IEEE Trans Neural Netw Learn Syst. 2024 Aug 9;PP. doi: 10.1109/TNNLS.2024.3436850. Online ahead of print.

ABSTRACT

Deep-learning-based methods play an important role in pansharpening that uses panchromatic images to enhance the spatial resolution of multispectral images while maintaining spectral features. However, most existing methods mainly consider only one fixed degradation in the training process. Therefore, their performance may drop significantly when the degradation of testing data is unknown (blind) and different from the training data, which is common in real-world applications. To address this issue, we proposed a deep variational network for blind pansharpening, named VBPN, which integrates degradation estimation and image fusion into a whole Bayesian framework. First, by taking the noise and blurring parameters of the multispectral image with the noise parameters of the panchromatic image as hidden variables, we parameterize the approximate posterior distribution for the fusion problem using neural networks. Since all parameters in this posterior distribution are explicitly modeled, the degradation parameters of the multispectral image and the panchromatic image are easily estimated. Furthermore, we designed VPBN composed of degradation estimation and image fusion subnetworks, which can optimize the fusion results guided by the variational inference according to the testing data. As a result, the blind pansharpening performance can be improved. In general, VPBN has good interpretability and generalization ability by combining the advantages of model-based and deep-learning-based approaches. Experiments on simulated and real datasets prove that VPBN can achieve state-of-the-art fusion results.

PMID:39120986 | DOI:10.1109/TNNLS.2024.3436850

Health Informatics J. 2024 Jul-Sep;30(3):14604582241274511. doi: 10.1177/14604582241274511.

ABSTRACT

Background: Skeletal malocclusion is common among populations. Its severity often increases during adolescence, yet it is frequently overlooked. The introduction of deep learning in stomatology has opened a new avenue for self-health management. Methods: In this study, networks were trained using lateral photographs of 2109 newly diagnosed patients. The performance of the models was thoroughly evaluated using various metrics, such as sensitivity, specificity, accuracy, confusion matrix analysis, the receiver operating characteristic curve, and the area under the curve value. Heat maps were generated to further interpret the models' decisions. A comparative analysis was performed to assess the proposed models against the expert judgment of orthodontic specialists. Results: The modified models reached an impressive average accuracy of 84.50% (78.73%-88.87%), with both sex and developmental stage information contributing to the AI system's enhanced performance. The heat maps effectively highlighted the distinct characteristics of skeletal class II and III malocclusion in specific regions. In contrast, the specialist achieved a mean accuracy of 71.89% (65.25%-77.64%). Conclusions: Deep learning appears to be a promising tool for assisting in the screening of skeletal malocclusion. It provides valuable insights for expanding the use of AI in self-monitoring and early detection within a family environment.

PMID:39120929 | DOI:10.1177/14604582241274511

Alzheimers Dement. 2023 Dec;19 Suppl 24:e082896. doi: 10.1002/alz.082896.

ABSTRACT

BACKGROUND: A dataset[1,2] of electroencephalography(EEG) of frontotemporal dementia(FTD), alzheimer`s disease(AD) patients and healthy control(HC) were classified using convolutional neural network(CNN) and evaluated its performances METHOD: EEG dataset containing 88 subjects is downsampled and sliced into 10 seconds. Total dataset was divided into train, test and validation sets for each subject. CNN structure was used to extract temporal and spatial features from EEG and classify patients into 3 groups(FTD/AD/HC). Cross entropy loss was calculated to train the model using adam optimizer. Classification performances were measured to validate model such as accuracy, confusion matrix, AUC(area under curve), F1 Score.

RESULT: After training, validation accuracy was 95.35% and macro-averaged AUC was 0.9962. F1 score was 0.9469 and the minimum validation accuracy measured among subjects was 57.14% in FTD group. For AD group average accuracy was 92.79%, and for FTD group average accuracy was 97.52%. Average accuracy of healthy control group was 95.26%.

CONCLUSION: We implemented CNN model that can classify EEG of dementia patients with very high performances without expert-designed feature engineering process. These results imply that deep learning based approach is most promising for EEG-based patient classification.

PMID:39120921 | DOI:10.1002/alz.082896

Bioinformatics. 2024 Aug 9:btae497. doi: 10.1093/bioinformatics/btae497. Online ahead of print.

ABSTRACT

MOTIVATION: The emergence of drug-resistant pathogens represents a formidable challenge to global health. Using computational methods to identify the antibacterial peptides (ABPs), an alternative antimicrobial agent, has demonstrated advantages in further drug design studies. Most of the current approaches, however, rely on handcrafted features and underutilize structural information, which may affect prediction performance.

RESULTS: To present an ultra-accurate model for ABP identification, we propose a novel deep learning approach, PGAT-ABPp. PGAT-ABPp leverages structures predicted by AlphaFold2 and a pretrained protein language model, ProtT5-XL-U50 (ProtT5), to construct graphs. Then the graph attention network (GAT) is adopted to learn global discriminative features from the graphs. PGAT-ABPp outperforms the other fourteen state-of-the-art models in terms of Accuracy, F1-score and Matthews correlation coefficient on the independent test dataset. The results show that ProtT5 has significant advantages in the identification of ABPs and the introduction of spatial information further improves the prediction performance of the model. The interpretability analysis of key residues in known active ABPs further underscores the superiority of PGAT-ABPp.

AVAILABILITY: The datasets and source codes for the PGAT-ABPp model are available at https://github.com/moonseter/PGAT-ABPp/.

SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

PMID:39120878 | DOI:10.1093/bioinformatics/btae497

J Imaging Inform Med. 2024 Aug 9. doi: 10.1007/s10278-024-01075-0. Online ahead of print.

ABSTRACT

The skin prick test (SPT) is a key tool for identifying sensitized allergens associated with immunoglobulin E-mediated allergic diseases such as asthma, allergic rhinitis, atopic dermatitis, urticaria, angioedema, and anaphylaxis. However, the SPT is labor-intensive and time-consuming due to the necessity of measuring the sizes of the erythema and wheals induced by allergens on the skin. In this study, we used an image preprocessing method and a deep learning model to segment wheals and erythema in SPT images captured by a smartphone camera. Subsequently, we assessed the deep learning model's performance by comparing the results with ground-truth data. Using contrast-limited adaptive histogram equalization (CLAHE), an image preprocessing technique designed to enhance image contrast, we augmented the chromatic contrast in 46 SPT images from 33 participants. We established a deep learning model for wheal and erythema segmentation using 144 and 150 training datasets, respectively. The wheal segmentation model achieved an accuracy of 0.9985, a sensitivity of 0.5621, a specificity of 0.9995, and a Dice similarity coefficient of 0.7079, whereas the erythema segmentation model achieved an accuracy of 0.9660, a sensitivity of 0.5787, a specificity of 0.97977, and a Dice similarity coefficient of 0.6636. The use of image preprocessing and deep learning technology in SPT is expected to have a significant positive impact on medical practice by ensuring the accurate segmentation of wheals and erythema, producing consistent evaluation results, and simplifying diagnostic processes.

PMID:39120761 | DOI:10.1007/s10278-024-01075-0

Insights Imaging. 2024 Aug 9;15(1):202. doi: 10.1186/s13244-024-01751-3.

ABSTRACT

OBJECTIVES: To generate pseudo-CT (pCT) images of the pelvis from zero echo time (ZTE) MR sequences and compare them to conventional CT.

METHODS: Ninety-one patients were prospectively scanned with CT and MRI including ZTE sequences of the pelvis. Eleven ZTE image volumes were excluded due to implants and severe B1 field inhomogeneity. Out of the 80 data sets, 60 were used to train and update a deep learning (DL) model for pCT image synthesis from ZTE sequences while the remaining 20 cases were selected as an evaluation cohort. CT and pCT images were assessed qualitatively and quantitatively by two readers.

RESULTS: Mean pCT ratings of qualitative parameters were good to perfect (2-3 on a 4-point scale). Overall intermodality agreement between CT and pCT was good (ICC = 0.88 (95% CI: 0.85-0.90); p < 0.001) with excellent interreader agreements for pCT (ICC = 0.91 (95% CI: 0.88-0.93); p < 0.001). Most geometrical measurements did not show any significant difference between CT and pCT measurements (p > 0.05) with the exception of transverse pelvic diameter measurements and lateral center-edge angle measurements (p = 0.001 and p = 0.002, respectively). Image quality and tissue differentiation in CT and pCT were similar without significant differences between CT and pCT CNRs (all p > 0.05).

CONCLUSIONS: Using a DL-based algorithm, it is possible to synthesize pCT images of the pelvis from ZTE sequences. The pCT images showed high bone depiction quality and accurate geometrical measurements compared to conventional CT. CRITICAL RELEVANCE STATEMENT: pCT images generated from MR sequences allow for high accuracy in evaluating bone without the need for radiation exposure. Radiological applications are broad and include assessment of inflammatory and degenerative bone disease or preoperative planning studies.

KEY POINTS: pCT, based on DL-reconstructed ZTE MR images, may be comparable with true CT images. Overall, the intermodality agreement between CT and pCT was good with excellent interreader agreements for pCT. Geometrical measurements and tissue differentiation were similar in CT and pCT images.

PMID:39120752 | DOI:10.1186/s13244-024-01751-3

Brief Bioinform. 2024 Jul 25;25(5):bbae398. doi: 10.1093/bib/bbae398.

ABSTRACT

Predicting the strength of promoters and guiding their directed evolution is a crucial task in synthetic biology. This approach significantly reduces the experimental costs in conventional promoter engineering. Previous studies employing machine learning or deep learning methods have shown some success in this task, but their outcomes were not satisfactory enough, primarily due to the neglect of evolutionary information. In this paper, we introduce the Chaos-Attention net for Promoter Evolution (CAPE) to address the limitations of existing methods. We comprehensively extract evolutionary information within promoters using merged chaos game representation and process the overall information with modified DenseNet and Transformer structures. Our model achieves state-of-the-art results on two kinds of distinct tasks related to prokaryotic promoter strength prediction. The incorporation of evolutionary information enhances the model's accuracy, with transfer learning further extending its adaptability. Furthermore, experimental results confirm CAPE's efficacy in simulating in silico directed evolution of promoters, marking a significant advancement in predictive modeling for prokaryotic promoter strength. Our paper also presents a user-friendly website for the practical implementation of in silico directed evolution on promoters. The source code implemented in this study and the instructions on accessing the website can be found in our GitHub repository https://github.com/BobYHY/CAPE.

PMID:39120645 | DOI:10.1093/bib/bbae398

Adv Sci (Weinh). 2024 Aug 9:e2309862. doi: 10.1002/advs.202309862. Online ahead of print.

ABSTRACT

Perovskites have gained widespread attention across various fields such as photovoltaics, displays, and imaging. Despite their promising applications, achieving precise and high-quality patterning of perovskite films remains a challenge. In this study, femtosecond laser direct writing technology is utilized to achieve rapid and highly precise micro/nanofabrication on perovskites. The study successfully fabricates multiple structured and emission-tunable perovskite patterns composed of A2(FA)n-1PbnX3n+1 (A represents a series of long-chain amine cations, and X = Cl, Br, I), encompassing 2D, quasi-2D, and 3D structures. The study delves into the intricate interplay between fabrication technology and the growth of multi-dimensional perovskites: higher repetition rates, coupled with appropriate laser power, prove more conducive to perovskite growth. By employing precise halogen element design, the simultaneous generation of two distinct color quick-response (QR) code patterns is achieved through one-step laser processing. These mirrored QR codes offer a novel approach to anti-counterfeiting. To further enhance anti-counterfeiting capabilities, artificial intelligence (AI)-based methods are introduced for recognizing patterned perovskite anti-counterfeiting labels. The combination of deep learning algorithms and a non-deterministic manufacturing process provides a convenient means of identification and creates unclonable features. This integration of materials science, laser fabrication, and AI offers innovative solutions for the future of security features.

PMID:39120553 | DOI:10.1002/advs.202309862

J Appl Clin Med Phys. 2024 Aug 9:e14482. doi: 10.1002/acm2.14482. Online ahead of print.

ABSTRACT

BACKGROUND: Radiotherapy has been crucial in prostate cancer treatment. However, manual segmentation is labor intensive and highly variable among radiation oncologists. In this study, a deep learning based automated contouring model is constructed for clinical target volumes (CTVs) of intact and postoperative prostate cancer.

METHODS: Computed tomography (CT) data sets of 197 prostate cancer patients were collected. Two auto-delineation models were built for radical radiotherapy and postoperative radiotherapy of prostate cancer respectively, and each model included CTVn for pelvic lymph nodes and CTVp for prostate tumors or prostate tumor beds.

RESULTS: In the radical radiotherapy model, the volumetric dice (VD) coefficient of CTVn calculated by AI, was higher than that of the one delineated by the junior physicians (0.85 vs. 0.82, p = 0.018); In the postoperative radiotherapy model, the quantitative parameter of CTVn and CTVp, counted by AI, was better than that of the junior physicians. The median delineation time for AI was 0.23 min in the postoperative model and 0.26 min in the radical model, which were significantly shorter than those of the physicians (50.40 and 45.43 min, respectively, p < 0.001). The correction time of the senior physician for AI was much shorter compared with that for the junior physicians in both models (p < 0.001).

CONCLUSION: Using deep learning and attention mechanism, a highly consistent and time-saving contouring model was built for CTVs of pelvic lymph nodes and prostate tumors or prostate tumor beds for prostate cancer, which also might be a good approach to train junior radiation oncologists.

PMID:39120487 | DOI:10.1002/acm2.14482

Am J Primatol. 2024 Aug 9:e23666. doi: 10.1002/ajp.23666. Online ahead of print.

ABSTRACT

This paper provides a comprehensive review of the use of computational bioacoustics as well as signal and speech processing techniques in the analysis of primate vocal communication. We explore the potential implications of machine learning and deep learning methods, from the use of simple supervised algorithms to more recent self-supervised models, for processing and analyzing large data sets obtained within the emergence of passive acoustic monitoring approaches. In addition, we discuss the importance of automated primate vocalization analysis in tackling essential questions on animal communication and highlighting the role of comparative linguistics in bioacoustic research. We also examine the challenges associated with data collection and annotation and provide insights into potential solutions. Overall, this review paper runs through a set of common or innovative perspectives and applications of machine learning for primate vocal communication analysis and outlines opportunities for future research in this rapidly developing field.

PMID:39120066 | DOI:10.1002/ajp.23666

J Chem Phys. 2024 Aug 14;161(6):064101. doi: 10.1063/5.0224524.

ABSTRACT

In this work, we introduce PyCTRAMER, a comprehensive Python package designed for calculating charge transfer (CT) rate constants in disordered condensed-phase systems at finite temperatures, such as organic photovoltaic (OPV) materials. PyCTRAMER is a restructured and enriched version of the CTRAMER (Charge-Transfer RAtes from Molecular dynamics, Electronic structure, and Rate theory) package [Tinnin et al. J. Chem. Phys. 154, 214108 (2021)], enabling the computation of the Marcus CT rate constant and the six levels of the linearized semiclassical approximations of Fermi's golden rule (FGR) rate constant. It supports various types of intramolecular and intermolecular CT transitions from the excitonic states to CT state. Integrating quantum chemistry calculations, all-atom molecular dynamics (MD) simulations, spin-boson model construction, and rate constant calculations, PyCTRAMER offers an automatic workflow for handling photoinduced CT processes in explicit solvent environments and interfacial CT in amorphous donor/acceptor blends. The package also provides versatile tools for individual workflow steps, including electronic state analysis, state-specific force field construction, MD simulations, and spin-boson model construction from energy trajectories. We demonstrate the software's capabilities through two examples, highlighting both intramolecular and intermolecular CT processes in prototypical OPV systems.

PMID:39120028 | DOI:10.1063/5.0224524

Chin Med J (Engl). 2024 Aug 9. doi: 10.1097/CM9.0000000000003238. Online ahead of print.

NO ABSTRACT

PMID:39119631 | DOI:10.1097/CM9.0000000000003238

Front Neurol. 2024 Jul 25;15:1442025. doi: 10.3389/fneur.2024.1442025. eCollection 2024.

ABSTRACT

INTRODUCTION: We developed and externally validated a fully automated algorithm using deep learning to detect large vessel occlusion (LVO) in computed tomography angiography (CTA).

METHOD: A total of 2,045 patients with acute ischemic stroke who underwent CTA were included in the development of our model. We validated the algorithm using two separate external datasets: one with 64 patients (external 1) and another with 313 patients (external 2), with ischemic stroke. In the context of current clinical practice, thrombectomy amenable vessel occlusion (TAVO) was defined as an occlusion in the intracranial internal carotid artery (ICA), or in the M1 or M2 segment of the middle cerebral artery (MCA). We employed the U-Net for vessel segmentation on the maximum intensity projection images, followed by the application of the EfficientNetV2 to predict TAVO. The algorithm's diagnostic performance was evaluated by calculating the area under the receiver operating characteristics curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).

RESULTS: The mean age in the training and validation dataset was 68.7 ± 12.6; 56.3% of participants were men, and 18.0% had TAVO. The algorithm achieved AUC of 0.950 (95% CI, 0.915-0.971) in the internal test. For the external datasets 1 and 2, the AUCs were 0.970 (0.897-0.997) and 0.971 (0.924-0.990), respectively. With a fixed sensitivity of 0.900, the specificities and PPVs for the internal test, external test 1, and external test 2 were 0.891, 0.796, and 0.930, and 0.665, 0.583, and 0.667, respectively. The algorithm demonstrated a sensitivity and specificity of approximately 0.95 in both internal and external datasets, specifically for cases involving intracranial ICA or M1-MCA occlusion. However, the diagnostic performance was somewhat reduced for isolated M2-MCA occlusion; the AUC for the internal and combined external datasets were 0.903 (0.812-0.944) and 0.916 (0.816-0.963), respectively.

CONCLUSION: We developed and externally validated a fully automated algorithm that identifies TAVO. Further research is needed to evaluate its effectiveness in real-world clinical settings. This validated algorithm has the potential to assist early-career physicians, thereby streamlining the treatment process for patients who can benefit from endovascular treatment.

PMID:39119560 | PMC:PMC11306064 | DOI:10.3389/fneur.2024.1442025

Digit Health. 2024 Aug 7;10:20552076241272535. doi: 10.1177/20552076241272535. eCollection 2024 Jan-Dec.

ABSTRACT

BACKGROUND: Nonalcoholic fatty liver disease (NAFLD) is recognized as one of the most common chronic liver diseases worldwide. This study aims to assess the efficacy of automated machine learning (AutoML) in the identification of NAFLD using a population-based cross-sectional database.

METHODS: All data, including laboratory examinations, anthropometric measurements, and demographic variables, were obtained from the National Health and Nutrition Examination Survey (NHANES). NAFLD was defined by controlled attenuation parameter (CAP) in liver transient ultrasound elastography. The least absolute shrinkage and selection operator (LASSO) regression analysis was employed for feature selection. Six algorithms were utilized on the H2O-automated machine learning platform: Gradient Boosting Machine (GBM), Distributed Random Forest (DRF), Extremely Randomized Trees (XRT), Generalized Linear Model (GLM), eXtreme Gradient Boosting (XGBoost), and Deep Learning (DL). These algorithms were selected for their diverse strengths, including their ability to handle complex, non-linear relationships, provide high predictive accuracy, and ensure interpretability. The models were evaluated by area under receiver operating characteristic curves (AUC) and interpreted by the calibration curve, the decision curve analysis, variable importance plot, SHapley Additive exPlanation plot, partial dependence plots, and local interpretable model agnostic explanation plot.

RESULTS: A total of 4177 participants (non-NAFLD 3167 vs NAFLD 1010) were included to develop and validate the AutoML models. The model developed by XGBoost performed better than other models in AutoML, achieving an AUC of 0.859, an accuracy of 0.795, a sensitivity of 0.773, and a specificity of 0.802 on the validation set.

CONCLUSIONS: We developed an XGBoost model to better evaluate the presence of NAFLD. Based on the XGBoost model, we created an R Shiny web-based application named Shiny NAFLD (http://39.101.122.171:3838/App2/). This application demonstrates the potential of AutoML in clinical research and practice, offering a promising tool for the real-world identification of NAFLD.

PMID:39119551 | PMC:PMC11307367 | DOI:10.1177/20552076241272535

Front Plant Sci. 2024 Jul 25;15:1408047. doi: 10.3389/fpls.2024.1408047. eCollection 2024.

ABSTRACT

In both plant breeding and crop management, interpretability plays a crucial role in instilling trust in AI-driven approaches and enabling the provision of actionable insights. The primary objective of this research is to explore and evaluate the potential contributions of deep learning network architectures that employ stacked LSTM for end-of-season maize grain yield prediction. A secondary aim is to expand the capabilities of these networks by adapting them to better accommodate and leverage the multi-modality properties of remote sensing data. In this study, a multi-modal deep learning architecture that assimilates inputs from heterogeneous data streams, including high-resolution hyperspectral imagery, LiDAR point clouds, and environmental data, is proposed to forecast maize crop yields. The architecture includes attention mechanisms that assign varying levels of importance to different modalities and temporal features that, reflect the dynamics of plant growth and environmental interactions. The interpretability of the attention weights is investigated in multi-modal networks that seek to both improve predictions and attribute crop yield outcomes to genetic and environmental variables. This approach also contributes to increased interpretability of the model's predictions. The temporal attention weight distributions highlighted relevant factors and critical growth stages that contribute to the predictions. The results of this study affirm that the attention weights are consistent with recognized biological growth stages, thereby substantiating the network's capability to learn biologically interpretable features. Accuracies of the model's predictions of yield ranged from 0.82-0.93 R2 ref in this genetics-focused study, further highlighting the potential of attention-based models. Further, this research facilitates understanding of how multi-modality remote sensing aligns with the physiological stages of maize. The proposed architecture shows promise in improving predictions and offering interpretable insights into the factors affecting maize crop yields, while demonstrating the impact of data collection by different modalities through the growing season. By identifying relevant factors and critical growth stages, the model's attention weights provide valuable information that can be used in both plant breeding and crop management. The consistency of attention weights with biological growth stages reinforces the potential of deep learning networks in agricultural applications, particularly in leveraging remote sensing data for yield prediction. To the best of our knowledge, this is the first study that investigates the use of hyperspectral and LiDAR UAV time series data for explaining/interpreting plant growth stages within deep learning networks and forecasting plot-level maize grain yield using late fusion modalities with attention mechanisms.

PMID:39119495 | PMC:PMC11306015 | DOI:10.3389/fpls.2024.1408047

Front Vet Sci. 2024 Jul 23;11:1434991. doi: 10.3389/fvets.2024.1434991. eCollection 2024.

ABSTRACT

In the field of biomedical research, rats are widely used as experimental animals due to their short gestation period and strong reproductive ability. Accurate monitoring of the estrous cycle is crucial for the success of experiments. Traditional methods are time-consuming and rely on the subjective judgment of professionals, which limits the efficiency and accuracy of experiments. This study proposes an EfficientNet model to automate the recognition of the estrous cycle of female rats using deep learning techniques. The model optimizes performance through systematic scaling of the network depth, width, and image resolution. A large dataset of physiological data from female rats was used for training and validation. The improved EfficientNet model effectively recognized different stages of the estrous cycle. The model demonstrated high-precision feature capture and significantly improved recognition accuracy compared to conventional methods. The proposed technique enhances experimental efficiency and reduces human error in recognizing the estrous cycle. This study highlights the potential of deep learning to optimize data processing and achieve high-precision recognition in biomedical research. Future work should focus on further validation with larger datasets and integration into experimental workflows.

PMID:39119352 | PMC:PMC11306968 | DOI:10.3389/fvets.2024.1434991

Front Physiol. 2024 Jul 25;15:1425582. doi: 10.3389/fphys.2024.1425582. eCollection 2024.

ABSTRACT

OBJECTIVE: Recognizing emotions from electroencephalography (EEG) signals is a challenging task due to the complex, nonlinear, and nonstationary characteristics of brain activity. Traditional methods often fail to capture these subtle dynamics, while deep learning approaches lack explainability. In this research, we introduce a novel three-phase methodology integrating manifold embedding, multilevel heterogeneous recurrence analysis (MHRA), and ensemble learning to address these limitations in EEG-based emotion recognition.

APPROACH: The proposed methodology was evaluated using the SJTU-SEED IV database. We first applied uniform manifold approximation and projection (UMAP) for manifold embedding of the 62-lead EEG signals into a lower-dimensional space. We then developed MHRA to characterize the complex recurrence dynamics of brain activity across multiple transition levels. Finally, we employed tree-based ensemble learning methods to classify four emotions (neutral, sad, fear, happy) based on the extracted MHRA features.

MAIN RESULTS: Our approach achieved high performance, with an accuracy of 0.7885 and an AUC of 0.7552, outperforming existing methods on the same dataset. Additionally, our methodology provided the most consistent recognition performance across different emotions. Sensitivity analysis revealed specific MHRA metrics that were strongly associated with each emotion, offering valuable insights into the underlying neural dynamics.

SIGNIFICANCE: This study presents a novel framework for EEG-based emotion recognition that effectively captures the complex nonlinear and nonstationary dynamics of brain activity while maintaining explainability. The proposed methodology offers significant potential for advancing our understanding of emotional processing and developing more reliable emotion recognition systems with broad applications in healthcare and beyond.

PMID:39119215 | PMC:PMC11306145 | DOI:10.3389/fphys.2024.1425582

Inform Med Unlocked. 2024;45:101444. doi: 10.1016/j.imu.2023.101444. Epub 2024 Jan 6.

ABSTRACT

Different pathologies of the hip are characterized by the abnormal shape of the bony structures of the joint, namely the femur and the acetabulum. Three-dimensional (3D) models of the hip can be used for diagnosis, biomechanical simulation, and planning of surgical treatments. These models can be generated by building 3D surfaces of the joint's structures segmented on magnetic resonance (MR) images. Deep learning can avoid time-consuming manual segmentations, but its performance depends on the amount and quality of the available training data. Data augmentation and transfer learning are two approaches used when there is only a limited number of datasets. In particular, data augmentation can be used to artificially increase the size and diversity of the training datasets, whereas transfer learning can be used to build the desired model on top of a model previously trained with similar data. This study investigates the effect of data augmentation and transfer learning on the performance of deep learning for the automatic segmentation of the femur and acetabulum on 3D MR images of patients diagnosed with femoroacetabular impingement. Transfer learning was applied starting from a model trained for the segmentation of the bony structures of the shoulder joint, which bears some resemblance to the hip joint. Our results suggest that data augmentation is more effective than transfer learning, yielding a Dice similarity coefficient compared to ground-truth manual segmentations of 0.84 and 0.89 for the acetabulum and femur, respectively, whereas the Dice coefficient was 0.78 and 0.88 for the model based on transfer learning. The Accuracy for the two anatomical regions was 0.95 and 0.97 when using data augmentation, and 0.87 and 0.96 when using transfer learning. Data augmentation can improve the performance of deep learning models by increasing the diversity of the training dataset and making the models more robust to noise and variations in image quality. The proposed segmentation model could be combined with radiomic analysis for the automatic evaluation of hip pathologies.

PMID:39119151 | PMC:PMC11308385 | DOI:10.1016/j.imu.2023.101444

Front Oncol. 2024 Jul 25;14:1383323. doi: 10.3389/fonc.2024.1383323. eCollection 2024.

ABSTRACT

PURPOSE: A systematic review and meta-analysis were conducted to evaluate the diagnostic precision of radiomics in the differential diagnosis of parotid tumors, considering the increasing utilization of radiomics in tumor diagnosis. Although some researchers have attempted to apply radiomics in this context, there is ongoing debate regarding its accuracy.

METHODS: Databases of PubMed, Cochrane, EMBASE, and Web of Science up to May 29, 2024 were systematically searched. The quality of included primary studies was assessed using the Radiomics Quality Score (RQS) checklist. The meta-analysis was performed utilizing a bivariate mixed-effects model.

RESULTS: A total of 39 primary studies were incorporated. The machine learning model relying on MRI radiomics for diagnosis malignant tumors of the parotid gland, demonstrated a sensitivity of 0.80 [95% CI: 0.74, 0.86], SROC of 0.89 [95% CI: 0.27-0.99] in the validation set. The machine learning model based on MRI radiomics for diagnosis malignant tumors of the parotid gland, exhibited a sensitivity of 0.83[95% CI: 0.76, 0.88], SROC of 0.89 [95% CI: 0.17-1.00] in the validation set. The models also demonstrated high predictive accuracy for benign lesions.

CONCLUSION: There is great potential for radiomics-based models to improve the accuracy of diagnosing benign and malignant tumors of the parotid gland. To further enhance this potential, future studies should consider implementing standardized radiomics-based features, adopting more robust feature selection methods, and utilizing advanced model development tools. These measures can significantly improve the diagnostic accuracy of artificial intelligence algorithms in distinguishing between benign and malignant tumors of the parotid gland.

SYSTEMATIC REVIEW REGISTRATION: https://www.crd.york.ac.uk/prospero/, identifier CRD42023434931.

PMID:39119093 | PMC:PMC11306159 | DOI:10.3389/fonc.2024.1383323

Heart Rhythm O2. 2024 May 16;5(7):452-459. doi: 10.1016/j.hroo.2024.04.014. eCollection 2024 Jul.

ABSTRACT

BACKGROUND: Junctional ectopic tachycardia (JET) is a prevalent life-threatening arrhythmia in children with congenital heart disease. It has a marked resemblance to normal sinus rhythm, often leading to delay in diagnosis and management.

OBJECTIVE: The study sought to develop a novel multimodal automated arrhythmia detection tool that outperforms existing JET detection tools.

METHODS: This is a cohort study performed on 40 patients with congenital heart disease at Texas Children's Hospital. Electrocardiogram and central venous pressure waveform data produced by bedside monitors are captured by the Sickbay platform. Convolutional neural networks (CNNs) were trained to classify each heartbeat as either normal sinus rhythm or JET based only on raw electrocardiogram signals.

RESULTS: Our best model improved the area under the curve from 0.948 to 0.952 and the true positive rate at 5% false positive rate from 71.8% to 80.6%. Using a 3-model ensemble further improved the area under the curve to 0.953 and the true positive rate at 5% false positive rate to 85.2%. Results on a subset of data show that adding central venous pressure can significantly improve area under the receiver-operating characteristic curve from 0.646 to 0.825.

CONCLUSION: This study validates the efficacy of deep neural networks to notably improve JET detection accuracy. We have built a performant and reliable model that can be used to create a bedside alarm that diagnoses JET, allowing for precise diagnosis of this life-threatening postoperative arrhythmia and prompt intervention. Future validation of the model in a larger cohort is needed.

PMID:39119021 | PMC:PMC11305876 | DOI:10.1016/j.hroo.2024.04.014