Chemosphere. 2024 Sep 24:143404. doi: 10.1016/j.chemosphere.2024.143404. Online ahead of print.

ABSTRACT

The increasing presence of pharmaceuticals and personal care products (PPCPs) in aquatic systems pose significant environmental concerns. This study addresses this issue by synthesizing quaternized mesoporous SBA-15 (QSBA) with varied alkyl chain lengths of C1QSBA, C8QSBA, and C18QSBA. QSBA utilizes dual mechanisms: hydrophobic interactions via the alkyl chain and electrostatic attraction/ion exchange via the ammonium group. Diclofenac (DCF) and acetaminophen (ACT) were selected as target PPCPs due to their contrasting dissociation properties and hydrophobicity, which are the main characteristics of PPCPs. The adsorption of DCF and ACT revealed that longer alkyl chains enhanced the adsorption capacity of ACT through hydrophobic interactions, whereas dissociated DCF (DCF-) adsorption was superior owing to its high hydrophobicity (log Kow = 4.5) and electrostatic attraction. pH levels between 6 and 8 resulted in a high affinity for DCF-. Notably, among the three alkyl chains, only C18QSBA exhibited the most effective adsorption for DCF-. These PPCPs adsorption trends were confirmed through molecular simulations of adsorption under conditions in which competing ions coexisted. The molecular simulations show that while DCF- has lower adsorption energy than Cl-, OH-, and H3O+ ions in QSBA, enhancing its adsorption under various pH conditions. Conversely, ACT exhibits a higher adsorption energy, which reduces its adsorption efficiency. This suggests the potential application of QSBA with long alkyl chains in the treatment of highly hydrophobic and negatively charged PPCPs. Furthermore, this study emphasizes the importance of simulating adsorption under competing ion conditions.

PMID:39326708 | DOI:10.1016/j.chemosphere.2024.143404

ACS Appl Mater Interfaces. 2024 Sep 26. doi: 10.1021/acsami.4c12758. Online ahead of print.

ABSTRACT

Continuous and reliable monitoring of gait is crucial for health monitoring, such as postoperative recovery of bone joint surgery and early diagnosis of disease. However, existing gait analysis systems often suffer from large volumes and the requirement of special space for setting motion capture systems, limiting their application in daily life. Here, we develop an intelligent gait monitoring and analysis prediction system based on flexible piezoelectric sensors and deep learning neural networks with high sensitivity (241.29 mV/N), quick response (66 ms loading, 87 ms recovery), and excellent stability (R2 = 0.9946). The theoretical simulations and experiments confirm that the sensor provides exceptional signal feedback, which can easily acquire accurate gait data when fitted to shoe soles. By integrating high-quality gait data with a custom-built deep learning model, the system can detect and infer human motion states in real time (the recognition accuracy reaches 94.7%). To further validate the sensor's application in real life, we constructed a flexible wearable recognition system with human-computer interaction interface and a simple operation process for long-term and continuous tracking of athletes' gait, potentially aiding personalized health management, early detection of disease, and remote medical care.

PMID:39325961 | DOI:10.1021/acsami.4c12758

PLoS One. 2024 Sep 26;19(9):e0311199. doi: 10.1371/journal.pone.0311199. eCollection 2024.

ABSTRACT

Crop price forecasting is difficult in that supply is not as elastic as demand, therefore, supply and demand should be stabilized through long-term forecasting and pre-response to the price. In this study, we propose a Parametric Seasonal-Trend Autoregressive Neural Network (PaSTANet), which is a hybrid model that includes both a multi-kernel residual convolution neural network model and a Gaussian seasonality-trend model. To compare the performance of the PaSTANet, we used daily data from the Garak market for four crops: onion, radish, Chinese cabbage, and green onion, and performed long-term price forecasts for one year in 2023. The PaSTANet shows good performance on all four crops compared to other conventional statistical and deep learning-based models. In particular, for onion, the (mean absolute error (MAE) for the long-term forecast of 2023 is 107, outperforming the second-best Prophet (152) by 29.6%. Chinese cabbage, radish, and green onion all outperform the existing models with MAE of 2008, 3703, and 557, respectively. Moreover, using the confidence interval, the predicted price was categorized into three intervals: probability, caution, and warning. Comparing the percentage of classified intervals about the true prices in our test set, we found that they accurately detect the large price volatility.

PMID:39325794 | DOI:10.1371/journal.pone.0311199

J Appl Clin Med Phys. 2024 Sep 26:e14499. doi: 10.1002/acm2.14499. Online ahead of print.

ABSTRACT

BACKGROUND: Magnetic resonance imaging (MRI) and Computed tomography (CT) are crucial imaging techniques in both diagnostic imaging and radiation therapy. MRI provides excellent soft tissue contrast but lacks the direct electron density data needed to calculate dosage. CT, on the other hand, remains the gold standard due to its accurate electron density information in radiation therapy planning (RTP) but it exposes patients to ionizing radiation. Synthetic CT (sCT) generation from MRI has been a focused study field in the last few years due to cost effectiveness as well as for the objective of minimizing side-effects of using more than one imaging modality for treatment simulation. It offers significant time and cost efficiencies, bypassing the complexities of co-registration, and potentially improving treatment accuracy by minimizing registration-related errors. In an effort to navigate the quickly developing field of precision medicine, this paper investigates recent advancements in sCT generation techniques, particularly those using machine learning (ML) and deep learning (DL). The review highlights the potential of these techniques to improve the efficiency and accuracy of sCT generation for use in RTP by improving patient care and reducing healthcare costs. The intricate web of sCT generation techniques is scrutinized critically, with clinical implications and technical underpinnings for enhanced patient care revealed.

PURPOSE: This review aims to provide an overview of the most recent advancements in sCT generation from MRI with a particular focus of its use within RTP, emphasizing on techniques, performance evaluation, clinical applications, future research trends and open challenges in the field.

METHODS: A thorough search strategy was employed to conduct a systematic literature review across major scientific databases. Focusing on the past decade's advancements, this review critically examines emerging approaches introduced from 2013 to 2023 for generating sCT from MRI, providing a comprehensive analysis of their methodologies, ultimately fostering further advancement in the field. This study highlighted significant contributions, identified challenges, and provided an overview of successes within RTP. Classifying the identified approaches, contrasting their advantages and disadvantages, and identifying broad trends were all part of the review's synthesis process.

RESULTS: The review identifies various sCT generation approaches, consisting atlas-based, segmentation-based, multi-modal fusion, hybrid approaches, ML and DL-based techniques. These approaches are evaluated for image quality, dosimetric accuracy, and clinical acceptability. They are used for MRI-only radiation treatment, adaptive radiotherapy, and MR/PET attenuation correction. The review also highlights the diversity of methodologies for sCT generation, each with its own advantages and limitations. Emerging trends incorporate the integration of advanced imaging modalities including various MRI sequences like Dixon sequences, T1-weighted (T1W), T2-weighted (T2W), as well as hybrid approaches for enhanced accuracy.

CONCLUSIONS: The study examines MRI-based sCT generation, to minimize negative effects of acquiring both modalities. The study reviews 2013-2023 studies on MRI to sCT generation methods, aiming to revolutionize RTP by reducing use of ionizing radiation and improving patient outcomes. The review provides insights for researchers and practitioners, emphasizing the need for standardized validation procedures and collaborative efforts to refine methods and address limitations. It anticipates the continued evolution of techniques to improve the precision of sCT in RTP.

PMID:39325781 | DOI:10.1002/acm2.14499

PLoS One. 2024 Sep 26;19(9):e0310707. doi: 10.1371/journal.pone.0310707. eCollection 2024.

ABSTRACT

Over the last ten years, social media has become a crucial data source for businesses and researchers, providing a space where people can express their opinions and emotions. To analyze this data and classify emotions and their polarity in texts, natural language processing (NLP) techniques such as emotion analysis (EA) and sentiment analysis (SA) are employed. However, the effectiveness of these tasks using machine learning (ML) and deep learning (DL) methods depends on large labeled datasets, which are scarce in languages like Spanish. To address this challenge, researchers use data augmentation (DA) techniques to artificially expand small datasets. This study aims to investigate whether DA techniques can improve classification results using ML and DL algorithms for sentiment and emotion analysis of Spanish texts. Various text manipulation techniques were applied, including transformations, paraphrasing (back-translation), and text generation using generative adversarial networks, to small datasets such as song lyrics, social media comments, headlines from national newspapers in Chile, and survey responses from higher education students. The findings show that the Convolutional Neural Network (CNN) classifier achieved the most significant improvement, with an 18% increase using the Generative Adversarial Networks for Sentiment Text (SentiGan) on the Aggressiveness (Seriousness) dataset. Additionally, the same classifier model showed an 11% improvement using the Easy Data Augmentation (EDA) on the Gender-Based Violence dataset. The performance of the Bidirectional Encoder Representations from Transformers (BETO) also improved by 10% on the back-translation augmented version of the October 18 dataset, and by 4% on the EDA augmented version of the Teaching survey dataset. These results suggest that data augmentation techniques enhance performance by transforming text and adapting it to the specific characteristics of the dataset. Through experimentation with various augmentation techniques, this research provides valuable insights into the analysis of subjectivity in Spanish texts and offers guidance for selecting algorithms and techniques based on dataset features.

PMID:39325750 | DOI:10.1371/journal.pone.0310707

PLoS One. 2024 Sep 26;19(9):e0311323. doi: 10.1371/journal.pone.0311323. eCollection 2024.

NO ABSTRACT

PMID:39325725 | DOI:10.1371/journal.pone.0311323

IEEE J Biomed Health Inform. 2024 Sep 26;PP. doi: 10.1109/JBHI.2024.3467343. Online ahead of print.

ABSTRACT

Brain tumor detection has advanced significantly with the development of deep learning technology. Although multimodal data, such as Magnetic Resonance Imaging (MRI) and Computed Tomography (CT), has potential advantages in diagnostics, most existing studies rely solely on a single modality. This is because common fusion methods may lead to the loss of critical information when attempting multimodal fusion. Therefore, effectively integrating multimodal data has become a significant challenge. Additionally, medical image analysis requires large amounts of annotated data, and labeling images is a resourceintensive task that demands experienced professionals to spend a considerable amount of time. To address these challenges, this paper introduces a new unsupervised learning framework named Double-SimCLR. This framework builds on the foundation of contrastive learning and features a dual-branch structure, enabling direct and simultaneous processing of MRI and CT images for multimodal feature fusion. Given the "weak feature" characteristics of CT images (e.g., low soft tissue contrast and low resolution), we incorporated adaptive weight masking technology to enhance CT feature extraction. Moreover, we introduced a multimodal attention mechanism, which ensures that the model focuses on salient information, thereby elevating the precision and robustness of brain tumor detection. Even without substantial labeled data, experimental results demonstrate that Double-SimCLR achieves 93.458% accuracy, 92.463% precision, and a 93.058% F1-score, outperforming state-of-the-art (SOTA) models by 2.871%, 2.643%, and 3.098%, respectively.

PMID:39325615 | DOI:10.1109/JBHI.2024.3467343

IEEE Trans Neural Netw Learn Syst. 2024 Sep 26;PP. doi: 10.1109/TNNLS.2024.3449949. Online ahead of print.

ABSTRACT

Dynamic functional connectivity (DFC) extracted from resting-state functional magnetic resonance imaging (fMRI) has been widely used for neuropsychiatric disorder classifications. However, serious information redundancy within DFC matrices can significantly undermine the performance of classification models based on them. Moreover, traditional deep models cannot adapt well to connectivity-like data, and insufficient training samples further hinder their effective training. In this study, we proposed a novel region-state masked autoencoder (RS-MAE) for proficient representation learning based on DFC matrices and ultimately neuropsychiatric disorder classifications based on fMRI. Three strategies were taken to address the aforementioned limitations. First, masked autoencoder (MAE) was introduced to reduce redundancy within DFC matrices and learn effective representations of human brain function simultaneously. Second, region-state (RS) patch embedding was proposed to replace space-time patch embedding in video MAE to adapt to DFC matrices, in which only topological locality, rather than spatial locality, exists. Third, random state concatenation (RSC) was introduced as a DFC matrix augmentation approach, to alleviate the problem of training sample insufficiency. Neuropsychiatric disorder classifications were attained by fine-tuning the pretrained encoder included in RS-MAE. The performance of the proposed RS-MAE was evaluated on four publicly available datasets, achieving accuracies of 76.32%, 77.25%, 88.87%, and 76.53% for the attention deficit and hyperactivity disorder (ADHD), autism spectrum disorder (ASD), Alzheimer's disease (AD), and schizophrenia (SCZ) classification tasks, respectively. These results demonstrate the efficacy of the RS-MAE as a proficient deep learning model for neuropsychiatric disorder classifications.

PMID:39325609 | DOI:10.1109/TNNLS.2024.3449949

JMIR Mhealth Uhealth. 2024 Sep 26;12:e59469. doi: 10.2196/59469.

ABSTRACT

BACKGROUND: The increasing prevalence of obesity necessitates innovative approaches to better understand this health crisis, particularly given its strong connection to chronic diseases such as diabetes, cancer, and cardiovascular conditions. Monitoring dietary behavior is crucial for designing effective interventions that help decrease obesity prevalence and promote healthy lifestyles. However, traditional dietary tracking methods are limited by participant burden and recall bias. Exploring microlevel eating activities, such as meal duration and chewing frequency, in addition to eating episodes, is crucial due to their substantial relation to obesity and disease risk.

OBJECTIVE: The primary objective of the study was to develop an accurate and noninvasive system for automatically monitoring eating and chewing activities using sensor-equipped smart glasses. The system distinguishes chewing from other facial activities, such as speaking and teeth clenching. The secondary objective was to evaluate the system's performance on unseen test users using a combination of laboratory-controlled and real-life user studies. Unlike state-of-the-art studies that focus on detecting full eating episodes, our approach provides a more granular analysis by specifically detecting chewing segments within each eating episode.

METHODS: The study uses OCO optical sensors embedded in smart glasses to monitor facial muscle activations related to eating and chewing activities. The sensors measure relative movements on the skin's surface in 2 dimensions (X and Y). Data from these sensors are analyzed using deep learning (DL) to distinguish chewing from other facial activities. To address the temporal dependence between chewing events in real life, we integrate a hidden Markov model as an additional component that analyzes the output from the DL model.

RESULTS: Statistical tests of mean sensor activations revealed statistically significant differences across all 6 comparison pairs (P<.001) involving 2 sensors (cheeks and temple) and 3 facial activities (eating, clenching, and speaking). These results demonstrate the sensitivity of the sensor data. Furthermore, the convolutional long short-term memory model, which is a combination of convolutional and long short-term memory neural networks, emerged as the best-performing DL model for chewing detection. In controlled laboratory settings, the model achieved an F1-score of 0.91, demonstrating robust performance. In real-life scenarios, the system demonstrated high precision (0.95) and recall (0.82) for detecting eating segments. The chewing rates and the number of chews evaluated in the real-life study showed consistency with expected real-life eating behaviors.

CONCLUSIONS: The study represents a substantial advancement in dietary monitoring and health technology. By providing a reliable and noninvasive method for tracking eating behavior, it has the potential to revolutionize how dietary data are collected and used. This could lead to more effective health interventions and a better understanding of the factors influencing eating habits and their health implications.

PMID:39325528 | DOI:10.2196/59469

J Med Internet Res. 2024 Sep 26;26:e57852. doi: 10.2196/57852.

ABSTRACT

BACKGROUND: Clinical narratives are essential components of electronic health records. The adoption of electronic health records has increased documentation time for hospital staff, leading to the use of abbreviations and acronyms more frequently. This brevity can potentially hinder comprehension for both professionals and patients.

OBJECTIVE: This review aims to provide an overview of the types of short forms found in clinical narratives, as well as the natural language processing (NLP) techniques used for their identification, expansion, and disambiguation.

METHODS: In the databases Web of Science, Embase, MEDLINE, EBMR (Evidence-Based Medicine Reviews), and ACL Anthology, publications that met the inclusion criteria were searched according to PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines for a systematic scoping review. Original, peer-reviewed publications focusing on short-form processing in human clinical narratives were included, covering the period from January 2018 to February 2023. Short-form types were extracted, and multidimensional research methodologies were assigned to each target objective (identification, expansion, and disambiguation). NLP study recommendations and study characteristics were systematically assigned occurrence rates for evaluation.

RESULTS: Out of a total of 6639 records, only 19 articles were included in the final analysis. Rule-based approaches were predominantly used for identifying short forms, while string similarity and vector representations were applied for expansion. Embeddings and deep learning approaches were used for disambiguation.

CONCLUSIONS: The scope and types of what constitutes a clinical short form were often not explicitly defined by the authors. This lack of definition poses challenges for reproducibility and for determining whether specific methodologies are suitable for different types of short forms. Analysis of a subset of NLP recommendations for assessing quality and reproducibility revealed only partial adherence to these recommendations. Single-character abbreviations were underrepresented in studies on clinical narrative processing, as were investigations in languages other than English. Future research should focus on these 2 areas, and each paper should include descriptions of the types of content analyzed.

PMID:39325515 | DOI:10.2196/57852

Clin Nucl Med. 2024 Sep 25. doi: 10.1097/RLU.0000000000005441. Online ahead of print.

ABSTRACT

PURPOSE: PET/CT and MRI can accurately diagnose dementia but are expensive and inconvenient for patients. Therefore, we aimed to generate synthetic fluid-attenuated inversion recovery (FLAIR) images from 18F-FDG PET and CT images of the human brain using a generative adversarial network (GAN)-based deep learning framework called the CypixGAN, which combined the CycleGAN framework with the L1 loss function of the pix2pix.

PATIENTS AND METHODS: Data from 143 patients who underwent PET/CT and MRI were used for training (n = 79), validation (n = 20), and testing (n = 44) the deep learning frameworks. Synthetic FLAIR images were generated using the pix2pix, CycleGAN, and CypixGAN, and white matter hyperintensities (WMHs) were then segmented. The performance of CypixGAN was compared with that of the other frameworks.

RESULTS: The CypixGAN outperformed the pix2pix and CycleGAN in generating synthetic FLAIR images with superior visual quality. Peak signal-to-noise ratio and structural similarity index (mean ± standard deviation) estimated using the CypixGAN (20.23 ± 1.31 and 0.80 ± 0.02, respectively) were significantly higher than those estimated using the pix2pix (19.35 ± 1.43 and 0.79 ± 0.02, respectively) and CycleGAN (18.74 ± 1.49 and 0.78 ± 0.02, respectively) (P < 0.001). WMHs in synthetic FLAIR images generated using the CypixGAN closely resembled those in ground-truth images, as indicated by the low absolute percentage volume differences and high dice similarity coefficients.

CONCLUSIONS: The CypixGAN generated high-quality FLAIR images owing to the preservation of spatial information despite using unpaired images. This framework may help improve diagnostic performance and cost-effectiveness of PET/CT when MRI scan is unavailable.

PMID:39325494 | DOI:10.1097/RLU.0000000000005441

JAMA Ophthalmol. 2024 Sep 26. doi: 10.1001/jamaophthalmol.2024.3707. Online ahead of print.

ABSTRACT

IMPORTANCE: Myopic maculopathy (MM) is a major cause of vision impairment globally. Artificial intelligence (AI) and deep learning (DL) algorithms for detecting MM from fundus images could potentially improve diagnosis and assist screening in a variety of health care settings.

OBJECTIVES: To evaluate DL algorithms for MM classification and segmentation and compare their performance with that of ophthalmologists.

DESIGN, SETTING, AND PARTICIPANTS: The Myopic Maculopathy Analysis Challenge (MMAC) was an international competition to develop automated solutions for 3 tasks: (1) MM classification, (2) segmentation of MM plus lesions, and (3) spherical equivalent (SE) prediction. Participants were provided 3 subdatasets containing 2306, 294, and 2003 fundus images, respectively, with which to build algorithms. A group of 5 ophthalmologists evaluated the same test sets for tasks 1 and 2 to ascertain performance. Results from model ensembles, which combined outcomes from multiple algorithms submitted by MMAC participants, were compared with each individual submitted algorithm. This study was conducted from March 1, 2023, to March 30, 2024, and data were analyzed from January 15, 2024, to March 30, 2024.

EXPOSURE: DL algorithms submitted as part of the MMAC competition or ophthalmologist interpretation.

MAIN OUTCOMES AND MEASURES: MM classification was evaluated by quadratic-weighted κ (QWK), F1 score, sensitivity, and specificity. MM plus lesions segmentation was evaluated by dice similarity coefficient (DSC), and SE prediction was evaluated by R2 and mean absolute error (MAE).

RESULTS: The 3 tasks were completed by 7, 4, and 4 teams, respectively. MM classification algorithms achieved a QWK range of 0.866 to 0.901, an F1 score range of 0.675 to 0.781, a sensitivity range of 0.667 to 0.778, and a specificity range of 0.931 to 0.945. MM plus lesions segmentation algorithms achieved a DSC range of 0.664 to 0.687 for lacquer cracks (LC), 0.579 to 0.673 for choroidal neovascularization, and 0.768 to 0.841 for Fuchs spot (FS). SE prediction algorithms achieved an R2 range of 0.791 to 0.874 and an MAE range of 0.708 to 0.943. Model ensemble results achieved the best performance compared to each submitted algorithms, and the model ensemble outperformed ophthalmologists at MM classification in sensitivity (0.801; 95% CI, 0.764-0.840 vs 0.727; 95% CI, 0.684-0.768; P = .006) and specificity (0.946; 95% CI, 0.939-0.954 vs 0.933; 95% CI, 0.925-0.941; P = .009), LC segmentation (DSC, 0.698; 95% CI, 0.649-0.745 vs DSC, 0.570; 95% CI, 0.515-0.625; P < .001), and FS segmentation (DSC, 0.863; 95% CI, 0.831-0.888 vs DSC, 0.790; 95% CI, 0.742-0.830; P < .001).

CONCLUSIONS AND RELEVANCE: In this diagnostic study, 15 AI models for MM classification and segmentation on a public dataset made available for the MMAC competition were validated and evaluated, with some models achieving better diagnostic performance than ophthalmologists.

PMID:39325442 | DOI:10.1001/jamaophthalmol.2024.3707

Proc Natl Acad Sci U S A. 2024 Oct;121(40):e2409913121. doi: 10.1073/pnas.2409913121. Epub 2024 Sep 26.

ABSTRACT

Discrepancy is a well-known measure for the irregularity of the distribution of a point set. Point sets with small discrepancy are called low discrepancy and are known to efficiently fill the space in a uniform manner. Low-discrepancy points play a central role in many problems in science and engineering, including numerical integration, computer vision, machine perception, computer graphics, machine learning, and simulation. In this work, we present a machine learning approach to generate a new class of low-discrepancy point sets named Message-Passing Monte Carlo (MPMC) points. Motivated by the geometric nature of generating low-discrepancy point sets, we leverage tools from Geometric Deep Learning and base our model on graph neural networks. We further provide an extension of our framework to higher dimensions, which flexibly allows the generation of custom-made points that emphasize the uniformity in specific dimensions that are primarily important for the particular problem at hand. Finally, we demonstrate that our proposed model achieves state-of-the-art performance superior to previous methods by a significant margin. In fact, MPMC points are empirically shown to be either optimal or near-optimal with respect to the discrepancy for low dimension and small number of points, i.e., for which the optimal discrepancy can be determined.

PMID:39325425 | DOI:10.1073/pnas.2409913121

Acta Neurochir (Wien). 2024 Sep 26;166(1):381. doi: 10.1007/s00701-024-06267-9.

ABSTRACT

BACKGROUND: Detection and localization of cerebral microbleeds (CMBs) is crucial for disease diagnosis and treatment planning. However, CMB detection is labor-intensive, time-consuming, and challenging owing to its visual similarity to mimics. This study aimed to validate the performance of a three-dimensional (3D) deep learning model that not only detects CMBs but also identifies their anatomic location in real-world settings.

METHODS: A total of 21 patients with 116 CMBs and 12 without CMBs were visited in the neurosurgery outpatient department between January 2023 and October 2023. Three readers, including a board-certified neuroradiologist (reader 1), a resident in radiology (reader 2), and a neurosurgeon (reader 3) independently reviewed SWIs of 33 patients to detect CMBs and categorized their locations into lobar, deep, and infratentorial regions without any AI assistance. After a one-month washout period, the same datasets were redistributed randomly, and readers reviewed them again with the assistance of the 3D deep learning model. A comparison of the diagnostic performance between readers with and without AI assistance was performed.

RESULTS: All readers with an AI assistant (reader 1:0.991 [0.930-0.999], reader 2:0.922 [0.881-0.905], and reader 3:0.966 [0.928-0.984]) tended to have higher sensitivity per lesion than readers only (reader 1:0.905 [0.849-0.942], reader 2:0.621 [0.541-0.694], and reader 3:0.871 [0.759-0.935], p = 0.132, 0.017, and 0.227, respectively). In particular, radiology residents (reader 2) showed a statistically significant increase in sensitivity per lesion when using AI. There was no statistically significant difference in the number of FPs per patient for all readers with AI assistant (reader 1: 0.394 [0.152-1.021], reader 2: 0.727 [0.334-1.582], reader 3: 0.182 [0.077-0.429]) and reader only (reader 1: 0.364 [0.159-0.831], reader 2: 0.576 [0.240-1.382], reader 3: 0.121 [0.038-0.383], p = 0.853, 0.251, and 0.157, respectively). Our model accurately categorized the anatomical location of all CMBs.

CONCLUSIONS: Our model demonstrated promising potential for the detection and anatomical localization of CMBs, although further research with a larger and more diverse population is necessary to establish clinical utility in real-world settings.

PMID:39325068 | DOI:10.1007/s00701-024-06267-9

Clin Transl Gastroenterol. 2024 Sep 26. doi: 10.14309/ctg.0000000000000771. Online ahead of print.

ABSTRACT

Endoscopic ultrasound (EUS) allows characterization and biopsy of pancreatic lesions. Pancreatic cystic neoplasms (PCN) include in mucinous (M-PCN) and non-mucinous lesions (NM-PCN). Pancreatic ductal adenocarcinoma (P-DAC) is the commonest pancreatic solid lesion (PSL), followed by pancreatic neuroendocrine tumor (P-NET). While EUS is preferred for pancreatic lesion evaluation, its diagnostic accuracy is suboptimal. This multicentric study aims to develop a convolutional neural network (CNN) for detecting and distinguishing PCN (namely M-PCN and NM-PCN) and PSL (particularly P-DAC and P-NET). A CNN was developed with 378 EUS exams from 4 international reference centers (Centro Hospitalar Universitário São João, Hospital Universitario Puerta de Hierro Majadahonda, New York University Hospitals, Hospital das Clínicas FMUSP). 126.000 images were obtained - 19.528 M-PCN, 8.175 NM-PCN, 64.286 P-DAC, 29.153 P-NET and 4.858 normal pancreas images. A trinary CNN differentiated normal pancreas tissue from M-PCN and NM-PCN. A binary CNN distinguished P-DAC from P-NET. The total dataset was divided in a training and testing dataset (used for model's evaluation) in a 90/10% ratio. The model was evaluated through its sensitivity, specificity, positive and negative predictive values and accuracy. The CNN had 99.1% accuracy for identifying normal pancreatic tissue, 99.0% and 99.8% for M-PCN and NM-PCN, respectively. P-DAC and P-NET were distinguished with 94.0% accuracy. Our group developed the first worldwide CNN capable of detecting and differentiating the commonest PCN and PSL in EUS images, using exams from 4 centers in two continents, minimizing the impact of the demographic bias. Larger multicentric studies are needed for technology implementation.

PMID:39324610 | DOI:10.14309/ctg.0000000000000771

Pest Manag Sci. 2024 Sep 26. doi: 10.1002/ps.8442. Online ahead of print.

ABSTRACT

BACKGROUND: Forest ecosystems are under constant threat from wood-boring pests such as the Emerald ash borer (EAB), which remain elusive owing to their hidden life cycles within tree trunks. Early detection is vital to mitigate economic and ecological damage. The main current monitoring method is manual detection which is ineffective at early stages of infestation. This study introduces VibroEABNet, a deep learning-based joint recognition network designed to enhance the detection of EAB boring vibration signals, with a novel approach integrating denoising and recognition modules.

RESULTS: The proposed VibroEABNet model demonstrated exceptional performance, achieving an average accuracy of 98.98% across multiple signal-to-noise ratios (SNRs) in test datasets and a remarkable 97.5% accuracy in real forest datasets, surpassing traditional models and other deep learning networks evaluated in this study. These findings were supported by rigorous noise resistance analysis and real dataset evaluation, indicating the model's robustness and reliability in practical applications. Furthermore, the model's efficiency was highlighted by its inference time of 26 ms and a compact model size of 8.43 MB, underscoring its suitability for deployment in resource-limited environments.

CONCLUSION: The development of VibroEABNet marks a significant advancement in pest detection methodologies, offering a scalable, accurate and efficient solution for early monitoring of wood-boring pests. The integration of a denoising module within the network structure addresses the challenge of environmental noise, one of the primary limitations in acoustic monitoring of pests. Currently, this research is limited to a specific pest. Future work will focus on the applicability of this network to other wood-boring pests. © 2024 Society of Chemical Industry.

PMID:39324448 | DOI:10.1002/ps.8442

Huan Jing Ke Xue. 2024 Sep 8;45(9):5179-5187. doi: 10.13227/j.hjkx.202310217.

ABSTRACT

Accurate prediction of PM10 concentration is important for effectively managing PM10 exposure and mitigating health and economic risks posed to humans in dry bulk ports. However, accurately capturing the time-series nonlinear variation characteristics of PM10 concentration is challenging owing to the specific intensity of port operation activities and the influence of meteorological factors. To address such challenges, a novel combined deep learning model （CLAF） was proposed, merging cascaded convolutional neural networks （CNN）, long short-term memory （LSTM）, and an attention mechanism （AM）. This integrated model aimed to forecast hourly PM10 concentration in dry bulk ports. First, using the random forest characteristic importance algorithm, the distinct meteorological factors were identified among the selected five meteorological factors. These selected factors were incorporated into the prediction model along with the PM10 concentration. Subsequently, the CNN layer was employed to extract high-dimensional time-varying features from the input variables, while the LSTM layer captured sequential features and long-term dependencies. In the AM layer, different weights were assigned to the output components of the LSTM layer to amplify the effects of important information. Finally, three evaluation metrics were applied to compare the performance of the CLAF model with three basic models and three commonly used prediction models. Real-case data was collected and used in this study. Comparison results demonstrated that considering the meteorological factors could improve the prediction accuracy and fitting performance of PM10 concentration in ports. The CLAF model reduced the mean absolute error statistic by 13.92%-56.9%, decreased the mean square error statistic by 45.99%-81.02%, and improved the goodness-of-fit statistic by 3.2%-15.5%.

PMID:39323136 | DOI:10.13227/j.hjkx.202310217

J Med Internet Res. 2024 Sep 25. doi: 10.2196/58572. Online ahead of print.

ABSTRACT

BACKGROUND: While speech analysis holds promise for mental health assessment, research often focuses on single symptoms, despite symptom co-occurrences and interactions. In addition, predictive models in mental health do not properly assess speech-based systems' limitations, such as uncertainty, or fairness for a safe clinical deployment.

OBJECTIVE: We investigated the predictive potential of mobile-collected speech data for detecting and estimating depression, anxiety, fatigue, and insomnia, focusing on other factors than mere accuracy, in the general population.

METHODS: We included n=865 healthy adults and recorded their answers regarding their perceived mental and sleep states. We asked how they felt and if they had slept well lately. Clinically validated questionnaires measuring depression, anxiety, insomnia, and fatigue severity were also used. We developed a novel speech and machine learning pipeline involving voice activity detection, feature extraction, and model training. We automatically analyzed participants' speech with a fully ML automatic pipeline to capture speech variability. Then, we modelled speech with pretrained deep learning models that were pre-trained on a large open free database and we selected the best one on the validation set. Based on the best speech modelling approach, we evaluated clinical threshold detection, individual score prediction, model uncertainty estimation, and performance fairness across demographics (age, sex, education). We employed a train-validation-test split for all evaluations: to develop our models, select the best ones and assess the generalizability of held-out data.

RESULTS: The best model was WhisperM with a max pooling, and oversampling method. Our methods achieved good detection performance for all symptoms, depression (PHQ-9 AUC= 0.76F1=0.49, BDI AUC=0.78, F1=0,65), anxiety (GAD-7 F1=0.50, AUC=0.77) insomnia (AIS AUC=0.73, F1=0.62), and fatigue (MFI Total Score F1=0.88, AUC=0.68). These strengths were maintained for depression detection with BDI and Fatigue for abstention rates for uncertain cases (Risk-Coverage AUCs < 0.4). Individual symptom scores were predicted with good accuracy (Correlations were all significant, with Pearson strengths between 0.31 and 0.49). Fairness analysis revealed that models were consistent for sex (average Disparity Ratio (DR) = 0.86), to a lesser extent for education level (average Disparity Ratio (DR) = 0.47) and worse for age groups (average Disparity Ratio (DR) = 0.33).

CONCLUSIONS: This study demonstrates the potential of speech-based systems for multifaceted mental health assessment in the general population, not only for detecting clinical thresholds but also for estimating their severity. Addressing fairness and incorporating uncertainty estimation with selective classification are key contributions that can enhance the clinical utility and responsible implementation of such systems. This approach offers promise for more accurate and nuanced mental health assessments, benefiting both patients and clinicians.

PMID:39324329 | DOI:10.2196/58572

Front Artif Intell. 2024 Sep 11;7:1444136. doi: 10.3389/frai.2024.1444136. eCollection 2024.

ABSTRACT

BACKGROUND: Glaucoma (GLAU), Age-related Macular Degeneration (AMD), Retinal Vein Occlusion (RVO), and Diabetic Retinopathy (DR) are common blinding ophthalmic diseases worldwide.

PURPOSE: This approach is expected to enhance the early detection and treatment of common blinding ophthalmic diseases, contributing to the reduction of individual and economic burdens associated with these conditions.

METHODS: We propose an effective deep-learning pipeline that combine both segmentation model and classification model for diagnosis and grading of four common blinding ophthalmic diseases and normal retinal fundus.

RESULTS: In total, 102,786 fundus images of 75,682 individuals were used for training validation and external validation purposes. We test our model on internal validation data set, the micro Area Under the Receiver Operating Characteristic curve (AUROC) of which reached 0.995. Then, we fine-tuned the diagnosis model to classify each of the four disease into early and late stage, respectively, which achieved AUROCs of 0.597 (GL), 0.877 (AMD), 0.972 (RVO), and 0.961 (DR) respectively. To test the generalization of our model, we conducted two external validation experiments on Neimeng and Guangxi cohort, all of which maintained high accuracy.

CONCLUSION: Our algorithm demonstrates accurate artificial intelligence diagnosis pipeline for common blinding ophthalmic diseases based on Lesion-Focused fundus that overcomes the low-accuracy of the traditional classification method that based on raw retinal images, which has good generalization ability on diverse cases in different regions.

PMID:39324131 | PMC:PMC11422385 | DOI:10.3389/frai.2024.1444136

Indian J Orthop. 2024 Sep 11;58(10):1458-1473. doi: 10.1007/s43465-024-01259-4. eCollection 2024 Oct.

ABSTRACT

INTRODUCTION: Knee osteoarthritis (OA) is a prevalent condition that significantly impacts the quality of life, often leading to the need for knee replacement surgery. Accurate and timely identification of knee degeneration is crucial for effective treatment and management. Traditional methods of diagnosing OA rely heavily on radiological assessments, which can be time-consuming and subjective. This study aims to address these challenges by developing a deep learning-based method to predict the likelihood of knee replacement and the Kellgren-Lawrence (KL) grade of knee OA from X-ray images.

METHODOLOGY: We employed the Osteoarthritis Initiative (OAI) dataset and utilized a transfer learning approach with the Inception V3 architecture to enhance the accuracy of OA detection. Our approach involved training 14 different models-Xception, VGG16, VGG19, ResNet50, ResNet101, ResNet152, ResNet50V2, ResNet101V2, ResNet152V2, Inception V3, Inception, ResNetV2, DenseNet121, DenseNet169, DenseNet201-and comparing their performance.

RESULTS: The study incorporated pixel ratio computation and picture pre-processing, alongside a decision tree model for prediction. Our experiments revealed that the Inception V3 model achieved the highest training accuracy of 91% and testing accuracy of 67%, with notable performance in both training and validation phases. This model effectively identified the presence and severity of OA, correlating with the Kellgren-Lawrence scale and facilitating the assessment of knee replacement needs.

CONCLUSION: By integrating advanced deep learning techniques with radiological diagnostics, our methodology supports radiologists in making more accurate and prompt decisions regarding knee degeneration. The Inception V3 model stands out as the optimal choice for knee X-ray analysis, contributing to more efficient and timely healthcare delivery for patients with knee osteoarthritis.

PMID:39324090 | PMC:PMC11420401 | DOI:10.1007/s43465-024-01259-4