Early identification of pancreatitis remains a significant clinical diagnostic challenge that impacts patient outcomes. The evolution of quantitative imaging followed by deep learning models has shown great promise in the non-invasive diagnosis of pancreatitis and its complications. We provide an overview of advancements in diagnostic imaging and quantitative imaging methods along with the evolution of artificial intelligence (AI). In this article, we review the current and future states of methodology and limitations of AI in improving clinical support in the context of early detection and management of pancreatitis.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1007/s00261-024-04512-4 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Background: Hypothyroidism is a common sequela after radiotherapy for nasopharyngeal carcinoma (NPC). Magnetic resonance imaging (MRI) has gained prominence in thyroid imaging, leveraging its non-ionizing radiation, high spatial resolution, multiparameter and multidirectional imaging. Few previous studies have investigated the evaluation of radiation-induced thyroid injury by MRI.
View Article and Find Full Text PDFEvidence for direct dopaminergic connections between substantia nigra pars compacta and thalamus in young healthy humans.
Front Neural Circuits
January 2025
Department of Advanced Medical and Surgical Sciences, Advanced MRI Research Center, University of Campania "Luigi Vanvitelli", Naples, Italy.
The substantia nigra pars compacta (SNc), one of the main dopaminergic nuclei of the brain, exerts a regulatory function on the basal ganglia circuitry via the nigro-striatal pathway but its possible dopaminergic innervation of the thalamus has been only investigated in non-human primates. The impossibility of tract-tracing studies in humans has boosted advanced MRI techniques and multi-shell high-angular resolution diffusion MRI (MS-HARDI) has promised to shed more light on the structural connectivity of subcortical structures. Here, we estimated the possible dopaminergic innervation of the human thalamus via an MS-HARDI tractography of the SNc in healthy human young adults.
View Article and Find Full Text PDFDiffusion tensor imaging in peroneal neuropathy: a prospective, single-centre study.
BMJ Neurol Open
January 2025
Research Group experimental Neurosurgery and Neuroanatomy and the Leuven Brain Institute, KU Leuven, Leuven, Flanders, Belgium.
Objective: Diffusion tensor imaging (DTI) showed promising results in diagnosing upper limb neuropathies, but its value in patients with foot drop due to peroneal neuropathy has not yet been investigated. We aim to establish reference values for DTI metrics of the healthy peroneal nerve and to evaluate differences in DTI metrics between patients and healthy controls.
Methods: Diffusion-weighted images (DWI) from 22 pathological nerves, 14 asymptomatic patients' nerves and 65 healthy peroneal nerves were processed for quantitative assessment of fractional anisotropy (FA), radial diffusivity (RD), axial diffusivity and mean diffusivity.
Trichoscopic Analysis of Healthy Indian Males for Standardization of the Measurable Parameters: An Observational, Cross-sectional Study.
Indian Dermatol Online J
December 2024
The Venkat Centre for Advanced Dermatology, Plastic Surgery and ENT, Bengaluru, Karnataka, India.
Background: Trichoscopy is a simple, noninvasive tool to help in the diagnosis of various hair and scalp disorders. There is paucity of data on the normal trichoscopic parameters of hair density and diameter in the Indian population.
Aim: The aim of this study was to establish the trichoscopic patterns of hair and scalp in healthy Indian males and to provide a framework for future reference.
Visual-textual integration in LLMs for medical diagnosis: A preliminary quantitative analysis.
Comput Struct Biotechnol J
December 2024
Division of Data-Driven and Digital Medicine (D3M), Icahn School of Medicine at Mount Sinai, New York, NY, USA.
Background And Aim: Visual data from images is essential for many medical diagnoses. This study evaluates the performance of multimodal Large Language Models (LLMs) in integrating textual and visual information for diagnostic purposes.
Methods: We tested GPT-4o and Claude Sonnet 3.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!