Cornell University

Assessment of mechanical damage in canola using X-ray radiography and deep learning

Mechanical damage during post-harvest handling and processing can drastically impair the quality, germination potential, and market value of canola ( Brassica napus L.) seeds. Traditional visual inspection methods are subjective and limited to detecting external defects, often mi...

A homozygous hypomorphic FBN1 splice region variant in domestic cats with Marfan syndrome

Marfan syndrome (MFS) is an autosomal dominant connective tissue disease caused by variants in the fibrillin 1 ( FBN1 ) gene. While common in humans, spontaneous animal models are rarely reported. We present the first phenotypic and molecular characterization of MFS in domestic c...

Civil: causal and intuitive visual imitation learning

Abstract Today’s robots attempt to learn new tasks by imitating human examples. These robots watch the human complete the task, and then try to match the actions taken by the human expert. However, this standard approach to visual imitation learning is fundamentally limited: the...

Supply chain network design and food loss in the U.S. fresh produce system

The U.S. food supply chain provides year-round access to a diverse range of fresh fruits and vegetables, but the perishability of these products makes food loss a persistent sustainability challenge. While previous studies have primarily focused on food loss occurring at the prod...

Consensus-Based Definitions for Vocal Biomarkers: The International VOCAL Initiative.

Introduction: Voice-based health technologies are growing rapidly, but they lack standardized terminology, which hinders interdisciplinary collaboration, research quality, and clinical translation. The objective of this work was to develop universally accepted definitions in the...

Valuation of short-term rentals as income-producing residential assets: a hybrid-hedonic framework

Purpose This study examines whether financial performance mediates the relationship between conventional hedonic property attributes and short-term rental value, and whether short-term rentals should therefore be underwritten as hybrid income-producing residential assets rather t...

How Much Physics Should a Neural Network Know? Thermodynamics‐Informed Neural Networks for Rock Constitutive Modeling With Epistemic Uncertainty

Abstract Machine learning offers a flexible route to constitutive modeling, with two emergent questions for geoscience applications: what level of thermodynamic constraint should be embedded in the network architecture, and how should predictive uncertainty be quantified when ext...

Federal Funding Cuts and the Future of Health Care in Schools

This Viewpoint discusses threats to and protections for school-based health services.

The perils of a “hypertensive” diagnosis

The current framework for approaching patients with severe hypertension assigns every patient with arterial pressure above an arbitrary threshold to a state of either “hypertensive emergency” or “hypertensive urgency.” By labeling every condition in these patients a “hypertensive...

Data-driven massive reaction networks reveal mechanistic pathways underlying catalytic CO2 hydrogenation

Heterogeneous catalytic pathways for clean energy conversion involve thousands of elementary steps, but most models involve only a few dozen reactions. We combine extensive density functional theory calculations, machine learning for activation barrier prediction, and human intel...

Gene–Environment Interaction Mendelian Randomization Reveals Statin-Dependent Associations Between Metabolites and Lipid Traits

Introduction/Background: Observational links between circulating metabolites and lipid traits are often confounded by environmental factors. This study applied Mendelian randomization (MR) and gene–environment interaction MR (MR-G×E) to assess the average causal effects of geneti...

Pancreatic Cancer Screening and Early Detection: Where Are We Now?

Screening for pancreatic cancer with imaging techniques in high-risk individuals—including patients with a genetic predisposition, a family history, or precursor lesions—is critical for improving early detection and survival outcomes, and multimodal strategies that integrate AI-e...

Enhanced External Counterpulsation Versus Standard Medical Therapy for Chronic Refractory Angina: A Systematic Review and Meta-Analysis

Background: Chronic refractory angina is a disabling syndrome of persistent ischemic symptoms despite guideline-directed medical therapy and, in many patients, prior coronary revascularization. Enhanced external counterpulsation [EECP] is a noninvasive therapy that augments diast...

Establishment of Patient-Derived Xenotransplant and Cell Line Models for Canine B-Cell Lymphoma

High-grade canine B-cell lymphoma (cBCL) is a spontaneous cancer in dogs with similar pathologic features as human diffuse large B-cell lymphoma (DLBCL). The value of comparative oncology to both dogs and humans has long been recognized, but the progress in cBCL research has been...

Anterior Cervical Approaches for 2-Level Radiculopathy

Study Design: Anonymous, survey-based study. Objective: The primary objective of this study is to understand and assess the factors influencing the choice of cervical fusion, disc arthroplasty, and hybrid procedures for radiculopathy in the setting of 2-level cervical degenerativ...

Acute fibrinous and organising pneumonia (AFOP): a case series highlighting diverse aetiologies and clinical outcomes in three patients

Background Acute fibrinous and organising pneumonia (AFOP) is a rare histopathological pattern of acute lung injury characterised by intra-alveolar fibrin deposition and organising pneumonia. It has diverse aetiologies and highly variable clinical outcomes.Case presentations We r...

Epidemiology of respiratory viral infections among hematopoietic cellular therapy and chimeric antigen receptor T-cell therapy recipients in the post COVID-19 era

Respiratory viral infections (RVIs) remain a source of morbidity among hematopoietic cell transplant (HCT) or chimeric antigen receptor (CAR) T-cell therapy recipients. This study aims to understand the post-pandemic RVI epidemiology in cellular therapy recipients. IRB-approved r...

Modeling the interferon response to avian influenza

Highly pathogenic avian influenza viruses, such as H5N1, cause severe disease in humans and pose a persistent pandemic threat, yet the mechanism by which the type I interferon response shapes their within-host dynamics remains unclear. Here we fit three ordinary differential equa...

MACS3: A Peak-calling Platform for Bulk and Single-cell Regulatory Genomics

Since the original publication of Model-based Analysis for ChIP-Seq (MACS), the software has been widely used to identify enriched genomic regions in ChIP-seq, ATAC-seq, CUT&RUN, DNase-seq, and related regulatory genomics assays. Over the years, MACS has evolved substantially, wi...

Narrative 2 Numbers (N2N): Leveraging a Hackathon Approach to Generate Ideas and Approaches for Using Mixed Methods to Strengthen Public Health Preparedness and Response

ABSTRACT: Public health emergencies require rapid decision making using incomplete and evolving information, yet tools to quickly integrate actionable qualitative and quantitative data remain limited. To address this gap, we describe a replicable hackathon model that enabled the...