ResNet-152 convolutional neural networks were used as pre-trained networks for transfer learning and compared using 5-fold cross-validation.

RESULTS

All accuracies of the classification models were above 97%, while the AUC values were all above 0.99, confirming the high quality of the constructed models.

CONCLUSION

We show that transfer learning can be successfully used to detect Gibbs artefacts on magnetic resonance images. The main advantages of transfer learning are that it can be applied on small training datasets, the procedures to build the models are not so complicated, and they do not require much computational power. This shows the potential of transfer learning for the more general task of detecting artefacts in magnetic resonance images of patients, which consequently can improve and speed up the process of quality assessment in medical imaging practice.

Detection of prohibited and restricted object X-ray images based on Hi color space segmentation

BACKGROUND

X-ray imaging plays an important role in security inspection. However, the objects are complex, which makes it difficult to automatically detect prohibited and restricted objects.

OBJECTIVE

This study aims to develop and test a detection method based on a new image segmentation scheme to solve the problem of detecting prohibited and restricted objects from pseudo-color X-ray images with complex backgrounds.

METHODS

The internal mechanism of the influence of different color spaces on image segmentation effect is explored, and the color space component Hi is studied. Furthermore, the mechanism of the new Hi component and the influence law of its adjustable coefficient are revealed. Additionally, a detection method based on Hi color space segmentation for pseudo-color X-ray images is proposed. The segmentation and detection methods are then tested on actual X-ray images.

RESULTS

The results show that hue has the greatest influence on image segmentation effect of the pseudo-color X-ray images. For different pseudo-color X-ray images with complex backgrounds, applying the proposed new Hi color space segmentation method achieves overall accuracy of 0.974 and 1.0 in detecting the gun and knife, respectively.

CONCLUSION

The new X-ray image detection method based on the Hi color space segmentation proposed in this paper enables to better solve the complex background problem including object overlap and adhesion and thus more effectively meet the requirements of actual security inspection.

Implementation of and Experimentation with Ground-Penetrating Radar for Real-Time Automatic Detection of Buried Improvised Explosive Devices

This paper proposes the implementation of and experimentation with GPR for real-time automatic detection of buried IEDs. GPR, consisting of hardware and software, was implemented. A UWB antenna was designed and implemented, particularly for the operation of the GPR. The experiments were conducted in order to demonstrate the real-time automatic detection of buried IEDs using GPR with an R-CNN algorithm. In the experiments, the GPR was mounted on a pickup truck and a maintenance train in order to find the IEDs buried under a road and a railway, respectively. B-scan images were collected using the implemented GPR. R-CNN-based detection for the hyperbolic pattern, which indicates the buried IED, was performed along with pre-processing, for example, using zero offset removal, and background removal and filtering. Experimental results in terms of detecting the hyperbolic pattern in B-scan images were shown and verified that the proposed GPR system is superior to the conventional one using region analysis processing-based detection. Results also showed that pre-processing is required in order to improve and/or clean the hyperbolic pattern before detection. The GPR can automatically detect IEDs buried under roads and railways in real time by detecting the hyperbolic pattern appearing in the collected B-scan image.

A high-throughput fully automatic biosensing platform for efficient COVID-19 detection

We propose a label-free biosensor based on a porous silicon resonant microcavity and localized surface plasmon resonance. The biosensor detects SARS-CoV-2 antigen based on engineered trimeric angiotensin converting enzyme-2 binding protein, which is conserved across different variants. Robotic arms run the detection process including sample loading, incubation, sensor surface rinsing, and optical measurements using a portable spectrometer. Both the biosensor and the optical measurement system are readily scalable to accommodate testing a wide range of sample numbers. The limit of detection is 100 TCID_50/ml. The detection time is 5 min, and the throughput of one single robotic site is up to 384 specimens in 30 min. The measurement interface requires little training, has standard operation, and therefore is suitable for widespread use in rapid and onsite COVID-19 screening or surveillance.

Application of Deep Convolutional Neural Network for Automatic Detection of Digital Optical Fiber Repeater

The digital optical fiber repeater (DOFR) is an important infrastructure in the LTE networks, which solve the problem of poor regional signal quality. Various types of conventional measurement data from the LTE network cannot indicate whether a working DOFR is present in the cell. Currently, the detection of DOFRs relies solely on maintenance engineers for field detection. Manual detection methods are not timely or efficient, because of the large number and wide geographical distribution of DOFRs. Implementing automatic detection of DOFR can reduce the maintenance cost for mobile network operators. We treat the DOFR detection problem as a classification problem and employ a deep convolutional neural network (DCNN) to tackle it. The measurement report (MR) we used in this paper are tabular data, which is not an ideal input for DCNN. We propose a novel MR representation method that takes the overall MR data of a cell as a sample rather than a single record in the table, and represents the MR data as a pseudo-image matrix (PIM). The PIM will be used as the input for training DCNN, and the trained DCNN will be used to perform DOFR detection tasks. We conducted a series of experiments on real MR data, and the classification accuracy can achieve 93%. The proposed AI-based method can effectively detect the DOFR in a cell.

CoviDetNet: A new COVID-19 diagnostic system based on deep features of chest x-ray

COVID-19 has emerged as a global pandemic affecting the world, and its adverse effects on society still continue. So far, about 243.57 million people have been diagnosed with COVID-19, of which about 4.94 million have died. In this study, a new model, called COVIDetNet, is proposed for automated COVID-19 detection. A lightweight CNN architecture trained instead of the popular and pretrained convolution neural network (CNN) models such as VGG16, VGG19, AlexNet, ResNet50, ResNet100, and MobileNetV2 from scratch with chest x-ray (CXR) images was designed. A new feature set was created by concatenating the features of all layers of the designed CNN architecture. Then, the most efficient features chosen among the features concatenating with the Relief feature selection algorithm were classified using the support vector machine (SVM) method. The experimental works were carried out on a public COVID-19 CXR database. Experimental results demonstrated 99.24% accuracy, 99.60% specificity, 99.39% sensitivity, 99.04% precision, and an F1 score of 99.21%. Also, in comparison to AlexNet and VGG16 models, the deep feature extraction durations were reduced by approximately 6-fold and 38-fold, respectively. The COVIDetNet model provided a higher accuracy score than state-of-the-art models when compared to multi-class research studies. Overall, the proposed model will be beneficial for specialist medical staff to detect COVID-19 cases, as it provides faster and higher accuracy than existing CXR-based approaches.

Fast parametric curve matching (FPCM) for automatic spike detection

Epilepsy is a widely spread neurological disease, whose treatment often requires resection of the pathological cortical tissue. Interictal spike analysis observed in the non-invasively collected EEG or MEG data offers a way to localize epileptogenic cortical structures for surgery planning purposes. While a plethora of automatic spike detection techniques have been developed each with its own assumptions and limitations, non of them is ideal and the best results are achieved when the output of several automatic spike detectors are combined. This is especially true in the low signal-to-noise ratio conditions. To this end we propose a novel biomimetic approach for automatic spike detection based on a constrained mixed spline machinery that we dub as fast parametric curve matching (FPCM). Using the peak-wave shape parametrization, the constrained parametric morphological model is constructed and convolved with the observed multichannel data to very efficiently determine mixed spline parameters corresponding to each time-point in the dataset. Then the logical predicates that directly map to the expected interictal event morphology allow us to accomplish the spike detection task. The results of simulations mimicking typical low SNR scenario show the robustness and high ROC AUC values of the FPCM method as compared to the spike detection performed by the means of more conventional approaches such as wavelet decomposition, template matching or simple amplitude thresholding. Applied to the real MEG and EEG data from the human patients and to ECoG data from the rat, the FPCM technique demonstrates reliable detection of the interictal events and localization of epileptogenic zones concordant with independent conclusions made by the epileptologist. Since the FPCM is computationally light, tolerant to high amplitude artifacts and flexible to accommodate verbalized descriptions of the arbitrary target morphology, it may complement the existing arsenal of means for analysis of noisy interictal datasets.

Automatic Detection of Secundum Atrial Septal Defect in Children Based on Color Doppler Echocardiographic Images Using Convolutional Neural Networks

Secundum atrial septal defect (ASD) is one of the most common congenital heart diseases (CHDs). This study aims to evaluate the feasibility and accuracy of automatic detection of ASD in children based on color Doppler echocardiographic images using convolutional neural networks. In this study, we propose a fully automatic detection system for ASD, which includes three stages. The first stage is used to identify four target echocardiographic views (that is, the subcostal view focusing on the atrium septum, the apical four-chamber view, the low parasternal four-chamber view, and the parasternal short-axis view). These four echocardiographic views are most useful for the diagnosis of ASD clinically. The second stage aims to segment the target cardiac structure and detect candidates for ASD. The third stage is to infer the final detection by utilizing the segmentation and detection results of the second stage. The proposed ASD detection system was developed and validated using a training set of 4,031 cases containing 370,057 echocardiographic images and an independent test set of 229 cases containing 203,619 images, of which 105 cases with ASD and 124 cases with intact atrial septum. Experimental results showed that the proposed ASD detection system achieved accuracy, recall, precision, specificity, and F1 score of 0.8833, 0.8545, 0.8577, 0.9136, and 0.8546, respectively on the image-level averages of the four most clinically useful echocardiographic views. The proposed system can automatically and accurately identify ASD, laying a good foundation for the subsequent artificial intelligence diagnosis of CHDs.

A Robust, Fully Automatic Detection Method and Calculation Technique of Midline Shift in Intracranial Hemorrhage and Its Clinical Application

A midline shift (MLS) is an important clinical indicator for intracranial hemorrhage. In this study, we proposed a robust, fully automatic neural network-based model for the detection of MLS and compared it with MLSs drawn by clinicians; we also evaluated the clinical applications of the fully automatic model. We recruited 300 consecutive non-contrast CT scans consisting of 7269 slices in this study. Six different types of hemorrhage were included. The automatic detection of MLS was based on modified Keypoint R-CNN with keypoint detection followed by training on the ResNet-FPN-50 backbone. The results were further compared with manually drawn outcomes and manually defined keypoint calculations. Clinical parameters, including Glasgow coma scale (GCS), Glasgow outcome scale (GOS), and 30-day mortality, were also analyzed. The mean absolute error for the automatic detection of an MLS was 0.936 mm compared with the ground truth. The interclass correlation was 0.9899 between the automatic method and MLS drawn by different clinicians. There was high sensitivity and specificity in the detection of MLS at 2 mm (91.7%, 80%) and 5 mm (87.5%, 96.7%) and MLSs greater than 10 mm (85.7%, 97.7%). MLS showed a significant association with initial poor GCS and GCS on day 7 and was inversely correlated with poor 30-day GOS (p < 0.001). In conclusion, automatic detection and calculation of MLS can provide an accurate, robust method for MLS measurement that is clinically comparable to the manually drawn method.

End-to-End Deep Learning-Based Cells Detection in Microscopic Leucorrhea Images

Vaginitis is a prevalent gynecologic disease that threatens millions of women’s health. Although microscopic examination of vaginal discharge is an effective method to identify vaginal infections, manual analysis of microscopic leucorrhea images is extremely time-consuming and labor-intensive. To automate the detection and identification of visible components in microscopic leucorrhea images for early-stage diagnosis of vaginitis, we propose a novel end-to-end deep learning-based cells detection framework using attention-based detection with transformers (DETR) architecture. The transfer learning was applied to speed up the network convergence while maintaining the lowest annotation cost. To address the issue of detection performance degradation caused by class imbalance, the weighted sampler with on-the-fly data augmentation module was integrated into the detection pipeline. Additionally, the multi-head attention mechanism and the bipartite matching loss system of the DETR model perform well in identifying partially overlapping cells in real-time. With our proposed method, the pipeline achieved a mean average precision (mAP) of 86.00% and the average precision (AP) of epithelium, leukocyte, pyocyte, mildew, and erythrocyte was 96.76, 83.50, 74.20, 89.66, and 88.80%, respectively. The average test time for a microscopic leucorrhea image is approximately 72.3 ms. Currently, this cell detection method represents state-of-the-art performance.

Performance Analysis of Deep-Neural-Network-Based Automatic Diagnosis of Diabetic Retinopathy

Diabetic retinopathy (DR) is a human eye disease that affects people who are suffering from diabetes. It causes damage to their eyes, including vision loss. It is treatable; however, it takes a long time to diagnose and may require many eye exams. Early detection of DR may prevent or delay the vision loss. Therefore, a robust, automatic and computer-based diagnosis of DR is essential. Currently, deep neural networks are being utilized in numerous medical areas to diagnose various diseases. Consequently, deep transfer learning is utilized in this article. We employ five convolutional-neural-network-based designs (AlexNet, GoogleNet, Inception V4, Inception ResNet V2 and ResNeXt-50). A collection of DR pictures is created. Subsequently, the created collections are labeled with an appropriate treatment approach. This automates the diagnosis and assists patients through subsequent therapies. Furthermore, in order to identify the severity of DR retina pictures, we use our own dataset to train deep convolutional neural networks (CNNs). Experimental results reveal that the pre-trained model Se-ResNeXt-50 obtains the best classification accuracy of 97.53% for our dataset out of all pre-trained models. Moreover, we perform five different experiments on each CNN architecture. As a result, a minimum accuracy of 84.01% is achieved for a five-degree classification.

Remote monitoring of Cydia pomonella adults among an assemblage of nontargets in sex pheromone-kairomone-baited smart traps

BACKGROUND

Captures of codling moth, Cydia pomonella (L.), in traps are used to establish action thresholds and time insecticide sprays. The need for frequent trap inspections in often remote orchards has created a niche for remote sensing smart traps. A smart trap baited with a five-component pheromone-kairomone blend was evaluated for codling moth monitoring among an assemblage of other nontargets in apple and pear orchards.

RESULTS

Codling moth captures did not differ between the smart trap and a standard trap when both were checked manually. However, the correlation between automatic and manual counts of codling moth in the smart traps was low, R²  = 0.66 ÷ 0.87. False-negative identifications by the smart trap were infrequent <5%, but false-positive identifications accounted for up to 67% of the count. These errors were primarily due to the misidentification of three moth species of fairly similar-size to codling moth: apple clearwing moth Synanthedon myopaeformis (Borkhausen), oriental fruit moth Grapholita molesta (Busck), and carnation tortrix Cacoecimorpha pronubana (Hübner). Other false-positive counts were less frequent and included the misidentifications of dipterans, other arthropods, patches of moth scales, and the double counting of some moths.

CONCLUSION

Codling moth was successfully monitored remotely with a smart trap baited with a nonselective sex pheromone-kairomone lure, but automatic counts were inflated in some orchards due to mischaracterizations of primarily similar-sized nontarget moths. Improved image-identification algorithms are needed for smart traps baited with less-selective lures and with lure sets targeting multiple species.

A Current and Newly Proposed Artificial Intelligence Algorithm for Reading Small Bowel Capsule Endoscopy

Small bowel capsule endoscopy (SBCE) is one of the most useful methods for diagnosing small bowel mucosal lesions. However, it takes a long time to interpret the capsule images. To solve this problem, artificial intelligence (AI) algorithms for SBCE readings are being actively studied. In this article, we analyzed several studies that applied AI algorithms to SBCE readings, such as automatic lesion detection, automatic classification of bowel cleanliness, and automatic compartmentalization of small bowels. In addition to automatic lesion detection using AI algorithms, a new direction of AI algorithms related to shorter reading times and improved lesion detection accuracy should be considered. Therefore, it is necessary to develop an integrated AI algorithm composed of algorithms with various functions in order to be used in clinical practice.

A morphological trait involved in reproductive isolation between Drosophila sister species is sensitive to temperature

Male genitalia are usually extremely divergent between closely related species, but relatively constant within one species. Here we examine the effect of temperature on the shape of the ventral branches, a male genital structure involved in reproductive isolation, in the sister species Drosophila santomea and Drosophila yakuba. We designed a semi-automatic measurement machine learning pipeline that can reliably identify curvatures and landmarks based on manually digitized contours of the ventral branches. With this method, we observed that temperature does not affect ventral branches in D. yakuba but that in D. santomea ventral branches tend to morph into a D. yakuba-like shape at lower temperature. We found that male genitalia structures involved in reproductive isolation can be relatively variable within one species and can resemble the shape of closely related species' genitalia through plasticity to temperature. Our results suggest that reproductive isolation mechanisms can be dependent on the environmental context.

Algorithm for automatic detection of self-similarity and prediction of residual central respiratory events during continuous positive airway pressure

Study Objectives

Sleep-disordered breathing is a significant risk factor for cardiometabolic and neurodegenerative diseases. High loop gain (HLG) is a driving mechanism of central sleep apnea or periodic breathing. This study presents a computational approach that identifies “expressed/manifest” HLG via a cyclical self-similarity feature in effort-based respiration signals.

Methods

Working under the assumption that HLG increases the risk of residual central respiratory events during continuous positive airway pressure (CPAP), the full night similarity, computed during diagnostic non-CPAP polysomnography (PSG), was used to predict residual central events during CPAP (REC), which we defined as central apnea index (CAI) higher than 10. Central apnea labels are obtained both from manual scoring by sleep technologists and from an automated algorithm developed for this study. The Massachusetts General Hospital sleep database was used, including 2466 PSG pairs of diagnostic and CPAP titration PSG recordings.

Results

Diagnostic CAI based on technologist labels predicted REC with an area under the curve (AUC) of 0.82 ± 0.03. Based on automatically generated labels, the combination of full night similarity and automatically generated CAI resulted in an AUC of 0.85 ± 0.02. A subanalysis was performed on a population with technologist-labeled diagnostic CAI higher than 5. Full night similarity predicted REC with an AUC of 0.57 ± 0.07 for manual and 0.65 ± 0.06 for automated labels.

Conclusions

The proposed self-similarity feature, as a surrogate estimate of expressed respiratory HLG and computed from easily accessible effort signals, can detect periodic breathing regardless of admixed obstructive features such as flow limitation and can aid the prediction of REC.

OCT Hyperreflective Retinal Foci in Diabetic Retinopathy: A Semi-Automatic Detection Comparative Study

Optical coherence tomography (OCT) allows us to identify, into retinal layers, new morphological entities, which can be considered clinical biomarkers of retinal diseases. According to the literature, solitary, small (<30 µm), medium level hyperreflective (similar to retinal fiber layer) retinal foci (HRF) may represent aggregates of activated microglial cells and an in vivo biomarker of retinal inflammation. The identification and quantification of this imaging biomarker allows for estimating the level and possibly the amount of intraretinal inflammation in major degenerative retinal disorders, whose inflammatory component has already been demonstrated (diabetic retinopathy, age-related macular degeneration, radiation retinopathy). Currently, diabetic retinopathy (DR) probably represents the best clinical model to apply this analysis in the definition of this clinical biomarker. However, the main limitation to the clinical use of HRF is related to the technical difficulty of counting them: a time-consuming methodology, which also needs trained examiners. To contribute to solve this limitation, we developed and validated a new method for the semi-automatic detection of HRF in OCT scans. OCT scans of patients affected by DR, were analyzed. HRF were manually counted in High Resolution spectral domain OCT images. Then, the same OCT scans underwent semi-automatic HRF counting, using an ImageJ software with four different settings profiles. Statistical analysis showed an excellent intraclass correlation coefficient (ICC) between the manual count and each of the four semi-automated methods. The use of the second setting profile allows to obtain at the Bland–Altman graph a bias of −0.2 foci and a limit of agreement of ±16.3 foci. This validation approach opens the way not only to the reliable and daily clinical applicable quantification of HRF, but also to a better knowledge of the inflammatory component—including its progression and regression changes—of diabetic retinopathy.

Using Dynamic Features for Automatic Cervical Precancer Detection

Cervical cancer remains a major public health concern in developing countries due to financial and human resource constraints. Visual inspection with acetic acid (VIA) of the cervix was widely promoted and routinely used as a low-cost primary screening test in low- and middle-income countries. It can be performed by a variety of health workers and the result is immediate. VIA provides a transient whitening effect which appears and disappears differently in precancerous and cancerous lesions, as compared to benign conditions. Colposcopes are often used during VIA to magnify the view of the cervix and allow clinicians to visually assess it. However, this assessment is generally subjective and unreliable even for experienced clinicians. Computer-aided techniques may improve the accuracy of VIA diagnosis and be an important determinant in the promotion of cervical cancer screening. This work proposes a smartphone-based solution that automatically detects cervical precancer from the dynamic features extracted from videos taken during VIA. The proposed solution achieves a sensitivity and specificity of 0.9 and 0.87 respectively, and could be a solution for screening in countries that suffer from the lack of expensive tools such as colposcopes and well-trained clinicians.

Automatic Detection of the Circulating Cell-Free Methylated DNA Pattern of GCM2, ITPRIPL1 and CCDC181 for Detection of Early Breast Cancer and Surgical Treatment Response

The early detection of cancer can reduce cancer-related mortality. There is no clinically useful noninvasive biomarker for early detection of breast cancer. The aim of this study was to develop accurate and precise early detection biomarkers and a dynamic monitoring system following treatment. We analyzed a genome-wide methylation array in Taiwanese and The Cancer Genome Atlas (TCGA) breast cancer (BC) patients. Most breast cancer-specific circulating methylated CCDC181, GCM2 and ITPRIPL1 biomarkers were found in the plasma. An automatic analysis process of methylated ccfDNA was established. A combined analysis of CCDC181, GCM2 and ITPRIPL1 (CGIm) was performed in R using Recursive Partitioning and Regression Trees to establish a new prediction model. Combined analysis of CCDC181, GCM2 and ITPRIPL1 (CGIm) was found to have a sensitivity level of 97% and an area under the curve (AUC) of 0.955 in the training set, and a sensitivity level of 100% and an AUC of 0.961 in the test set. The circulating methylated CCDC181, GCM2 and ITPRIPL1 was also significantly decreased after surgery (all p < 0.001). The aberrant methylation patterns of the CCDC181, GCM2 and ITPRIPL1 genes means that they are potential biomarkers for the detection of early BC and can be combined with breast imaging data to achieve higher accuracy, sensitivity and specificity, facilitating breast cancer detection. They may also be applied to monitor the surgical treatment response.

Evaluation of the Fetal Left Ventricular Myocardial Performance Index (MPI) by Using an Automated Measurement of Doppler Signals in Normal Pregnancies

The myocardial performance index is widely used as an indicator of the heart’s performance. However, due to the subjective nature of ultrasonic testing, there are differences in the measurements among inspectors, requiring a quantitative and objective assessment. In this study, an automated program was developed to quantitatively evaluate the myocardial performance index (MPI) and the cardiac time intervals in the left ventricle for each trimester. One hundred and thirty-three pregnant women who visited the hospital for prenatal examinations were studied, and skilled inspectors obtained left ventricular blood flow waveforms from 47 fetuses in the 12 weeks, 54 fetuses in the 22 weeks, and 32 fetuses in the 31 weeks of pregnancy using a pulse Doppler mode of ultrasound equipment. The acquired images automatically measured the isovolumetric contraction time (IVCT), isovolumetric relaxation time (IVRT,) ejection time (ET), and filling time (FT), and calculated the Tei index (TI) and the K-index (KI); each interval was manually measured during the actual inspection for comparison. In this study, the ultrasonic Doppler waveform was objectively analyzed and measured by the automated program, and it will help with the evaluation of fetal heart function.

X-Vectors: New Quantitative Biomarkers for Early Parkinson's Disease Detection From Speech

Many articles have used voice analysis to detect Parkinson's disease (PD), but few have focused on the early stages of the disease and the gender effect. In this article, we have adapted the latest speaker recognition system, called x-vectors, in order to detect PD at an early stage using voice analysis. X-vectors are embeddings extracted from Deep Neural Networks (DNNs), which provide robust speaker representations and improve speaker recognition when large amounts of training data are used. Our goal was to assess whether, in the context of early PD detection, this technique would outperform the more standard classifier MFCC-GMM (Mel-Frequency Cepstral Coefficients—Gaussian Mixture Model) and, if so, under which conditions. We recorded 221 French speakers (recently diagnosed PD subjects and healthy controls) with a high-quality microphone and via the telephone network. Men and women were analyzed separately in order to have more precise models and to assess a possible gender effect. Several experimental and methodological aspects were tested in order to analyze their impacts on classification performance. We assessed the impact of the audio segment durations, data augmentation, type of dataset used for the neural network training, kind of speech tasks, and back-end analyses. X-vectors technique provided better classification performances than MFCC-GMM for the text-independent tasks, and seemed to be particularly suited for the early detection of PD in women (7–15% improvement). This result was observed for both recording types (high-quality microphone and telephone).

Fast and Accurate Detection of COVID-19 Along With 14 Other Chest Pathologies Using a Multi-Level Classification: Algorithm Development and Validation Study

BACKGROUND

COVID-19 has spread very rapidly, and it is important to build a system that can detect it in order to help an overwhelmed health care system. Many research studies on chest diseases rely on the strengths of deep learning techniques. Although some of these studies used state-of-the-art techniques and were able to deliver promising results, these techniques are not very useful if they can detect only one type of disease without detecting the others.

OBJECTIVE

The main objective of this study was to achieve a fast and more accurate diagnosis of COVID-19. This study proposes a diagnostic technique that classifies COVID-19 x-ray images from normal x-ray images and those specific to 14 other chest diseases.

METHODS

In this paper, we propose a novel, multilevel pipeline, based on deep learning models, to detect COVID-19 along with other chest diseases based on x-ray images. This pipeline reduces the burden of a single network to classify a large number of classes. The deep learning models used in this study were pretrained on the ImageNet dataset, and transfer learning was used for fast training. The lungs and heart were segmented from the whole x-ray images and passed onto the first classifier that checks whether the x-ray is normal, COVID-19 affected, or characteristic of another chest disease. If it is neither a COVID-19 x-ray image nor a normal one, then the second classifier comes into action and classifies the image as one of the other 14 diseases.

RESULTS

We show how our model uses state-of-the-art deep neural networks to achieve classification accuracy for COVID-19 along with 14 other chest diseases and normal cases based on x-ray images, which is competitive with currently used state-of-the-art models. Due to the lack of data in some classes such as COVID-19, we applied 10-fold cross-validation through the ResNet50 model. Our classification technique thus achieved an average training accuracy of 96.04% and test accuracy of 92.52% for the first level of classification (ie, 3 classes). For the second level of classification (ie, 14 classes), our technique achieved a maximum training accuracy of 88.52% and test accuracy of 66.634% by using ResNet50. We also found that when all the 16 classes were classified at once, the overall accuracy for COVID-19 detection decreased, which in the case of ResNet50 was 88.92% for training data and 71.905% for test data.

CONCLUSIONS

Our proposed pipeline can detect COVID-19 with a higher accuracy along with detecting 14 other chest diseases based on x-ray images. This is achieved by dividing the classification task into multiple steps rather than classifying them collectively.

Automatic Fetal Middle Sagittal Plane Detection in Ultrasound Using Generative Adversarial Network

Background and Objective: In the first trimester of pregnancy, fetal growth, and abnormalities can be assessed using the exact middle sagittal plane (MSP) of the fetus. However, the ultrasound (US) image quality and operator experience affect the accuracy. We present an automatic system that enables precise fetal MSP detection from three-dimensional (3D) US and provides an evaluation of its performance using a generative adversarial network (GAN) framework. Method: The neural network is designed as a filter and generates masks to obtain the MSP, learning the features and MSP location in 3D space. Using the proposed image analysis system, a seed point was obtained from 218 first-trimester fetal 3D US volumes using deep learning and the MSP was automatically extracted. Results: The experimental results reveal the feasibility and excellent performance of the proposed approach between the automatically and manually detected MSPs. There was no significant difference between the semi-automatic and automatic systems. Further, the inference time in the automatic system was up to two times faster than the semi-automatic approach. Conclusion: The proposed system offers precise fetal MSP measurements. Therefore, this automatic fetal MSP detection and measurement approach is anticipated to be useful clinically. The proposed system can also be applied to other relevant clinical fields in the future.

Automatic identification of compressions and ventilations during CPR based on the fuzzy c-means clustering and deep belief network

Background

A transthoracic impedance (TTI) signal is an important indicator of the quality of chest compressions (CCs) during cardiopulmonary resuscitation (CPR). We proposed an automatic detection algorithm including the wavelet decomposition, fuzzy c-means (FCM) clustering, and deep belief network (DBN) to identify the compression and ventilation waveforms for evaluating the quality of CPR.

Methods

TTI signals were collected from a cardiac arrest model that electrically induced cardiac arrest in pigs. All signals were denoised using the wavelet and morphology method. The potential compression and ventilation waveforms were marked using an algorithm with a multi-resolution window. The compressions and ventilations in these waveforms were identified and classified using the FCM clustering and DBN methods.

Results

Using the FCM clustering method, the positive predictive values (PPVs) for compressions and ventilations were 99.7% and 95.7%, respectively. The sensitivities of recognition were 99.8% for compressions and 95.1% for ventilations. The DBN approach exhibited similar PPV and sensitivity results to the FCM clustering method. The time cost was satisfactory using either of these techniques.

Conclusions

Our findings suggest that FCM clustering and DBN can be utilized to effectively and accurately evaluate CPR quality, and provide information for improving the success rate of CPR. Our real-time algorithms using FCM clustering and DBN eliminated most distortions and noises effectively, and correctly identified the compression and ventilation waveforms with a low time cost.

Adaptive Quasi-Unsupervised Detection of Smoke Plume by LiDAR

The early detection of fire is one of the possible applications of LiDAR techniques. The smoke generated by a fire is mainly compounded of CO₂, H₂O, particulate, and other combustion products, which involve the local variation of the scattering of the electromagnetic wave at specific wavelengths. The increases of the backscattering coefficient are transduced in peaks on the signal of the backscattering power recorded by the LiDAR system, located exactly where the smoke plume is, allowing not only the detection of a fire but also its localization. The signal processing of the LiDAR signals is critical in the determination of the performances of the fire detection. It is important that the sensitivity of the apparatus is high enough but also that the number of false alarms is small, in order to avoid the trigger of useless and expensive countermeasures. In this work, a new analysis method, based on an adaptive quasi-unsupervised approach was used to ensure that the algorithm is continuously updated to the boundary conditions of the system, such as the weather and experimental apparatus issues. The method has been tested on an experimental campaign of 227 pulses and the performances have been analyzed in terms of sensitivity and specificity.

Automatically Detected Pecking Activity in Group-Housed Turkeys

Simple Summary

Cannibalism is one of the biggest welfare issues of today’s turkey husbandry. We hypothesized that changes in pecking activity might indicate imminent cannibalism. Therefore, in this pilot study a newly developed automatic pecking activity detection was validated, and continuously applied to gain information about pecking activity of group-housed turkeys during the rearing phase and before a cannibalistic outbreak. The pecking object was used by turkeys the whole recording time. Activity on the object was highest in the morning. No clear trend in pecking activity development before an outbreak has yet been found. Pecking detection has to be further tested under various farm conditions. The system can be used in further research in order to survey changes in pecking activity in turkeys.

Abstract

In search for an early warning system for cannibalism, in this study a newly developed automatic pecking activity detection system was validated and used to investigate how pecking activity changes over the rearing phase and before cannibalistic outbreaks. Data were recorded on two farms, one with female (intact beaks) and the other with male (trimmed beaks) turkeys. A metallic pecking object that was equipped with a microphone was installed in the barn and video monitored. Pecking activity was continuously recorded and fed into a CNN (Convolutional neural network) model that automatically detected pecks. The CNN was validated on both farms, and very satisfactory detection performances were reached (mean sensitivity/recall, specificity, accuracy, precision, and F1-score around 90% or higher). The extent of pecking at the object differed between farms, but the objects were used during the whole recording time, with highest activities in the morning hours. Daily pecking frequencies showed a low downward trend over the rearing period, although on both farms they increased again in week 5 of life. No clear associations between pecking frequencies and in total three cannibalistic outbreaks on farm 1 in one batch could be found. The detection system is usable for further research, but it should be further automated. It should also be further tested under various farm conditions.

Validation of an Automatic Arousal Detection Algorithm for Whole-Night Sleep EEG Recordings

Arousals during sleep are transient accelerations of the EEG signal, considered to reflect sleep perturbations associated with poorer sleep quality. They are typically detected by visual inspection, which is time consuming, subjective, and prevents good comparability across scorers, studies and research centres. We developed a fully automatic algorithm which aims at detecting artefact and arousal events in whole-night EEG recordings, based on time-frequency analysis with adapted thresholds derived from individual data. We ran an automated detection of arousals over 35 sleep EEG recordings in healthy young and older individuals and compared it against human visual detection from two research centres with the aim to evaluate the algorithm performance. Comparison across human scorers revealed a high variability in the number of detected arousals, which was always lower than the number detected automatically. Despite indexing more events, automatic detection showed high agreement with human detection as reflected by its correlation with human raters and very good Cohen's kappa values. Finally, the sex of participants and sleep stage did not influence performance, while age may impact automatic detection, depending on the human rater considered as gold standard. We propose our freely available algorithm as a reliable and time-sparing alternative to visual detection of arousals.

Nocturnal eye movements in patients with idiopathic rapid eye movement sleep behaviour disorder and patients with Parkinson's disease

Patients with idiopathic rapid-eye-movement (REM) sleep behaviour disorder (iRBD) have a high risk of converting into manifest α-synucleinopathies. Eye movements (EMs) are controlled by neurons in the lower brainstem, midbrain and frontal areas, and may be affected by the early neurodegenerative process seen in iRBD. Studies have reported impairment of the oculomotor function in patients with Parkinson's disease (PD) during wakefulness, but no studies have investigated EMs during sleep. We aimed to evaluate nocturnal EMs in iRBD and PD, hypothesizing that these patients present abnormal EM distribution during sleep. Twenty-eight patients with periodic limb movement disorder (PLMD), 24 iRBD, 23 PD without RBD (PDwoRBD), 29 PD and RBD (PDwRBD) and 24 controls were included. A validated EM detector automatically identified EM periods between lights off and on. The EM coverage was computed as the percentage of time containing EMs during stable wake after lights off, N1, N2, N3 and REM sleep. Between-group comparisons revealed that PDwRBD had significantly less EM coverage during wake and significantly higher EM coverage during N2 compared to controls and PLMD patients. PDwoRBD showed significantly less EM coverage during wake compared to controls and higher EM coverage during N2 compared to controls and PLMD. Finally, iRBD showed less coverage of EM during wake compared to controls. The same trend was observed between iRBD and controls in N2 but was not significant. The different profiles of EM coverage in iRBD and PD with/without RBD may mirror different stages of central nervous system involvement across neurodegenerative disease progression.

Detecting Soil Microarthropods with a Camera-Supported Trap

There is an increasing need to monitor activity and population growth of arthropods; however, this is a time-consuming and financially demanding process. Using sensors to detect arthropods in the field can help to follow their dynamics in time. Improving our earlier device, we developed a new camera-supported probe to detect soil microarthropods. An opto-electronic sensor ring detects the caught microarthropod individuals what activates a camera. The camera takes pictures of a specimen when it arrives in the camera chamber. A vacuum device was built into the probe which pumps up the specimen from the probe to a sample container. Here, we describe the construction and operation of the probe. We investigated the precision of the process in a laboratory experiment using living microarthropods and evaluated the accuracy of the probes in a semi-natural investigation when environmental noise was present. Under semi-natural conditions, the percentages of success, i.e., the photographed specimens compared to the caught ones, were between 60% and 70% at the investigated taxa. The automatic camera shooting helped in distinguishing insects from irrelevant detections while collecting the trapped insects allowed species-level determination. This information together serves as a basis for the automatic visual recognition of microarthropod species.

Applications of advanced signal processing and machine learning in the neonatal hypoxic-ischemic electroencephalogram

Perinatal hypoxic-ischemic-encephalopathy significantly contributes to neonatal death and life-long disability such as cerebral palsy. Advances in signal processing and machine learning have provided the research community with an opportunity to develop automated real-time identification techniques to detect the signs of hypoxic-ischemic-encephalopathy in larger electroencephalography/amplitude-integrated electroencephalography data sets more easily. This review details the recent achievements, performed by a number of prominent research groups across the world, in the automatic identification and classification of hypoxic-ischemic epileptiform neonatal seizures using advanced signal processing and machine learning techniques. This review also addresses the clinical challenges that current automated techniques face in order to be fully utilized by clinicians, and highlights the importance of upgrading the current clinical bedside sampling frequencies to higher sampling rates in order to provide better hypoxic-ischemic biomarker detection frameworks. Additionally, the article highlights that current clinical automated epileptiform detection strategies for human neonates have been only concerned with seizure detection after the therapeutic latent phase of injury. Whereas recent animal studies have demonstrated that the latent phase of opportunity is critically important for early diagnosis of hypoxic-ischemic-encephalopathy electroencephalography biomarkers and although difficult, detection strategies could utilize biomarkers in the latent phase to also predict the onset of future seizures.

Electroencephalogram studies of hypoxic ischemia in fetal and neonatal animal models

Alongside clinical achievements, experiments conducted on animal models (including primate or non-primate) have been effective in the understanding of various pathophysiological aspects of perinatal hypoxic/ischemic encephalopathy (HIE). Due to the reasonably fair degree of flexibility with experiments, most of the research around HIE in the literature has been largely concerned with the neurodevelopmental outcome or how the frequency and duration of HI seizures could relate to the severity of perinatal brain injury, following HI insult. This survey concentrates on how EEG experimental studies using asphyxiated animal models (in rodents, piglets, sheep and non-human primate monkeys) provide a unique opportunity to examine from the exact time of HI event to help gain insights into HIE where human studies become difficult.

Automatic Detection and Modeling of Underground Pipes Using a Portable 3D LiDAR System

Automatic and accurate mapping and modeling of underground infrastructure has become indispensable for several important tasks ranging from urban planning and construction to safety and hazard mitigation. However, this offers several technical and operational challenges. The aim of this work is to develop a portable automated mapping solution for the 3D mapping and modeling of underground pipe networks during renovation and installation work when the infrastructure is being laid down in open trenches. The system is used to scan the trench and then the 3D scans obtained from the system are registered together to form a 3D point cloud of the trench containing the pipe network using a modified global ICP (iterative closest point) method. In the 3D point cloud, pipe-like structures are segmented using fuzzy C-means clustering and then modeled using a nested MSAC (M-estimator SAmpling Consensus) algorithm. The proposed method is evaluated on real data pertaining to three different sites, containing several different types of pipes. We report an overall registration error of less than 7 % , an overall segmentation accuracy of 85 % and an overall modeling error of less than 5 % . The evaluated results not only demonstrate the efficacy but also the suitability of the proposed solution.

Automatic detection of calcium phosphate deposit plugs at the terminal ends of kidney tubules

Kidney stones are a common urologic condition with a high amount of recurrence. Recurrence depends on a multitude of factors the incidence of precursors to kidney stones, plugs, and plaques. One method of characterising the stone precursors is endoscopic assessment, though it is manual and time-consuming. Deep learning has become a popular technique for semantic segmentation because of the high accuracy that has been demonstrated. The present Letter examined the efficacy of deep learning to segment the renal papilla, plaque, and plugs. A U-Net model with ResNet-34 encoder was tested; the Letter examined dropout (to avoid overtraining) and two different loss functions (to address the class imbalance problem. The models were then trained in 1666 images and tested on 185 images. The Jaccard-cross-entropy loss function was more effective than the focal loss function. The model with the dropout rate 0.4 was found to be more effective due to its generalisability. The model was largely successful at delineating the papilla. The model was able to correctly detect the plaques and plugs; however, small plaques were challenging. Deep learning was found to be applicable for segmentation of an endoscopic image for the papilla, plaque, and plug, with room for improvement.

A Power Spectral Density-Based Method to Detect Tremor and Tremor Intermittency in Movement Disorders

There is no objective gold standard to detect tremors. This concerns not only the choice of the algorithm and sensors, but methods are often designed to detect tremors in one specific group of patients during the performance of a specific task. Therefore, the aim of this study is twofold. First, an objective quantitative method to detect tremor windows (TWs) in accelerometer and electromyography recordings is introduced. Second, the tremor stability index (TSI) is determined to indicate the advantage of detecting TWs prior to analysis. Ten Parkinson’s disease (PD) patients, ten essential tremor (ET) patients, and ten healthy controls (HC) performed a resting, postural and movement task. Data was split into 3-s windows, and the power spectral density was calculated for each window. The relative power around the peak frequency with respect to the power in the tremor band was used to classify the windows as either tremor or non-tremor. The method yielded a specificity of 96.45%, sensitivity of 84.84%, and accuracy of 90.80% of tremor detection. During tremors, significant differences were found between groups in all three parameters. The results suggest that the introduced method could be used to determine under which conditions and to which extent undiagnosed patients exhibit tremors.

A Variance-reduction Approach to Detection of the Thyroid-nodule Boundary on Ultrasound Images

To perform computer-aided diagnosis of the thyroid nodules on ultrasound images, the location and boundary of nodules should be clearly defined. However, the identification of thyroid nodule boundary is a difficult issue due to the biological characteristics of the nodules, the physics and quality of ultrasound imaging, and the subjective factors and operating conditions of the operator. In this study, we propose a novel and semiautomatic method for detecting the boundary of thyroid nodule based on the Variance-Reduction (V-R) statistics without image preprocessing. The region of interest (ROI) is first automatically generated according to the initial inputs of the nodule's major and minor axes. The boundary candidate pixel points are then extracted by using the V-R statistics from the grayscale values of all pixel points in the ROI. Three filtering methods are further applied to eliminate the outlier pixel points to ensure that the remaining candidate pixel points are located on the nodule boundary. Finally, the remaining pixel points are smoothened and linked together to form the final boundary. The proposed method is validated with ultrasound images of 538 thyroid nodules, with manual delineation by experienced radiologist as gold standard. The effectiveness is evaluated and compared with previous publications using boundary error metrics and overlapping area metrics with the same data set. The results show that the normalized average mean boundary error is 1.02%, the true positive overlapping area ratio achieves 93.66% and false positive overlapping area ratio is limited to 7.68%. In conclusion, our proposed method is reliable and effective in detecting thyroid nodule boundary on ultrasound images.

Automatic detection of sleep apnea events based on inter-band energy ratio obtained from multi-band EEG signal

Sleep apnea is a potentially serious sleep disorder characterised by abnormal pauses in breathing. Electroencephalogram (EEG) signal analysis plays an important role for detecting sleep apnea events. In this research work, a method is proposed on the basis of inter-band energy ratio features obtained from multi-band EEG signals for subject-specific classification of sleep apnea and non-apnea events. The K-nearest neighbourhood classifier is used for classification purpose. Unlike conventional methods, instead of classifying apnea patient and healthy person, the objective here is to differentiate apnea and non-apnea events of an apnea patient, which makes the task very challenging. Extensive experimentation is carried out on EEG data of several subjects obtained from a publicly available database. Comprehensive experimental results reveal that the proposed method offers very satisfactory classification performance in terms of sensitivity, specificity and accuracy.

Automatic Analysis of EEGs Using Big Data and Hybrid Deep Learning Architectures

Brain monitoring combined with automatic analysis of EEGs provides a clinical decision support tool that can reduce time to diagnosis and assist clinicians in real-time monitoring applications (e.g., neurological intensive care units). Clinicians have indicated that a sensitivity of 95% with specificity below 5% was the minimum requirement for clinical acceptance. In this study, a high-performance automated EEG analysis system based on principles of machine learning and big data is proposed. This hybrid architecture integrates hidden Markov models (HMMs) for sequential decoding of EEG events with deep learning-based post-processing that incorporates temporal and spatial context. These algorithms are trained and evaluated using the Temple University Hospital EEG, which is the largest publicly available corpus of clinical EEG recordings in the world. This system automatically processes EEG records and classifies three patterns of clinical interest in brain activity that might be useful in diagnosing brain disorders: (1) spike and/or sharp waves, (2) generalized periodic epileptiform discharges, (3) periodic lateralized epileptiform discharges. It also classifies three patterns used to model the background EEG activity: (1) eye movement, (2) artifacts, and (3) background. Our approach delivers a sensitivity above 90% while maintaining a specificity below 5%. We also demonstrate that this system delivers a low false alarm rate, which is critical for any spike detection application.

Nicotine increases sleep spindle activity

Studies have shown that both nicotine and sleep spindles are associated with enhanced memorisation. Further, a few recent studies have shown how cholinergic input through nicotinic and muscarinic receptors can trigger or modulate sleep processes in general, and sleep spindles in particular. To better understand the interaction between nicotine and sleep spindles, we compared in a single blind randomised study the characteristics of sleep spindles in 10 healthy participants recorded for 2 nights, one with a nicotine patch and one with a sham patch. We investigated differences in sleep spindle duration, amplitude, intra-spindle oscillation frequency and density (i.e. spindles per min). We found that under nicotine, spindles are more numerous (average increase: 0.057 spindles per min; 95% confidence interval: [0.025-0.089]; p = .0004), have higher amplitude (average amplification: 0.260 μV; confidence interval: [0.119-0.402]; p = .0032) and last longer (average lengthening: 0.025 s; confidence interval: [0.017-0.032]; p = 2.7e-11). These results suggest that nicotine can increase spindle activity by acting on nicotinic acetylcholine receptors, and offer an attractive hypothesis for common mechanisms that may support memorisation improvements previously reported to be associated with nicotine and sleep spindles.

A Smartphone-Based System for Automated Bedside Detection of Crackle Sounds in Diffuse Interstitial Pneumonia Patients

In this work, we present a mobile health system for the automated detection of crackle sounds comprised by an acoustical sensor, a smartphone device, and a mobile application (app) implemented in Android. Although pulmonary auscultation with traditional stethoscopes had been used for decades, it has limitations for detecting discontinuous adventitious respiratory sounds (crackles) that commonly occur in respiratory diseases. The proposed app allows the physician to record, store, reproduce, and analyze respiratory sounds directly on the smartphone. Furthermore, the algorithm for crackle detection was based on a time-varying autoregressive modeling. The performance of the automated detector was analyzed using: (1) synthetic fine and coarse crackle sounds randomly inserted to the basal respiratory sounds acquired from healthy subjects with different signal to noise ratios, and (2) real bedside acquired respiratory sounds from patients with interstitial diffuse pneumonia. In simulated scenarios, for fine crackles, an accuracy ranging from 84.86% to 89.16%, a sensitivity ranging from 93.45% to 97.65%, and a specificity ranging from 99.82% to 99.84% were found. The detection of coarse crackles was found to be a more challenging task in the simulated scenarios. In the case of real data, the results show the feasibility of using the developed mobile health system in clinical no controlled environment to help the expert in evaluating the pulmonary state of a subject.

Students' learning style detection using tree augmented naive Bayes

Students are characterized according to their own distinct learning styles. Discovering students' learning style is significant in the educational system in order to provide adaptivity. Past researches have proposed various approaches to detect the students' learning styles. Among all, the Bayesian network has emerged as a widely used method to automatically detect students' learning styles. On the other hand, tree augmented naive Bayesian network has the ability to improve the naive Bayesian network in terms of better classification accuracy. In this paper, we evaluate the performance of the tree augmented naive Bayesian in automatically detecting students' learning style in the online learning environment. The experimental results are promising as the tree augmented naive Bayes network is shown to achieve higher detection accuracy when compared to the Bayesian network.