Gastric Cancer. 2025 Apr 15. doi: 10.1007/s10120-025-01614-w. Online ahead of print.

ABSTRACT

BACKGROUND: We developed and evaluated a skeletal muscle deep-learning (SMDL) model using skeletal muscle computed tomography (CT) imaging to predict the survival of patients with gastric cancer (GC).

METHODS: This multicenter retrospective study included patients who underwent curative resection of GC between April 2008 and December 2020. Preoperative CT images at the third lumbar vertebra were used to develop a Transformer-based SMDL model for predicting recurrence-free survival (RFS) and disease-specific survival (DSS). The predictive performance of the SMDL model was assessed using the area under the curve (AUC) and benchmarked against both alternative artificial intelligence models and conventional body composition parameters. The association between the model score and survival was assessed using Cox regression analysis. An integrated model combining SMDL signature with clinical variables was constructed, and its discrimination and fairness were evaluated.

RESULTS: A total of 1242, 311, and 94 patients were assigned to the training, internal, and external validation cohorts, respectively. The Transformer-based SMDL model yielded AUCs of 0.791-0.943 for predicting RFS and DSS across all three cohorts and significantly outperformed other models and body composition parameters. The model score was a strong independent prognostic factor for survival. Incorporating the SMDL signature into the clinical model resulted in better prognostic prediction performance. The false-negative and false-positive rates of the integrated model were similar across sex and age subgroups, indicating robust fairness.

CONCLUSIONS: The Transformer-based SMDL model could accurately predict survival of GC and identify patients at high risk of recurrence or death, thereby assisting clinical decision-making.

PMID:40232557 | DOI:10.1007/s10120-025-01614-w

Opt Lett. 2025 Apr 15;50(8):2642-2645. doi: 10.1364/OL.557452.

ABSTRACT

Current camera-array-based integral imaging lacks tampering protection, making images vulnerable to falsification and requiring high computational costs. This Letter proposes an alternative 3D integral imaging scheme that ensures clear light field display while enabling tampering detection and self-recovery. Pixel mapping and deep learning co-extract depth and angular data pixel-wisely, regulating the region of interest of 3D light field for initial verification. Multi-viewpoint recovery information is embedded to reconstruct a complete elemental image array. When tampered with, the altered region can be identified and double-recovered. Experiments demonstrate remarkable parallax effects and effective tampering detection with recovery from multiple perspectives.

PMID:40232459 | DOI:10.1364/OL.557452

Opt Lett. 2025 Apr 15;50(8):2558-2561. doi: 10.1364/OL.557170.

ABSTRACT

In this Letter, we report what we believe to be a new type of abruptly autofocusing beams, termed symmetric butterfly Gaussian beams (SBGBs). The proposed beams appear to have a high degree of tunability for their focal position, focal length, focal intensity, and propagation trajectory. In addition, we propose a deep learning-based model for quick and accurate predictions of the propagation properties of SBGBs, achieving an average relative error of no more than 2.1% and being 8000 times faster than that of split-Fourier transform algorithms. This work may open a new platform for optical manipulation, optical communication, and biomedical applications.

PMID:40232438 | DOI:10.1364/OL.557170

Abdom Radiol (NY). 2025 Apr 15. doi: 10.1007/s00261-025-04942-8. Online ahead of print.

ABSTRACT

BACKGROUND AND PURPOSE: Endometriosis affects 5-10% of women of reproductive age. Despite its prevalence, diagnosing endometriosis through imaging remains challenging. Advances in deep learning (DL) are revolutionizing the diagnosis and management of complex medical conditions. This study aims to evaluate DL tools in enhancing the accuracy of multi-sequence MRI-based detection of endometriosis.

METHOD: We gathered a patient cohort from our institutional database, composed of patients with pathologically confirmed endometriosis from 2015 to 2024. We created an age-matched control group that underwent a similar MR protocol without an endometriosis diagnosis. We used sagittal fat-saturated T1-weighted (T1W FS) pre- and post-contrast and T2-weighted (T2W) MRIs. Our dataset was split at the patient level, allocating 12.5% for testing and conducting seven-fold cross-validation on the remainder. Seven abdominal radiologists with experience in endometriosis MRI and complex surgical planning and one women's imaging fellow with specific training in endometriosis MRI reviewed a random selection of images and documented their endometriosis detection.

RESULTS: 395 and 356 patients were included in the case and control groups respectively. The final 3D-DenseNet-121 classifier model demonstrated robust performance. Our findings indicated the most accurate predictions were obtained using T2W, T1W FS pre-, and post-contrast images. Using an ensemble technique on the test set resulted in an F1 Score of 0.881, AUROCC of 0.911, sensitivity of 0.976, and specificity of 0.720. Radiologists achieved 84.48% and 87.93% sensitivity without and with AI assistance in detecting endometriosis. The agreement among radiologists in predicting labels for endometriosis was measured as a Fleiss' kappa of 0.5718 without AI assistance and 0.6839 with AI assistance.

CONCLUSION: This study introduced the first DL model to use multi-sequence MRI on a large cohort, showing results equivalent to human detection by trained readers in identifying endometriosis.

PMID:40232413 | DOI:10.1007/s00261-025-04942-8

Acta Radiol. 2025 Apr 15:2841851251333974. doi: 10.1177/02841851251333974. Online ahead of print.

ABSTRACT

BackgroundAutism spectrum disorder (ASD) is a neurodevelopmental disease marked by a variety of repetitive behaviors and social communication difficulties.PurposeTo develop a generalizable machine learning (ML) classifier that can accurately and effectively predict ASD in children.Material and MethodsThis paper makes use of neuroimaging data from the Autism Brain Imaging Data Exchange (ABIDE I and II) datasets through a combination of structural and functional magnetic resonance imaging data. Several ML models, such as Support Vector Machines (SVM), CatBoost, random forest (RF), and stack classifiers, were tested to demonstrate which model performs the best in ASD classification when used alongside a deep convolutional neural network.ResultsResults showed that stack classifier performed the best among the models, with the highest accuracy of 81.68%, sensitivity of 85.08%, and specificity of 79.13% for ABIDE I, and 81.34%, 83.61%, and 82.21% for ABIDE II, showing its superior ability to identify complex patterns in neuroimaging data. SVM performed poorly across all metrics, showing its limitations in dealing with high-dimensional neuroimaging data.ConclusionThe results show that the application of ML models, especially ensemble approaches like stack classifier, holds significant promise in improving the accuracy with which ASD is detected using neuroimaging and thus shows their potential for use in clinical applications and early intervention strategies.

PMID:40232228 | DOI:10.1177/02841851251333974

Foods. 2025 Mar 18;14(6):1024. doi: 10.3390/foods14061024.

ABSTRACT

In order to overcome the notable limitations of current methods for monitoring grain storage states, particularly in the early warning of potential risks and the analysis of the spatial distribution of grain temperatures within the granary, this study proposes a multi-model fusion approach based on a deep learning framework for grain storage state monitoring and risk alert. This approach combines two advanced three-dimensional deep learning models, a grain storage state classification model based on 3D DenseNet and a temperature field prediction model based on 3DCNN-LSTM. First, the grain storage state classification model based on 3D DenseNet efficiently extracts features from three-dimensional grain temperature data to achieve the accurate classification of storage states. Second, the temperature prediction model based on 3DCNN-LSTM incorporates historical grain temperature and absolute water potential data to precisely predict the dynamic changes in the granary's temperature field. Finally, the grain temperature prediction results are input into the 3D DenseNet to provide early warnings for potential condensation and mildew risks within the grain pile. Comparative experiments with multiple baseline models show that the 3D DenseNet model achieves an accuracy of 97.38% in the grain storage state classification task, significantly outperforming other models. The 3DCNN-LSTM model shows high prediction accuracy in temperature forecasting, with MAE of 0.24 °C and RMSE of 0.28 °C. Furthermore, in potential risk alert experiments, the model effectively captures the temperature trend in the grain storage environment and provides early warnings, particularly for mildew and condensation risks, demonstrating the potential of this method for grain storage safety monitoring and risk alerting. This study provides a smart grain storage solution which contributes to ensuring food safety and enhancing the efficiency of grain storage management.

PMID:40232114 | DOI:10.3390/foods14061024

Foods. 2025 Mar 13;14(6):983. doi: 10.3390/foods14060983.

ABSTRACT

The fermentation of oolong tea is a critical process that determines its quality and flavor. Current fermentation control relies on tea makers' sensory experience, which is labor-intensive and time-consuming. In this study, using Tieguanyin oolong tea as the research object, features including the tea water loss rate, aroma, image color, and texture were obtained using weight sensors, a tin oxide-type gas sensor, and a visual acquisition system. Support vector regression (SVR), random forest (RF) machine learning, and long short-term memory (LSTM) deep learning algorithms were employed to establish models for assessing the fermentation degree based on both single features and fused multi-source features, respectively. The results showed that in the test set of the fermentation degree models based on single features, the mean absolute error (MAE) ranged from 4.537 to 6.732, the root mean square error (RMSE) ranged from 5.980 to 9.416, and the coefficient of determination (R2) values varied between 0.898 and 0.959. In contrast, the data fusion models demonstrated superior performance, with the MAE reduced to 2.232-2.783, the RMSE reduced to 2.693-3.969, and R2 increased to 0.982-0.991, confirming that feature fusion enhanced characterization accuracy. Finally, the Sparrow Search Algorithm (SSA) was applied to optimize the data fusion models. After optimization, the models exhibited a MAE ranging from 1.703 to 2.078, a RMSE from 2.258 to 3.230, and R2 values between 0.988 and 0.994 on the test set. The application of the SSA further enhanced model accuracy, with the Fusion-SSA-LSTM model demonstrating the best performance. The research results enable online real-time monitoring of the fermentation degree of Tieguanyin oolong tea, which contributes to the automated production of Tieguanyin oolong tea.

PMID:40231982 | DOI:10.3390/foods14060983

Curr Res Food Sci. 2025 Mar 21;10:101030. doi: 10.1016/j.crfs.2025.101030. eCollection 2025.

ABSTRACT

The growing demand for sustainable, nutritious, and environmentally friendly food sources has placed chickpea flour as a vital component in the global shift to plant-based diets. However, the inherent variability in the composition of chickpea flour, influenced by genetic diversity, environmental conditions, and processing techniques, poses significant challenges to standardisation and quality control. This study explores the integration of deep learning models with near-infrared (NIR) spectroscopy to improve the accuracy and efficiency of chickpea flour quality assessment. Using a dataset comprising 136 chickpea varieties, the research compares the performance of several state-of-the-art deep learning models, including Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and Graph Convolutional Networks (GCNs), and compares the most effective model, CNN, against the traditional Partial Least Squares Regression (PLSR) method. The results demonstrate that CNN-based models outperform PLSR, providing more accurate predictions for key quality attributes such as protein content, starch, soluble sugars, insoluble fibres, total lipids, and moisture levels. The study highlights the potential of AI-enhanced NIR spectroscopy to revolutionise quality assessment in the food industry by offering a non-destructive, rapid, and reliable method for analysing chickpea flour. Despite the challenges posed by the limited dataset, deep learning models exhibit capabilities that suggest that further advancements would allow their industrial applicability. This research paves the way for broader applications of AI-driven quality control in food production, contributing to the development of more consistent and high-quality plant-based food products.

PMID:40231315 | PMC:PMC11995126 | DOI:10.1016/j.crfs.2025.101030

Adv Radiat Oncol. 2025 Mar 8;10(5):101757. doi: 10.1016/j.adro.2025.101757. eCollection 2025 May.

ABSTRACT

PURPOSE: Heterogeneity correction is vital in radiation therapy treatment planning to ensure accurate dose delivery. Brain cancer stereotactic treatments, like Gamma Knife radiosurgery (GKRS), often rely on homogeneous water-based calculations despite the potential heterogeneity impact near bony structures. This study aims to develop a method for generating synthetic dose plans incorporating heterogeneity effects without additional computed tomography (CT) scans.

METHODS AND MATERIALS: Magnetic resonance imaging and CT images, TMR10-based, and convolution-based dose distributions were used from 100 retrospectively collected and 22 prospectively collected GKRS patients. A conditional Generative Adversarial Network was trained to translate TMR10 into synthetic convolution (sConv) doses.

RESULTS: The generated sConv dose demonstrated qualitative and quantitative similarity to the actual convolution (Conv) dose, showcasing better agreement of dose distributions and improved isodose volume similarity with the Conv dose in comparison to the TMR10 dose (γ pass rate; sConv dose, 92.43%; TMR10 dose, 74.18%. Prescription isodose dice; sConv dose, 91.7%; TMR10 dose, 89.7%). Skull-induced scatter and attenuation effects were accurately reflected in the sConv dose, indicating the usefulness of the new dose prediction model as an alternative to the time-consuming convolution dose calculations.

CONCLUSIONS: Our deep learning approach offers a feasible solution for heterogeneity-corrected dose planning in GKRS, circumventing additional CT scans and lengthy calculation times. This method's effectiveness in preserving dose distribution characteristics in a heterogeneous medium while only requiring a homogeneous dose plan highlights its utility for including the process in the routine treatment planning workflows. Further refinement and validation with diverse patient cohorts can enhance its applicability and impact in clinical settings.

PMID:40231287 | PMC:PMC11994306 | DOI:10.1016/j.adro.2025.101757

Int J Dent. 2025 Apr 7;2025:7583275. doi: 10.1155/ijod/7583275. eCollection 2025.

ABSTRACT

Objective: Peri-implant bone regeneration is crucial for dental implant success, particularly in managing peri-implantitis, which causes inflammation and bone loss. SP7 (Osterix) is vital for osteoblast differentiation and bone matrix formation. Advances in deep neural networks (DNNs) offer new ways to analyze protein sequences, potentially improving our understanding of SP7's role in bone formation. This study aims to develop and utilize DNNs to predict the SP7 protein sequence and understand its role in peri-implant bone formation. Materials: and Methods: Sequences were retrieved from UniProt IDs Q8TDD2 and Q9V3Z2 using the UniProt dataset. The sequences were Sp7 fasta sequences. These sequences were located, and their quality was assessed. We built an architecture that can handle a wide range of input sequences using a DNN technique, with computing needs based on the length of the input sequences. Results: Protein sequences were analyzed using a DNN architecture with ADAM optimizer over 50 epochs, achieving a sensitivity of 0.89 and a specificity of 0.82. The receiver operating characteristic (ROC) curve demonstrated high true-positive rates and low false-positive rates, indicating robust model performance. Precision-recall analysis underscored the model's effectiveness in handling imbalanced data, with significant area under the curve (AUC-PR). Epoch plots highlighted consistent model accuracy throughout training, confirming its reliability for protein sequence analysis. Conclusion: The DNN employed with ADAM optimizer demonstrated robust performance in analyzing protein sequences, achieving an accuracy of 0.85 and high sensitivity and specificity. The ROC curve highlighted the model's effectiveness in distinguishing true positives from false positives, which is essential for reliable protein classification. These findings suggest that the developed model is promising for enhancing predictive capabilities in computational biology and biomedical research, particularly in protein function prediction and therapeutic development applications.

PMID:40231202 | PMC:PMC11996267 | DOI:10.1155/ijod/7583275

Adv Neural Inf Process Syst. 2024;37:133975-133998.

ABSTRACT

People with brain or spinal cord-related paralysis often need to rely on others for basic tasks, limiting their independence. A potential solution is brain-machine interfaces (BMIs), which could allow them to voluntarily control external devices (e.g., robotic arm) by decoding brain activity to movement commands. In the past decade, deep-learning decoders have achieved state-of-the-art results in most BMI applications, ranging from speech production to finger control. However, the 'black-box' nature of deep-learning decoders could lead to unexpected behaviors, resulting in major safety concerns in real-world physical control scenarios. In these applications, explainable but lower-performing decoders, such as the Kalman filter (KF), remain the norm. In this study, we designed a BMI decoder based on KalmanNet, an extension of the KF that augments its operation with recurrent neural networks to compute the Kalman gain. This results in a varying "trust" that shifts between inputs and dynamics. We used this algorithm to predict finger movements from the brain activity of two monkeys. We compared KalmanNet results offline (pre-recorded data, n = 13 days) and online (real-time predictions, n = 5 days) with a simple KF and two recent deep-learning algorithms: tcFNN (non-ReFIT version) and LSTM. KalmanNet achieved comparable or better results than other deep learning models in offline and online modes, relying on the dynamical model for stopping while depending more on neural inputs for initiating movements. We further validated this mechanism by implementing a heteroscedastic KF that used the same strategy, and it also approached state-of-the-art performance while remaining in the explainable domain of standard KFs. However, we also see two downsides to KalmanNet. KalmanNet shares the limited generalization ability of existing deep-learning decoders, and its usage of the KF as an inductive bias limits its performance in the presence of unseen noise distributions. Despite this trade-off, our analysis successfully integrates traditional controls and modern deep-learning approaches to motivate high-performing yet still explainable BMI designs.

PMID:40231170 | PMC:PMC11996206

Data Brief. 2025 Mar 21;60:111489. doi: 10.1016/j.dib.2025.111489. eCollection 2025 Jun.

ABSTRACT

FaciaVox is a multimodal biometric dataset that consists of face images and voice recordings under both masked and unmasked conditions. The term ``FaciaVox'' is strategically chosen to create a distinct and easily memorable name. This name selection serves to highlight the dataset's multimodal characteristics, as well as its relevance to biometric recognition tasks. The FaciaVox dataset consists of contributions from 100 participants from 20 different countries, each providing 18 facial images and 60 audio recordings. The facial images are stored in JPG format, while the audio recordings are saved as WAV files, ensuring compatibility with standard processing tools. Participants are categorized by age into four distinct groups: Group 1 includes individuals below 16 years of age; Group 2 corresponds to those aged 16 up to less than 31; Group 3 encompasses participants aged 31 up to less than 46; and Group 4 represents individuals aged 46 and above. The data collection was conducted in two distinct environments: a professional soundproof studio and a conventional classroom. While the studio provided a controlled setting, the classroom introduced variables such as echo and sound reflections. Some participants were recorded in the studio, while others were recorded in the classroom, as detailed in the file named 'FaciaVox list' which specifies where each participant was recorded. Participants were positioned at 70-100 cm from the iPhone's rear camera, utilizing three specific zoom levels (1x, 3x, and 5x) to obtain a collection of facial photos. Each participant submitted a total of 18 facial photos, comprising six different images captured at each magnification level. The six different images encompassed a sequence of conditions: the initial set was captured without the use of a face mask, followed by subsequent images where participants donned a disposable mask, transitioned to a reusable mask, then advanced to a dual-layer cloth mask. Subsequently, a silicon face shield was introduced along with the cloth mask, concluding in final images where the silicon shield was worn independently. Each participant was instructed to speak ten sentences, switching between English and Arabic, under the six previously mentioned conditions. The speech was recorded using the Zoom H6 Handy Recorder. The FaciaVox dataset provides an extensive range of study options in the fields of face images and audio signals with and without face mask. This broad dataset serves as a foundational resource for investigating a wide range of cutting-edge applications, including but not limited to multimodal biometrics, cross-domain biometric fusion, age and gender estimation, human-machine interaction, deep learning, speech intelligence, voice cloning, image inpainting, and security and surveillance.

PMID:40231156 | PMC:PMC11994902 | DOI:10.1016/j.dib.2025.111489

Front Immunol. 2025 Mar 31;16:1540087. doi: 10.3389/fimmu.2025.1540087. eCollection 2025.

ABSTRACT

The growing application of immune checkpoint inhibitors (ICIs) in cancer immunotherapy has underscored the critical need for reliable methods to identify patient populations likely to respond to ICI treatments, particularly in lung cancer treatment. Currently, the tumor proportion score (TPS), a crucial biomarker for patient selection, relies on manual interpretation by pathologists, which often shows substantial variability and inconsistency. To address these challenges, we innovatively developed multi-instance learning for TPS (MiLT), an innovative artificial intelligence (AI)-powered tool that predicts TPS from whole slide images. Our approach leverages multiple instance learning (MIL), which significantly reduces the need for labor-intensive cell-level annotations while maintaining high accuracy. In comprehensive validation studies, MiLT demonstrated remarkable consistency with pathologist assessments (intraclass correlation coefficient = 0.960, 95% confidence interval = 0.950-0.971) and robust performance across both internal and external cohorts. This tool not only standardizes TPS evaluation but also adapts to various clinical standards and provides time-efficient predictions, potentially transforming routine pathological practice. By offering a reliable, AI-assisted solution, MiLT could significantly improve patient selection for immunotherapy and reduce inter-observer variability among pathologists. These promising results warrant further exploration in prospective clinical trials and suggest new possibilities for integrating advanced AI in pathological diagnostics. MiLT represents a significant step toward more precise and efficient cancer immunotherapy decision-making.

PMID:40230846 | PMC:PMC11994606 | DOI:10.3389/fimmu.2025.1540087

J Pathol Inform. 2025 Mar 12;17:100437. doi: 10.1016/j.jpi.2025.100437. eCollection 2025 Apr.

ABSTRACT

The prognostic relevance of tumor-infiltrating lymphocytes (TILs) in non-small cell Lung cancer (NSCLC) is well-established. However, manual TIL quantification in hematoxylin and eosin (H&E) whole slide images (WSIs) is laborious and prone to variability. To address this, we aim to develop and validate an automated computational pipeline for the quantification of TILs in WSIs of NSCLC. Such a solution in computational pathology can accelerate TIL evaluation, thereby standardizing the prognostication process and facilitating personalized treatment strategies. We develop an end-to-end automated pipeline for TIL estimation in Lung cancer WSIs by integrating a patch extraction approach based on hematoxylin component filtering with a machine learning-based patch classification and cell quantification method using the HoVer-Net model architecture. Additionally, we employ randomized patch sampling to further reduce the processed patch amount. We evaluate the effectiveness of the patch sampling procedure, the pipeline's ability to identify informative patches and computational efficiency, and the clinical value of produced scores using patient survival data. Our pipeline demonstrates the ability to selectively process informative patches, achieving a balance between computational efficiency and prognostic integrity. The pipeline filtering excludes approximately 70% of all patch candidates. Further, only 5% of eligible patches are necessary to retain the pipeline's prognostic accuracy (c-index = 0.65), resulting in a linear reduction of the total computational time compared to the filtered patch subset analysis. The pipeline's TILs score has a strong association with patient survival and outperforms traditional CD8 immunohistochemical scoring (c-index = 0.59). Kaplan-Meier analysis further substantiates the TILs score's prognostic value. This study introduces an automated pipeline for TIL evaluation in Lung cancer WSIs, providing a prognostic tool with potential to improve personalized treatment in NSCLC. The pipeline's computational advances, particularly in reducing processing time, and clinical relevance demonstrate a step forward in computational pathology.

PMID:40230809 | PMC:PMC11994347 | DOI:10.1016/j.jpi.2025.100437

J Soc Cardiovasc Angiogr Interv. 2025 Mar 18;4(3Part B):102567. doi: 10.1016/j.jscai.2025.102567. eCollection 2025 Mar.

ABSTRACT

Artificial intelligence has promising impact on patients with congenital heart disease, a vulnerable population with life-long health care needs and, often, a substantially higher risk of death than the general population. This review explores the role artificial intelligence has had on cardiac imaging, electrophysiology, interventional procedures, and intensive care monitoring as it relates to children and adults with congenital heart disease. Machine learning and deep learning algorithms have enhanced not only imaging segmentation and processing but also diagnostic accuracy namely reducing interobserver variability. This has a meaningful impact in complex congenital heart disease improving anatomic diagnosis, assessment of cardiac function, and predicting long-term outcomes. Image processing has benefited procedural planning for interventional cardiology, allowing for a higher quality and density of information to be extracted from the same imaging modalities. In electrophysiology, deep learning models have enhanced the diagnostic potential of electrocardiograms, detecting subtle yet meaningful variation in signals that enable early diagnosis of cardiac dysfunction, risk stratification of mortality, and more accurate diagnosis and prediction of arrhythmias. In the congenital heart disease population, this has the potential for meaningful prolongation of life. Postoperative care in the cardiac intensive care unit is a data-rich environment that is often overwhelming. Detection of subtle data trends in this environment for early detection of morbidity is a ripe avenue for artificial intelligence algorithms to be used. Examples like early detection of catheter-induced thrombosis have already been published. Despite their great promise, artificial intelligence algorithms are still limited by hurdles such as data standardization, algorithm validation, drift, and explainability.

PMID:40230672 | PMC:PMC11993855 | DOI:10.1016/j.jscai.2025.102567

J Soc Cardiovasc Angiogr Interv. 2025 Mar 18;4(3Part B):102558. doi: 10.1016/j.jscai.2024.102558. eCollection 2025 Mar.

ABSTRACT

Artificial intelligence (AI) has revolutionized the field of cardiovascular imaging, serving as a unifying force that brings together multiple modalities under a single platform. The utility of noninvasive imaging ranges from diagnostic assessment and guiding interventions to prognostic stratification. Multimodality imaging has demonstrated important potential, particularly in patients with heterogeneous diseases, such as heart failure and atrial fibrillation. Facilitating complex interventional procedures requires accurate image acquisition and interpretation along with precise decision-making. The unique nature of interventional cardiology procedures benefiting from different imaging modalities presents an ideal target for the development of AI-assisted decision-making tools to improve workflow in the catheterization laboratory and personalize the need for transcatheter interventions. This review explores the advancements of AI in noninvasive cardiovascular imaging and interventional cardiology, addressing the clinical use and challenges of current imaging modalities, emerging trends, and promising applications as well as considerations for safe implementation of AI tools in clinical practice. Current practice has moved well beyond the question of whether we should or should not use AI in clinical health care settings. AI, in all its forms, has become deeply embedded in clinical workflows, particularly in cardiovascular imaging and interventional cardiology. It can, in the future, not only add precision and quantification but also serve as a means by which to fuse and link multimodalities together. It is only by understanding how AI techniques work, that the field can be harnessed for the greater good and avoid uninformed bias or misleading diagnoses.

PMID:40230671 | PMC:PMC11993891 | DOI:10.1016/j.jscai.2024.102558

Front Plant Sci. 2025 Mar 31;16:1554193. doi: 10.3389/fpls.2025.1554193. eCollection 2025.

ABSTRACT

We present a novel method for soybean [Glycine max (L.) Merr.] yield estimation leveraging high-throughput seed counting via computer vision and deep learning techniques. Traditional methods for collecting yield data are labor-intensive, costly, and prone to equipment failures at critical data collection times and require transportation of equipment across field sites. Computer vision, the field of teaching computers to interpret visual data, allows us to extract detailed yield information directly from images. By treating it as a computer vision task, we report a more efficient alternative, employing a ground robot equipped with fisheye cameras to capture comprehensive videos of soybean plots from which images are extracted in a variety of development programs. These images are processed through the P2PNet-Yield model, a deep learning framework, where we combined a feature extraction module (the backbone of the P2PNet-Soy) and a yield regression module to estimate seed yields of soybean plots. Our results are built on 2 years of yield testing plot data-8,500 plots in 2021 and 650 plots in 2023. With these datasets, our approach incorporates several innovations to further improve the accuracy and generalizability of the seed counting and yield estimation architecture, such as the fisheye image correction and data augmentation with random sensor effects. The P2PNet-Yield model achieved a genotype ranking accuracy score of up to 83%. It demonstrates up to a 32% reduction in time to collect yield data as well as costs associated with traditional yield estimation, offering a scalable solution for breeding programs and agricultural productivity enhancement.

PMID:40230608 | PMC:PMC11994694 | DOI:10.3389/fpls.2025.1554193

Best Pract Res Clin Rheumatol. 2025 Apr 13:102064. doi: 10.1016/j.berh.2025.102064. Online ahead of print.

ABSTRACT

This update addresses new developments in imaging of axial spondyloarthritis from the past 5 years. These have focused mostly on enhanced CT and MRI-based technologies that bring greater precision to the assessment of both inflammatory and structural lesions in the sacroiliac joint. An international consensus has recommended a 4-sequence MRI for routine diagnostic evaluation of the sacroiliac joint aimed at depicting the location and extent of inflammation as well as an erosion-sensitive sequence for structural damage. The latter include high resolution thin slice sequences that accentuate the interface between subchondral bone and the overlying cartilage and joint space as well as synthetic CT, a deep learning-based technique that transforms certain MRI sequences into images resembling CT. Algorithms based on deep learning derived from plain radiographic, CT, and MRI datasets are increasingly more accurate at identifying sacroiliitis and individual lesions observed on images of the sacroiliac joints and spine.

PMID:40229184 | DOI:10.1016/j.berh.2025.102064

Zhongguo Zhen Jiu. 2025 Apr 12;45(4):413-420. doi: 10.13703/j.0255-2930.20240611-0001. Epub 2025 Jan 7.

ABSTRACT

OBJECTIVE: To develop an artificial intelligence-assisted system for the automatic detection of the features of common 21 auricular points based on the YOLOv8 neural network.

METHODS: A total of 660 human auricular images from three research centers were collected from June 2019 to February 2024. The rectangle boxes and features of images were annotated using the LabelMe5.3.1 tool and converted them into a format compatible with the YOLO model. Using these data, transfer learning and fine-tuning training were conducted on different scales of pretrained YOLO neural network models. The model's performance was evaluated on validation and test sets, including the mean average precision (mAP) at various thresholds, recall rate (recall), frames per second (FPS) and confusion matrices. Finally, the model was deployed on a local computer, and the real-time detection of human auricular images was conducted using a camera.

RESULTS: Five different versions of the YOLOv8 key-point detection model were developed, including YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8l, and YOLOv8x. On the validation set, YOLOv8n showed the best performance in terms of speed (225.736 frames per second) and precision (0.998). On the external test set, YOLOv8n achieved the accuracy of 0.991, the sensitivity of 1.0, and the F1 score of 0.995. The localization performance of auricular point features showed the average accuracy of 0.990, the precision of 0.995, and the recall of 0.997 under 50% intersection ration (mAP50).

CONCLUSION: The key-point detection model of 21 common auricular points based on YOLOv8n exhibits the excellent predictive performance, which is capable of rapidly and automatically locating and classifying auricular points.

PMID:40229149 | DOI:10.13703/j.0255-2930.20240611-0001

NMR Biomed. 2025 May;38(5):e70029. doi: 10.1002/nbm.70029.

ABSTRACT

Previous work indicates evidence that cerebrospinal fluid (CSF) plays a crucial role in brain waste clearance processes and that altered flow patterns are associated with various diseases of the central nervous system. In this study, we investigate the potential of deep learning to predict the distribution in human brain of a gadolinium-based CSF contrast agent (tracer) administered intrathecal. For this, T1-weighted magnetic resonance imaging (MRI) scans taken at multiple time points before and after injection were utilized. We propose a U-net-based supervised learning model to predict pixel-wise signal increase at its peak after 24 h. Performance is evaluated based on different tracer distribution stages provided during training, including predictions from baseline scans taken before injection. Our findings show that training with imaging data from only the first 2-h postinjection yields tracer flow predictions comparable to models trained with additional later-stage scans. Validation against ventricular reflux gradings from neuroradiologists confirmed alignment with expert evaluations. These results demonstrate that deep learning-based methods for CSF flow prediction deserve more attention, as minimizing MR imaging without compromising clinical analysis could enhance efficiency, improve patient well-being and lower healthcare costs.

PMID:40229147 | DOI:10.1002/nbm.70029