Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.22768 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908991318130688 |
|---|---|
| author | Nowak, Sebastian Laß, Jann-Frederick Mesropyan, Narine Salam, Babak Piel, Nico Bahaaeldin, Mohammed Block, Wolfgang Sprinkart, Alois Martin Luetkens, Julian Alexander Wulff, Benjamin Isaak, Alexander |
| author_facet | Nowak, Sebastian Laß, Jann-Frederick Mesropyan, Narine Salam, Babak Piel, Nico Bahaaeldin, Mohammed Block, Wolfgang Sprinkart, Alois Martin Luetkens, Julian Alexander Wulff, Benjamin Isaak, Alexander |
| contents | Purpose: To design, implement, evaluate, and report on the regulatory requirements of a self-hosted LLM infrastructure for radiology adhering to the principle of least privilege, emphasizing technical feasibility, network isolation, and clinical utility.
Materials and Methods: The isolation-first, containerized LLM inference stack relies on strict network segmentation, host-enforced egress filtering, and active isolation monitoring preventing unauthorized external connectivity. An accompanying deployment package provides automated isolation and hardening tests. The system served the open-weights DeepSeek-R1 model via vLLM. In a one-week pilot phase, 22 residents and radiologists were free to use 10 predefined prompt-templates whenever they considered them useful in daily work. Afterward, they rated clinical utility and system stability on an 0-10 Likert scale and reported observed critical errors in model output.
Results: The applied institutional governance pathway achieved approval from clinic management, compliance, data protection and information security officers for processing unanonymized PHI. The system was rated stable and user friendly during the pilot. Source text-anchored tasks, such as report corrections or simplifications, and radiology guideline recommendations received the highest utility ratings, whereas open-ended conclusion generation based on findings resulted in the highest frequency of critical errors, such as clinically relevant hallucinations or omissions.
Conclusion: The proposed isolation-first on-premise architecture enabled overcoming regulatory borders, showed promising clinical utility in text-anchored tasks and is the current base to serve open-weights LLMs as an official service of a German University Hospital with over 10,000 employees. The deployment package were made publicly available (https://github.com/ukbonn/ukb-gpt). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_22768 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Secure On-Premise Deployment of Open-Weights Large Language Models in Radiology: An Isolation-First Architecture with Prospective Pilot Evaluation Nowak, Sebastian Laß, Jann-Frederick Mesropyan, Narine Salam, Babak Piel, Nico Bahaaeldin, Mohammed Block, Wolfgang Sprinkart, Alois Martin Luetkens, Julian Alexander Wulff, Benjamin Isaak, Alexander Computers and Society Computation and Language Purpose: To design, implement, evaluate, and report on the regulatory requirements of a self-hosted LLM infrastructure for radiology adhering to the principle of least privilege, emphasizing technical feasibility, network isolation, and clinical utility. Materials and Methods: The isolation-first, containerized LLM inference stack relies on strict network segmentation, host-enforced egress filtering, and active isolation monitoring preventing unauthorized external connectivity. An accompanying deployment package provides automated isolation and hardening tests. The system served the open-weights DeepSeek-R1 model via vLLM. In a one-week pilot phase, 22 residents and radiologists were free to use 10 predefined prompt-templates whenever they considered them useful in daily work. Afterward, they rated clinical utility and system stability on an 0-10 Likert scale and reported observed critical errors in model output. Results: The applied institutional governance pathway achieved approval from clinic management, compliance, data protection and information security officers for processing unanonymized PHI. The system was rated stable and user friendly during the pilot. Source text-anchored tasks, such as report corrections or simplifications, and radiology guideline recommendations received the highest utility ratings, whereas open-ended conclusion generation based on findings resulted in the highest frequency of critical errors, such as clinically relevant hallucinations or omissions. Conclusion: The proposed isolation-first on-premise architecture enabled overcoming regulatory borders, showed promising clinical utility in text-anchored tasks and is the current base to serve open-weights LLMs as an official service of a German University Hospital with over 10,000 employees. The deployment package were made publicly available (https://github.com/ukbonn/ukb-gpt). |
| title | Secure On-Premise Deployment of Open-Weights Large Language Models in Radiology: An Isolation-First Architecture with Prospective Pilot Evaluation |
| topic | Computers and Society Computation and Language |
| url | https://arxiv.org/abs/2604.22768 |