Pancancer outcome prediction via a unified weakly supervised deep learning model.

Accurate prognosis prediction is essential for guiding cancer treatment and improving patient outcomes. While recent studies have demonstrated the potential of histopathological images in survival analysis, existing models are typically developed in a cancer-specific manner, lack extensive external validation, and often rely on molecular data that are not routinely available in clinical practice. To address these limitations, we present PROGPATH, a unified model capable of integrating histopathological image features with routinely collected clinical variables to achieve pancancer prognosis prediction.

Association between ultra-processed food consumption and lung cancer risk: a population-based cohort study.

Background: The evidence on associations between ultra-processed foods (UPF) and lung cancer risk is limited and inconsistent.

Research Question: Are UPF associated with an increased risk of lung cancer, non-small cell lung cancer (NSCLC) and small cell lung cancer (SCLC)？ METHODS: Data of participants in this study were collected from the Prostate, Lung, Colorectal and Ovarian (PLCO) Cancer Screening Trial. Dietary intakes were assessed through a validated diet history questionnaire.

Accelerometer-measured multidimensional physical activity patterns and physical functional decline: a prospective national cohort study of aging.

Background: Physical activity (PA) is crucial for maintaining physical function in older adults, but relationships between multidimensional PA patterns and functional decline remain unclear. This study examined associations between accelerometer-measured PA patterns and physical function decline in older adults.

Methods: We conducted a prospective cohort study with 1-year follow-up using data from 586 community-dwelling participants aged ≥65 years in the National Health and Aging Trends Study (2021-2022).

Large Context, Deeper Insights: Harnessing Large Language Models for Advancing Protein-Protein Interaction Analysis.

Protein-protein interactions (PPIs) are involved in nearly all biological processes. Understanding and analysis of PPI is key to revealing biological networks and identifying new therapeutic targets. Various computational approaches have been proposed as an alternative to the experimental investigation of PPIs.

Advancing hierarchical neural networks with scale-aware pyramidal feature learning for medical image dense prediction.

Background And Objective: Hierarchical neural networks are pivotal in medical imaging for multi-scale representation, aiding in tasks such as object detection and segmentation. However, their effectiveness is often limited by the loss of intra-scale information and misalignment of inter-scale features. Our study introduces the Integrated-Scale Pyramidal Interactive Reconfiguration to Enhance feature learning (INSPIRE).

Counterfactual Bidirectional Co-Attention Transformer for Integrative Histology-Genomic Cancer Risk Stratification.

Applying deep learning to predict patient prognostic survival outcomes using histological whole-slide images (WSIs) and genomic data is challenging due to the morphological and transcriptomic heterogeneity present in the tumor microenvironment. Existing deep learning-enabled methods often exhibit learning biases, primarily because the genomic knowledge used to guide directional feature extraction from WSIs may be irrelevant or incomplete. This results in a suboptimal and sometimes myopic understanding of the overall pathological landscape, potentially overlooking crucial histological insights.

Rethinking Copy-Paste for Consistency Learning in Medical Image Segmentation.

Semi-supervised learning based on consistency learning offers significant promise for enhancing medical image segmentation. Current approaches use copy-paste as an effective data perturbation technique to facilitate weak-to-strong consistency learning. However, these techniques often lead to a decrease in the accuracy of synthetic labels corresponding to the synthetic data and introduce excessive perturbations to the distribution of the training data.

From physical activity patterns to cognitive status: development and validation of novel digital biomarkers for cognitive assessment in older adults.

Background: This study aims to investigate the associations between signal-level physical activity (PA) features derived from wrist accelerometry data and cognitive status in older adults, and to evaluate their potential predictive value when combined with demographics.

Methods: We analyzed PA data from 3,363 older adults (NHATS: n = 747; NHANES: n = 2,616), with each participant contributing a complete 3-day continuous activity sequence. We extracted the most relevant PA features associated with cognitive function using feature engineering and recursive feature elimination.

Deep Learning-Enabled Integration of Histology and Transcriptomics for Tissue Spatial Profile Analysis.

Spatially resolved transcriptomics enable comprehensive measurement of gene expression at subcellular resolution while preserving the spatial context of the tissue microenvironment. While deep learning has shown promise in analyzing SCST datasets, most efforts have focused on sequence data and spatial localization, with limited emphasis on leveraging rich histopathological insights from staining images. We introduce GIST, a deep learning-enabled gene expression and histology integration for spatial cellular profiling.

Association of whole grain food consumption with lung cancer risk: a prospective cohort study.

Background: Whether the intake of whole grain foods can protect against lung cancer is a long-standing question of considerable public health import, but the epidemiologic evidence has been limited. Therefore we aim to investigate the relationship between whole grain food consumption and lung cancer in the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial (PLCO) cohort.

Methods: Diet was assessed with a self-administered Diet History Questionnaire (DHQ) at baseline.

Transcoronary study of biomarkers in patients with heart failure: Insights into intracardiac production.

Aims: Biomarkers are pivotal in the management of heart failure (HF); however, their lack of cardiac specificity could limit clinical utility. This study aimed to investigate the transcoronary changes and intracardiac production of these biomarkers.

Methods: Transcoronary gradients for B-type natriuretic peptide (BNP) and five novel biomarkers-galectin-3 (Gal-3), soluble suppression of tumourigenicity 2 (sST2), tissue inhibitor of metalloproteinase 1 (TIMP-1), growth differentiation factor 15 (GDF-15) and myeloperoxidase (MPO)-were determined using femoral artery (FA) and coronary sinus (CS) samples from 30 HF patients and 10 non-HF controls.

Predicting physical functioning status in older adults: insights from wrist accelerometer sensors and derived digital biomarkers of physical activity.

Objective: Conventional physical activity (PA) metrics derived from wearable sensors may not capture the cumulative, transitions from sedentary to active, and multidimensional patterns of PA, limiting the ability to predict physical function impairment (PFI) in older adults. This study aims to identify unique temporal patterns and develop novel digital biomarkers from wrist accelerometer data for predicting PFI and its subtypes using explainable artificial intelligence techniques.

Materials And Methods: Wrist accelerometer streaming data from 747 participants in the National Health and Aging Trends Study (NHATS) were used to calculate 231 PA features through time-series analysis techniques-Tsfresh.

A systematic evaluation of computational methods for cell segmentation.

Cell segmentation is a fundamental task in analyzing biomedical images. Many computational methods have been developed for cell segmentation and instance segmentation, but their performances are not well understood in various scenarios. We systematically evaluated the performance of 18 segmentation methods to perform cell nuclei and whole cell segmentation using light microscopy and fluorescence staining images.

HiCervix: An Extensive Hierarchical Dataset and Benchmark for Cervical Cytology Classification.

Cervical cytology is a critical screening strategy for early detection of pre-cancerous and cancerous cervical lesions. The challenge lies in accurately classifying various cervical cytology cell types. Existing automated cervical cytology methods are primarily trained on databases covering a narrow range of coarse-grained cell types, which fail to provide a comprehensive and detailed performance analysis that accurately represents real-world cytopathology conditions.

Federated attention consistent learning models for prostate cancer diagnosis and Gleason grading.

Artificial intelligence (AI) holds significant promise in transforming medical imaging, enhancing diagnostics, and refining treatment strategies. However, the reliance on extensive multicenter datasets for training AI models poses challenges due to privacy concerns. Federated learning provides a solution by facilitating collaborative model training across multiple centers without sharing raw data.

Coping with groundwater pollution in high-nitrate leaching areas: The efficacy of denitrification.

The Ningxia Yellow River irrigation area, characterized by an arid climate and high leaching of NO-N, exhibits complex and unique groundwater nitrate (NO-N) pollution, with denitrification serving as the principal mechanism for NO-N removal. The characteristics of N leaching from paddy fields and NO-N removal by groundwater denitrification were investigated through a two-year field observation. The leaching losses of total nitrogen (TN) and NO-N accounted for 10.

A systematic evaluation of computational methods for cell segmentation.

Cell segmentation is a fundamental task in analyzing biomedical images. Many computational methods have been developed for cell segmentation and instance segmentation, but their performances are not well understood in various scenarios. We systematically evaluated the performance of 18 segmentation methods to perform cell nuclei and whole cell segmentation using light microscopy and fluorescence staining images.

PhaseFIT: live-organoid phase-fluorescent image transformation via generative AI.

Organoid models have provided a powerful platform for mechanistic investigations into fundamental biological processes involved in the development and function of organs. Despite the potential for image-based phenotypic quantification of organoids, their complex 3D structure, and the time-consuming and labor-intensive nature of immunofluorescent staining present significant challenges. In this work, we developed a virtual painting system, PhaseFIT (phase-fluorescent image transformation) utilizing customized and morphologically rich 2.

Metabolomics Profiling Predicts Ventricular Arrhythmia in Patients with an Implantable Cardioverter Defibrillator.

Implantable cardioverter defibrillators (ICDs) reduce sudden cardiac death (SCD) when patients experience life-threatening ventricular arrhythmias (LTVA). However, current strategies determining ICD patient selection and risk stratification are inefficient. We used metabolomics to assess whether dysregulated metabolites are associated with LTVA and identify potential biomarkers.

Machine learning for cryosection pathology predicts the 2021 WHO classification of glioma.

Background: Timely and accurate intraoperative cryosection evaluations remain the gold standard for guiding surgical treatments for gliomas. However, the tissue-freezing process often generates artifacts that make histologic interpretation difficult. In addition, the 2021 WHO Classification of Tumors of the Central Nervous System incorporates molecular profiles in the diagnostic categories, so standard visual evaluation of cryosections alone cannot completely inform diagnoses based on the new classification system.

Retracted: Ultra-processed food consumption and risk of dementia and Alzheimer's disease: Long-term results from the Framingham Offspring Study.

Retraction: Wang, K, Tang, W, Hao, X, Zhao, J. Ultra-processed food consumption and risk of dementia and Alzheimer's disease: Long-term results from the Framingham Offspring Study. Alzheimer's Dement.

A Comparison of the Electrophysiological and Anatomic Characteristics of Pacing Different Branches of the Left Bundle Conduction System.

Left bundle branch pacing (LBBP) is a rapidly growing conduction system pacing technique. However, little is known regarding the electrophysiological characteristics of different types of LBBP. We aimed to evaluate the electrophysiological characteristics and anatomic lead location with pacing different branches of the left bundle branch.

Contrast-enhanced image-guided lead deployment for left bundle branch pacing.

Background: Left bundle branch pacing (LBBP) is a novel conduction system pacing modality, but pacing lead deployment remains challenging.

Objectives: This study aimed to evaluate the feasibility of visualization-enhanced lead deployment for LBBP implantation and to assess LBBP characteristics on the basis of lead tip location.

Methods: Successful LBBP with a well-defined lead tip location by visualization of the tricuspid value annulus in 20 patients was retrospectively analyzed to develop an image-guided technique to identify the LBBP target site.