J Voice. 2025 Feb 1:S0892-1997(24)00486-7. doi: 10.1016/j.jvoice.2024.12.048. Online ahead of print.

ABSTRACT

PURPOSE: Voice pathology detection is a rapidly evolving field of scientific research focused on the identification and diagnosis of voice disorders. Early detection and diagnosis of these disorders is critical, as it increases the likelihood of effective treatment and reduces the burden on medical professionals.

METHODS: The objective of this scientific paper is to develop a comprehensive model that utilizes various deep learning techniques to improve the detection of voice pathology. To achieve this, the paper employs several techniques to extract a set of sensitive features from the original voice signal by analyzing the time-frequency characteristics of the signal. In this regard, as a means of extracting these features, a state-of-the-art approach combining Gammatonegram features with Scalogram Teager_Kaiser Energy Operator (TKEO) features is proposed, and the proposed feature extraction scheme is named Combine Gammatonegram with (TKEO) Scalogram (CGT Scalogram). In this study, ResNet deep learning is used to recognize healthy voices from pathological voices. To evaluate the performance of the proposed model, it is trained and tested using the Saarbrucken voice database.

RESULTS: In the end, the proposed system yielded impressive results with an accuracy of 96%, a precision of 96.3%, and a recall of 96.1% for binary classification and an accuracy of 94.4%, a precision of 94.5%, and a recall of 94% for multi-class.

CONCLUSION: The results of the experiments demonstrate the effectiveness of the feature selection technique in maximizing the prediction accuracy in both binary and multi-class classifications.

PMID:39894721 | DOI:10.1016/j.jvoice.2024.12.048

Lab Invest. 2025 Jan 31:104101. doi: 10.1016/j.labinv.2025.104101. Online ahead of print.

ABSTRACT

Most gastric cancer (GC) patients exhibit microsatellite stability (MSS), yet comprehensive subtyping for prognostic prediction and clinical treatment decisions for MSS GC is lacking. In this work, RNA-sequencing gene expression data and clinical information of MSS GC patients were obtained from The Cancer Genome Atlas (TCGA) and the Gene Expression Omnibus (GEO) databases. We employed several machine learning methods to develop and validate a signature based on immune-related genes (IRGs) for subtyping MSS GC patients. Moreover, two deep learning models based on the Vision Transformer (ViT) architecture were developed to predict GC tumor tiles and identify MSS GC subtypes from digital pathology slides. Microsatellite status was evaluated by immunohistochemistry, and prognostic data as well as H&E whole slide images were collected from 105 MSS GC patients to serve as an independent validation cohort. A signature comprising five IRGs was established and validated, stratifying MSS GC patients into high-risk (MSS-HR) and low-risk (MSS-LR) groups. This signature demonstrated consistent performance, with areas under the receiver operating characteristic (ROC) curve (AUC) of 0.65, 0.70, and 0.70 at 1, 3, and 5 years in the TCGA cohort, and 0.70, 0.60, and 0.62 in the GEO cohort, respectively. The MSS-HR subtype exhibited higher levels of tumor immune dysfunction and exclusion, suggesting a greater potential for immune escape compared to the MSS-LR subtype. Moreover, the MSS-HR/LR subtypes showed differential sensitivities to various therapeutic drugs. Leveraging morphological differences, the tumor recognition segmentation model (TRSM) achieved an impressive AUC of 0.97, while the MSS-HR/LR identification model (MSSIM) effectively classified MSS-HR/LR subtypes with an AUC of 0.94. Both models demonstrated promising results in classifying MSS GC patients in the external validation cohort, highlighting the strong ability to accurately differentiate between MSS GC subtypes. The IRGs-related MSS-HR/LR subtypes had potential in enhancing outcome prediction accuracy and guide treatment strategies. This research may optimize precision treatment and improve the prognosis for MSS GC patients.

PMID:39894411 | DOI:10.1016/j.labinv.2025.104101

Acta Biomater. 2025 Jan 31:S1742-7061(25)00079-0. doi: 10.1016/j.actbio.2025.01.059. Online ahead of print.

ABSTRACT

The surface modification of titanium (Ti) and its alloys is crucial for improving their osteogenic capability, as their bio-inert nature limits effective osseointegration despite their prevalent use in orthopedic implants. However, these modification methods produce varied surface properties, making it challenging to standardize criteria for assessing the osteogenic capacity of implant surfaces. Additionally, traditional evaluation experiments are time-consuming and inefficient. To overcome these limitations, this study introduced a high-throughput, efficient screening method for assessing the osteogenic capability of implant surfaces based on early cell morphology and deep learning. The Orthopedic Implants-Osteogenic Differentiation Network (OIODNet) was developed using early cell morphology images and corresponding alkaline phosphatase (ALP) activity values from cells cultured on Ti and its alloy surfaces, achieving performance metrics exceeding 0.98 across all six evaluation parameters. Validation through metal-polyphenol network (MPN) coatings and cell experiments demonstrated a strong correlation between OIODNet's predictions and actual ALP activity outcomes, confirming its accuracy in predicting osteogenic potential based on early cell morphology. The Osteogenic Predictor application offers an intuitive tool for predicting the osteogenic capacity of implant surfaces. Overall, this research highlights the potential to accelerate progress at the intersection of artificial intelligence and biomaterials, paving the way for more efficient screening of osteogenic capabilities in orthopedic implants. STATEMENT OF SIGNIFICANCE: By leveraging deep learning, this study introduces the Orthopedic Implants-Osteogenic Differentiation Network (OIODNet), which utilizes early cell morphology data and alkaline phosphatase (ALP) activity values to provide a high-throughput, accurate method for predicting osteogenic capability. With performance metrics exceeding 0.98, OIODNet's accuracy was further validated through experiments involving metal-polyphenol network (MPN) coatings, showing a strong correlation between the model's predictions and experimental outcomes. This research offers a powerful tool for more efficient screening of implant surfaces, marking a transformative step in the integration of artificial intelligence and biomaterials, while opening new avenues for advancing orthopedic implant technologies.

PMID:39894326 | DOI:10.1016/j.actbio.2025.01.059

Spine J. 2025 Jan 31:S1529-9430(25)00053-1. doi: 10.1016/j.spinee.2025.01.020. Online ahead of print.

ABSTRACT

BACKGROUND CONTEXT: Accurate and consistent measurement of sagittal alignment is challenging, particularly in patients with severe coronal deformities, including degenerative lumbar scoliosis (DLS).

PURPOSE: This study aimed to develop and validate an artificial intelligence (AI)-based system for automating the measurement of key sagittal parameters, including lumbar lordosis, pelvic incidence, pelvic tilt, and sacral slope, with a focus on its applicability across a wide range of deformities, including severe coronal deformities, such as DLS.

DESIGN: Retrospective observational study.

PATIENT SAMPLE: A total of 1,011 standing lumbar lateral radiographs, including DLS.

OUTCOME MEASURE: Interclass and intraclass correlation coefficients (CC), and Bland-Altman plots.

METHODS: The model utilizes a deep-learning framework, incorporating a U-Net for segmentation and a Keypoint Region-based Convolutional Neural Network for keypoint detection. The ground truth masks were annotated by an experienced orthopedic specialist. The performance of the model was evaluated against ground truth measurements and assessments from two expert raters using interclass and intraclass CC, and Bland-Altman plots.

RESULTS: In the test set of 113 patients, 39 (34.5%) had DLS, with a mean Cobb's angle of 14.8° ± 4.4°. The AI model achieved an intraclass CC of 1.00 across all parameters, indicating perfect consistency. Interclass CCs comparing the AI model to ground truth ranged from 0.96 to 0.99, outperforming experienced orthopedic surgeons. Bland-Altman analysis revealed no significant systemic bias, with most differences falling within clinically acceptable ranges. A 5-fold cross-validation further demonstrated robust performance, with interclass CCs ranging from 0.96 to 0.99 across diverse subsets.

CONCLUSION: This AI-based system offers a reliable and efficient automated measurement of sagittal parameters in spinal deformities, including severe coronal deformities. The superior performance of the model compared with that of expert raters highlights its potential for clinical applications.

PMID:39894276 | DOI:10.1016/j.spinee.2025.01.020

Radiother Oncol. 2025 Jan 31:110770. doi: 10.1016/j.radonc.2025.110770. Online ahead of print.

ABSTRACT

PURPOSE: This multicenter study aimed to develop and validate a multiscale deep learning radiomics nomogram for predicting recurrence-free survival (RFS) in patients with pancreatic ductal adenocarcinoma (PDAC).

MATERIALS AND METHODS: A total of 469 PDAC patients from four hospitals were divided into training and test sets. Handcrafted radiomics and deep learning (DL) features were extracted from optimal regions of interest, encompassing both intratumoral and peritumoral areas. Univariate Cox regression, LASSO regression, and multivariate Cox regression selected features for three image signatures (intratumoral, peritumoral radiomics, and DL). A multiscale nomogram was constructed and validated against the 8th AJCC staging system.

RESULTS: The 4 mm peritumoral VOI yielded the best radiomics prediction, while a 15 mm expansion was optimal for deep learning. The multiscale nomogram demonstrated a C-index of 0.82 (95 % CI: 0.78-0.85) in the training set and 0.70 (95 % CI: 0.64-0.76) in the external test 1 (high-volume hospital), with the external test 2 (low-volume hospital) showing a C-index of 0.78 (95 % CI: 0.65-0.91). These outperformed the AJCC system's C-index (0.54-0.57). The area under the curve (AUC) for recurrence prediction at 0.5, 1, and 2 years was 0.89, 0.94, and 0.89 in the training set, with AUC values ranging from 0.75 to 0.97 in the external validation sets, consistently surpassing the AJCC system across all sets.. Kaplan-Meier analysis confirmed significant differences in prognosis between high- and low-risk groups (P < 0.01 across all cohorts).

CONCLUSION: The multiscale nomogram effectively stratifies recurrence risk in PDAC patients, enhancing presurgical clinical decision-making and potentially improving patient outcomes.

PMID:39894259 | DOI:10.1016/j.radonc.2025.110770

Neuroimage. 2025 Jan 31:121045. doi: 10.1016/j.neuroimage.2025.121045. Online ahead of print.

ABSTRACT

INTRODUCTION: Altered neurometabolism is an important pathological mechanism in many neurological diseases and brain cancer, which can be mapped non-invasively by Magnetic Resonance Spectroscopic Imaging (MRSI). Advanced MRSI using non-cartesian compressed-sense acquisition enables fast high-resolution metabolic imaging but has lengthy reconstruction times that limits throughput and needs expert user interaction. Here, we present a robust and efficient Deep Learning reconstruction embedded in a physical model within an end-to-end automated processing pipeline to obtain high-quality metabolic maps.

METHODS: Fast high-resolution whole-brain metabolic imaging was performed at 3.4 mm3 isotropic resolution with acquisition times between 4:11-9:21 min:s using ECCENTRIC pulse sequence on a 7T MRI scanner. Data were acquired in a high-resolution phantom and 27 human participants, including 22 healthy volunteers and 5 glioma patients. A deep neural network using recurring interlaced convolutional layers with joint dual-space feature representation was developed for deep learning ECCENTRIC reconstruction (Deep-ER). 21 subjects were used for training and 6 subjects for testing. Deep-ER performance was compared to iterative compressed sensing Total Generalized Variation reconstruction using image and spectral quality metrics.

RESULTS: Deep-ER demonstrated 600-fold faster reconstruction than conventional methods, providing improved spatial-spectral quality and metabolite quantification with 12%-45% (P<0.05) higher signal-to-noise and 8%-50% (P<0.05) smaller Cramer-Rao lower bounds. Metabolic images clearly visualize glioma tumor heterogeneity and boundary. Deep-ER generalizes reliably to unseen data.

CONCLUSION: Deep-ER provides efficient and robust reconstruction for sparse-sampled MRSI. The accelerated acquisition-reconstruction MRSI is compatible with high-throughput imaging workflow. It is expected that such improved performance will facilitate basic and clinical MRSI applications for neuroscience and precision medicine.

PMID:39894238 | DOI:10.1016/j.neuroimage.2025.121045

Mar Pollut Bull. 2025 Feb 1;213:117608. doi: 10.1016/j.marpolbul.2025.117608. Online ahead of print.

ABSTRACT

Motivated by the need of rapid detection of living microalgae cells in ship ballast water, this study is intended to determine the activities of microalgae using stained microscopic images and detect the living cells with image processing algorithms. The staining selectivity on living cells of neutral red dye is utilized to distinguish the activities of microalgae. A deep-learning-based detection model was designed and tested using the microscopic images of stained microalgae cells. The results showed that the deep learning model achieved high accuracies without considering the activities of microalgae: The model's average precisions (APs) on Platymonas helgolandica tsingtaoensis and Alexandrium catenella were 99.3 % and 98.3 %, respectively. In contrast, the detection accuracies of living microalgae cells were slightly lower: The model's APs on living Platymonas helgolandica tsingtaoensis and Alexandrium catenella were 91.7 % and 91.9 %, respectively. The model achieved high detection accuracy and determined the activities of microalgae cells.

PMID:39893717 | DOI:10.1016/j.marpolbul.2025.117608

Environ Sci Technol. 2025 Feb 2. doi: 10.1021/acs.est.4c10595. Online ahead of print.

ABSTRACT

Aqueous film-forming foams (AFFFs) are complex product mixtures that often contain per- and polyfluorinated alkyl substances (PFAS) to enhance fire suppression and protect firefighters. However, PFAS have been associated with a range of adverse health effects (e.g., liver and thyroid disease and cancer), and innovative approach methods to better understand their toxicity potential and identify safer alternatives are needed. In this study, we investigated a set of 30 substances (e.g., AFFF, PFAS, and clinical drugs) using differentiated cultures of human hepatocytes (HepaRG, 2D), high-throughput transcriptomics, deep learning of cell morphology images, and liver enzyme leakage assays with benchmark dose analysis to (1) predict the potency ranges for human liver injury, (2) delineate gene- and pathway-level transcriptomic points-of-departure for molecular hazard characterization and prioritization, (3) characterize human hepatocellular response similarities to inform regulatory read-across efforts, and (4) introduce an innovative approach to translate mechanistic hepatocellular response data to predict the potency ranges for PFAS-induced hepatomegaly in vivo. Collectively, these data fill important mechanistic knowledge gaps with PFAS/AFFF and represent a scalable platform to address the thousands of PFAS in commerce for greener chemistries and next-generation risk assessments.

PMID:39893674 | DOI:10.1021/acs.est.4c10595

STAR Protoc. 2025 Jan 31;6(1):103593. doi: 10.1016/j.xpro.2024.103593. Online ahead of print.

ABSTRACT

Here, we present a protocol for the rapid functional screening of gene editing and addition strategies in patient-derived organoids using the deep-learning-based tool DETECTOR (detection of targeted editing of cystic fibrosis transmembrane conductance regulator [CFTR] in organoids). We describe steps for wet-lab experiments, image acquisition, and CFTR function analysis by DETECTOR. We also detail procedures for applying pre-trained models and training custom models on new customized datasets. For complete details on the use and execution of this protocol, refer to Bulcaen et al.1.

PMID:39893642 | DOI:10.1016/j.xpro.2024.103593

Anal Chem. 2025 Feb 2. doi: 10.1021/acs.analchem.4c05113. Online ahead of print.

ABSTRACT

Mass spectrometry is used to determine infectious microbial species in thousands of clinical laboratories across the world. The vast amount of data allows modern data analysis methods that harvest more information and potentially answer new questions. Here, we present an end-to-end deep learning model for predicting antibiotic resistance using raw matrix assisted laser desorption ionization mass spectrometry (MALDI-MS) data. We used a 1-dimensional convolutional neural network to model (almost) raw data, skipping conventional peak-picking and directly predict resistance. The model's performance is state-of-the-art, having AUCs between 0.93 and 0.99 in all antimicrobial resistance phenotypes and validates across time and location. Feature attribution values highlight important insights into the model and how the end-to-end workflow can be improved further. This study showcases that reliable resistance phenotyping using MALDI-MS data is attainable and highlights the gains of using end-to-end deep learning for spectrometry data.

PMID:39893590 | DOI:10.1021/acs.analchem.4c05113

Network. 2025 Feb 1:1-40. doi: 10.1080/0954898X.2025.2452280. Online ahead of print.

ABSTRACT

Stroke remains a leading global health concern and early diagnosis and accurate identification of stroke lesions are essential for improving treatment outcomes and reducing long-term disabilities. Computed Tomography (CT) imaging is widely used in clinical settings for diagnosing stroke, assessing lesion size, and determining the severity. However, the accurate segmentation and early detection of stroke lesions in CT images remain challenging. Thus, a Jaccard_Residual SqueezeNet is proposed for predicting stroke from CT images with the integration of the Internet of Things (IoT). The Jaccard_Residual SqueezeNet is the integration of the Jaccard index in Residual SqueezeNet. Firstly, the brain CT image is routed to the Base Station (BS) using the Fractional Jellyfish Search Pelican Optimization Algorithm (FJSPOA) and preprocessing is accomplished by median filter. Then, the skull segmentation is accomplished by ENet and then feature extraction is done. Lastly, Stroke is detected using the Jaccard_Residual SqueezeNet. The values of throughput, energy, distance, trust, and delay determined in terms of routing are 72.172 Mbps, 0.580J, 22.243 m, 0.915, and 0.083S. Also, the accuracy, sensitivity, precision, and F1-score for stroke detection are 0.902, 0.896, 0.916, and 0.906. These findings suggest that Jaccard_Residual SqueezeNet offers a robust and efficient platform for stroke detection.

PMID:39893512 | DOI:10.1080/0954898X.2025.2452280

Med Image Anal. 2025 Jan 29;101:103462. doi: 10.1016/j.media.2025.103462. Online ahead of print.

ABSTRACT

Resting-state functional magnetic resonance imaging (rs-fMRI) is a noninvasive technique pivotal for understanding human neural mechanisms of intricate cognitive processes. Most rs-fMRI studies compute a single static functional connectivity matrix across brain regions of interest, or dynamic functional connectivity matrices with a sliding window approach. These approaches are at risk of oversimplifying brain dynamics and lack proper consideration of the goal at hand. While deep learning has gained substantial popularity for modeling complex relational data, its application to uncovering the spatiotemporal dynamics of the brain is still limited. In this study we propose a novel interpretable deep learning framework that learns goal-specific functional connectivity matrix directly from time series and employs a specialized graph neural network for the final classification. Our model, DSAM, leverages temporal causal convolutional networks to capture the temporal dynamics in both low- and high-level feature representations, a temporal attention unit to identify important time points, a self-attention unit to construct the goal-specific connectivity matrix, and a novel variant of graph neural network to capture the spatial dynamics for downstream classification. To validate our approach, we conducted experiments on the Human Connectome Project dataset with 1075 samples to build and interpret the model for the classification of sex group, and the Adolescent Brain Cognitive Development Dataset with 8520 samples for independent testing. Compared our proposed framework with other state-of-art models, results suggested this novel approach goes beyond the assumption of a fixed connectivity matrix, and provides evidence of goal-specific brain connectivity patterns, which opens up potential to gain deeper insights into how the human brain adapts its functional connectivity specific to the task at hand. Our implementation can be found on https://github.com/bishalth01/DSAM.

PMID:39892220 | DOI:10.1016/j.media.2025.103462

Radiography (Lond). 2025 Jan 31;31(2):102878. doi: 10.1016/j.radi.2025.01.013. Online ahead of print.

ABSTRACT

INTRODUCTION: AI-based segmentation techniques in brain MRI have revolutionized neuroimaging by enhancing the accuracy and efficiency of brain structure analysis. These techniques are pivotal for diagnosing neurodegenerative diseases, classifying psychiatric conditions, and predicting brain age. This scoping review synthesizes current methodologies, identifies key trends, and highlights gaps in the use of automatic and semi-automatic segmentation tools in brain MRI, particularly focusing on their application to healthy populations and clinical utility.

METHODS: A scoping review was conducted following Arksey and O'Malley's framework and PRISMA-ScR guidelines. A comprehensive search was performed across six databases for studies published between 2014 and 2024. Studies focused on AI-based brain segmentation in healthy populations, and patients with neurodegenerative diseases, and psychiatric disorders were included, while reviews, case series, and studies without human participants were excluded.

RESULTS: Thirty-two studies were included, employing various segmentation tools and AI models such as convolutional neural networks for segmenting gray matter, white matter, cerebrospinal fluid, and pathological regions. FreeSurfer, which utilizes algorithmic techniques, are also commonly used for automated segmentation. AI models demonstrated high accuracy in brain age prediction, neurodegenerative disease classification, and psychiatric disorder subtyping. Longitudinal studies tracked disease progression, while multimodal approaches integrating MRI with fMRI and PET enhanced diagnostic precision.

CONCLUSION: AI-based segmentation techniques provide scalable solutions for neuroimaging, advancing personalized brain health strategies and supporting early diagnosis of neurological and psychiatric conditions. However, challenges related to standardization, generalizability, and ethical considerations remain.

IMPLICATIONS FOR PRACTICE: The integration of AI tools and algorithm-based methods into clinical workflows can enhance diagnostic accuracy and efficiency, but greater focus on model interpretability, standardization of imaging protocols, and patient consent processes is needed to ensure responsible adoption in practice.

PMID:39892049 | DOI:10.1016/j.radi.2025.01.013

Soc Sci Med. 2025 Jan 10;367:117690. doi: 10.1016/j.socscimed.2025.117690. Online ahead of print.

ABSTRACT

Alcohol is a highly addictive substance, presenting significant global public health concerns, particularly among adolescents. Previous studies have been limited by traditional research methods, making it challenging to encompass diverse risk factors and automate screening or prediction of adolescents' alcohol use. This study aimed to develop prediction algorithms for adolescent alcohol use in South Korea using machine learning (ML) and deep learning (DL) models, and to identify important features. The study utilized a combination of DL (i.e., Auto-encoder) and ML (i.e., Logistic regression, Ridge, LASSO, Elasticnet, Decision tree, Random forest, AdaBoost, and XGBoost) algorithms to develop the prediction models. It involves 41,239 Korean adolescents and 46 socio-ecological input variables based on cross-sectional data. The analysis revealed that the prediction algorithms had AUC scores ranging from 0.6325 to 0.7214. The feature importance analysis indicates that variables within the domains of sociodemographic characteristics, physical and mental health, behavioral problems, family factors, school factors, and social factors all play significant roles. The developed algorithms enable automatic and early identification of adolescent alcohol use within public health practice settings. By leveraging a comprehensive array of input variables, these methods surpass the limitations of traditional regression approaches, offering novel insights into the critical risk factors associated with alcohol use among Korean adolescents, thereby facilitating early and targeted prevention efforts.

PMID:39892039 | DOI:10.1016/j.socscimed.2025.117690

Int J Med Inform. 2025 Jan 30;196:105812. doi: 10.1016/j.ijmedinf.2025.105812. Online ahead of print.

ABSTRACT

BACKGROUND: With advancements in medical technology and science, chronic obstructive pulmonary disease (COPD), one of the world's three major chronic diseases, has seen numerous remarkable outcomes when combined with artificial intelligence, particularly in disease diagnosis. However, the diagnostic performance of these AI models still lacks comprehensive evidence. Therefore, this study quantitatively analyzed the diagnostic performance of AI models in CT images of COPD patients, aiming to promote the development of related research in the future.

METHODS: PubMed, Cochrane Library, Web of Science, and Embase were retrieved up to September 1, 2024. The QUADAS-2 evaluation tool was used to assess the quality of the included studies. Meta-analysis of the included researches was performed using Stata18, RevMan 5.4, and Meta-Disc 1.4 software to merge sensitivity, specificity and plot a summary receiver operating characteristic curve (SROC). Heterogeneity was assessed using the Q statistic, and sources of inter-study heterogeneity were explored through meta-regression analysis.

RESULTS: Twenty-two of 3280 identified studies were eligible. Meta-analysis was performed on 15 of these studies, encompassing a total of 22,817 patients for which statistical metrics were reported or could be calculated. Seven studies were based on deep learning (DL) model, three on machine learning (ML) model, and five on DL model with multiple-instance learning (MIL) mechanisms. One study evaluated both DL and ML models. The meta-analysis results showed that the pooled sensitivity of all DL and ML models was 86 % (95 %CI 78-91 %), specificity was 87 % (95 %CI 83-91 %), and area under the curve was 93 % (95 %CI 90-95 %). Subgroup analyses revealed no significant difference in diagnostic sensitivity and specificity between DL and ML models (sensitivity 82 % (95 %CI 76-87 %), 93 % (95 %CI 85-97 %); specificity 87 % (95 %CI 79-91 %), 84 % (95 %CI 79-88 %), and the DL model with MIL (sensitivity 87 % (95 %CI 61-96 %); specificity 89 % (95 %CI 78-95 %) improved the performance of DL model, but this improvement was not statistically significant (p > 0.05).

CONCLUSION: Both DL and ML models for diagnosing COPD using CT images exhibited high accuracy. There was no significant difference in diagnostic efficacy between the two types of AI models, and the addition of the MIL mechanism may enhance the performance of the DL model.

PMID:39891985 | DOI:10.1016/j.ijmedinf.2025.105812

Sci Rep. 2025 Feb 1;15(1):4021. doi: 10.1038/s41598-025-86251-0.

ABSTRACT

This paper provides a novel approach to estimating CO₂ emissions with high precision using machine learning based on DPRNNs with NiOA. The data preparation used in the present methodology involves sophisticated stages such as Principal Component Analysis (PCA) as well as Blind Source Separation (BSS) to reduce noise as well as to improve feature selection. This purified input dataset is used in the DPRNNs model, where both short and long-term temporal dependencies in the data are captured well. NiOA is utilized to tune those parameters; as a result, the prediction accuracy is quite spectacular. Experimental results also demonstrate that the proposed NiOA-DPRNNs framework gets the highest value of R2 (0.9736), lowest error rates and fitness values than other existing models and optimization methods. From the Wilcoxon and ANOVA analyses, one can approve the specificity and consistency of the findings. Liebert and Ruple firmly rethink this rather simple output as a robust theoretic and empirical framework for evaluating and projecting CO2 emissions; they also view it as a helpful guide for policymakers fighting global warming. Further study can build up this theory to include other greenhouse gases and create methods enabling instantaneous tracking for sophisticated and responsive approaches.

PMID:39893234 | DOI:10.1038/s41598-025-86251-0

Sci Rep. 2025 Feb 1;15(1):3985. doi: 10.1038/s41598-025-88199-7.

ABSTRACT

Biochemical recurrence (BCR) of prostate cancer (PCa) negatively impacts patients' post-surgery quality of life, and the traditional predictive models have shown limited accuracy. This study develops an AI-based prognostic model using deep learning that incorporates androgen receptor (AR) regional features from whole-slide images (WSIs). Data from 545 patients across two centres are used for training and validation. The model showed strong performances, with high accuracy in identifying regions with high AR expression and BCR prediction. This AI model may help identify high-risk patients, aiding in better treatment strategies, particularly in underdeveloped areas.

PMID:39893198 | DOI:10.1038/s41598-025-88199-7

Sci Data. 2025 Feb 1;12(1):196. doi: 10.1038/s41597-025-04382-5.

ABSTRACT

The remarkable progress of deep learning in dermatological tasks has brought us closer to achieving diagnostic accuracies comparable to those of human experts. However, while large datasets play a crucial role in the development of reliable deep neural network models, the quality of data therein and their correct usage are of paramount importance. Several factors can impact data quality, such as the presence of duplicates, data leakage across train-test partitions, mislabeled images, and the absence of a well-defined test partition. In this paper, we conduct meticulous analyses of three popular dermatological image datasets: DermaMNIST, its source HAM10000, and Fitzpatrick17k, uncovering these data quality issues, measure the effects of these problems on the benchmark results, and propose corrections to the datasets. Besides ensuring the reproducibility of our analysis, by making our analysis pipeline and the accompanying code publicly available, we aim to encourage similar explorations and to facilitate the identification and addressing of potential data quality issues in other large datasets.

PMID:39893183 | DOI:10.1038/s41597-025-04382-5

Adv Sci (Weinh). 2025 Feb 1:e2407825. doi: 10.1002/advs.202407825. Online ahead of print.

ABSTRACT

Designing voxelized composite structures via 4D printing involves creating voxel units with distinct material properties that transform in response to stimuli; however, optimally distributing these properties to achieve specific target shapes remains a significant challenge. This study introduces an optimization method combining deep learning (DL) and an evolutionary algorithm, focusing on a solvent-responsive hydrogel as the target material. A sequence-enhanced parallel convolutional neural network is developed and generated a dataset through finite element simulations. This DL model enables high-precision prediction of hydrogel deformation. Furthermore, a progressive evolutionary algorithm (PEA) is proposed by integrating the DL model to construct a DL-PEA framework. This framework supports rapid reverse engineering of the desired shape, and the average design time for specified target shapes is reduced to ≈3.04 s. The present findings illustrate how 4D printing of optimized hydrogel designs can effectively transform in response to environmental stimuli. This work provides a new perspective on the application of hydrogels in 4D printing and presents an efficient tool for optimizing 4D-printed voxelized composite structures.

PMID:39893044 | DOI:10.1002/advs.202407825

Am J Transplant. 2025 Jan 30:S1600-6135(25)00047-4. doi: 10.1016/j.ajt.2025.01.041. Online ahead of print.

ABSTRACT

This study aimed to identify the parenchymal structural features by both CT and histology that associate with death-censored graft failure in recipients of living donor kidneys. We analyzed kidney recipients of ABO-compatible living donor kidneys from 2000-2020 with follow-up through 2023. Cortical volume and thickness, individual medullary pyramid volume and count, glomerular volume, nephrosclerosis, and nephron number were assessed by deep learning models applied to the predonation CT and by morphometric histology analysis from the biopsy at the time of transplantation. There were 3098 recipients followed a median 5 years with 346 graft failure events. In adjusted analyses, the only structural measures associated with graft failure were fewer medullary pyramids on CT and a higher fraction of interstitial fibrosis and tubular atrophy (IFTA) on histology. Having ≤15 pyramids donated occurred in 9% and was associated with a graft failure incidence of 2.5 per 100 person-years compared to 1.6 per 100 person-years in the 17% with ≥26 pyramids donated. Fewer medullary pyramids were associated with a lower 1-year eGFR, which mediated the subsequent risk of graft failure. IFTA >1% is also associated with graft failure. Medullary pyramid count is a potentially useful predonation prognostic biomarker for graft failure in transplant recipients.

PMID:39892790 | DOI:10.1016/j.ajt.2025.01.041