Taehee Lee

Signal, not noise: learning to measure emphysema beyond the −950 HU threshold

Hongseok Ko, Jiyoung Song, Taehee Lee

kr (code pays fourni par la source)

Do Accuracy Gains Reflect Genuine Visual Understanding? A Multi-Model Evaluation of Vision–Language Models in Thoracic Imaging

Jiyoung Song, Won Gi Jeong, Hongseok Ko, Eui Jin Hwang et autres

kr (code pays fourni par la source)

Determinants of Reader-LLM Interaction in Thoracic Radiology: Impact of Model Confidence and Reader Expertise

Jiyoung Song, Won Gi Jeong, Dae Hee Han, Hongseok Ko et autres

= .007) were protective, reducing acceptance of incorrect suggestions. Conclusion Successful reader-LLM collaboration is associated with model confidence and reader expertise, with rationale quality facilitating correct advice uptake but increasing overreliance on incorrect suggestions. © RSNA, 2026

kr, us, th, my (code pays fourni par la source)

Conformations of Linker Histone H1 Bound to Nucleosome Arrays

Bo Yuan, Subhra Kanti Das, Weilin Wang, Gillian S. Camacho et autres

• The CTD of linker histone H1 is extended when bound to a nucleosome array. • Linker histone H1 CTD is dynamic when bound to a nucleosome array. • H1 CTD adopts a heterogeneous ensemble of conformations in a nucleosome array. • …

us (code pays fourni par la source)

Decoupling Visual Parsing and Diagnostic Reasoning for Vision-Language Models (GPT-4o and GPT-5): Analysis Using Thoracic Imaging Quiz Cases

Dae Hee Han, Eui Jin Hwang, Soon Ho Yoon, Hyungjin Kim et autres

Background: Vision-language models (VLMs) have potential to identify findings on radiologic imaging (i.e., visual parsing) and translate findings into diagnoses (i.e., diagnostic reasoning). Current VLMs have shown insufficient performance to support clinical integration.

kr, us (code pays fourni par la source)

P2.15.04 End-Of-Life Systemic Therapy and Survival in Metastatic Lung Cancer: A Territory-Wide Real-World Studyof 24,608 Patients

S. Wang, Hong Zhou, Taehee Lee, Zhimao Ye et autres

hk, cn, us (code pays fourni par la source)

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

Taehee Lee, Sooyong Chae, Seong Ho Park, Charles E. Kahn et autres

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.

kr, us (code pays fourni par la source)

Evaluation of Vision-Language Models for Detection and Deidentification of Medical Images with Burned-In Protected Health Information

Taehee Lee, Hyungjin Kim, Seong Ho Park, Sooyong Chae et autres

OpenAI’s ChatGPT-4o achieved more than 95% accuracy in detecting burned-in protected health information and obscured it on 81% of medical images, suggesting its potential to improve data privacy and workflow efficiency.

kr (code pays fourni par la source)

Availability and transparency of artificial intelligence models in radiology: a meta-research study

Taehee Lee, Jong Hyuk Lee, Soon Ho Yoon, Seong Ho Park et autres

OBJECTIVES: This meta-research study explored the availability of artificial intelligence (AI) models from development studies published in leading radiology journals in 2022, with availability defined as the transparent reporting of relevant technical details, such as model architecture and weights, necessary for independent …

kr, Éthiopie, pr (code pays fourni par la source)

Diagnostic Delays, Worse Prognosis: The Importance of Prompt Follow-up in Stage I Lung Cancer

Chang Min Park, Taehee Lee

N

kr (code pays fourni par la source)

Editorial Comment: Enhancing Radiologist Sensitivity for Incidental Pulmonary Embolism Detection With Artificial Intelligence—A Prospective Validation Study

Taehee Lee

kr (code pays fourni par la source)

Prognostic value of lateral lymph node metastasis in pretreatment MRI for rectal cancer in patients undergoing neoadjuvant chemoradiation followed by surgical resection without lateral lymph node dissection: A systemic review and meta-analysis

Taehee Lee, Natally de Souza Maciel Rocha Horvat, Marc Jeffrey Gollub, Julio García‐Aguilar et autres

kr, us (code pays fourni par la source)