Sci Rep. 2025 Feb 20;15(1):6245. doi: 10.1038/s41598-025-90514-1.

NO ABSTRACT

PMID:39979555 | DOI:10.1038/s41598-025-90514-1

Cardiovasc Eng Technol. 2025 Feb 20. doi: 10.1007/s13239-025-00775-0. Online ahead of print.

ABSTRACT

The prevalence of coronary artery disease (CAD) has become the major cause of death across the world in recent years. The accurate segmentation of coronary artery is important in clinical diagnosis and treatment of coronary artery disease (CAD) such as stenosis detection and plaque analysis. Deep learning techniques have been shown to assist medical experts in diagnosing diseases using biomedical imaging. There are many methods which employ 2D DL models for medical image segmentation. The 2D Pyramid Scene Parsing Neural Network (PSPNet) has potential in this domain but not explored for the segmentation of coronary arteries from 3D Coronary Computed Tomography Angiography (CCTA) images. The contribution of present research work is to propose the modification of 2D PSPNet into 3D PSPNet for segmenting the coronary arteries from 3D CCTA images. The innovative factor is to evaluate the network performance by employing Global processing and Patch based processing methods. The experimental results achieved a Dice Similarity Coefficient (DSC) of 0.76 for Global process method and 0.73 for Patch based method using a subset of 200 images from the ImageCAS dataset.

PMID:39979546 | DOI:10.1007/s13239-025-00775-0

Sci Rep. 2025 Feb 20;15(1):6194. doi: 10.1038/s41598-025-90648-2.

ABSTRACT

Confined columns, such as round-ended concrete-filled steel tubular (CFST) columns, are integral to modern infrastructure due to their high load-bearing capacity and structural efficiency. The primary objective of this study is to develop accurate, data-driven approaches for predicting the axial load-carrying capacity (Pcc​) of these columns and to benchmark their performance against existing analytical solutions. Using an extensive dataset of 200 CFST stub column tests, this research evaluates three machine learning (ML) models - LightGBM, XGBoost, and CatBoost - and three deep learning (DL) models - Deep Neural Network (DNN), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM). Key input features include concrete strength, column length, cross-sectional dimensions, steel tube thickness, and yield strength, which were analysed to uncover underlying relationships. The results indicate that CatBoost delivers the highest predictive accuracy, achieving an RMSE of 396.50 kN and an R2 of 0.932, surpassing XGBoost (RMSE: 449.57 kN, R2: 0.906) and LightGBM (RMSE: 449.57 kN, R2: 0.916). Deep learning models were less effective, with the DNN attaining an RMSE of 496.19 kN and R2 of 0.958, while the LSTM underperformed substantially (RMSE: 2010.46 kN, R2: 0.891). SHapley Additive exPlanations (SHAP) identified cross-sectional width as the most critical feature, contributing positively to capacity, and column length as a significant negative influencer. A user-friendly, Python-based interface was also developed, enabling real-time predictions for practical engineering applications. Comparison with 10 analytical models demonstrates that these traditional methods, though deterministic, struggle to capture the nonlinear interactions inherent in CFST columns, thus yielding lower accuracy and higher variability. In contrast, the data-driven models presented here offer robust, adaptable, and interpretable solutions, underscoring their potential to transform design and analysis practices for CFST columns, ultimately fostering safer and more efficient structural systems.

PMID:39979519 | DOI:10.1038/s41598-025-90648-2

JCO Clin Cancer Inform. 2025 Feb;9:e2400198. doi: 10.1200/CCI-24-00198. Epub 2025 Feb 20.

ABSTRACT

PURPOSE: Primary barriers to application of immune checkpoint inhibitor (ICI) therapy for cancer include severe side effects (such as potentially life threatening pneumonitis [PN]), which can cause the discontinuation of treatment. Predicting which patients may develop PN while on ICI would improve both safety and potential efficacy because treatments could be safely administered for longer or discontinued before severe toxicity.

METHODS: Starting from a cohort of 3,351 patients with cancer who received previous ICI therapy at the Vanderbilt University Medical Center, we curated 2,700 contrast chest computed tomography (CT) volumes for 671 patients. Three different pure imaging models predicted the potential for PN using only a single time point before the first ICI dose.

RESULTS: The first model used 109 radiomics features only and achieved an AUC of 0.747 (CI, 0.705 to 0.789) with a positive predictive value (PPV) of 0.244 (CI, 0.211 to 0.276) at a sensitivity of 0.553 (CI, 0.485 to 0.621) using mainly features describing the global lung properties. The second model used a convolutional neural network (CNN) on the raw CTs to improve to an AUC of 0.819 (CI, 0.781 to 0.857) with a PPV of 0.244 (CI, 0.203 to 0.284) at a sensitivity of 0.743 (CI, 0.681 to 0.806). The third model combined both radiomics and deep learning but, with an AUC of 0.829 (CI, 0.797 to 0.862) and a PPV of 0.254 (CI, 0.228 to 0.281) at a sensitivity of 0.780 (CI, 0.721 to 0.840), did not show a significant improvement on the CNN-only model.

CONCLUSION: This new model suggests the utility of deep learning in PN prediction over traditional pure radiomics and promises better management for patients receiving ICI and the ability to better stratify patients in immunotherapy drug trials.

PMID:39977708 | DOI:10.1200/CCI-24-00198

Hum Reprod Update. 2025 Feb 20:dmaf002. doi: 10.1093/humupd/dmaf002. Online ahead of print.

ABSTRACT

BACKGROUND: Ovarian aging occurs earlier than the aging of many other organs and has a lasting impact on women's overall health and well-being. However, effective interventions to slow ovarian aging remain limited, primarily due to an incomplete understanding of the underlying molecular mechanisms and drug targets. Recent advances in omics data resources, combined with innovative computational tools, are offering deeper insight into the molecular complexities of ovarian aging, paving the way for new opportunities in drug discovery and development.

OBJECTIVE AND RATIONALE: This review aims to synthesize the expanding multi-omics data, spanning genome, transcriptome, proteome, metabolome, and microbiome, related to ovarian aging, from both tissue-level and single-cell perspectives. We will specially explore how the analysis of these emerging omics datasets can be leveraged to identify novel drug targets and guide therapeutic strategies for slowing and reversing ovarian aging.

SEARCH METHODS: We conducted a comprehensive literature search in the PubMed database using a range of relevant keywords: ovarian aging, age at natural menopause, premature ovarian insufficiency (POI), diminished ovarian reserve (DOR), genomics, transcriptomics, epigenomics, DNA methylation, RNA modification, histone modification, proteomics, metabolomics, lipidomics, microbiome, single-cell, genome-wide association studies (GWAS), whole-exome sequencing, phenome-wide association studies (PheWAS), Mendelian randomization (MR), epigenetic target, drug target, machine learning, artificial intelligence (AI), deep learning, and multi-omics. The search was restricted to English-language articles published up to September 2024.

OUTCOMES: Multi-omics studies have uncovered key mechanisms driving ovarian aging, including DNA damage and repair deficiencies, inflammatory and immune responses, mitochondrial dysfunction, and cell death. By integrating multi-omics data, researchers can identify critical regulatory factors and mechanisms across various biological levels, leading to the discovery of potential drug targets. Notable examples include genetic targets such as BRCA2 and TERT, epigenetic targets like Tet and FTO, metabolic targets such as sirtuins and CD38+, protein targets like BIN2 and PDGF-BB, and transcription factors such as FOXP1.

WIDER IMPLICATIONS: The advent of cutting-edge omics technologies, especially single-cell technologies and spatial transcriptomics, has provided valuable insights for guiding treatment decisions and has become a powerful tool in drug discovery aimed at mitigating or reversing ovarian aging. As technology advances, the integration of single-cell multi-omics data with AI models holds the potential to more accurately predict candidate drug targets. This convergence offers promising new avenues for personalized medicine and precision therapies, paving the way for tailored interventions in ovarian aging.

REGISTRATION NUMBER: Not applicable.

PMID:39977580 | DOI:10.1093/humupd/dmaf002

PLoS One. 2025 Feb 20;20(2):e0317461. doi: 10.1371/journal.pone.0317461. eCollection 2025.

ABSTRACT

Coal and gas outburst (CGO) is a complicated natural disaster in underground coal mine production. In constructing smart mines, predicting CGO risks efficiently and accurately is necessary. This paper proposes a CGO risk prediction method based on data augmentation and a neuroevolution algorithm, denoted as ANEAT. First, sample features are applied to the transfer function using a pointwise intensity transformation to obtain new feature samples. It solves the problems of imbalanced data samples and insufficient diversity. Second, the feature importance score sorting and Sparse PCA dimensionality reduction are performed on the data-augmented samples. It provides the initial genome code for the evolutionary neural network. Finally, an evolutionary neural network for CGO prediction is constructed through population initialization, fitness evaluation, species differentiation, genome mutation, and recombination. The optimal phenotype is obtained in the evolutionary generations. In the experiment, we verify the effectiveness of ANEAT from multiple aspects such as data augmentation effectiveness analysis, deep learning model comparison, swarm intelligence optimization algorithm comparison, and other method comparisons. The results show that the MAE, RMSE, and EVAR indexes of ANEAT on the test set are 0.0816, 0.1322, and 0.8972, respectively. It has the optimal CGO prediction effect. ANEAT realizes the high-precision mapping of feature parameters and outburst risk with a lightweight network architecture, which can be well applied to CGO prediction.

PMID:39977390 | DOI:10.1371/journal.pone.0317461

Bioinformatics. 2025 Feb 20:btaf078. doi: 10.1093/bioinformatics/btaf078. Online ahead of print.

ABSTRACT

MOTIVATION: S-sulfhydration, a crucial post-translational protein modification, is pivotal in cellular recognition, signaling processes, and the development and progression of cardiovascular and neurological disorders, so identifying S-sulfhydration sites is crucial for studies in cell biology. Deep learning shows high efficiency and accuracy in identifying protein sites compared to traditional methods that often lack sensitivity and specificity in accurately locating nonsulfhydration sites. Therefore, we employ deep learning methods to tackle the challenge of pinpointing S-sulfhydration sites.

RESULTS: In this work, we introduce a deep learning approach called Sul-BertGRU, designed specifically for predicting S-sulfhydration sites in proteins, that integrates multi-directional gated recurrent unit (GRU) and BERT. First, Sul-BertGRU proposes an information entropy-enhanced BERT (IE-BERT) to preprocess protein sequences and extract initial features. Subsequently, confidence learning is employed to eliminate potential S-sulfhydration samples from the nonsulfhydration samples and select reliable negative samples. Then, considering the directional nature of the modification process, protein sequences are categorized into left, right, and full sequences centred on cysteines. We build a multi-directional GRU to enhance the extraction of directional sequence features and model the details of the enzymatic reaction involved in S-sulfhydration. Ultimately, we apply a parallel multi-head self-attention mechanism alongside a convolutional neural network (CNN) to deeply analyze sequence features that might be missed at a local level. Sul-BertGRU achieves sensitivity, specificity, precision, accuracy, Matthews correlation coefficient, and area under the curve scores of 85.82%, 68.24%, 74.80%, 77.44%, 55.13%, and 77.03%, respectively. Sul-BertGRU demonstrates exceptional performance and proves to be a reliable method for predicting protein S-sulfhydration sites.

AVAILABILITY AND IMPLEMENTATION: The source code and data are available at https://github.com/Severus0902/Sul-BertGRU/.

SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

PMID:39977366 | DOI:10.1093/bioinformatics/btaf078

Proc Natl Acad Sci U S A. 2025 Feb 25;122(8):e2411492122. doi: 10.1073/pnas.2411492122. Epub 2025 Feb 20.

ABSTRACT

Longitudinal imaging data are routinely acquired for health studies and patient monitoring. A central goal in longitudinal studies is tracking relevant change over time. Traditional methods remove nuisance variation with custom pipelines to focus on significant changes. In this work, we present a machine learning-based method that automatically ignores irrelevant changes and extracts the time-varying signal of interest. Our method, called Learning-based Inference of Longitudinal imAge Changes (LILAC), performs a pairwise comparison of longitudinal images in order to make a temporal difference prediction. LILAC employs a convolutional Siamese architecture to extract feature pairs, followed by subtraction and a bias-free fully connected layer to learn meaningful temporal image differences. We first showcase LILAC's ability to capture key longitudinal changes by simply training it to predict the temporal ordering of images. In our experiments, temporal ordering accuracy exceeded 0.98, and predicted time differences were strongly correlated with actual changes in relevant variables (Pearson Correlation Coefficient r = 0.911 with embryo phase change, and r = 0.875 with time interval in wound healing). Next, we trained LILAC to explicitly predict specific targets, such as the change in clinical scores in patients with mild cognitive impairment. LILAC models achieved over a 40% reduction in root mean square error compared to baseline methods. Our empirical results demonstrate that LILAC effectively localizes and quantifies relevant individual-level changes in longitudinal imaging data, offering valuable insights for studying temporal mechanisms or guiding clinical decisions.

PMID:39977323 | DOI:10.1073/pnas.2411492122

Int J Comput Assist Radiol Surg. 2025 Feb 20. doi: 10.1007/s11548-025-03335-y. Online ahead of print.

ABSTRACT

PURPOSE: While deep learning methods have shown great promise in improving the effectiveness of prostate cancer (PCa) diagnosis by detecting suspicious lesions from trans-rectal ultrasound (TRUS), they must overcome multiple simultaneous challenges. There is high heterogeneity in tissue appearance, significant class imbalance in favor of benign examples, and scarcity in the number and quality of ground truth annotations available to train models. Failure to address even a single one of these problems can result in unacceptable clinical outcomes.

METHODS: We propose TRUSWorthy, a carefully designed, tuned, and integrated system for reliable PCa detection. Our pipeline integrates self-supervised learning, multiple-instance learning aggregation using transformers, random-undersampled boosting and ensembling: These address label scarcity, weak labels, class imbalance, and overconfidence, respectively. We train and rigorously evaluate our method using a large, multi-center dataset of micro-ultrasound data.

RESULTS: Our method outperforms previous state-of-the-art deep learning methods in terms of accuracy and uncertainty calibration, with AUROC and balanced accuracy scores of 79.9% and 71.5%, respectively. On the top 20% of predictions with the highest confidence, we can achieve a balanced accuracy of up to 91%.

CONCLUSION: The success of TRUSWorthy demonstrates the potential of integrated deep learning solutions to meet clinical needs in a highly challenging deployment setting, and is a significant step toward creating a trustworthy system for computer-assisted PCa diagnosis.

PMID:39976857 | DOI:10.1007/s11548-025-03335-y

Eur J Trauma Emerg Surg. 2025 Feb 20;51(1):115. doi: 10.1007/s00068-025-02779-w.

ABSTRACT

OBJECTIVES: Pediatric elbow fractures are a common injury among children. Recent advancements in artificial intelligence (AI), particularly deep learning (DL), have shown promise in diagnosing these fractures. This study systematically evaluated the performance of DL models in detecting pediatric elbow fractures.

MATERIALS AND METHODS: A comprehensive search was conducted in PubMed (Medline), EMBASE, and IEEE Xplore for studies published up to October 20, 2023. Studies employing DL models for detecting elbow fractures in patients aged 0 to 16 years were included. Key performance metrics, including sensitivity, specificity, and area under the curve (AUC), were extracted. The study was registered in PROSPERO (ID: CRD42023470558).

RESULTS: The search identified 22 studies, of which six met the inclusion criteria for the meta-analysis. The pooled sensitivity of DL models for pediatric elbow fracture detection was 0.93 (95% CI: 0.91-0.96). Specificity values ranged from 0.84 to 0.92 across studies, with a pooled estimate of 0.89 (95% CI: 0.85-0.92). The AUC ranged from 0.91 to 0.99, with a pooled estimate of 0.95 (95% CI: 0.93-0.97). Further analysis highlighted the impact of preprocessing techniques and the choice of model backbone architecture on performance.

CONCLUSION: DL models demonstrate exceptional accuracy in detecting pediatric elbow fractures. For optimal performance, we recommend leveraging backbone architectures like ResNet, combined with manual preprocessing supervised by radiology and orthopedic experts.

PMID:39976732 | DOI:10.1007/s00068-025-02779-w

Eur J Nucl Med Mol Imaging. 2025 Feb 20. doi: 10.1007/s00259-025-07145-x. Online ahead of print.

ABSTRACT

BACKGROUND: Myocardial perfusion imaging (MPI) using single-photon emission computed tomography (SPECT) is a well-established modality for noninvasive diagnostic assessment of coronary artery disease (CAD). However, the time-consuming and experience-dependent visual interpretation of SPECT images remains a limitation in the clinic.

PURPOSE: We aimed to develop advanced models to diagnose CAD using different supervised and semi-supervised deep learning (DL) algorithms and training strategies, including transfer learning and data augmentation, with SPECT-MPI and invasive coronary angiography (ICA) as standard of reference.

MATERIALS AND METHODS: A total of 940 patients who underwent SPECT-MPI were enrolled (281 patients included ICA). Quantitative perfusion SPECT (QPS) was used to extract polar maps of rest and stress states. We defined two different tasks, including (1) Automated CAD diagnosis with expert reader (ER) assessment of SPECT-MPI as reference, and (2) CAD diagnosis from SPECT-MPI based on reference ICA reports. In task 2, we used 6 strategies for training DL models. We implemented 13 different DL models along with 4 input types with and without data augmentation (WAug and WoAug) to train, validate, and test the DL models (728 models). One hundred patients with ICA as standard of reference (the same patients in task 1) were used to evaluate models per vessel and per patient. Metrics, such as the area under the receiver operating characteristics curve (AUC), accuracy, sensitivity, specificity, precision, and balanced accuracy were reported. DeLong and pairwise Wilcoxon rank sum tests were respectively used to compare models and strategies after 1000 bootstraps on the test data for all models. We also compared the performance of our best DL model to ER's diagnosis.

RESULTS: In task 1, DenseNet201 Late Fusion (AUC = 0.89) and ResNet152V2 Late Fusion (AUC = 0.83) models outperformed other models in per-vessel and per-patient analyses, respectively. In task 2, the best models for CAD prediction based on ICA were Strategy 3 (a combination of ER- and ICA-based diagnosis in train data), WoAug InceptionResNetV2 EarlyFusion (AUC = 0.71), and Strategy 5 (semi-supervised approach) WoAug ResNet152V2 EarlyFusion (AUC = 0.77) in per-vessel and per-patient analyses, respectively. Moreover, saliency maps showed that models could be helpful for focusing on relevant spots for decision making.

CONCLUSION: Our study confirmed the potential of DL-based analysis of SPECT-MPI polar maps in CAD diagnosis. In the automation of ER-based diagnosis, models' performance was promising showing accuracy close to expert-level analysis. It demonstrated that using different strategies of data combination, such as including those with and without ICA, along with different training methods, like semi-supervised learning, can increase the performance of DL models. The proposed DL models could be coupled with computer-aided diagnosis systems and be used as an assistant to nuclear medicine physicians to improve their diagnosis and reporting, but only in the LAD territory.

CLINICAL TRIAL NUMBER: Not applicable.

PMID:39976703 | DOI:10.1007/s00259-025-07145-x

J Appl Clin Med Phys. 2025 Feb 20:e70031. doi: 10.1002/acm2.70031. Online ahead of print.

ABSTRACT

PURPOSE: To compare image quality and clinical utility of a T2-weighted (T2W) 3-dimensional (3D) fast spin echo (FSE) sequence using deep learning reconstruction (DLR) versus conventional reconstruction for rectal magnetic resonance imaging (MRI).

METHODS: The study included 50 patients with rectal cancer who underwent rectal MRI consecutively between July 7, 2020 and January 20, 2021 using a T2W 3D FSE sequence with DLR and conventional reconstruction. Three radiologists reviewed the two sets of images, scoring overall SNR, motion artifacts, and overall image quality on a 3-point scale and indicating clinical preference for DLR or conventional reconstruction based on those three criteria as well as image characterization of bowel wall layer definition, tumor invasion of muscularis propria, residual disease, fibrosis, nodal margin, and extramural venous invasion.

RESULTS: Image quality was rated as moderate or good for both DLR and conventional reconstruction for most cases. DLR was preferred over conventional reconstruction in all of the categories except for bowel wall layer definition.

CONCLUSION: Both conventional reconstruction and DLR provide acceptable image quality for T2W 3D FSE imaging of rectal cancer. DLR was clinically preferred over conventional reconstruction in almost all categories.

PMID:39976552 | DOI:10.1002/acm2.70031

Med Phys. 2025 Feb 20. doi: 10.1002/mp.17696. Online ahead of print.

ABSTRACT

BACKGROUND: Deformable medical image registration aims to align image pairs with local differences, improving the accuracy of medical analyses and assisting various diagnostic scenarios.

PURPOSE: We aim to overcome these challenges: Deep learning-based registration approaches have greatly enhanced registration speed and accuracy by continuously improving registration networks and processes. However, the lack of extensive medical datasets limits the complexity of registration models. Optimizing registration networks within a fixed dataset often leads to overfitting, hindering further accuracy improvements and reducing generalization capabilities.

METHODS: We explore the application of the foundational model DINOv2 to registration tasks, leveraging its prior knowledge to support learning-based unsupervised registration networks and overcome network bottlenecks to improve accuracy. We investigate three modes of DINOv2-assisted registration, including direct registration architecture, enhanced architecture, and refined architecture. Additionally, we study the applicability of three feature aggregation methods-convolutional interaction, direct fusion, and cross-attention-within the proposed DINOv2-based registration frameworks.

RESULTS: We conducted extensive experiments on the IXI and OASIS public datasets, demonstrating that the enhanced and refined architectures notably improve registration accuracy, reduce data dependency, and maintain strong generalization capabilities.

CONCLUSION: This study offers novel approaches for applying foundational models to deformable image registration tasks.

PMID:39976314 | DOI:10.1002/mp.17696

Stat Med. 2025 Feb 28;44(5):e70020. doi: 10.1002/sim.70020.

ABSTRACT

Freezing of Gait (FOG) is a prevalent symptom in advanced Parkinson's Disease (PD), characterized by intermittent transitions between normal gait and freezing episodes. This study introduces a novel graph-theoretic approach to detect FOG from video data of PD patients. We construct a sequence of pose graphs that represent the spatial relations and temporal progression of a patient's posture over time. Each graph node corresponds to an estimated joint position, while the edges reflect the anatomical connections and their proximity. We propose a hypothesis testing procedure that deploys the Fréchet statistics to identify break points in time between regular gait and FOG episodes, where we model the central tendency and dispersion of the pose graphs in the presentation of graph Laplacian matrices by computing their Fréchet mean and variance. We implement binary segmentation and incremental computation in our algorithm for efficient calculation. The proposed framework is validated on two datasets, Kinect3D and AlphaPose, demonstrating its effectiveness in detecting FOG from video data. The proposed approach that extracts matrix features is distinct from the prevailing pixel-based deep learning methods. It provides a new perspective on feature extraction for FOG detection and potentially contributes to improved diagnosis and treatment of PD.

PMID:39976295 | DOI:10.1002/sim.70020

ArXiv [Preprint]. 2025 Feb 1:arXiv:2501.14158v2.

ABSTRACT

Magnetic resonance imaging (MRI) is a non-invasive imaging modality and provides comprehensive anatomical and functional insights into the human body. However, its long acquisition times can lead to patient discomfort, motion artifacts, and limiting real-time applications. To address these challenges, strategies such as parallel imaging have been applied, which utilize multiple receiver coils to speed up the data acquisition process. Additionally, compressed sensing (CS) is a method that facilitates image reconstruction from sparse data, significantly reducing image acquisition time by minimizing the amount of data collection needed. Recently, deep learning (DL) has emerged as a powerful tool for improving MRI reconstruction. It has been integrated with parallel imaging and CS principles to achieve faster and more accurate MRI reconstructions. This review comprehensively examines DL-based techniques for MRI reconstruction. We categorize and discuss various DL-based methods, including end-to-end approaches, unrolled optimization, and federated learning, highlighting their potential benefits. Our systematic review highlights significant contributions and underscores the potential of DL in MRI reconstruction. Additionally, we summarize key results and trends in DL-based MRI reconstruction, including quantitative metrics, the dataset, acceleration factors, and the progress of and research interest in DL techniques over time. Finally, we discuss potential future directions and the importance of DL-based MRI reconstruction in advancing medical imaging. To facilitate further research in this area, we provide a GitHub repository that includes up-to-date DL-based MRI reconstruction publications and public datasets-https://github.com/mosaf/Awesome-DL-based-CS-MRI.

PMID:39975448 | PMC:PMC11838702

ArXiv [Preprint]. 2025 Jan 27:arXiv:2501.15712v1.

ABSTRACT

Computational modeling of cardiovascular function has become a critical part of diagnosing, treating and understanding cardiovascular disease. Most strategies involve constructing anatomically accurate computer models of cardiovascular structures, which is a multistep, time-consuming process. To improve the model generation process, we herein present SeqSeg (sequential segmentation): a novel deep learning based automatic tracing and segmentation algorithm for constructing image-based vascular models. SeqSeg leverages local U-Net-based inference to sequentially segment vascular structures from medical image volumes. We tested SeqSeg on CT and MR images of aortic and aortofemoral models and compared the predictions to those of benchmark 2D and 3D global nnU-Net models, which have previously shown excellent accuracy for medical image segmentation. We demonstrate that SeqSeg is able to segment more complete vasculature and is able to generalize to vascular structures not annotated in the training data.

PMID:39975447 | PMC:PMC11838707

ArXiv [Preprint]. 2025 Jan 24:arXiv:2311.11046v2.

ABSTRACT

Major depressive disorder (MDD) is a complex psychiatric disorder that affects the lives of hundreds of millions of individuals around the globe. Even today, researchers debate if morphological alterations in the brain are linked to MDD, likely due to the heterogeneity of this disorder. The application of deep learning tools to neuroimaging data, capable of capturing complex non-linear patterns, has the potential to provide diagnostic and predictive biomarkers for MDD. However, previous attempts to demarcate MDD patients and healthy controls (HC) based on segmented cortical features via linear machine learning approaches have reported low accuracies. Here, we used globally representative data from the ENIGMA-MDD working group containing 7,012 participants from 30 sites (N=2,772 MDD and N=4,240 HC), which allows a comprehensive analysis with generalizable results. Based on the hypothesis that integration of vertex-wise cortical features can improve classification performance, we evaluated the classification of a DenseNet and a Support Vector Machine (SVM), with the expectation that the former would outperform the latter. We found that both classifiers exhibited close to chance performance (balanced accuracy DenseNet: 51%; SVM: 53%), when estimated on unseen sites. Slightly higher classification performance (balanced accuracy DenseNet: 58%; SVM: 55%) was found when the cross-validation folds contained subjects from all sites, indicating site effect. In conclusion, the integration of vertex-wise morphometric features and the use of the non-linear classifier did not lead to the differentiability between MDD and HC. Our results support the notion that MDD classification on this combination of such features and classifiers is unfeasible. Perhaps more sophisticated integration of multimodal information may lead to a higher performance in this diagnostic task.

PMID:39975425 | PMC:PMC11838705

bioRxiv [Preprint]. 2025 Feb 8:2025.02.07.637149. doi: 10.1101/2025.02.07.637149.

ABSTRACT

As spatial molecular data grow in scope and resolution, there is a pressing need to identify key spatial structures associated with disease. Current approaches often rely on hand-crafted features such as local abundances of manually annotated, discrete cell types, which may overlook important signals. Here we introduce variational inference-based microniche analysis (VIMA), a method that combines deep learning with principled statistics to discover associated spatial features with greater flexibility and precision. VIMA uses a variational autoencoder to extract numerical "fingerprints" from small tissue patches that capture their biological content. It uses these fingerprints to define a large number of "microniches" - small, potentially overlapping groups of tissue patches with highly similar biology that span multiple samples. It then uses rigorous statistics to identify microniches whose abundance correlates with case-control status. We show in simulations that VIMA is well calibrated and more powerful and accurate than other approaches. We then apply VIMA to a 140-gene spatial transcriptomics dataset in Alzheimer's dementia, a 54-marker CO-Detection by indEXing (CODEX) dataset in ulcerative colitis (UC), and a 7-marker immunohistochemistry dataset in rheumatoid arthritis (RA), in each case recapitulating known biology and identifying novel spatial features of disease.

PMID:39975274 | PMC:PMC11839118 | DOI:10.1101/2025.02.07.637149

bioRxiv [Preprint]. 2025 Jan 27:2025.01.24.634753. doi: 10.1101/2025.01.24.634753.

ABSTRACT

Given the successful graft-versus-leukemia cell treatment effect observed with allogeneic hematopoietic stem cell transplant for patients with refractory or relapsed acute myeloid leukemia, immunotherapies have also been investigated in the nontransplant setting. Here, we use a multi-omic approach to investigate spatiotemporal interactions in the bone marrow niche between leukemia cells and immune cells in patients with refractory or relapsed acute myeloid leukemia treated with a combination of the immune checkpoint inhibitor pembrolizumab and hypomethylating agent decitabine. We derived precise segmentation data by extensively training nuclear and membrane cell segmentation models, which enabled accurate transcript assignment and deep learning-feature-based image analysis. To overcome read-depth limitations, we integrated the single-cell RNA sequencing data with single-cell-resolution spatial transcriptomic data from the same sample. Quantifying cell-cell distances between cell edges rather than cell centroids allowed us to conduct a more accurate downstream analysis of the tumor microenvironment, revealing that multiple cell types of interest had global enrichment or local enrichment proximal to leukemia cells after pembrolizumab treatment, which could be associated with their clinical responses. Furthermore, ligand-receptor analysis indicated a potential increase in TWEAK signaling between leukemia cells and immune cells after pembrolizumab treatment.

HIGHLIGHTS: Spatial transcriptomic analysis of R-AML bone marrow niches provides detailed information about intercellular interactions in the tumor microenvironment.Immunotherapy shifts the cell composition of the leukemia neighborhood.

PMID:39975227 | PMC:PMC11838223 | DOI:10.1101/2025.01.24.634753

bioRxiv [Preprint]. 2025 Jan 29:2025.01.29.634860. doi: 10.1101/2025.01.29.634860.

ABSTRACT

Identification of neuron type is critical to understand computation in neural circuits through extracellular recordings in awake, behaving animal subjects. Yet, modern recording probes have limited power to resolve neuron type. Here, we leverage the well-characterized architecture of the cerebellar circuit to perform expert identification of neuron type from extracellular recordings in behaving non-human primates. Using deep-learning classifiers we evaluate the information contained in readily accessible extracellular features for neuron identification. Waveform, discharge statistics, anatomical layer, and functional interactions each can inform neuron labels for a sizable fraction of cerebellar units. Together, as inputs to a deep-learning classifier, the features perform even better. Our tools and methodologies, validated during smooth pursuit eye movements in the cerebellar floccular complex of awake behaving monkeys, can guide expert identification of neuron type during cerebellar-dependent tasks in behaving animals across species. They lay the groundwork for characterization of information processing in the cerebellar cortex.

IMPACT STATEMENT: To understand how the brain performs computations in the service of behavior, we develop methods to link neuron type to functional activity within well-characterized neural circuits. Here, we show how features derived from extracellular recordings provide complementary information to disambiguate neuron identity in the cerebellar cortex.

PMID:39975199 | PMC:PMC11838295 | DOI:10.1101/2025.01.29.634860