Philipp Prucker
YOU?
Author Swipe
View article: Evaluation of commercial AI algorithms for the detection of fractures, effusions, and dislocations on real-world clinical data: A prospective registry study
Evaluation of commercial AI algorithms for the detection of fractures, effusions, and dislocations on real-world clinical data: A prospective registry study Open
Current tools should be used as adjuncts rather than replacements for radiologists and reporting radiographers. Multicenter validation and more diverse training data are necessary to improve generalizability and robustness.
View article: Real-world clinical impact of three commercial AI algorithms on musculoskeletal radiography interpretation: A prospective crossover reader study
Real-world clinical impact of three commercial AI algorithms on musculoskeletal radiography interpretation: A prospective crossover reader study Open
In a real-world clinical setting, AI-assisted interpretation of musculoskeletal radiographs reduced reading time and increased diagnostic confidence without materially affecting diagnostic performance. These findings support AI assistance …
View article: Privacy-Preserving Generation of Structured Lymphoma Progression Reports from Cross-sectional Imaging: A Comparative Analysis of Llama 3.3 and Llama 4
Privacy-Preserving Generation of Structured Lymphoma Progression Reports from Cross-sectional Imaging: A Comparative Analysis of Llama 3.3 and Llama 4 Open
Efficient processing of radiology reports for monitoring disease progression is crucial in oncology. Although large language models (LLMs) show promise in extracting structured information from medical reports, privacy concerns limit their…
View article: PARROT: An Open Multilingual Radiology Reports Dataset
PARROT: An Open Multilingual Radiology Reports Dataset Open
Rationale and Objectives: To develop and validate PARROT (Polyglottal Annotated Radiology Reports for Open Testing), a large, multicentric, open-access dataset of fictional radiology reports spanning multiple languages for testing natural …
View article: Performance of open-source and proprietary large language models in generating patient-friendly radiology chest CT reports
Performance of open-source and proprietary large language models in generating patient-friendly radiology chest CT reports Open
Llama-3-70b shows strong potential in generating quality, patient-friendly radiology reports, challenging proprietary models. With further adaptation, open-source LLMs could advance patient-friendly reporting technology.
View article: Evaluation of a Retrieval-Augmented Generation-Powered Chatbot for Pre-CT Informed Consent: a Prospective Comparative Study
Evaluation of a Retrieval-Augmented Generation-Powered Chatbot for Pre-CT Informed Consent: a Prospective Comparative Study Open
This study aims to investigate the feasibility, usability, and effectiveness of a Retrieval-Augmented Generation (RAG)-powered Patient Information Assistant (PIA) chatbot for pre-CT information counseling compared to the standard physician…
View article: Autonomous medical evaluation for guideline adherence of large language models
Autonomous medical evaluation for guideline adherence of large language models Open
View article: Multilingual feasibility of GPT-4o for automated Voice-to-Text CT and MRI report transcription
Multilingual feasibility of GPT-4o for automated Voice-to-Text CT and MRI report transcription Open
This study demonstrates the potential of GPT-4o for multilingual transcription of radiology reports, effectively handling both English and German with minimal errors and high semantic understanding. Future research should compare GPT-4o wi…
View article: Large language models for structured reporting in radiology: past, present, and future
Large language models for structured reporting in radiology: past, present, and future Open
View article: Reproducibility of CT-based opportunistic vertebral volumetric bone mineral density measurements from an automated segmentation framework
Reproducibility of CT-based opportunistic vertebral volumetric bone mineral density measurements from an automated segmentation framework Open
View article: LST-AI: A deep learning ensemble for accurate MS lesion segmentation
LST-AI: A deep learning ensemble for accurate MS lesion segmentation Open
View article: LST-AI: a Deep Learning Ensemble for Accurate MS Lesion Segmentation
LST-AI: a Deep Learning Ensemble for Accurate MS Lesion Segmentation Open
Automated segmentation of brain white matter lesions is crucial for both clinical assessment and scientific research in multiple sclerosis (MS). Over a decade ago, we introduced an engineered lesion segmentation tool, LST. While recent les…
View article: Long-term reproducibility of opportunistically assessed vertebral bone mineral density and texture features in routine clinical multi-detector computed tomography using an automated segmentation framework
Long-term reproducibility of opportunistically assessed vertebral bone mineral density and texture features in routine clinical multi-detector computed tomography using an automated segmentation framework Open
Opportunistic assessment of texture features in a single scanner environment using the presented CNN-based framework yields substantial reproducibility, outperforming vBMD reproducibility. Lowest scan-rescan variability was found for highe…