Comput Methods Programs Biomed. 2024 Oct 15;257:108458. doi: 10.1016/j.cmpb.2024.108458. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVE: Transcranial focused ultrasound (tFUS) is an emerging non-invasive therapeutic technology that offers new brain stimulation modality. Precise localization of the acoustic focus to the desired brain target throughout the procedure is needed to ensure the safety and effectiveness of the treatment, but acoustic distortion caused by the skull poses a challenge. Although computational methods can provide the estimated location and shape of the focus, the computation has not reached sufficient speed for real-time inference, which is demanded in real-world clinical situations. Leveraging the advantages of deep learning, we propose multi-modal networks capable of generating intracranial pressure map in real-time.

METHODS: The dataset consisted of free-field pressure maps, intracranial pressure maps, medical images, and transducer placements was obtained from 11 human subjects. The free-field and intracranial pressure maps were computed using the k-space method. We developed network models based on convolutional neural networks and the Swin Transformer, featuring a multi-modal encoder and a decoder.

RESULTS: Evaluations on foreseen data achieved high focal volume conformity of approximately 93% for both computed tomography (CT) and magnetic resonance (MR) data. For unforeseen data, the networks achieved the focal volume conformity of 88% for CT and 82% for MR. The inference time of the proposed networks was under 0.02 s, indicating the feasibility for real-time simulation.

CONCLUSIONS: The results indicate that our networks can effectively and precisely perform real-time simulation of the intracranial pressure map during tFUS applications. Our work will enhance the safety and accuracy of treatments, representing significant progress for low-intensity focused ultrasound (LIFU) therapies.

PMID:39437458 | DOI:10.1016/j.cmpb.2024.108458

IEEE Rev Biomed Eng. 2024 Oct 22;PP. doi: 10.1109/RBME.2024.3485022. Online ahead of print.

ABSTRACT

Magnetic Resonance Imaging (MRI) is a pivotal clinical diagnostic tool, yet its extended scanning times often compromise patient comfort and image quality, especially in volumetric, temporal and quantitative scans. This review elucidates recent advances in MRI acceleration via data and physics-driven models, leveraging techniques from algorithm unrolling models, enhancement-based methods, and plug-and-play models to the emerging full spectrum of generative model-based methods. We also explore the synergistic integration of data models with physics-based insights, encompassing the advancements in multi-coil hardware accelerations like parallel imaging and simultaneous multi-slice imaging, and the optimization of sampling patterns. We then focus on domain-specific challenges and opportunities, including image redundancy exploitation, image integrity, evaluation metrics, data heterogeneity, and model generalization. This work also discusses potential solutions and future research directions, with an emphasis on the role of data harmonization and federated learning for further improving the general applicability and performance of these methods in MRI reconstruction.

PMID:39437302 | DOI:10.1109/RBME.2024.3485022

IEEE Trans Image Process. 2024 Oct 22;PP. doi: 10.1109/TIP.2024.3482182. Online ahead of print.

ABSTRACT

The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving the robustness towards noisy labels in classification tasks, the problem of noisy labels in deep metric learning (DML) remains under-explored. Existing noisy label learning methods designed for DML mainly discard suspicious noisy samples, resulting in a waste of the training data. To address this issue, we propose a noise-robust DML framework with SubGroup-based Positive-pair Selection (SGPS), which constructs reliable positive pairs for noisy samples to enhance the sample utilization. Specifically, SGPS first effectively identifies clean and noisy samples by a probability-based clean sample selectionstrategy. To further utilize the remaining noisy samples, we discover their potential similar samples based on the subgroup information given by a subgroup generation module and then aggregate them into informative positive prototypes for each noisy sample via a positive prototype generation module. Afterward, a new contrastive loss is tailored for the noisy samples with their selected positive pairs. SGPS can be easily integrated into the training process of existing pair-wise DML tasks, like image retrieval and face recognition. Extensive experiments on multiple synthetic and real-world large-scale label noise datasets demonstrate the effectiveness of our proposed method. Without any bells and whistles, our SGPS framework outperforms the state-of-the-art noisy label DML methods.

PMID:39437295 | DOI:10.1109/TIP.2024.3482182

IEEE J Biomed Health Inform. 2024 Oct 22;PP. doi: 10.1109/JBHI.2024.3484994. Online ahead of print.

ABSTRACT

Post-stroke upper limb dysfunction severely impacts patients' daily life quality. Utilizing sEMG signals to predict patients' motion intentions enables more effective rehabilitation by precisely adjusting the assistance level of rehabilitation robots. Employing the muscle synergy (MS) features can establish more accurate and robust mappings between sEMG and motion intentions. However, traditional matrix factorization algorithms based on blind source separation still exhibit certain limitations in extracting MS features. This paper proposes four deep learning models to extract MS features from four distinct perspectives: spatiotemporal convolutional kernels, compression and reconstruction of sEMG, graph topological structure, and the anatomy of target muscles. Among these models, the one based on 3DCNN predicts motion intentions from the muscle anatomy perspective for the first time. It reconstructs 1D sEMG samples collected at each time point into 2D sEMG frames based on the anatomical distribution of target muscles and sEMG electrode placement. These 2D frames are then stacked as video segments and input into 3DCNN for MS feature extraction. Experimental results on both our wrist motion dataset and public Ninapro DB2 dataset demonstrate that the proposed 3DCNN model outperforms other models in terms of prediction accuracy, robustness, training efficiency, and MS feature extraction for continuous prediction of wrist flexion/extension angles. Specifically, the average nRMSE and R2 values of 3DCNN on these two datasets are (0.14/0.93) and (0.04/0.95), respectively. Furthermore, compared to existing studies, the 3DCNN outperforms musculoskeletal models based on direct collocation optimization, physics-informed GANs, and CNN-LSTM-based deep Kalman filter models when evaluated on our dataset.

PMID:39437291 | DOI:10.1109/JBHI.2024.3484994

IEEE Trans Neural Netw Learn Syst. 2024 Oct 21;PP. doi: 10.1109/TNNLS.2024.3477320. Online ahead of print.

ABSTRACT

Emergence, a global property of complex adaptive systems (CASs) constituted by interactive agents, is prevalent in real-world dynamic systems, e.g., network-level traffic congestions. Detecting its formation and evaporation helps to monitor the state of a system, allowing it to issue a warning signal for harmful emergent phenomena. Since there is no centralized controller of CAS, detecting emergence based on each agent's local observation is desirable but challenging. Existing works are unable to capture emergence-related spatial patterns, and fail to model the nonlinear relationships among agents. This article proposes a hierarchical framework with spatio-temporal consistency learning (HSTCL) to solve these two problems by learning the system representation and agent representations, respectively. Spatio-temporal encoders (STEs) composed of spatial and temporal transformers are designed to capture agents' nonlinear relationships and the system's complex evolution. Agents' and the system's representations are learned to preserve the spatio-temporal consistency by minimizing the spatial and temporal dissimilarities in a self-supervised manner in the latent space. Our method achieves more accurate detection than traditional methods and deep learning methods on three datasets with well-known yet hard-to-detect emergent behaviors. Notably, our hierarchical framework is generic in incorporating other deep learning methods for agent-level and system-level detection.

PMID:39437286 | DOI:10.1109/TNNLS.2024.3477320

IEEE Trans Image Process. 2024 Oct 21;PP. doi: 10.1109/TIP.2024.3480696. Online ahead of print.

ABSTRACT

Lens flare is a common phenomenon when strong light rays arrive at the camera sensor and a clean scene is consequently mixed up with various opaque and semi-transparent artifacts. Existing deep learning methods are always constrained with limited real image pairs for training. Though recent synthesis-based approaches are found effective, synthesized pairs still deviate from the real ones as the mixing mechanism of flare artifacts and scenes in the wild always depends on a line of undetermined factors, such as lens structure, scratches, etc. In this paper, we present a new perspective from the blind nature of the flare removal task in a knowledge-driven manner. Specifically, we present a simple yet effective flare-level estimator to predict the corruption level of a flare-corrupted image. The estimated flare-level can be interpreted as additive information of the gap between corrupted images and their flare-free correspondences to facilitate a network at both training and testing stages adaptively. Besides, we utilize a flare-level modulator to better integrate the estimations into networks. We also devise a flare-aware block for more accurate flare recognition and reconstruction. Additionally, we collect a new real-world flare dataset for benchmarking, namely WiderFlare. Extensive experiments on three benchmark datasets demonstrate that our method outperforms state-of-the-art methods quantitatively and qualitatively.

PMID:39437280 | DOI:10.1109/TIP.2024.3480696

IEEE J Biomed Health Inform. 2024 Oct 21;PP. doi: 10.1109/JBHI.2024.3483812. Online ahead of print.

ABSTRACT

Predicting drug-drug interactions (DDIs) is a significant concern in the field of deep learning. It can effectively reduce potential adverse consequences and improve therapeutic safety. Graph neural network (GNN)-based models have made satisfactory progress in DDI event prediction. However, most existing models overlook crucial drug structure and interaction information, which is necessary for accurate DDI event prediction. To tackle this issue, we introduce a new method called MRGCDDI. This approach employs contrastive learning, but unlike conventional methods, it does not require data augmentation, thereby avoiding additional noise. MRGCDDI maintains the semantics of the graphical data during encoder perturbation through a simple yet effective contrastive learning approach, without the need for manual trial and error, tedious searching, or expensive domain knowledge to select enhancements. The approach presented in this study effectively integrates drug features extracted from drug molecular graphs and information from multi-relational drug-drug interaction (DDI) networks. Extensive experimental results demonstrate that MRGCDDI outperforms state-of-the-art methods on both datasets. Specifically, on Deng's dataset, MRGCDDI achieves an average increase of 4.33% in accuracy, 11.57% in Macro-F1, 10.97% in Macro-Recall, and 10.64% in Macro-Precision. Similarly, on Ryu's dataset, the model shows improvements with an average increase of 2.42% in accuracy, 3.86% in Macro-F1, 3.49% in Macro-Recall, and 2.75% in Macro-Precision. All the data and codes of this work are available at https://github.com/Nokeli/MRGCDDI.

PMID:39437275 | DOI:10.1109/JBHI.2024.3483812

IEEE Trans Pattern Anal Mach Intell. 2024 Oct 21;PP. doi: 10.1109/TPAMI.2024.3484183. Online ahead of print.

ABSTRACT

We developed an intelligent innovative orientation method to improve the accuracy of polarization compasses in harsh conditions: weak skylight polarization patterns resulting from unfavorable weather conditions (e.g., haze, sandstorms) or locally destroyed skylight polarization conditions caused by occlusions (e.g., buildings, trees). First, the skylight polarization status was determined with the degree of linear polarization threshold analysis method and a bionic polarization enhancement sensing model was constructed to simulate the enhanced perception mechanism identified in the Syrphidae visual neural pathway, highly efficient in dark or weakly illuminated environments. The bionic model successfully enhanced the information content extracted from weak polarization patterns. Second, polarization pixel interferences, caused by occlusions under locally destroyed skylight polarization conditions, were removed with a convolutional neural network for image segmentation and the sky area of interest was identified. Finally, the incomplete angle of polarization map derived after image segmentation was fitted using our optimized adaptive antisymmetric ring algorithm. On the basis of the strong angle-of-polarization antisymmetry along the solar meridian, information extracted from the sparse and irregular polarization pixels was analyzed to derive a high-accuracy polarization orientation solution. The whole method intelligently realizes pattern analysis and deep learning intelligent processing, efficiently rotates to manage polarization disorientation. The experimental results demonstrated the performance of the proposed method in compensating for reduced orientation accuracy under degraded polarization conditions, its robustness against perturbations, and its beneficial impact on the environmental adaptability of bionic polarization compasses.

PMID:39437271 | DOI:10.1109/TPAMI.2024.3484183

Invest Radiol. 2024 Oct 23. doi: 10.1097/RLI.0000000000001131. Online ahead of print.

ABSTRACT

PURPOSE: Sybil is a validated publicly available deep learning-based algorithm that can accurately predict lung cancer risk from a single low-dose computed tomography (LDCT) scan. We aimed to study the effect of image reconstruction parameters and CT scanner manufacturer on Sybil's performance.

MATERIALS AND METHODS: Using LDCTs of a subset of the National Lung Screening Trial participants, which we previously used for internal validation of the Sybil algorithm (test set), we ran the Sybil algorithm on LDCT series pairs matched on kilovoltage peak, milliampere-seconds, reconstruction interval, reconstruction diameter, and either reconstruction filter or axial slice thickness. We also evaluated the cumulative effect of these parameters by combining the best- and the worst-performing parameters. A subanalysis compared Sybil's performance by CT manufacturer. We considered any LDCT positive if future lung cancer was subsequently confirmed by biopsy or surgical resection. The areas under the curve (AUCs) for each series pair were compared using DeLong's test.

RESULTS: There was no difference in Sybil's performance between 1049 pairs of standard versus bone reconstruction filter (AUC at 1 year 0.84 [95% confidence interval (CI): 0.70-0.99] vs 0.86 [95% CI: 0.75-0.98], P = 0.87) and 1961 pairs of standard versus lung reconstruction filter (AUC at 1 year 0.98 [95% CI: 0.97-0.99] vs 0.98 [95% CI: 0.96-0.99], P = 0.81). Similarly, there was no difference in 1288 pairs comparing 2-mm versus 5-mm axial slice thickness (AUC at 1 year 0.98 [95% CI: 0.94-1.00] vs 0.99 [95% CI: 0.97-0.99], P = 0.68). The best-case scenario combining a lung reconstruction filter with 2-mm slice thickness compared with the worst-case scenario combining a bone reconstruction filter with 2.5-mm slice thickness uncovered a significantly different performance at years 2-4 (P = 0.03). Subanalysis showed no significant difference in performance between Siemens and Toshiba scanners.

CONCLUSIONS: Sybil's predictive performance for future lung cancer risk is robust across different reconstruction filters and axial slice thicknesses, demonstrating its versatility in various imaging settings. Combining favorable reconstruction parameters can significantly enhance predictive ability at years 2-4. The absence of significant differences between Siemens and Toshiba scanners further supports Sybil's versatility.

PMID:39437009 | DOI:10.1097/RLI.0000000000001131

PLoS One. 2024 Oct 22;19(10):e0310057. doi: 10.1371/journal.pone.0310057. eCollection 2024.

ABSTRACT

Automatic authorship identification is a challenging task that has been the focus of extensive research in natural language processing. Regardless of the progress made in attributing authorship, the need for corpora in under-resourced languages impedes advancing and examining present methods. To address this gap, we investigate the problem of authorship attribution in Albanian. We introduce a newly compiled corpus of Albanian newsroom columns and literary works and analyze machine-learning methods for detecting authorship. We create a set of hand-crafted features targeting various categories (lexical, morphological, and structural) relevant to Albanian and experiment with multiple classifiers using two different multiclass classification strategies. Furthermore, we compare our results to those obtained using deep learning models. Our investigation focuses on identifying the best combination of features and classification methods. The results reveal that lexical features are the most effective set of linguistic features, significantly improving the performance of various algorithms in the authorship attribution task. Among the machine learning algorithms evaluated, XGBoost demonstrated the best overall performance, achieving an F1 score of 0.982 on literary works and 0.905 on newsroom columns. Additionally, deep learning models such as fastText and BERT-multilingual showed promising results, highlighting their potential applicability in specific scenarios in Albanian writings. These findings contribute to the understanding of effective methods for authorship attribution in low-resource languages and provide a robust framework for future research in this area. The careful analysis of the different scenarios and the conclusions drawn from the results provide valuable insights into the potential and limitations of the methods and highlight the challenges in detecting authorship in Albanian. Promising results are reported, with implications for improving the methods used in Albanian authorship attribution. This study provides a valuable resource for future research and a reference for researchers in this domain.

PMID:39436898 | DOI:10.1371/journal.pone.0310057

Med Biol Eng Comput. 2024 Oct 22. doi: 10.1007/s11517-024-03221-w. Online ahead of print.

ABSTRACT

Bone metastasis is one of the most common forms of metastasis in the late stages of malignancy. The early detection of bone metastases can help clinicians develop appropriate treatment plans. CT images are essential for diagnosing and assessing bone metastases in clinical practice. However, early bone metastasis lesions occupy a small part of the image and display variable sizes as the condition progresses, which adds complexity to the detection. To improve diagnostic efficiency, this paper proposes a novel algorithm-MFP-YOLO. Building on the YOLOv5 algorithm, this approach introduces a feature extraction module capable of capturing global information and designs a new content-aware feature pyramid structure to improve the network's capability in processing lesions of varying sizes. Moreover, this paper innovatively applies a transformer-structure decoder to bone metastasis detection. A dataset comprising 3921 CT images was created specifically for this task. The proposed method outperforms the baseline model with a 5.5% increase in precision and a 7.7% boost in recall. The experimental results indicate that this method can meet the needs of bone metastasis detection tasks in real scenarios and provide assistance for medical diagnosis.

PMID:39436545 | DOI:10.1007/s11517-024-03221-w

ACS Sens. 2024 Oct 22. doi: 10.1021/acssensors.4c02186. Online ahead of print.

ABSTRACT

Combining wearable sensors with modern technologies such as internet of things and big data to monitor or intervene in obesity-induced chronic diseases, such as obstructive sleep apnea, type II diabetes, cardiovascular diseases, and Alzheimer's disease, is of great significance to the self-health management of human beings. This study designed a loofah-conducting graphite four friction layer enhanced triboelectric nanogenerator (LG-TENG) and developed a health management system for human motion recognition and early warning of sleep breathing abnormalities. By uniformly spraying and depositing conductive graphite on the surface of the loofah and the elastic film cross-interlocking bending structure design, the signal strength of the LG-TENG has been improved by 390%. The stable output signal is still maintained after 1500 s of continuous operation at a frequency of 2 Hz. LG-TENG can realize accurate motion analysis by muscle contraction state. Combining different deep learning models resulted in 98.1% accuracy in recognizing seven categories of displacement speeds for an individual and 96.46% accuracy in recognizing seven categories of displacement speeds for three individuals. In addition, the sleep breathing monitoring early warning system was developed by integrating Bluetooth wireless transmission and upper computer analysis technology. This system aims to analyze and provide real-time warnings for sleep-breathing abnormalities. This research promotes an innovation of TENG technology based on the advantages of natural materials, recyclability and low cost. It offers new ideas for self-health management and scientific exercise for obese people, showing a broad application prospect.

PMID:39436357 | DOI:10.1021/acssensors.4c02186

Brief Funct Genomics. 2024 Oct 22:elae042. doi: 10.1093/bfgp/elae042. Online ahead of print.

ABSTRACT

The study of brain age has emerged over the past decade, aiming to estimate a person's age based on brain imaging scans. Ideally, predicted brain age should match chronological age in healthy individuals. However, brain structure and function change in the presence of brain-related diseases. Consequently, brain age also changes in affected individuals, making the brain age gap (BAG)-the difference between brain age and chronological age-a potential biomarker for brain health, early screening, and identifying age-related cognitive decline and disorders. With the recent successes of artificial intelligence in healthcare, it is essential to track the latest advancements and highlight promising directions. This review paper presents recent machine learning techniques used in brain age estimation (BAE) studies. Typically, BAE models involve developing a machine learning regression model to capture age-related variations in brain structure from imaging scans of healthy individuals and automatically predict brain age for new subjects. The process also involves estimating BAG as a measure of brain health. While we discuss recent clinical applications of BAE methods, we also review studies of biological age that can be integrated into BAE research. Finally, we point out the current limitations of BAE's studies.

PMID:39436320 | DOI:10.1093/bfgp/elae042

Radiology. 2024 Oct;313(1):e232746. doi: 10.1148/radiol.232746.

ABSTRACT

Background Natural language processing (NLP) is commonly used to annotate radiology datasets for training deep learning (DL) models. However, the accuracy and potential biases of these NLP methods have not been thoroughly investigated, particularly across different demographic groups. Purpose To evaluate the accuracy and demographic bias of four NLP radiology report labeling tools on two chest radiograph datasets. Materials and Methods This retrospective study, performed between April 2022 and April 2024, evaluated chest radiograph report labeling using four NLP tools (CheXpert [rule-based], RadReportAnnotator [RRA; DL-based], OpenAI's GPT-4 [DL-based], cTAKES [hybrid]) on a subset of the Medical Information Mart for Intensive Care (MIMIC) chest radiograph dataset balanced for representation of age, sex, and race and ethnicity (n = 692) and the entire Indiana University (IU) chest radiograph dataset (n = 3665). Three board-certified radiologists annotated the chest radiograph reports for 14 thoracic disease labels. NLP tool performance was evaluated using several metrics, including accuracy and error rate. Bias was evaluated by comparing performance between demographic subgroups using the Pearson χ2 test. Results The IU dataset included 3665 patients (mean age, 49.7 years ± 17 [SD]; 1963 female), while the MIMIC dataset included 692 patients (mean age, 54.1 years ± 23.1; 357 female). All four NLP tools demonstrated high accuracy across findings in the IU and MIMIC datasets, as follows: CheXpert (92.6% [47 516 of 51 310], 90.2% [8742 of 9688]), RRA (82.9% [19 746 of 23 829], 92.2% [2870 of 3114]), GPT-4 (94.3% [45 586 of 48 342], 91.6% [6721 of 7336]), and cTAKES (84.7% [43 436 of 51 310], 88.7% [8597 of 9688]). RRA and cTAKES had higher accuracy (P < .001) on the MIMIC dataset, while CheXpert and GPT-4 had higher accuracy on the IU dataset. Differences (P < .001) in error rates were observed across age groups for all NLP tools except RRA on the MIMIC dataset, with the highest error rates for CheXpert, RRA, and cTAKES in patients older than 80 years (mean, 15.8% ± 5.0) and the highest error rate for GPT-4 in patients 60-80 years of age (8.3%). Conclusion Although commonly used NLP tools for chest radiograph report annotation are accurate when evaluating reports in aggregate, demographic subanalyses showed significant bias, with poorer performance in older patients. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Cai in this issue.

PMID:39436298 | DOI:10.1148/radiol.232746

Transplantation. 2024 Aug 6. doi: 10.1097/TP.0000000000005153. Online ahead of print.

ABSTRACT

The Banff classification is regularly updated to integrate recent advances in the characterization of kidney allograft rejection, gathering novel diagnostic, prognostic, and theragnostic data into a diagnostic and pathogenesis-based framework. Despite ongoing research on noninvasive biomarkers of kidney rejection, the Banff classification remains, to date, biopsy-centered, primarily relying on a semiquantitative histological scoring system that overall lacks reproducibility and granularity. Besides, the ability of histopathological injuries and transcriptomics analyses from bulk tissue to accurately infer the pathogenesis of rejection is questioned. This review discusses findings from past, current, and emerging innovative tools that have the potential to enhance the characterization of allograft rejection from tissue samples. First, the digitalization of pathological workflows and the rise of deep learning should yield more reproducible and quantitative results from routine slides. Additionally, novel histomorphometric features of kidney rejection could be discovered with an overall genuine clinical implementation perspective. Second, multiplex immunohistochemistry enables in-depth in situ phenotyping of cells from formalin-fixed samples, which can decipher the heterogeneity of the immune infiltrate during kidney allograft rejection. Third, transcriptomics from bulk tissue is gradually integrated into the Banff classification, and its specific context of use is currently under extensive consideration. Finally, single-cell transcriptomics and spatial transcriptomics from formalin-fixed and paraffin-embedded samples are emerging techniques capable of producing up to genome-wide data with unprecedented precision levels. Combining all these approaches gives us hope for novel advances that will address the current blind spots of the Banff system.

PMID:39436268 | DOI:10.1097/TP.0000000000005153

Semin Ophthalmol. 2024 Oct 22:1-9. doi: 10.1080/08820538.2024.2414353. Online ahead of print.

ABSTRACT

PURPOSE: To describe the application of artificial intelligence (AI) in ophthalmic diseases and its possible future directions.

METHODS: A retrospective review of the literature from PubMed, Web of Science, and Embase databases (2019-2024).

RESULTS: AI assists in cataract diagnosis, classification, preoperative lens calculation, surgical risk, postoperative vision prediction, and follow-up. For glaucoma, AI enhances early diagnosis, progression prediction, and surgical risk assessment. It detects diabetic retinopathy early and predicts treatment effects for diabetic macular edema. AI analyzes fundus images for age-related macular degeneration (AMD) diagnosis and risk prediction. Additionally, AI quantifies and grades vitreous opacities in uveitis. For retinopathy of prematurity, AI facilitates disease classification, predicting disease occurrence and severity. Recently, AI also predicts systemic diseases by analyzing fundus vascular changes.

CONCLUSIONS: AI has been extensively used in diagnosing, following up, and predicting treatment outcomes for common blinding eye diseases. In addition, it also has a unique role in the prediction of systemic diseases.

PMID:39435874 | DOI:10.1080/08820538.2024.2414353

J Chem Phys. 2024 Oct 28;161(16):164702. doi: 10.1063/5.0232141.

ABSTRACT

We uncover the origin of unique electronic structures of single-atom alloys (SAAs) by interpretable deep learning. The approach integrates tight-binding moment theory with graph neural networks to accurately describe the local electronic structure of transition and noble metal sites upon perturbation. We emphasize the complex interplay of interatomic orbital coupling and on-site orbital resonance, which shapes the d-band characteristics of an active site, shedding light on the origin of free-atom-like d-states that are often observed in SAAs involving d10 metal hosts. This theory-infused neural network approach significantly enhances our understanding of the electronic properties of single-site catalytic materials beyond traditional theories.

PMID:39435835 | DOI:10.1063/5.0232141

Ren Fail. 2024 Dec;46(2):2417740. doi: 10.1080/0886022X.2024.2417740. Epub 2024 Oct 22.

ABSTRACT

We developed a multimodal ultrasound (US) deep learning (DL) fusion model to automatically classify early fibrosis in patients with chronic kidney disease (CKD). This prospective study included patients with CKD who underwent continuous gray-scale US, superb microvascular imaging, and strain elastography from May to November 2022. According to the pathological tubular atrophy and interstitial fibrosis score, patients were divided into minimal and mild groups (affected area ≤10% and 11 - 25% of the total cortical volume, respectively). The dataset was divided into training (70%) and test (30%) sets. A DL model combining the features of the three US modes was developed to predict early fibrosis in patients with CKD. We compared these findings with the area under the receiver operating characteristic curve (AUC) of the clinical model by analyzing the receiver operating characteristic curve in the test set. The AUC of single-mode DL based on gray-scale US, superb microvascular imaging, and strain elastography was 0.682, 0.745, and 0.648, respectively, while that of the multimodal US DL model was 0.86. The accuracy, specificity, and sensitivity of the multimodal US DL model were 0.779, 0.767, and 0.796, respectively, and the negative and positive predictive values were 0.842 and 0.706, respectively. The AUC of the multimodal US DL model was significantly better than that of the single-mode DL and clinical models. The DL algorithm developed using multimodal US images can effectively predict early fibrosis in patients with CKD with significantly greater accuracy than single-mode DL or clinical models.

PMID:39435700 | DOI:10.1080/0886022X.2024.2417740

Big Data. 2024 Oct 22. doi: 10.1089/big.2023.0117. Online ahead of print.

ABSTRACT

The influence maximization problem has several issues, including low infection rates and high time complexity. Many proposed methods are not suitable for large-scale networks due to their time complexity or free parameter usage. To address these challenges, this article proposes a local heuristic called Embedding Technique for Influence Maximization (ETIM) that uses shell decomposition, graph embedding, and reduction, as well as combined local structural features. The algorithm selects candidate nodes based on their connections among network shells and topological features, reducing the search space and computational overhead. It uses a deep learning-based node embedding technique to create a multidimensional vector of candidate nodes and calculates the dependency on spreading for each node based on local topological features. Finally, influential nodes are identified using the results of the previous phases and newly defined local features. The proposed algorithm is evaluated using the independent cascade model, showing its competitiveness and ability to achieve the best performance in terms of solution quality. Compared with the collective influence global algorithm, ETIM is significantly faster and improves the infection rate by an average of 12%.

PMID:39435527 | DOI:10.1089/big.2023.0117

Acta Radiol. 2024 Oct 22:2841851241288507. doi: 10.1177/02841851241288507. Online ahead of print.

ABSTRACT

BACKGROUND: Low-keV virtual monoenergetic images (VMIs) of dual-energy computed tomography (CT) enhances iodine contrast for detecting small arteries like the Adamkiewicz artery (AKA), but image noise can be problematic. Deep-learning image reconstruction (DLIR) effectively reduces noise without sacrificing image quality.

PURPOSE: To evaluate whether DLIR on low-keV VMIs of dual-energy CT scans improves the visualization of the AKA.

MATERIAL AND METHODS: We enrolled 29 patients who underwent CT angiography before aortic repair. VMIs obtained at 70 and 40 keV were reconstructed using hybrid iterative reconstruction (HIR), and 40 keV VMIs were reconstructed using DLIR. The image noise of the spinal cord, the maximum CT values of the anterior spinal artery (ASA), and the contrast-to-noise ratio (CNR) of the ASA were compared. The overall image quality and the delineation of the AKA were evaluated on a 4-point score (1 = poor, 4 = excellent).

RESULTS: The mean image noise of the spinal cord was significantly lower on 40-keV DLIR than on 40-keV HIR scans; they were significantly higher than on 70-keV HIR images. The CNR of the ASA was highest on the 40-keV DLIR images among the three reconstruction images. The mean image quality scores for 40-keV DLIR and 70-keV HIR scans were comparable, and higher than of 40-keV HIR images. The mean delineation scores for 40-keV HIR and 40-keV DLIR scans were significantly higher than for 70-keV HIR images.

CONCLUSION: Visualization of the AKA was significantly better on low-keV VMIs subjected to DLIR than conventional HIR images.

PMID:39435504 | DOI:10.1177/02841851241288507