Generative artificial intelligence enables the generation of bone scintigraphy images and improves generalization of deep learning models in data-constrained environments.

Purpose: Advancements of deep learning in medical imaging are often constrained by the limited availability of large, annotated datasets, resulting in underperforming models when deployed under real-world conditions. This study investigated a generative artificial intelligence (AI) approach to create synthetic medical images taking the example of bone scintigraphy scans, to increase the data diversity of small-scale datasets for more effective model training and improved generalization.

Methods: We trained a generative model on Tc-bone scintigraphy scans from 9,170 patients in one center to generate high-quality and fully anonymized annotated scans of patients representing two distinct disease patterns: abnormal uptake indicative of (i) bone metastases and (ii) cardiac uptake indicative of cardiac amyloidosis.

Comparative Assessment of CMR-Determined Extracellular Volume Metrics in Predicting Adverse Outcomes.

Extracellular volume (ECV) by cardiovascular magnetic resonance (CMR) imaging is associated with disease burden and clinical outcomes. Recent studies in patients with valvular heart disease (VHD) have suggested that the indexed total ECV (iECV) = ECVx(LV/1.05)/body surface area may supersede ECV in terms of prognostication.

Assembling branched and macrocyclic peptides on proteins.

A two-step, biocompatible strategy enables site-specific generation of branched and macrocyclic peptide-protein conjugates. Solvent-exposed cysteines on proteins are modified by a small bifunctional reagent at near-physiological pH, followed by cyanopyridine-aminothiol click reactions to create branched or macrocyclic peptide architectures. This method offers design strategies for next-generation protein therapeutics.

Clinical Phenotype and Prognosis of Asymptomatic Patients With Transthyretin Cardiac Amyloid Infiltration.

Importance: Patients with transthyretin (ATTR) cardiac amyloid infiltration are increasingly diagnosed at earlier disease stages with no heart failure (HF) symptoms and a wide range of cardiac amyloid infiltration.

Objective: To characterize the clinical phenotype and natural history of asymptomatic patients with ATTR cardiac amyloid infiltration.

Design, Setting, And Participants: This cohort study analyzed data of all patients at 12 international centers for amyloidosis from January 1, 2008, through December 31, 2023.

Peptide-Bismuth Tricycles: Maximizing Stability by Constraint.

Constrained peptides possess excellent properties for identifying lead compounds in drug discovery. While it has become increasingly straightforward to discover selective high-affinity peptide ligands, especially through genetically encoded libraries, their stability and bioavailability remain significant challenges. By integrating macrocyclization chemistry with bismuth binding, we generated series of linear, cyclic, bicyclic, and tricyclic peptides with identical sequences.