About

Charles E Kahn Jr., MD, MS, FACR, is a Professor of Radiology at the Hospital of the University of Pennsylvania. He is an active member of the medical staff in the Department of Radiology at Chester County Hospital, Penn Presbyterian Medical Center, and Pennsylvania Hospital. Dr. Kahn serves as the Vice Chair of the Department of Radiology at the University of Pennsylvania. His professional focus includes radiology and medical imaging, with involvement in academic and clinical activities at the University of Pennsylvania.

Research topics

• Political Science
• Medicine
• Medical emergency

Selected publications

• 2025 Manuscript Reviewers: A Note of Thanks

  Radiology Artificial Intelligence · 2026-03-01

  articleSenior author
  PublisherDOI

• ROADMAP: An Ontology of Medical AI Models and Datasets

  Radiology Artificial Intelligence · 2026-03-11 · 2 citations

  articleSenior author

  This work introduces ROADMAP (Radiology Ontology of AI Datasets, Models and Projects), an ontology that standardizes metadata for artificial intelligence (AI) models, datasets, and projects, enabling interoperable description, discovery, and transparent use of AI resources.

  PublisherDOI

• Microstructural and diffusion tensor imaging of clozapine for treatment-resistant schizophrenia

  Progress in Neuro-Psychopharmacology and Biological Psychiatry · 2026-04-01

  articleOpen access

  BACKGROUND: Clozapine (CLZ) demonstrates superior efficacy for treatment-resistant schizophrenia (TRS), but mechanisms underlying its effects remain unknown. Pathophysiologic links between cortical regions and the basal ganglia (BG) characterize schizophrenia and are implicated in the mechanism of CLZ's action. Here, we examined CLZ's efficacy with diffusion weighted imaging (DWI) to examine microstructural and white matter-related measures within and between cortical and BG regions. METHODS: Twenty-six participants with TRS and moderate-to-severe psychosis underwent DWI scanning while starting CLZ, and nineteen were re-scanned after twelve weeks of treatment. Symptoms across treatment were measured via the Brief Psychiatric Rating Scale. DWI scans were processed to derive an array of microstructural measures in frontal and BG gray matter parcels and white matter-related measures in corticostriatal tracts. Exploratory analyses linked results with published functional connectivity findings. RESULTS: We found significant links between CLZ response and increased mean kurtosis (MK) in the left dorsolateral putamen, left ventral caudate, and left globus pallidus. Additionally, significant relationships between striatal segments of corticostriatal white matter tracts and CLZ response were observed, including increased MK, decreased axial diffusivity, and decreased fractional anisotropy. Exploratory findings linked changes in BG microstructure with published corticostriatal connectivity findings. CONCLUSION: Our results implicate microstructural changes within gray matter regions of BG and white matter changes within the striatum as mechanisms underlying CLZ treatment. These findings further elucidate CLZ's mechanism of action and warrant further analyses that explore pharmacologic effects at the microstructural level.

  PublisherDOI

• Reporting checklist for foundation and large language models in medical research (REFINE): an international consensus guideline

  Diagnostic and Interventional Radiology · 2026-02-26 · 3 citations

  articleOpen access

  PURPOSE: To develop the REporting checklist for FoundatIon and large laNguagE models (REFINE), an international reporting guideline for transparent and reproducible reporting of foundation model (FM) and large language model (LLM) studies in medical research, including imaging artificial intelligence (AI) applications. METHODS: The protocol was prespecified and publicly archived. A modified Delphi process was conducted to establish reporting standards for unimodal and multimodal FM and LLM applications involving text, imaging, and structured data. The steering committee coordinated protocol development, expert recruitment, all Delphi rounds, and the harmonization phase. Decisions were made based on predefined consensus thresholds. In Rounds 1 and 2, structured ratings and free-text feedback informed iterative revisions. In the post-Delphi harmonization phase, terminology was standardized, and detailed reporting instructions were finalized. RESULTS: The REFINE development group comprised 57 contributors from 17 countries, and 54 panelists from 16 countries completed Rounds 1 and 2. The harmonization phase was completed by three expert panelists and the steering committee. The entire process produced a 44-item, six-section framework with standardized terminology and detailed reporting instructions, supported by an online platform for practical use (https://refinechecklist.github.io/refine/checklist.html). CONCLUSION: The REFINE provides a comprehensive, consensus-based reporting standard for medical FM and LLM research, including imaging AI studies. The online version facilitates practical implementation. CLINICAL SIGNIFICANCE: The REFINE enables transparent, comparable, and reproducible reporting of FM and LLM studies, supporting reliable evidence synthesis in medical and imaging-focused AI studies.

  PublisherOA PDFDOI

• Large Language Model–Generated Expansion of the RadLex Ontology: Application to Multinational Datasets of Chest CT Reports

  American Journal of Roentgenology · 2026-01-14

  article

  The LLM-based approach provides a practical and scalable solution for expanding radiology ontologies while maintaining semantic alignment; the method can aid real-world natural language processing applications.

  PublisherDOI

• Hepatic and abdominal adiposity in type 2 diabetes as assessed with machine learning on computed tomography scans

  Diabetes Obesity and Metabolism · 2026-02-18

  articleOpen access

  AIMS: The combined assessment of multiple abdominal imaging traits in relation to type 2 diabetes remains incompletely characterised. The study examines these relationships on computed tomography (CT) scans from a large-scale, racially diverse, disease-focused medical biobank. MATERIALS AND METHODS: Deep learning algorithms were applied to patients with abdominal CT scans in the Penn Medicine BioBank to quantify image-derived phenotypes, including spleen-hepatic attenuation difference (SHAD) for hepatic steatosis (HS), liver and spleen volumes (SV), abdominal visceral and subcutaneous adipose tissue (VAT and SAT, respectively) and visceral-to-subcutaneous ratio (VSR). One thousand five hundred and ninety-four patients (62 years, 49.4% male, 59.3% White), comprising 950 nondiabetics and 644 diabetics, were included in analysis with diabetes status determined by a 6.5% haemoglobin A1c cutoff. RESULTS: ) than nondiabetics. In multivariate analyses adjusting for age, sex, race and body mass index (BMI), diabetes was independently associated with SHAD (odds ratios [OR] 1.04, 95% confidence interval [1.02-1.05]), SV (OR 4.53 [1.89-10.99]) and VSR (OR 2.87, [1.96-4.20]). Combined regression analysis showed no relationship between splenomegaly and type 2 diabetes once controlling for hepatic factors (OR 1.08, [0.95-1.23]), but uncovered a stronger VSR correlation (OR 1.40, [1.20-1.63]) than BMI (OR 1.14, [1.01-1.29]). CONCLUSIONS: Hepatic steatosis, hepatomegaly and visceral adiposity on CT are associated with type 2 diabetes. Hepatic changes may influence spleen size effects on diabetes. VSR can serve as an alternative to traditional obesity metrics to accurately reflect diabetes risk.

  PublisherOA PDFDOI

• Metrics for Artificial Intelligence in Medicine: A Reference Resource

  Radiology Artificial Intelligence · 2026-03-11 · 2 citations

  articleSenior authorCorresponding

  A comprehensive, machine-interpretable taxonomy of artificial intelligence (AI) performance metrics provides a shared vocabulary and structured foundation to facilitate rigorous, transparent, and responsible evaluation of medical AI systems.

  PublisherDOI

• Editor’s Recognition Awards

  Radiology Artificial Intelligence · 2026-03-01

  article1st authorCorresponding
  PublisherDOI

• Using a Vision-Language Model to Generate Visual Abstracts for Radiology Journals

  Radiology · 2025-09-01 · 2 citations

  articleOpen access

  Vision-language models are not yet suitable for fully autonomous publication but can provide first drafts that, when combined with human–artificial intelligence codevelopment, may enhance visual abstract production efficiency and quality.

  PublisherDOI

• Editor’s Recognition Awards

  Radiology Artificial Intelligence · 2025-03-01

  article1st authorCorresponding
  PublisherDOI

Frequent coauthors

• Kahn Ce

  186 shared

• Carl T. Wittwer

  University of Utah

  64 shared

• Gregory Tsongalis

  64 shared

• Greg Miller

  West Virginia University

  64 shared

• David E. Bruns

  64 shared

• Yi‐Ju Li

  64 shared

• Rossa W. K. Chiu

  Prince of Wales Hospital

  64 shared

• Edwin Ullman

  Virginia Commonwealth University

  64 shared

Labs

• Charles E Kahn LabPI

Education

• MS, Computer Sciences

  University of Wisconsin Madison

  2003

• MD, College of Medicine

  University of Illinois at Chicago

  1985

• BA, Mathematics

  University of Wisconsin Madison

  1981