An LLM-Based Active Assistant and Smart Manual for CT Imaging Workflows
Aliakbari Mamaghani Z, Vorberg L, Maier A, Katzmann A, Taubmann O (2026)
Publication Type: Conference contribution
Publication year: 2026
Journal
Publisher: Springer Science and Business Media Deutschland GmbH
Book Volume: 16146 LNCS
Pages Range: 45-52
Conference Proceedings Title: Lecture Notes in Computer Science
Event location: Daejeon
ISBN: 9783032075017
DOI: 10.1007/978-3-032-07502-4_6
Abstract
Performing medical imaging exams ideally requires technologists to have deep clinical knowledge and technical expertise to operate scanners effectively and efficiently. However, there is a shortage of highly qualified workforce in radiology while patient volumes are rising steadily. Therefore, intelligent assistance is needed to streamline workflow adjustments and reduce manual workload. This study presents a Large Language Model (LLM)-based chatbot to assist clinical staff in Computed Tomography (CT) protocol and postprocessing setup by integrating device-specific information and patient-specific clinical data. As an active assistant integrated in a scan workflow prototype, it provides responses with actionable links that allow users to modify protocol settings directly. At the same time, it acts as a smart manual enhanced with patient-specific context, referencing and linking to both official device documentation as well as clinical indication and prior diagnostic reports. This is realized with an advanced Retrieval Augmented Generation (RAG) with pre- and post-retrieval strategies to improve contextual relevance. An LLM-based evaluation was employed to assess performance. We achieved 95.0% alignment with predefined expectations using GPT-4o mini, and 98.3% with GPT-4o. To evaluate the effect of the applied techniques, an ablation study was conducted. Omitting few-shot examples and instruction-based prompting reduced expectation alignment to 71.4% and 60.5%, respectively. When both were removed, it decreased to 55.0%. The findings underscore the effectiveness of prompt engineering in guiding LLMs to produce accurate, clinically relevant outputs in the correct format.
Authors with CRIS profile
Linda Vorberg
Lehrstuhl für Informatik 5 (Mustererkennung)
Andreas Maier
Lehrstuhl für Informatik 5 (Mustererkennung)
How to cite
APA:
Aliakbari Mamaghani, Z., Vorberg, L., Maier, A., Katzmann, A., & Taubmann, O. (2026). An LLM-Based Active Assistant and Smart Manual for CT Imaging Workflows. In Hien Van Nguyen, Akash Awasthi, Vishal M. Patel, Ngan Le, Yuyin Zhou, Sheng Liu, S. Kevin Zhou (Eds.), Lecture Notes in Computer Science (pp. 45-52). Daejeon, KR: Springer Science and Business Media Deutschland GmbH.
MLA:
Aliakbari Mamaghani, Zeinab, et al. "An LLM-Based Active Assistant and Smart Manual for CT Imaging Workflows." Proceedings of the 1st International Workshop on Emerging LLM/LMM Applications in Medical Imaging, ELAMI 2025, Held in Conjunction with the 28th International conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2025, Daejeon Ed. Hien Van Nguyen, Akash Awasthi, Vishal M. Patel, Ngan Le, Yuyin Zhou, Sheng Liu, S. Kevin Zhou, Springer Science and Business Media Deutschland GmbH, 2026. 45-52.
BibTeX: Download