Search

Computer-assisted diagnosis (CAD) plays a key role in cancer diagnosis or screening. Whereas, current CAD performs poorly on whole slide image (WSI) analysis, and thus fails to generalize well. This research aims to develop an automatic classification system to distinguish between different types of carcinomas. Obtaining rich deep features in multi-class classification while achieving high accuracy is still a challenging problem. The detection and classification of cancerous cells in WSI are quite challenging due to the misclassification of normal lumps and cancerous cells. This is due to cluttering, occlusion, and irregular cell distribution. Researchers in the past mostly obtained the hand-crafted features while neglecting the above-mentioned challenges which led to a reduction of the classification accuracy. To mitigate this problem we proposed an efficient dual attention-based network (CytoNet). The proposed network is composed of two main modules (i) Efficient-Net and (ii) Dual Attention Module (DAM). Efficient-Net is capable of obtaining higher accuracy and enhancing efficiency as compared to existing Convolutional Neural Networks (CNNs). It is also useful to obtain the most generic features as it has been trained on ImageNet. Whereas DAM is very robust in obtaining attention and targeted features while negating the background. In this way, the combination of an efficient and attention module is useful to obtain the robust, and intrinsic features to obtain comparable performance. Further, we evaluated the proposed network on two well-known datasets (i) Our generated thyroid dataset (ii) Mendeley Cervical dataset (Hussain in Data Brief, 2019) with enhanced performance compared to their counterparts. CytoNet demonstrated a 99% accuracy rate on the thyroid dataset in comparison to its counterpart. The precision, recall, and F1-score values achieved on the Mendeley Cervical dataset are 0.992, 0.985, and 0.977, respectively. The code implementation is available on GitHub. https://github.com/naveedilyas/CytoNet-An-Efficient-Dual-Attention-based-Automatic-Prediction-of-Cancer-Sub-types-in-Cytol.

Explainability of convolutional neural networks (CNNs) is integral for their adoption into radiological practice. Commonly used attribution methods localize image areas important for CNN prediction but do not characterize relevant imaging features underlying these areas, acting as a barrier to the adoption of CNNs for clinical use. We therefore propose Semantic Exploration and Explainability using a Style-based Generative Adversarial Autoencoder Network (SEE-GAAN), an explainability framework that uses latent space manipulation to generate a sequence of synthetic images that semantically visualizes how clinical and CNN features manifest within medical images. Visual analysis of changes in these sequences then facilitates the interpretation of features, thereby improving explainability. SEE-GAAN was first developed on a cohort of 26,664 chest radiographs across 15,409 patients from our institution. SEE-GAAN sequences were then generated across several clinical features and CNN predictions of NT-pro B-type natriuretic peptide (BNPP) as a proxy for acute heart failure. Radiological interpretations indicated SEE-GAAN sequences captured relevant changes in anatomical and pathological morphology associated with clinical and CNN predictions and clarified ambiguous areas highlighted by commonly used attribution methods. Our study demonstrates SEE-GAAN can facilitate our understanding of clinical features for imaging biomarker exploration and improve CNN transparency over commonly used explainability methods.

Symbolic regression with polynomial neural networks and polynomial neural ordinary differential equations (ODEs) are two recent and powerful approaches for equation recovery of many science and engineering problems. However, these methods provide point estimates for the model parameters and are currently unable to accommodate noisy data. We address this challenge by developing and validating the following Bayesian inference methods: the Laplace approximation, Markov Chain Monte Carlo (MCMC) sampling methods, and variational inference. We have found the Laplace approximation to be the best method for this class of problems. Our work can be easily extended to the broader class of symbolic neural networks to which the polynomial neural network belongs.

We proposed an end-to-end deep learning convolutional neural network (DCNN) for region-of-interest based multi-parameter quantification (RMQ-Net) to accelerate quantitative ultrashort echo time (UTE) MRI of the knee joint with automatic multi-tissue segmentation and relaxometry mapping. The study involved UTE-based T1 (UTE-T1) and Adiabatic T1ρ (UTE-AdiabT1ρ) mapping of the knee joint of 65 human subjects, including 20 normal controls, 29 with doubtful-minimal osteoarthritis (OA), and 16 with moderate-severe OA. Comparison studies were performed on UTE-T1 and UTE-AdiabT1ρ measurements using 100%, 43%, 26%, and 18% UTE MRI data as the inputs and the effects on the prediction quality of the RMQ-Net. The RMQ-net was modified and retrained accordingly with different combinations of inputs. Both ROI-based and voxel-based Pearson correlation analyses were performed. High Pearson correlation coefficients were achieved between the RMQ-Net predicted UTE-T1 and UTE-AdiabT1ρ results and the ground truth for segmented cartilage with acceleration factors ranging from 2.3 to 5.7. With an acceleration factor of 5.7, the Pearson r-value achieved 0.908 (ROI-based) and 0.945 (voxel-based) for UTE-T1, and 0.733 (ROI-based) and 0.895 (voxel-based) for UTE-AdiabT1ρ, correspondingly. The results demonstrated that RMQ-net can significantly accelerate quantitative UTE imaging with automated segmentation of articular cartilage in the knee joint.

PURPOSE: This study uses deep neural network-generated rim-to-disc area ratio (RADAR) measurements and the disc damage likelihood scale (DDLS) to measure the rate of optic disc rim loss in a large cohort of glaucoma patients. METHODS: A deep neural network was used to calculate RADAR and DDLS for each optic disc photograph (ODP). Patient demographics, diagnosis, intraocular pressure (IOP), and mean deviation (MD) from perimetry were analyzed as risk factors for faster progression of RADAR. Receiver operating characteristic (ROC) curves were used to compare RADAR and DDLS in their utility to distinguish glaucoma from glaucoma suspect (GS) and for detecting glaucoma progression. RESULTS: A total of 13,679 ODPs with evidence of glaucomatous optic nerve damage from 4106 eyes of 2407 patients with glaucoma or GS were included. Of these eyes, 3264 (79.5%) had a diagnosis of glaucoma, and 842 (20.5%) eyes were GS. Mean ± SD baseline RADAR of GS and glaucoma were 0.67 ± 0.13 and 0.57 ± 0.18, respectively (P < 0.001). Older age, greater IOP fluctuation, baseline MD, right eye, and diagnosis of secondary open-angle glaucoma were associated with slope of RADAR. The mean baseline DDLS of GS and glaucoma were 3.78 and 4.39, respectively. Both RADAR and DDLS showed a less steep slope in advanced glaucoma. In glaucoma, the change of RADAR and DDLS correlated with the corresponding change in MD. RADAR and DDLS had a similar ability to discriminate glaucoma from GS and detect disease progression. Area under the ROC curve of RADAR and DDLS was 0.658 and 0.648. CONCLUSIONS: Automated calculation of RADAR and DDLS with a neural network can be used to evaluate the extent and long-term rate of optic disc rim loss and is further evidence of long-term nerve fiber loss in treated patients with glaucoma. TRANSLATIONAL RELEVANCE: Our study provides a large clinic-based experience for RADAR and DDLS measurements in GS and glaucoma with a neural network.

Objective. Physiological data are often low quality and thereby compromises the effectiveness of related health monitoring. The primary goal of this study is to develop a robust foundation model that can effectively handle low-quality issue in physiological data.Approach. We introduce SiamQuality, a self-supervised learning approach using convolutional neural networks (CNNs) as the backbone. SiamQuality learns to generate similar representations for both high and low quality photoplethysmography (PPG) signals that originate from similar physiological states. We leveraged a substantial dataset of PPG signals from hospitalized intensive care patients, comprised of over 36 million 30 s PPG pairs.Main results. After pre-training the SiamQuality model, it was fine-tuned and tested on six PPG downstream tasks focusing on cardiovascular monitoring. Notably, in tasks such as respiratory rate estimation and atrial fibrillation detection, the models performance exceeded the state-of-the-art by 75% and 5%, respectively. The results highlight the effectiveness of our model across all evaluated tasks, demonstrating significant improvements, especially in applications for heart monitoring on wearable devices.Significance. This study underscores the potential of CNNs as a robust backbone for foundation models tailored to physiological data, emphasizing their capability to maintain performance despite variations in data quality. The success of the SiamQuality model in handling real-world, variable-quality data opens new avenues for the development of more reliable and efficient healthcare monitoring technologies.

A neural network was developed to detect and characterize bowel obstruction, a common cause of acute abdominal pain. In this retrospective study, 202 CT scans of 165 patients with bowel obstruction from March to June 2022 were included and partitioned into training and test data sets. A multi-channel neural network was trained to segment the gastrointestinal tract, and to predict the diameter and the longitudinal position (longitude) along the gastrointestinal tract using a novel embedding. Its performance was compared to manual segmentations using the Dice score, and to manual measurements of the diameter and longitude using intraclass correlation coefficients (ICC). ROC curves as well as sensitivity and specificity were calculated for diameters above a clinical threshold for obstruction, and for longitudes corresponding to small bowel. In the test data set, Dice score for segmentation of the gastrointestinal tract was 78 ± 8%. ICC between measured and predicted diameters was 0.72, indicating moderate agreement. ICC between measured and predicted longitude was 0.85, indicating good agreement. AUROC was 0.90 for detection of dilated bowel, and was 0.95 and 0.90 for differentiation of the proximal and distal gastrointestinal tract respectively. Overall sensitivity and specificity for dilated small bowel were 0.83 and 0.90. Since obstruction is diagnosed based on the diameter and longitude of the bowel, this neural network and embedding may enable detection and characterization of this important disease on CT.

Identifying and characterizing mobile genetic elements in sequencing data is essential for understanding their diversity, ecology, biotechnological applications and impact on public health. Here we introduce geNomad, a classification and annotation framework that combines information from gene content and a deep neural network to identify sequences of plasmids and viruses. geNomad uses a dataset of more than 200,000 marker protein profiles to provide functional gene annotation and taxonomic assignment of viral genomes. Using a conditional random field model, geNomad also detects proviruses integrated into host genomes with high precision. In benchmarks, geNomad achieved high classification performance for diverse plasmids and viruses (Matthews correlation coefficient of 77.8% and 95.3%, respectively), substantially outperforming other tools. Leveraging geNomad's speed and scalability, we processed over 2.7 trillion base pairs of sequencing data, leading to the discovery of millions of viruses and plasmids that are available through the IMG/VR and IMG/PR databases. geNomad is available at https://portal.nersc.gov/genomad .

Message passing neural networks (MPNNs) on molecular graphs generate continuous and differentiable encodings of small molecules with state-of-the-art performance on protein-ligand complex scoring tasks. Here, we describe the proximity graph network (PGN) package, an open-source toolkit that constructs ligand-receptor graphs based on atom proximity and allows users to rapidly apply and evaluate MPNN architectures for a broad range of tasks. We demonstrate the utility of PGN by introducing benchmarks for affinity and docking score prediction tasks. Graph networks generalize better than fingerprint-based models and perform strongly for the docking score prediction task. Overall, MPNNs with proximity graph data structures augment the prediction of ligand-receptor complex properties when ligand-receptor data are available.

OBJECTIVE: Increased subcutaneous and visceral adipose tissue (SAT/VAT) volume is associated with risk for cardiometabolic diseases. This work aimed to develop and evaluate automated abdominal SAT/VAT segmentation on longitudinal MRI in adults with overweight/obesity using attention-based competitive dense (ACD) 3D U-Net and 3D nnU-Net with full field-of-view volumetric multi-contrast inputs. MATERIALS AND METHODS: 920 adults with overweight/obesity were scanned twice at multiple 3 T MRI scanners and institutions. The first scan was divided into training/validation/testing sets (n = 646/92/182). The second scan from the subjects in the testing set was used to evaluate the generalizability for longitudinal analysis. Segmentation performance was assessed by measuring Dice scores (DICE-SAT, DICE-VAT), false negatives (FN), and false positives (FP). Volume agreement was assessed using the intraclass correlation coefficient (ICC). RESULTS: ACD 3D U-Net achieved rapid ( 0.997) in longitudinal analysis. DISCUSSION: ACD 3D U-Net and 3D nnU-Net can be automated tools to quantify abdominal SAT/VAT volume rapidly, accurately, and longitudinally in adults with overweight/obesity.

Deep learning-based mammographic evaluations could noninvasively assess response to breast cancer chemoprevention. We evaluated change in a convolutional neural network-based breast cancer risk model applied to mammograms among women enrolled in SWOG S0812, which randomly assigned 208 premenopausal high-risk women to receive oral vitamin D3 20 000 IU weekly or placebo for 12 months. We applied the convolutional neural network model to mammograms collected at baseline (n = 109), 12 months (n = 97), and 24 months (n = 67) and compared changes in convolutional neural network-based risk score between treatment groups. Change in convolutional neural network-based risk score was not statistically significantly different between vitamin D and placebo groups at 12 months (0.005 vs 0.002, P = .875) or at 24 months (0.020 vs 0.001, P = .563). The findings are consistent with the primary analysis of S0812, which did not demonstrate statistically significant changes in mammographic density with vitamin D supplementation compared with placebo. There is an ongoing need to evaluate biomarkers of response to novel breast cancer chemopreventive agents.

Adaptation is a universal aspect of neural systems that changes circuit computations to match prevailing inputs. These changes facilitate efficient encoding of sensory inputs while avoiding saturation. Conventional artificial neural networks (ANNs) have limited adaptive capabilities, hindering their ability to reliably predict neural output under dynamic input conditions. Can embedding neural adaptive mechanisms in ANNs improve their performance? To answer this question, we develop a new deep learning model of the retina that incorporates the biophysics of photoreceptor adaptation at the front-end of conventional convolutional neural networks (CNNs). These conventional CNNs build on 'Deep Retina,' a previously developed model of retinal ganglion cell (RGC) activity. CNNs that include this new photoreceptor layer outperform conventional CNN models at predicting male and female primate and rat RGC responses to naturalistic stimuli that include dynamic local intensity changes and large changes in the ambient illumination. These improved predictions result directly from adaptation within the phototransduction cascade. This research underscores the potential of embedding models of neural adaptation in ANNs and using them to determine how neural circuits manage the complexities of encoding natural inputs that are dynamic and span a large range of light levels.

PurposeHigh quality scan prescription that optimally covers the area of interest with scan planes aligned to relevant anatomical structures is crucial for error-free radiologic interpretation. The goal of this project was to develop a machine learning pipeline for oblique scan prescription that could be trained on localizer images and metadata from previously acquired MR exams.MethodsA novel Multislice Rotational Region-based Convolutional Neural Network (MS-R2CNN) architecture was developed. Based on this architecture, models for automated prescription sagittal lumbar spine acquisitions from axial, sagittal, and coronal localizer slices were trained. The automated prescription pipeline was integrated with the scanner console software and evaluated in experiments with healthy volunteers (N = 3) and patients with lower-back pain (N = 20).ResultsExperiments in healthy volunteers demonstrated high accuracy of automated prescription in all subjects. There was good agreement between alignment and coverage of manual and automated prescriptions, as well as consistent views of the lumbar spine at different positions of the subjects within the scanner bore. In patients with lower-back pain, the generated prescription was applied in 18 cases (90% of the total number). None of the cases required major adjustment, while in 11 cases (55%) there were minor manual adjustments to the generated prescription.ConclusionsThis study demonstrates the ability of oriented object detection-based models to be trained to prescribe oblique lumbar spine MRI acquisitions without the need of manual annotation or feature engineering and the feasibility of using machine learning-based pipelines on the scanner for automated prescription of MRI acquisitions.

BACKGROUND: Language in nonmedical data sets is known to transmit human-like biases when used in natural language processing (NLP) algorithms that can reinforce disparities. It is unclear if NLP algorithms of medical notes could lead to similar transmissions of biases. RESEARCH QUESTION: Can we identify implicit bias in clinical notes, and are biases stable across time and geography? STUDY DESIGN AND METHODS: To determine whether different racial and ethnic descriptors are similar contextually to stigmatizing language in ICU notes and whether these relationships are stable across time and geography, we identified notes on critically ill adults admitted to the University of California, San Francisco (UCSF), from 2012 through 2022 and to Beth Israel Deaconess Hospital (BIDMC) from 2001 through 2012. Because word meaning is derived largely from context, we trained unsupervised word-embedding algorithms to measure the similarity (cosine similarity) quantitatively of the context between a racial or ethnic descriptor (eg, African-American) and a stigmatizing target word (eg, nonco-operative) or group of words (violence, passivity, noncompliance, nonadherence). RESULTS: In UCSF notes, Black descriptors were less likely to be similar contextually to violent words compared with White descriptors. Contrastingly, in BIDMC notes, Black descriptors were more likely to be similar contextually to violent words compared with White descriptors. The UCSF data set also showed that Black descriptors were more similar contextually to passivity and noncompliance words compared with Latinx descriptors. INTERPRETATION: Implicit bias is identifiable in ICU notes. Racial and ethnic group descriptors carry different contextual relationships to stigmatizing words, depending on when and where notes were written. Because NLP models seem able to transmit implicit bias from training data, use of NLP algorithms in clinical prediction could reinforce disparities. Active debiasing strategies may be necessary to achieve algorithmic fairness when using language models in clinical research.

An important difference between brains and deep neural networks is the way they learn. Nervous systems learn online where a stream of noisy data points are presented in a non-independent, identically distributed way. Further, synaptic plasticity in the brain depends only on information local to synapses. Deep networks, on the other hand, typically use non-local learning algorithms and are trained in an offline, non-noisy, independent, identically distributed setting. Understanding how neural networks learn under the same constraints as the brain is an open problem for neuroscience and neuromorphic computing. A standard approach to this problem has yet to be established. In this paper, we propose that discrete graphical models that learn via an online maximum a posteriori learning algorithm could provide such an approach. We implement this kind of model in a neural network called the Sparse Quantized Hopfield Network. We show our model outperforms state-of-the-art neural networks on associative memory tasks, outperforms these networks in online, continual settings, learns efficiently with noisy inputs, and is better than baselines on an episodic memory task.

BackgroundWhole brain delineation (WBD) is utilized in neuroimaging analysis for data preprocessing and deriving whole brain image metrics. Current automated WBD techniques for analysis of preclinical brain MRI data show limited accuracy when images present with significant neuropathology and anatomical deformations, such as that resulting from organophosphate intoxication (OPI) and Alzheimer's Disease (AD), and inadequate generalizability.MethodsA modified 2D U-Net framework was employed for WBD of MRI rodent brains, consisting of 27 convolutional layers, batch normalization, two dropout layers and data augmentation, after training parameter optimization. A total of 265 T2-weighted 7.0 T MRI scans were utilized for the study, including 125 scans of an OPI rat model for neural network training. For testing and validation, 20 OPI rat scans and 120 scans of an AD rat model were utilized. U-Net performance was evaluated using Dice coefficients (DC) and Hausdorff distances (HD) between the U-Net-generated and manually segmented WBDs.ResultsThe U-Net achieved a DC (median[range]) of 0.984[0.936-0.990] and HD of 1.69[1.01-6.78] mm for OPI rat model scans, and a DC (mean[range]) of 0.975[0.898-0.991] and HD of 1.49[0.86-3.89] for the AD rat model scans.Comparison with existing methodsThe proposed approach is fully automated and robust across two rat strains and longitudinal brain changes with a computational speed of 8 seconds/scan, overcoming limitations of manual segmentation.ConclusionsThe modified 2D U-Net provided a fully automated, efficient, and generalizable segmentation approach that achieved high accuracy across two disparate rat models of neurological diseases.

PurposeThis study aimed to compare a new Artificial Intelligence (AI) method to conventional mathematical warping in accurately overlaying peripheral retinal vessels from two different imaging devices: confocal scanning laser ophthalmoscope (cSLO) wide-field images and SLO ultra-wide field images.MethodsImages were captured using the Heidelberg Spectralis 55-degree field-of-view and Optos ultra-wide field. The conventional mathematical warping was performed using Random Sample Consensus-Sample and Consensus sets (RANSAC-SC). This was compared to an AI alignment algorithm based on a one-way forward registration procedure consisting of full Convolutional Neural Networks (CNNs) with Outlier Rejection (OR CNN), as well as an iterative 3D camera pose optimization process (OR CNN + Distortion Correction [DC]). Images were provided in a checkerboard pattern, and peripheral vessels were graded in four quadrants based on alignment to the adjacent box.ResultsA total of 660 boxes were analysed from 55 eyes. Dice scores were compared between the three methods (RANSAC-SC/OR CNN/OR CNN + DC): 0.3341/0.4665/4784 for fold 1-2 and 0.3315/0.4494/4596 for fold 2-1 in composite images. The images composed using the OR CNN + DC have a median rating of 4 (out of 5) versus 2 using RANSAC-SC. The odds of getting a higher grading level are 4.8 times higher using our OR CNN + DC than RANSAC-SC (p

Objective.Artificial neural networks (ANNs) are state-of-the-art tools for modeling and decoding neural activity, but deploying them in closed-loop experiments with tight timing constraints is challenging due to their limited support in existing real-time frameworks. Researchers need a platform that fully supports high-level languages for running ANNs (e.g. Python and Julia) while maintaining support for languages that are critical for low-latency data acquisition and processing (e.g. C and C++).Approach.To address these needs, we introduce the Backend for Realtime Asynchronous Neural Decoding (BRAND). BRAND comprises Linux processes, termednodes, which communicate with each other in agraphvia streams of data. Its asynchronous design allows for acquisition, control, and analysis to be executed in parallel on streams of data that may operate at different timescales. BRAND uses Redis, an in-memory database, to send data between nodes, which enables fast inter-process communication and supports 54 different programming languages. Thus, developers can easily deploy existing ANN models in BRAND with minimal implementation changes.Main results.In our tests, BRAND achieved

This article provides an overview of the origins and early development of sports video games. The first generation of sports video games were developed by scientists in laboratories for academic purposes. Together with the rise of microcomputers and the widespread adoption of television (TV) sets, commercial video games began to emerge in the early 1970s. Like their laboratory predecessors, most of the first-generation commercial games were sports-themed and primarily designed as a platform for competition between players. In the second half of the 1970s, ball-and-paddle-based games began to be replaced by more sophisticated games adopting the rules and actions of real-life sports. By the late 1970s and early 1980s, intense competition between video game companies gave birth to many innovative titles, with various sports disciplines adapted into games. Most of the sports games created in this period were based on competitive sports including American football, basketball, baseball, soccer, and tennis, as well as recreational sports like bowling, pool, and darts, many of them long popular in Western Europe and North America, some with a huge fan base in Japan. They were clearly produced to cater to the needs of gamers and sports fans in the world's three major TV, personal computer, video game, and sports markets at the time. [ABSTRACT FROM AUTHOR]

Traditional histochemical staining of post-mortem samples often confronts inferior staining quality due to autolysis caused by delayed fixation of cadaver tissue, and such chemical staining procedures covering large tissue areas demand substantial labor, cost and time. Here, we demonstrate virtual staining of autopsy tissue using a trained neural network to rapidly transform autofluorescence images of label-free autopsy tissue sections into brightfield equivalent images, matching hematoxylin and eosin (H&E) stained versions of the same samples. The trained model can effectively accentuate nuclear, cytoplasmic and extracellular features in new autopsy tissue samples that experienced severe autolysis, such as COVID-19 samples never seen before, where the traditional histochemical staining fails to provide consistent staining quality. This virtual autopsy staining technique provides a rapid and resource-efficient solution to generate artifact-free H&E stains despite severe autolysis and cell death, also reducing labor, cost and infrastructure requirements associated with the standard histochemical staining.

Recent developments in protein design rely on large neural networks with up to 100s of millions of parameters, yet it is unclear which residue dependencies are critical for determining protein function. Here, we show that amino acid preferences at individual residues-without accounting for mutation interactions-explain much and sometimes virtually all of the combinatorial mutation effects across 8 datasets (R2 ~ 78-98%). Hence, few observations (~100 times the number of mutated residues) enable accurate prediction of held-out variant effects (Pearson r > 0.80). We hypothesized that the local structural contexts around a residue could be sufficient to predict mutation preferences, and develop an unsupervised approach termed CoVES (Combinatorial Variant Effects from Structure). Our results suggest that CoVES outperforms not just model-free methods but also similarly to complex models for creating functional and diverse protein variants. CoVES offers an effective alternative to complicated models for identifying functional protein mutations.

Traditional systems for indoor pressure sensing and human activity recognition (HAR) rely on costly, high-resolution mats and computationally intensive neural network-based (NN-based) models that are prone to noise. In contrast, we design a cost-effective and noise-resilient pressure mat system for HAR, leveraging Velostat for intelligent pressure sensing and a novel hyperdimensional computing (HDC) classifier that is lightweight and highly noise resilient. To measure the performance of our system, we collected two datasets, capturing the static and continuous nature of human movements. Our HDC-based classification algorithm shows an accuracy of 93.19%, improving the accuracy by 9.47% over state-of-the-art CNNs, along with an 85% reduction in energy consumption. We propose a new HDC noise-resilient algorithm and analyze the performance of our proposed method in the presence of three different kinds of noise, including memory and communication, input, and sensor noise. Our system is more resilient across all three noise types. Specifically, in the presence of Gaussian noise, we achieve an accuracy of 92.15% (97.51% for static data), representing a 13.19% (8.77%) improvement compared to state-of-the-art CNNs.

The retina and primary visual cortex (V1) both exhibit diverse neural populations sensitive to diverse visual features. Yet it remains unclear how neural populations in each area partition stimulus space to span these features. One possibility is that neural populations are organized into discrete groups of neurons, with each group signaling a particular constellation of features. Alternatively, neurons could be continuously distributed across feature-encoding space. To distinguish these possibilities, we presented a battery of visual stimuli to the mouse retina and V1 while measuring neural responses with multi-electrode arrays. Using machine learning approaches, we developed a manifold embedding technique that captures how neural populations partition feature space and how visual responses correlate with physiological and anatomical properties of individual neurons. We show that retinal populations discretely encode features, while V1 populations provide a more continuous representation. Applying the same analysis approach to convolutional neural networks that model visual processing, we demonstrate that they partition features much more similarly to the retina, indicating they are more like big retinas than little brains.

The prediction of depression is a crucial area of research which makes it one of the top priorities in mental health research as it enables early intervention and can lead to higher success rates in treatment. Self-reported feelings by patients represent a valuable biomarker for predicting depression as they can be expressed in a lower-dimensional network form, offering an advantage in visualizing the interactive characteristics of depression-related feelings. Furthermore, the network form of data expresses high-dimensional data in a compact form, making the data easy to use as input for the machine learning processes. In this study, we applied the graph convolutional network (GCN) algorithm, an effective machine learning tool for handling network data, to predict depression-prone patients using the network form of self-reported log data as the input. We took a data augmentation step to expand the initially small dataset and fed the resulting data into the GCN algorithm, which achieved a high level of accuracy from 86-97% and an F1 (harmonic mean of precision and recall) score of 0.83-0.94 through three experimental cases. In these cases, the ratio of depressive cases varied, and high accuracy and F1 scores were observed in all three cases. This study not only demonstrates the potential for predicting depression-prone patients using self-reported logs as a biomarker in advance, but also shows promise in handling small data sets in the prediction, which is critical given the challenge of obtaining large datasets for biomarker research. The combination of self-reported logs and the GCN algorithm is a promising approach for predicting depression and warrants further investigation.

Computational cognitive models have been used extensively to formalize cognitive processes. Model parameters offer a simple way to quantify individual differences in how humans process information. Similarly, model comparison allows researchers to identify which theories, embedded in different models, provide the best accounts of the data. Cognitive modeling uses statistical tools to quantitatively relate models to data that often rely on computing/estimating the likelihood of the data under the model. However, this likelihood is computationally intractable for a substantial number of models. These relevant models may embody reasonable theories of cognition, but are often under-explored due to the limited range of tools available to relate them to data. We contribute to filling this gap in a simple way using artificial neural networks (ANNs) to map data directly onto model identity and parameters, bypassing the likelihood estimation. We test our instantiation of an ANN as a cognitive model fitting tool on classes of cognitive models with strong inter-trial dependencies (such as reinforcement learning models), which offer unique challenges to most methods. We show that we can adequately perform both parameter estimation and model identification using our ANN approach, including for models that cannot be fit using traditional likelihood-based methods. We further discuss our work in the context of the ongoing research leveraging simulation-based approaches to parameter estimation and model identification, and how these approaches broaden the class of cognitive models researchers can quantitatively investigate.

Passive acoustic monitoring is an essential tool for studying beaked whale populations. This approach can monitor elusive and pelagic species, but the volume of data it generates has overwhelmed researchers ability to quantify species occurrence for effective conservation and management efforts. Automation of data processing is crucial, and machine learning algorithms can rapidly identify species using their sounds. Beaked whale acoustic events, often infrequent and ephemeral, can be missed when co-occurring with signals of more abundant, and acoustically active species that dominate acoustic recordings. Prior efforts on large-scale classification of beaked whale signals with deep neural networks (DNNs) have approached the class as one of many classes, including other odontocete species and anthropogenic signals. That approach tends to miss ephemeral events in favor of more common and dominant classes. Here, we describe a DNN method for improved classification of beaked whale species using an extensive dataset from the western North Atlantic. We demonstrate that by training a DNN to focus on the taxonomic family of beaked whales, ephemeral events were correctly and efficiently identified to species, even with few echolocation clicks. By retrieving ephemeral events, this method can support improved estimation of beaked whale occurrence in regions of high odontocete acoustic activity.

Deep learning shows promise for automating detection and classification of wildlife from digital aerial imagery to support cost-efficient remote sensing solutions for wildlife population monitoring. To support in-flight orthorectification and machine learning processing to detect and classify wildlife from imagery in near real-time, we evaluated deep learning methods that address hardware limitations and the need for processing efficiencies to support the envisioned in-flight workflow. We developed an annotated dataset for a suite of marine birds from high-resolution digital aerial imagery collected over open water environments to train the models. The proposed 3-stage workflow for automated, in-flight data processing includes: 1) image filtering based on the probability of any bird occurrence, 2) bird instance detection, and 3) bird instance classification. For image filtering, we compared the performance of a binary classifier with Mask Region-based Convolutional Neural Network (Mask R-CNN) as a means of sub-setting large volumes of imagery based on the probability of at least one bird occurrence in an image. On both the validation and test datasets, the binary classifier achieved higher performance than Mask R-CNN for predicting bird occurrence at the image-level. We recommend the binary classifier over Mask R-CNN for workflow first-stage filtering. For bird instance detection, we leveraged Mask R-CNN as our detection framework and proposed an iterative refinement method to bootstrap our predicted detections from loose ground-truth annotations. We also discuss future work to address the taxonomic classification phase of the envisioned workflow.

Based on the theory of cognitive linguistics, this article investigates computer-related conceptual metaphors in discourses in online Vietnamese newspapers to clarify how Vietnamese people conceptualize the target domain of "brain" via the source domain of "computer". This study aimed to answer two questions: "In online Vietnamese articles, which thinking mechanism is used to conceptualize the human brain as a computer?" and "What similarities from the target domain are activated and mapped onto the source domain?" With the correlations in experience and knowledge projected from the source domain to the target domain, the logical relationship in organizing the mapping scheme of conceptual metaphors, the article points out a type of thinking in the conceptual structure dominated by the 4.0 industrial civilization which is both universal and typical of Vietnamese people's mind. [ABSTRACT FROM AUTHOR]

Introduction: In spite of rapid advances in evidence-based treatments for attention deficit hyperactivity disorder (ADHD), community access to rigorous gold-standard diagnostic assessments has lagged far behind due to barriers such as the costs and limited availability of comprehensive diagnostic evaluations. Digital assessment of attention and behavior has the potential to lead to scalable approaches that could be used to screen large numbers of children and/or increase access to highquality, scalable diagnostic evaluations, especially if designed using user-centered participatory and ability-based frameworks. Current research on assessment has begun to take a user-centered approach by actively involving participants to ensure the development of assessments that meet the needs of users (e.g., clinicians, teachers, patients). Methods: The objective of this mapping review was to identify and categorize digital mental health assessments designed to aid in the initial diagnosis of ADHD as well as ongoing monitoring of symptoms following diagnosis. Results: Results suggested that the assessment tools currently described in the literature target both cognition and motor behaviors. These assessments were conducted using a variety of technological platforms, including telemedicine, wearables/sensors, the web, virtual reality, serious games, robots, and computer applications/software. Discussion: Although it is evident that there is growing interest in the design of digital assessment tools, research involving tools with the potential for widespread deployment is still in the early stages of development. As these and other tools are developed and evaluated, it is critical that researchers engage patients and key stakeholders early in the design process. [ABSTRACT FROM AUTHOR]

Key points While typically diagnosed with biopsy, ECRS may be predicted preoperatively with the use of AI. Various AI models have been used, with pooled sensitivity of 0.857 and specificity of 0.850. We found no statistically significant difference between the accuracy of various AI models. While typically diagnosed with biopsy, ECRS may be predicted preoperatively with the use of AI.Various AI models have been used, with pooled sensitivity of 0.857 and specificity of 0.850.We found no statistically significant difference between the accuracy of various AI models. [ABSTRACT FROM AUTHOR]

The beginning of the twenty-first century is marked by the rapid development of information technologies in all areas of scientific development. At the same time, information is increasingly becoming a strategic resource, a productive force, and an expensive commodity. Computer systems and network technologies are developing very rapidly. Accordingly, new methods for protecting information are also emerging rapidly. The problem of information protection and reliable provision of its security is one of the most important problems of our time. Therefore, the topic is very relevant. The unification of computer systems leads to the creation of global networks and expansion of access to information resources. The increase in the complexity of software leads to a decrease in their reliability and an increase in the number of vulnerabilities. Computer networks, due to their specific nature, simply cannot function and develop normally without ignoring information security issues. [ABSTRACT FROM AUTHOR]

Background: Studies have shown that prolonged television watching increases obesity risk among children. However, few studies examined the associations with other types of screen time, such as computer and smartphone use, using a prospective cohort study design. Further, little is known about the specific non-screen time activity that may yield the most benefits when reallocating screen time to other activities. Methods: We conducted a prospective cohort analysis using 3-year follow-up data from the Korean Children and Youth Panel Survey 2018 (n = 2,023; 4th grade elementary students who were not obese at baseline). Average time spent watching television, using computer and smartphone, and other after-school activities were self-reported at baseline. Weight and height were also self-reported at baseline and follow-up surveys through 2021. We performed multivariable logistic regression models to estimate odds ratios (ORs) and 95% confidence intervals (CIs) for the associations between screen time and obesity incidence, adjusting for potential confounders. We also performed isotemporal substitution models to examine the associations of reallocating screen time to other non-screen time activities (physical activity, sleeping, hanging out with friends, reading, studying, and chatting with parents) in an equal time-exchange manner. Results: Longer combined screen time (≥ 240 vs. <120 m/d) was statistically significantly associated with an increased obesity risk (OR [95% CI] = 1.68 [1.03, 2.73]). The direction of associations with television watching (≥ 180 vs. <60 m/d: OR [95% CI] = 2.86 [1.58, 5.20]), computer use (≥ 120 vs. <60 m/d: 1.38 [0.52, 3.64]), and smartphone use (≥ 180 vs. <60 m/d: 1.42 [0.76, 2.65]) were all positive, although the association was most apparent and statistically significant for television watching only. The associations did not change after additional adjustment for other lifestyle factors, including physical activity, sleep, and breakfast skipping. In the isotemporal substitution models, reallocating 1-hour of screen time to reading (OR [95% CI] = 0.67 [0.48, 0.93]) was associated with a decreased obesity risk. Reallocating 1-hour of screen time to physical activity was only marginally significantly associated with obesity risk (0.79 [0.62, 1.01]). Conclusions: Our data suggest that more efforts should focus on reducing screen time and increasing time for other non-screen time activities, particularly reading, for obesity prevention in children. [ABSTRACT FROM AUTHOR]

Background and Objectives: Non-specific neck and shoulder pain (NSNSP) is prevalent among working adults. The increased use of electronic devices and prevalence of remote working and study following the COVID-19 pandemic have raised concerns about the potential rise in such conditions. This study aims to investigate the associations between work-related, lifestyle factors and NSNSP in the adult Southeast Asian Singaporean population. Materials and Methods: An online survey was administered electronically to Singaporeans aged 21 and above. Demographic data, NSNSP prevalence, computer and smartphone usage durations, sleep patterns, and exercise frequency were captured after obtaining informed consent (SIT institutional review board approval #2023014). Results: A total of 302 validated responses were recorded, including 212 suffering from NSNSP versus 90 in the comparison group. The NSNSP group showed significantly longer smartphone usage (5.37 ± 3.50 h/day) compared to the comparison group (4.46 ± 3.36 h/day, p = 0.04). Furthermore, the NSNSP group had lower exercise frequency (2.10 ± 1.74 days/week vs. 2.93 ± 2.21 days/week, p < 0.01) and shorter weekly exercise duration (2.69 ± 3.05 h/week vs. 4.11 ± 4.15 h/week, p < 0.01). The average NSNSP severity in this group was 34.9 ± 19.96 out of 100, correlating significantly with age (r = 0.201, p < 0.01) and BMI (r = 0.27, p < 0.01). Conclusions: This preliminary cross-sectional study examines characteristics of adult Southeast Asians with NSNSP post-COVID-19 pandemic. The findings indicate significantly longer smartphone use and less exercise in NSNSP respondents, with both age and body mass index (BMI) demonstrating significant correlations with NSNSP severity. [ABSTRACT FROM AUTHOR]

Advancements in diagnostic methods and surgical techniques for keratoconus (KC) have increased non-invasive treatment options. Successful surgical planning for KC involves a combination of clinical science, empirical evidence, and surgical expertise. Assessment of disease progression is crucial, and halting the progression should be the focus if it is progressive. While surgeons used to rely on experience alone to decide the surgical method, comparing the network of primary factors, such as visual acuity, across studies can help them choose the most appropriate treatments for each patient and achieve optimal outcomes. Meticulous tabulation methods facilitate interpretation, highlighting the importance of selecting the correct surgical and rehabilitation approach based on each patient's condition and stage of the disease. We detail the outcomes of a comprehensive network meta-analysis comparing the effectiveness of various combined therapeutic refractive treatments for KC at identical stages of the disease, spanning 4 distinct follow-up intervals. Additionally, the comprehensive analysis suggests that for corneas with optimal best corrected visual acuity (BCVA) preoperatively (classified as regular), combining phakic intraocular lenses with intracorneal ring segments (ICRS) and corneal cross-linking (CXL) could offer the best therapeutic approach provided the disease stage does not exceed stage 3. For irregular corneas, although initial follow-ups show a significant difference in BCVA with surface ablation, longer-term follow-ups recommend combining surface ablation with ICRS and CXL, especially at higher stages. [ABSTRACT FROM AUTHOR]

Copyright of Arquivos Brasileiros de Oftalmologia is the property of Arquivos Brasileiros de Oftalmologia and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Tractors are the most important agricultural power machinery. With the development of tractors toward large-scale and electrification, the design of modern tractor transmission systems increasingly relies on computer simulation technology. However, tractor transmission systems, especially power-shift transmissions and CVTs, are highly complex industrial products that involve specialized knowledge from multiple disciplines. Engineers and researchers find it difficult to choose the correct mathematical model and grasp the trend of technological development when applying simulation technology. To address this issue, we conducted a systematic review of the field and carried out the following work: First, the types and basic principles of tractor transmission systems were introduced; Second, the modeling methods and applications of computer simulation technology in the structural optimization, power-shift control, and energy saving of tractor transmission systems were reviewed; Finally, the method of obtaining simulation parameters through system identification was introduced. Although computer simulation technology has been applied in the development of all tractor transmission systems, there are still some issues that need attention, such as the lack of established shift quality evaluation indicators and driving cycles suitable for tractors, which are crucial for the reliability of simulation results but are rarely studied. These issues need to be addressed in future work. [ABSTRACT FROM AUTHOR]

PURPOSE: Two-dimensional radiotherapy is often used to treat cervical cancer in low- and middle-income countries, but treatment planning can be challenging and time-consuming. Neural networks offer the potential to greatly decrease planning time through automation, but the impact of the wide range of hyperparameters to be set during training on model accuracy has not been exhaustively investigated. In the current study, we evaluated the effect of several convolutional neural network architectures and hyperparameters on 2D radiotherapy treatment field delineation. METHODS: Six commonly used deep learning architectures were trained to delineate four-field box apertures on digitally reconstructed radiographs for cervical cancer radiotherapy. A comprehensive search of optimal hyperparameters for all models was conducted by varying the initial learning rate, image normalization methods, and (when appropriate) convolutional kernel size, the number of learnable parameters via network depth and the number of feature maps per convolution, and nonlinear activation functions. This yielded over 1700 unique models, which were all trained until performance converged and then tested on a separate dataset. RESULTS: Of all hyperparameters, the choice of initial learning rate was most consistently significant for improved performance on the test set, with all top-performing models using learning rates of 0.0001. The optimal image normalization was not consistent across architectures. High overlap (mean Dice similarity coefficient = 0.98) and surface distance agreement (mean surface distance

The human auditory system extracts rich linguistic abstractions from speech signals. Traditional approaches to understanding this complex process have used linear feature-encoding models, with limited success. Artificial neural networks excel in speech recognition tasks and offer promising computational models of speech processing. We used speech representations in state-of-the-art deep neural network (DNN) models to investigate neural coding from the auditory nerve to the speech cortex. Representations in hierarchical layers of the DNN correlated well with the neural activity throughout the ascending auditory system. Unsupervised speech models performed at least as well as other purely supervised or fine-tuned models. Deeper DNN layers were better correlated with the neural activity in the higher-order auditory cortex, with computations aligned with phonemic and syllabic structures in speech. Accordingly, DNN models trained on either English or Mandarin predicted cortical responses in native speakers of each language. These results reveal convergence between DNN model representations and the biological auditory pathway, offering new approaches for modeling neural coding in the auditory cortex.

Abstract Background We examined the associations between screen time and adolescent obesity and the associations of reallocating screen time to other activities using isotemporal substitution models. Understanding the association between screen time and obesity may provide additional insights into effective obesity prevention strategies in adolescents. Methods We conducted a cross-sectional analysis of 5,180 adolescents (4th and 7th grade students) from the Korean Children and Youth Panel Survey 2018. Participants reported their height, weight, and average time spent watching television, using computer, using smartphone, and other after-school activities. Obesity was defined as BMI-for-age and -sex ≥ 95th percentile based on the 2017 Korean National Growth Charts. We performed multivariable logistic regression to estimate odds ratios (ORs) and 95% confidence intervals (CIs) for the associations between screen time and obesity prevalence, adjusting for potential confounders. Results Prolonged smartphone use (≥ 180 vs.

Abstract Background Studies have shown that prolonged television watching increases obesity risk among children. However, few studies examined the associations with other types of screen time, such as computer and smartphone use, using a prospective cohort study design. Further, little is known about the specific non-screen time activity that may yield the most benefits when reallocating screen time to other activities. Methods We conducted a prospective cohort analysis using 3-year follow-up data from the Korean Children and Youth Panel Survey 2018 (n = 2,023; 4th grade elementary students who were not obese at baseline). Average time spent watching television, using computer and smartphone, and other after-school activities were self-reported at baseline. Weight and height were also self-reported at baseline and follow-up surveys through 2021. We performed multivariable logistic regression models to estimate odds ratios (ORs) and 95% confidence intervals (CIs) for the associations between screen time and obesity incidence, adjusting for potential confounders. We also performed isotemporal substitution models to examine the associations of reallocating screen time to other non-screen time activities (physical activity, sleeping, hanging out with friends, reading, studying, and chatting with parents) in an equal time-exchange manner. Results Longer combined screen time (≥ 240 vs.

A primary challenge of high-throughput imaging flow cytometry (IFC) is to analyze the vast amount of imaging data, especially in applications where ground truth labels are unavailable or hard to obtain. We present an unsupervised deep embedding algorithm, the Deep Convolutional Autoencoder-based Clustering (DCAEC) model, to cluster label-free IFC images without any prior knowledge of input labels. The DCAEC model first encodes the input images into the latent representations and then clusters based on the latent representations. Using the DCAEC model, we achieve a balanced accuracy of 91.9% for human white blood cell (WBC) clustering and 97.9% for WBC/leukemia clustering using the 3D IFC images and 3D DCAEC model. Above all, although no human recognizable features can separate the clusters of cells with protein localization, we demonstrate the fused DCAEC model can achieve a cluster balanced accuracy of 85.3% from the label-free 2D transmission and 3D side scattering images. To reveal how the neural network recognizes features beyond human ability, we use the gradient-weighted class activation mapping method to discover the cluster-specific visual patterns automatically. Evaluation results show that the automatically identified salient image regions have strong cluster-specific visual patterns for different clusters, which we believe is a stride for the interpretable neural network for cell analysis with high-throughput IFCs.

Lung adenocarcinoma (LUAD) is a morphologically heterogeneous disease with five predominant histologic subtypes. Fully supervised convolutional neural networks can improve the accuracy and reduce the subjectivity of LUAD histologic subtyping using hematoxylin and eosin (H&E)-stained whole slide images (WSIs). However, developing supervised models with good prediction accuracy usually requires extensive manual data annotation, which is time-consuming and labor-intensive. This work proposes three self-supervised learning (SSL) pretext tasks to reduce labeling effort. These tasks not only leverage the multi-resolution nature of the H&E WSIs but also explicitly consider the relevance to the downstream task of classifying the LUAD histologic subtypes. Two tasks involve predicting the spatial relationship between tiles cropped from lower and higher magnification WSIs. We hypothesize that these tasks induce the model to learn to distinguish different tissue structures presented in the images, thus benefiting the downstream classification. The third task involves predicting the eosin stain from the hematoxylin stain, inducing the model to learn cytoplasmic features relevant to LUAD subtypes. The effectiveness of the three proposed SSL tasks and their ensemble was demonstrated by comparison with other state-of-the-art pretraining and SSL methods using three publicly available datasets. Our work can be extended to any other cancer type where tissue architectural information is important. The model could be used to expedite and complement the process of routine pathology diagnosis tasks. The code is available at https://github.com/rina-ding/ssl_luad_classification.

PURPOSE: Predict central 10° global and local visual field (VF) measurements from macular optical coherence tomography (OCT) volume scans with deep learning (DL). METHODS: This study included 1121 OCT volume scans and 10-2 VFs from 289 eyes (257 patients). Macular scans were used to estimate 10-2 VF mean deviation (MD), threshold sensitivities (TS), and total deviation (TD) values at 68 locations. A three-dimensional (3D) convolutional neural network based on the 3D DenseNet121 architecture was used for prediction. We compared DL predictions to those from baseline linear models. We carried out 10-fold stratified cross-validation to optimize generalizability. The performance of the DL and baseline models was compared based on correlations between ground truth and predicted VF measures and mean absolute error (MAE; ground truth - predicted values). RESULTS: Average (SD) MD was -9.3 (7.7) dB. Average (SD) correlations between predicted and ground truth MD and MD MAE were 0.74 (0.09) and 3.5 (0.4) dB, respectively. Estimation accuracy deteriorated with worsening MD. Average (SD) Pearson correlations between predicted and ground truth TS and MAEs for DL and baseline model were 0.71 (0.05) and 0.52 (0.05) (P < 0.001) and 6.5 (0.6) and 7.5 (0.5) dB (P < 0.001), respectively. For TD, correlation (SD) and MAE (SD) for DL and baseline models were 0.69 (0.02) and 0.48 (0.05) (P < 0.001) and 6.1 (0.5) and 7.8 (0.5) dB (P < 0.001), respectively. CONCLUSIONS: Macular OCT volume scans can be used to predict global central VF parameters with clinically relevant accuracy. TRANSLATIONAL RELEVANCE: Macular OCT imaging may be used to confirm and supplement central VF findings using deep learning.

The present study investigates whether less computer access is associated with an increase or decrease in cyberbullying and face-to-face bullying victimization. Data were derived from the 2009-2010 Health Behavior in School-Aged Children U.S. Study, consisting of 12,642 adolescents aged 11, 13, and 15 years (Mage = 12.95). We found that less computer usage was negatively associated with cyberbullying victimization and face-to-face bullying victimization. The findings from the study have implications for research and practice.

The single-step approach has become the most widely-used methodology for genomic evaluations when only a subset of phenotyped individuals in the pedigree are genotyped, where the genotypes for non-genotyped individuals are imputed based on gene contents (i.e., genotypes) of genotyped individuals through their pedigree relationships. We proposed a new method named single-step neural network with mixed models (NNMM) to represent single-step genomic evaluations as a neural network of three sequential layers: pedigree, genotypes, and phenotypes. These three sequential layers of information create a unified network instead of two separate steps, allowing the unobserved gene contents of non-genotyped individuals to be sampled based on pedigree, observed genotypes of genotyped individuals, and phenotypes. In addition to imputation of genotypes using all three sources of information, including phenotypes, genotypes, and pedigree, single-step NNMM provides a more flexible framework to allow nonlinear relationships between genotypes and phenotypes, and for individuals to be genotyped with different single-nucleotide polymorphism (SNP) panels. The single-step NNMM has been implemented in the software package JWAS.

We propose a subject-aware contrastive learning deep fusion neural network framework for effectively classifying subjects confidence levels in the perception of visual stimuli. The framework, called WaveFusion, is composed of lightweight convolutional neural networks for per-lead time-frequency analysis and an attention network for integrating the lightweight modalities for final prediction. To facilitate the training of WaveFusion, we incorporate a subject-aware contrastive learning approach by taking advantage of the heterogeneity within a multi-subject electroencephalogram dataset to boost representation learning and classification accuracy. The WaveFusion framework demonstrates high accuracy in classifying confidence levels by achieving a classification accuracy of 95.7% while also identifying influential brain regions.

Bowel obstruction is a common cause of acute abdominal pain. The development of algorithms for automated detection and characterization of bowel obstruction on CT has been limited by the effort required for manual annotation. Visual image annotation with an eye tracking device may mitigate that limitation. The purpose of this study is to assess the agreement between visual and manual annotations for bowel segmentation and diameter measurement, and to assess agreement with convolutional neural networks (CNNs) trained using that data. Sixty CT scans of 50 patients with bowel obstruction from March to June 2022 were retrospectively included and partitioned into training and test data sets. An eye tracking device was used to record 3-dimensional coordinates within the scans, while a radiologist cast their gaze at the centerline of the bowel, and adjusted the size of a superimposed ROI to approximate the diameter of the bowel. For each scan, 59.4 ± 15.1 segments, 847.9 ± 228.1 gaze locations, and 5.8 ± 1.2 m of bowel were recorded. 2d and 3d CNNs were trained using this data to predict bowel segmentation and diameter maps from the CT scans. For comparisons between two repetitions of visual annotation, CNN predictions, and manual annotations, Dice scores for bowel segmentation ranged from 0.69 ± 0.17 to 0.81 ± 0.04 and intraclass correlations [95% CI] for diameter measurement ranged from 0.672 [0.490-0.782] to 0.940 [0.933-0.947]. Thus, visual image annotation is a promising technique for training CNNs to perform bowel segmentation and diameter measurement in CT scans of patients with bowel obstruction.