Int J Comput Assist Radiol Surg. 2024 Jul 4. doi: 10.1007/s11548-024-03221-z. Online ahead of print.

ABSTRACT

PURPOSE: Cardiac perfusion MRI is vital for disease diagnosis, treatment planning, and risk stratification, with anomalies serving as markers of underlying ischemic pathologies. AI-assisted methods and tools enable accurate and efficient left ventricular (LV) myocardium segmentation on all DCE-MRI timeframes, offering a solution to the challenges posed by the multidimensional nature of the data. This study aims to develop and assess an automated method for LV myocardial segmentation on DCE-MRI data of a local hospital.

METHODS: The study consists of retrospective DCE-MRI data from 55 subjects acquired at the local hospital using a 1.5 T MRI scanner. The dataset included subjects with and without cardiac abnormalities. The timepoint for the reference frame (post-contrast LV myocardium) was identified using standard deviation across the temporal sequences. Iterative image registration of other temporal images with respect to this reference image was performed using Maxwell's demons algorithm. The registered stack was fed to the model built using the U-Net framework for predicting the LV myocardium at all timeframes of DCE-MRI.

RESULTS: The mean and standard deviation of the dice similarity coefficient (DSC) for myocardial segmentation using pre-trained network Net_cine is 0.78 ± 0.04, and for the fine-tuned network Net_dyn which predicts mask on all timeframes individually, it is 0.78 ± 0.03. The DSC for Net_dyn ranged from 0.71 to 0.93. The average DSC achieved for the reference frame is 0.82 ± 0.06.

CONCLUSION: The study proposed a fast and fully automated AI-assisted method to segment LV myocardium on all timeframes of DCE-MRI data. The method is robust, and its performance is independent of the intra-temporal sequence registration and can easily accommodate timeframes with potential registration errors.

PMID:38965165 | DOI:10.1007/s11548-024-03221-z

Top Curr Chem (Cham). 2024 Jul 4;382(3):23. doi: 10.1007/s41061-024-00469-6.

ABSTRACT

In recent years, there has been a notable increase in the scientific community's interest in rational protein design. The prospect of designing an amino acid sequence that can reliably fold into a desired three-dimensional structure and exhibit the intended function is captivating. However, a major challenge in this endeavor lies in accurately predicting the resulting protein structure. The exponential growth of protein databases has fueled the advancement of the field, while newly developed algorithms have pushed the boundaries of what was previously achievable in structure prediction. In particular, using deep learning methods instead of brute force approaches has emerged as a faster and more accurate strategy. These deep-learning techniques leverage the vast amount of data available in protein databases to extract meaningful patterns and predict protein structures with improved precision. In this article, we explore the recent developments in the field of protein structure prediction. We delve into the newly developed methods that leverage deep learning approaches, highlighting their significance and potential for advancing our understanding of protein design.

PMID:38965117 | DOI:10.1007/s41061-024-00469-6

J Visc Surg. 2024 Jul 3:S1878-7886(24)00090-0. doi: 10.1016/j.jviscsurg.2024.06.007. Online ahead of print.

ABSTRACT

BACKGROUND: With steep posterior anorectal angulation, transanal total mesorectal excision (taTME) may have a risk of dissection in the wrong plane or starting higher up, resulting in leaving distal mesorectum behind. Although the distal mesorectal margin can be assessed by preoperative MRI, it needs skilled radiologist and high-definition image for accurate evaluation. This study developed a deep neural network (DNN) to predict the optimal level of distal mesorectal margin.

METHODS: A total of 182 pelvic MRI images extracted from the cancer image archive (TCIA) database were included. A DNN was developed using gender, the degree of anterior and posterior anorectal angles as input variables while the difference between anterior and posterior mesorectal distances from anal verge was selected as a target. The predictability power was assessed by regression values (R) which is the correlation between the predicted outputs and actual targets.

RESULTS: The anterior angle was an obtuse angle while the posterior angle varied from acute to obtuse with mean angle difference 35.5°±14.6. The mean difference between the anterior and posterior mesorectal end distances was 18.6±6.6mm. The developed DNN had a very close correlation with the target during training, validation, and testing (R=0.99, 0.81, and 0.89, P<0.001). The predicted level of distal mesorectal margin was closely correlated with the actual optimal level (R=0.91, P<0.001).

CONCLUSIONS: Artificial intelligence can assist in either making or confirming the preoperative decisions. Furthermore, the developed model can alert the surgeons for this potential risk and the necessity of re-positioning the proctectomy incision.

PMID:38964939 | DOI:10.1016/j.jviscsurg.2024.06.007

Biosystems. 2024 Jul 2:105264. doi: 10.1016/j.biosystems.2024.105264. Online ahead of print.

ABSTRACT

Computational analysis of paratope-epitope interactions between antibodies and their corresponding antigens can facilitate our understanding of the molecular mechanism underlying humoral immunity and boost the design of new therapeutics for many diseases. The recent breakthrough in artificial intelligence has made it possible to predict protein-protein interactions and model their structures. Unfortunately, detecting antigen-binding sites associated with a specific antibody is still a challenging problem. To tackle this challenge, we implemented a deep learning model to characterize interaction patterns between antibodies and their corresponding antigens. With high accuracy, our model can distinguish between antibody-antigen complexes and other types of protein-protein complexes. More intriguingly, we can identify antigens from other common protein binding regions with an accuracy of higher than 70% even if we only have the epitope information. This indicates that antigens have distinct features on their surface that antibodies can recognize. Additionally, our model was unable to predict the partnerships between antibodies and their particular antigens. This result suggests that one antigen may be targeted by more than one antibody and that antibodies may bind to previously unidentified proteins. Taken together, our results support the precision of antibody-antigen interactions while also suggesting positive future progress in the prediction of specific pairing.

PMID:38964652 | DOI:10.1016/j.biosystems.2024.105264

IEEE J Biomed Health Inform. 2024 Jul 4;PP. doi: 10.1109/JBHI.2024.3423461. Online ahead of print.

ABSTRACT

Pulse wave analysis, a non-invasive and cuffless approach, holds promise for blood pressure (BP) measurement in precision medicine. In recent years, pulse wave learning for BP estimation has undergone extensive scrutiny. However, prevailing methods still encounter challenges in grasping comprehensive features from pulse waves and generalizing these insights for precise BP estimation. In this study, we propose a general pulse wave deep learning (PWDL) approach for BP estimation, introducing the OVAR-BPnet model to powerfully capture intricate pulse wave features and showcasing its effectiveness on multiple types of pulse waves. The approach involves constructing population pulse waves and employing a model comprising an omni-scale convolution subnet, a Vision Transformer subnet, and a multilayer perceptron subnet. This design enables the learning of both single-period and multi-period waveform features from multiple subjects. Additionally, the approach employs a data augmentation strategy to enhance the morphological features of pulse waves and devise a label sequence regularization strategy to strengthen the intrinsic relationship of the subnets' output. Notably, this is the first study to validate the performance of the deep learning approach of BP estimation on three types of pulse waves: photoplethysmography, forehead imaging photoplethysmography, and radial artery pulse pressure waveform. Experiments show that the OVAR-BPnet model has achieved advanced levels in both evaluation indicators and international evaluation criteria, demonstrating its excellent competitiveness and generalizability. The PWDL approach has the potential for widespread application in convenient and continuous BP monitoring systems.

PMID:38963748 | DOI:10.1109/JBHI.2024.3423461

IEEE Trans Pattern Anal Mach Intell. 2024 Jul 4;PP. doi: 10.1109/TPAMI.2024.3423382. Online ahead of print.

ABSTRACT

In deep learning, different kinds of deep networks typically need different optimizers, which have to be chosen after multiple trials, making the training process inefficient. To relieve this issue and consistently improve the model training speed across deep networks, we propose the ADAptive Nesterov momentum algorithm, Adan for short. Adan first reformulates the vanilla Nesterov acceleration to develop a new Nesterov momentum estimation (NME) method, which avoids the extra overhead of computing gradient at the extrapolation point. Then Adan adopts NME to estimate the gradient's first- and second-order moments in adaptive gradient algorithms for convergence acceleration. Besides, we prove that Adan finds an ϵ-approximate first-order stationary point within O(ϵ-3.5) stochastic gradient complexity on the non-convex stochastic problems (e.g.deep learning problems), matching the best-known lower bound. Extensive experimental results show that Adan consistently surpasses the corresponding SoTA optimizers on vision, language, and RL tasks and sets new SoTAs for many popular networks and frameworks, eg ResNet, ConvNext, ViT, Swin, MAE, DETR, GPT-2, Transformer-XL, and BERT. More surprisingly, Adan can use half of the training cost (epochs) of SoTA optimizers to achieve higher or comparable performance on ViT, GPT-2, MAE, etc, and also shows great tolerance to a large range of minibatch size, e.g.from 1k to 32k. Code is released at https://github.com/sail-sg/Adan, and has been used in multiple popular deep learning frameworks or projects.

PMID:38963744 | DOI:10.1109/TPAMI.2024.3423382

Int J Cardiovasc Imaging. 2024 Jul 4. doi: 10.1007/s10554-024-03173-0. Online ahead of print.

ABSTRACT

Coronary computed angiography (CCTA) with non-invasive fractional flow reserve (FFR) calculates lesion-specific ischemia when compared with invasive FFR and can be considered for patients with stable chest pain and intermediate-grade stenoses according to recent guidelines. The objective of this study was to compare a new CCTA-based artificial-intelligence deep-learning model for FFR prediction (FFRAI) to computational fluid dynamics CT-derived FFR (FFRCT) in patients with intermediate-grade coronary stenoses with FFR as reference standard. The FFRAI model was trained with curved multiplanar-reconstruction CCTA images of 500 stenotic vessels in 413 patients, using FFR measurements as the ground truth. We included 37 patients with 39 intermediate-grade stenoses on CCTA and invasive coronary angiography, and with FFRCT and FFR measurements in this retrospective proof of concept study. FFRAI was compared with FFRCT regarding the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and diagnostic accuracy for predicting FFR ≤ 0.80. Sensitivity, specificity, PPV, NPV, and diagnostic accuracy of FFRAI in predicting FFR ≤ 0.80 were 91% (10/11), 82% (23/28), 67% (10/15), 96% (23/24), and 85% (33/39), respectively. Corresponding values for FFRCT were 82% (9/11), 75% (21/28), 56% (9/16), 91% (21/23), and 77% (30/39), respectively. Diagnostic accuracy did not differ significantly between FFRAI and FFRCT (p = 0.12). FFRAI performed similarly to FFRCT for predicting intermediate-grade coronary stenoses with FFR ≤ 0.80. These findings suggest FFRAI as a potential non-invasive imaging tool for guiding therapeutic management in these stenoses.

PMID:38963591 | DOI:10.1007/s10554-024-03173-0

Med Biol Eng Comput. 2024 Jul 4. doi: 10.1007/s11517-024-03157-1. Online ahead of print.

ABSTRACT

Continuous blood pressure (BP) provides essential information for monitoring one's health condition. However, BP is currently monitored using uncomfortable cuff-based devices, which does not support continuous BP monitoring. This paper aims to introduce a blood pressure monitoring algorithm based on only photoplethysmography (PPG) signals using the deep neural network (DNN). The PPG signals are obtained from 125 unique subjects with 218 records and filtered using signal processing algorithms to reduce the effects of noise, such as baseline wandering, and motion artifacts. The proposed algorithm is based on pulse wave analysis of PPG signals, extracted various domain features from PPG signals, and mapped them to BP values. Four feature selection methods are applied and yielded four feature subsets. Therefore, an ensemble feature selection technique is proposed to obtain the optimal feature set based on major voting scores from four feature subsets. DNN models, along with the ensemble feature selection technique, outperformed in estimating the systolic blood pressure (SBP) and diastolic blood pressure (DBP) compared to previously reported approaches that rely only on the PPG signal. The coefficient of determination ( R 2 ) and mean absolute error (MAE) of the proposed algorithm are 0.962 and 2.480 mmHg, respectively, for SBP and 0.955 and 1.499 mmHg, respectively, for DBP. The proposed approach meets the Advancement of Medical Instrumentation standard for SBP and DBP estimations. Additionally, according to the British Hypertension Society standard, the results attained Grade A for both SBP and DBP estimations. It concludes that BP can be estimated more accurately using the optimal feature set and DNN models. The proposed algorithm has the potential ability to facilitate mobile healthcare devices to monitor continuous BP.

PMID:38963467 | DOI:10.1007/s11517-024-03157-1

Environ Monit Assess. 2024 Jul 4;196(8):699. doi: 10.1007/s10661-024-12817-6.

ABSTRACT

The United Nations (UN) emphasizes the pivotal role of sustainable agriculture in addressing persistent starvation and working towards zero hunger by 2030 through global development. Intensive agricultural practices have adversely impacted soil quality, necessitating soil nutrient analysis for enhancing farm productivity and environmental sustainability. Researchers increasingly turn to Artificial Intelligence (AI) techniques to improve crop yield estimation and optimize soil nutrition management. This study reviews 155 papers published from 2014 to 2024, assessing the use of machine learning (ML) and deep learning (DL) in predicting soil nutrients. It highlights the potential of hyperspectral and multispectral sensors, which enable precise nutrient identification through spectral analysis across multiple bands. The study underscores the importance of feature selection techniques to improve model performance by eliminating redundant spectral bands with weak correlations to targeted nutrients. Additionally, the use of spectral indices, derived from mathematical ratios of spectral bands based on absorption spectra, is examined for its effectiveness in accurately predicting soil nutrient levels. By evaluating various performance measures and datasets related to soil nutrient prediction, this paper offers comprehensive insights into the applicability of AI techniques in optimizing soil nutrition management. The insights gained from this review can inform future research and policy decisions to achieve global development goals and promote environmental sustainability.

PMID:38963427 | DOI:10.1007/s10661-024-12817-6

Bioinformatics. 2024 Jul 4:btae437. doi: 10.1093/bioinformatics/btae437. Online ahead of print.

ABSTRACT

MOTIVATION: Protein-protein Interaction (PPI) networks are crucial for automatically annotating protein functions. As multiple PPI networks exist for the same set of proteins that capture properties from different aspects, it is a challenging task to effectively utilize these heterogeneous networks. Recently, several deep learning models have combined PPI networks from all evidence, or concatenated all graph embeddings for protein function prediction. However, the lack of a judicious selection procedure prevents the effective harness of information from different PPI networks, as these networks vary in densities, structures, and noise levels. Consequently, combining protein features indiscriminately could increase the noise level, leading to decreased model performance.

RESULTS: We develop DualNetGO, a dual network model comprised of a classifier and a selector, to predict protein functions by effectively selecting features from different sources including graph embeddings of PPI networks, protein domain and subcellular location information. Evaluation of DualNetGO on human and mouse datasets in comparison with other network-based models show at least 4.5%, 6.2% and 14.2% improvement on Fmax in BP, MF and CC Gene Ontology categories respectively for human, and 3.3%, 10.6% and 7.7% improvement on Fmax for mouse. We demonstrate the generalization capability of our model by training and testing on the CAFA3 data, and show its versatility by incorporating Esm2 embeddings. We further show that our model is insensitive to the choice of graph embedding method and is time- and memory-saving. These results demonstrate that combining a subset of features including PPI networks and protein attributes selected by our model is more effective in utilizing PPI network information than only using one kind of or concatenating graph embeddings from all kinds of PPI networks.

AVAILABILITY AND IMPLEMENTATION: The source code of DualNetGO and some of the experiment data are available at: https://github.com/georgedashen/DualNetGO.

SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

PMID:38963311 | DOI:10.1093/bioinformatics/btae437

Vestn Oftalmol. 2024;140(3):82-87. doi: 10.17116/oftalma202414003182.

ABSTRACT

This article reviews literature on the use of artificial intelligence (AI) for screening, diagnosis, monitoring and treatment of glaucoma. The first part of the review provides information how AI methods improve the effectiveness of glaucoma screening, presents the technologies using deep learning, including neural networks, for the analysis of big data obtained by methods of ocular imaging (fundus imaging, optical coherence tomography of the anterior and posterior eye segments, digital gonioscopy, ultrasound biomicroscopy, etc.), including a multimodal approach. The results found in the reviewed literature are contradictory, indicating that improvement of the AI models requires further research and a standardized approach. The use of neural networks for timely detection of glaucoma based on multimodal imaging will reduce the risk of blindness associated with glaucoma.

PMID:38962983 | DOI:10.17116/oftalma202414003182

F1000Res. 2024 Jun 26;13:691. doi: 10.12688/f1000research.150773.1. eCollection 2024.

ABSTRACT

BACKGROUND: Non-contrast Computed Tomography (NCCT) plays a pivotal role in assessing central nervous system disorders and is a crucial diagnostic method. Iterative reconstruction (IR) methods have enhanced image quality (IQ) but may result in a blotchy appearance and decreased resolution for subtle contrasts. The deep-learning image reconstruction (DLIR) algorithm, which integrates a convolutional neural network (CNN) into the reconstruction process, generates high-quality images with minimal noise. Hence, the objective of this study was to assess the IQ of the Precise Image (DLIR) and the IR technique (iDose 4) for the NCCT brain.

METHODS: This is a prospective study. Thirty patients who underwent NCCT brain were included. The images were reconstructed using DLIR-standard and iDose 4. Qualitative IQ analysis parameters, such as overall image quality (OQ), subjective image noise (SIN), and artifacts, were measured. Quantitative IQ analysis parameters such as Computed Tomography (CT) attenuation (HU), image noise (IN), posterior fossa index (PFI), signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) in the basal ganglia (BG) and centrum-semiovale (CSO) were measured. Paired t-tests were performed for qualitative and quantitative IQ analyses between the iDose 4 and DLIR-standard. Kappa statistics were used to assess inter-observer agreement for qualitative analysis.

RESULTS: Quantitative IQ analysis showed significant differences (p<0.05) in IN, SNR, and CNR between the iDose 4 and DLIR-standard at the BG and CSO levels. IN was reduced (41.8-47.6%), SNR (65-82%), and CNR (68-78.8%) were increased with DLIR-standard. PFI was reduced (27.08%) the DLIR-standard. Qualitative IQ analysis showed significant differences (p<0.05) in OQ, SIN, and artifacts between the DLIR standard and iDose 4. The DLIR standard showed higher qualitative IQ scores than the iDose 4.

CONCLUSION: DLIR standard yielded superior quantitative and qualitative IQ compared to the IR technique (iDose4). The DLIR-standard significantly reduced the IN and artifacts compared to iDose 4 in the NCCT brain.

PMID:38962692 | PMC:PMC11221345 | DOI:10.12688/f1000research.150773.1

Cureus. 2024 Jun 3;16(6):e61585. doi: 10.7759/cureus.61585. eCollection 2024 Jun.

ABSTRACT

Qure.AI, a leading company in artificial intelligence (AI) applied to healthcare, has developed a suite of innovative solutions to revolutionize medical diagnosis and treatment. With a plethora of FDA-approved tools for clinical use, Qure.AI continually strives for innovation in integrating AI into healthcare systems. This article delves into the efficacy of Qure.AI's chest X-ray interpretation tool, "qXR," in medicine, drawing from a comprehensive review of clinical trials conducted by various institutions. Key applications of AI in healthcare include machine learning, deep learning, and natural language processing (NLP), all of which contribute to enhanced diagnostic accuracy, efficiency, and speed. Through the analysis of vast datasets, AI algorithms assist physicians in interpreting medical data and making informed decisions, thereby improving patient care outcomes. Illustrative examples highlight AI's impact on medical imaging, particularly in the diagnosis of conditions such as breast cancer, heart failure, and pulmonary nodules. AI can significantly reduce diagnostic errors and expedite the interpretation of medical images, leading to more timely interventions and treatments. Furthermore, AI-powered predictive analytics enable early detection of diseases and facilitate personalized treatment plans, thereby reducing healthcare costs and improving patient outcomes. The efficacy of AI in healthcare is underscored by its ability to complement traditional diagnostic methods, providing physicians with valuable insights and support in clinical decision-making. As AI continues to evolve, its role in patient care and medical research is poised to expand, promising further advancements in diagnostic accuracy and treatment efficacy.

PMID:38962585 | PMC:PMC11221395 | DOI:10.7759/cureus.61585

Algorithms. 2024 Apr;17(4):141. doi: 10.3390/a17040141. Epub 2024 Mar 28.

ABSTRACT

Breast cancer is the most common cancer affecting women globally. Despite the significant impact of deep learning models on breast cancer diagnosis and treatment, achieving fairness or equitable outcomes across diverse populations remains a challenge when some demographic groups are underrepresented in the training data. We quantified the bias of models trained to predict breast cancer stage from a dataset consisting of 1000 biopsies from 842 patients provided by AIM-Ahead (Artificial Intelligence/Machine Learning Consortium to Advance Health Equity and Researcher Diversity). Notably, the majority of data (over 70%) were from White patients. We found that prior to post-processing adjustments, all deep learning models we trained consistently performed better for White patients than for non-White patients. After model calibration, we observed mixed results, with only some models demonstrating improved performance. This work provides a case study of bias in breast cancer medical imaging models and highlights the challenges in using post-processing to attempt to achieve fairness.

PMID:38962581 | PMC:PMC11221567 | DOI:10.3390/a17040141

Front Artif Intell. 2024 Jun 19;7:1414707. doi: 10.3389/frai.2024.1414707. eCollection 2024.

ABSTRACT

Integration between constrained optimization and deep networks has garnered significant interest from both research and industrial laboratories. Optimization techniques can be employed to optimize the choice of network structure based not only on loss and accuracy but also on physical constraints. Additionally, constraints can be imposed during training to enhance the performance of networks in specific contexts. This study surveys the literature on the integration of constrained optimization with deep networks. Specifically, we examine the integration of hyper-parameter tuning with physical constraints, such as the number of FLOPS (FLoating point Operations Per Second), a measure of computational capacity, latency, and other factors. This study also considers the use of context-specific knowledge constraints to improve network performance. We discuss the integration of constraints in neural architecture search (NAS), considering the problem as both a multi-objective optimization (MOO) challenge and through the imposition of penalties in the loss function. Furthermore, we explore various approaches that integrate logic with deep neural networks (DNNs). In particular, we examine logic-neural integration through constrained optimization applied during the training of NNs and the use of semantic loss, which employs the probabilistic output of the networks to enforce constraints on the output.

PMID:38962503 | PMC:PMC11220227 | DOI:10.3389/frai.2024.1414707

Nat Mach Intell. 2023 Dec;5(12):1390-1401. doi: 10.1038/s42256-023-00751-0. Epub 2023 Nov 6.

ABSTRACT

Protein kinases regulate various cellular functions and hold significant pharmacological promise in cancer and other diseases. Although kinase inhibitors are one of the largest groups of approved drugs, much of the human kinome remains unexplored but potentially druggable. Computational approaches, such as machine learning, offer efficient solutions for exploring kinase-compound interactions and uncovering novel binding activities. Despite the increasing availability of three-dimensional (3D) protein and compound structures, existing methods predominantly focus on exploiting local features from one-dimensional protein sequences and two-dimensional molecular graphs to predict binding affinities, overlooking the 3D nature of the binding process. Here we present KDBNet, a deep learning algorithm that incorporates 3D protein and molecule structure data to predict binding affinities. KDBNet uses graph neural networks to learn structure representations of protein binding pockets and drug molecules, capturing the geometric and spatial characteristics of binding activity. In addition, we introduce an algorithm to quantify and calibrate the uncertainties of KDBNet's predictions, enhancing its utility in model-guided discovery in chemical or protein space. Experiments demonstrated that KDBNet outperforms existing deep learning models in predicting kinase-drug binding affinities. The uncertainties estimated by KDBNet are informative and well-calibrated with respect to prediction errors. When integrated with a Bayesian optimization framework, KDBNet enables data-efficient active learning and accelerates the exploration and exploitation of diverse high-binding kinase-drug pairs.

PMID:38962391 | PMC:PMC11221792 | DOI:10.1038/s42256-023-00751-0

Front Neuroergon. 2024 Jun 19;5:1287794. doi: 10.3389/fnrgo.2024.1287794. eCollection 2024.

ABSTRACT

A recent development in deep learning techniques has attracted attention to the decoding and classification of electroencephalogram (EEG) signals. Despite several efforts to utilize different features in EEG signals, a significant research challenge is using time-dependent features in combination with local and global features. Several attempts have been made to remodel the deep learning convolution neural networks (CNNs) to capture time-dependency information. These features are usually either handcrafted features, such as power ratios, or splitting data into smaller-sized windows related to specific properties, such as a peak at 300 ms. However, these approaches partially solve the problem but simultaneously hinder CNNs' capability to learn from unknown information that might be present in the data. Other approaches, like recurrent neural networks, are very suitable for learning time-dependent information from EEG signals in the presence of unrelated sequential data. To solve this, we have proposed an encoding kernel (EnK), a novel time-encoding approach, which uniquely introduces time decomposition information during the vertical convolution operation in CNNs. The encoded information lets CNNs learn time-dependent features in addition to local and global features. We performed extensive experiments on several EEG data sets-physical human-robot collaborations, P300 visual-evoked potentials, motor imagery, movement-related cortical potentials, and the Dataset for Emotion Analysis Using Physiological Signals. The EnK outperforms the state of the art with an up to 6.5% reduction in mean squared error (MSE) and a 9.5% improvement in F1-scores compared to the average for all data sets together compared to base models. These results support our approach and show a high potential to improve the performance of physiological and non-physiological data. Moreover, the EnK can be applied to virtually any deep learning architecture with minimal effort.

PMID:38962279 | PMC:PMC11220250 | DOI:10.3389/fnrgo.2024.1287794

NAR Genom Bioinform. 2024 Jul 2;6(3):lqae078. doi: 10.1093/nargab/lqae078. eCollection 2024 Sep.

ABSTRACT

Protein language models have been tested and proved to be reliable when used on curated datasets but have not yet been applied to full proteomes. Accordingly, we tested how two different machine learning-based methods performed when decoding functional information from the proteomes of selected model organisms. We found that protein language models are more precise and informative than deep learning methods for all the species tested and across the three gene ontologies studied, and that they better recover functional information from transcriptomic experiments. The results obtained indicate that these language models are likely to be suitable for large-scale annotation and downstream analyses, and we recommend a guide for their use.

PMID:38962255 | PMC:PMC11217674 | DOI:10.1093/nargab/lqae078

Front Psychol. 2024 Jun 19;15:1335682. doi: 10.3389/fpsyg.2024.1335682. eCollection 2024.

ABSTRACT

Deep learning from collaboration occurs if the learner enacts interactive activities in the sense of leveraging the knowledge externalized by co-learners as resource for own inferencing processes and if these interactive activities in turn promote the learner's deep comprehension outcomes. This experimental study investigates whether inducing dyad members to enact constructive preparation activities can promote deep learning from subsequent collaboration while examining prior knowledge as moderator. In a digital collaborative learning environment, 122 non-expert university students assigned to 61 dyads studied a text about the human circulatory system and then prepared individually for collaboration according to their experimental conditions: the preparation tasks varied across dyads with respect to their generativity, that is, the degree to which they required the learners to enact constructive activities (note-taking, compare-contrast, or explanation). After externalizing their answer to the task, learners in all conditions inspected their partner's externalization and then jointly discussed their text understanding via chat. Results showed that more rather than less generative tasks fostered constructive preparation but not interactive collaboration activities or deep comprehension outcomes. Moderated mediation analyses considering actor and partner effects indicated the indirect effects of constructive preparation activities on deep comprehension outcomes via interactive activities to depend on prior knowledge: when own prior knowledge was relatively low, self-performed but not partner-performed constructive preparation activities were beneficial. When own prior knowledge was relatively high, partner-performed constructive preparation activities were conducive while one's own were ineffective or even detrimental. Given these differential effects, suggestions are made for optimizing the instructional design around generative preparation tasks to streamline the effectiveness of constructive preparation activities for deep learning from digital collaboration.

PMID:38962237 | PMC:PMC11220279 | DOI:10.3389/fpsyg.2024.1335682

Data Brief. 2024 Mar 1;54:110284. doi: 10.1016/j.dib.2024.110284. eCollection 2024 Jun.

ABSTRACT

Pomegranate fruit disease detection and classification based on computer vision remains challenging because of various diseases, building the task of collecting or creating datasets is extremely difficult. The usage of machine learning and deep learning in farming has increased significantly in recent years. For developing precise and consistent machine learning models and reducing misclassification in real-time situations, efficient and clean datasets are a key obligation. The current pomegranate fruit diseases classification standardized and publicly accessible datasets for agriculture are not adequate to train the models efficiently. To address this issue, our primary goal of the current study is to create an image dataset of pomegranate fruits of numerous diseases that is ready to use and publicly available. We have composed 5 types of pomegranate fruit healthy and diseases from different places like Ballari, Bengaluru, Bagalakote, Etc. These images were taken from July to October 2023. The dataset contains 5099 pomegranate fruit images which are labeled and classified into 5 types: Healthy, Bacterial blight, Anthracnose, Cercospora fruit spot, and Alternaria fruit spot. The dataset comprises 5 folders entitled with corresponding diseases. This dataset might be useful for locating pomegranate diseases in other nations as well as increasing the production of pomegranate yield. This dataset is extremely useful for researchers of machine learning or deep learning in the field of agriculture for emerging computer vision applications.

PMID:38962206 | PMC:PMC11220843 | DOI:10.1016/j.dib.2024.110284