Saved in:
Bibliographic Details
Main Authors: Tankel, Idan, Mazor, Nir, Brada, Rafi, LeBedis, Christina, ben-Yosef, Guy
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.14732
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914470429720576
author Tankel, Idan
Mazor, Nir
Brada, Rafi
LeBedis, Christina
ben-Yosef, Guy
author_facet Tankel, Idan
Mazor, Nir
Brada, Rafi
LeBedis, Christina
ben-Yosef, Guy
contents Incidental findings in CT scans, though often benign, can have significant clinical implications and should be reported following established guidelines. Traditional manual inspection by radiologists is time-consuming and variable. This paper proposes a novel framework that leverages large language models (LLMs) and foundational vision-language models (VLMs) in a plan-and-execute agentic approach to improve the efficiency and precision of incidental findings detection, classification, and reporting for abdominal CT scans. Given medical guidelines for abdominal organs, the process of managing incidental findings is automated through a planner-executor framework. The planner, based on LLM, generates Python scripts using predefined base functions, while the executor runs these scripts to perform the necessary checks and detections, via VLMs, segmentation models, and image processing subroutines. We demonstrate the effectiveness of our approach through experiments on a CT abdominal benchmark for three organs, in a fully automatic end-to-end manner. Our results show that the proposed framework outperforms existing pure VLM-based approaches in terms of accuracy and efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2512_14732
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle INFORM-CT: INtegrating LLMs and VLMs FOR Incidental Findings Management in Abdominal CT
Tankel, Idan
Mazor, Nir
Brada, Rafi
LeBedis, Christina
ben-Yosef, Guy
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Image and Video Processing
Incidental findings in CT scans, though often benign, can have significant clinical implications and should be reported following established guidelines. Traditional manual inspection by radiologists is time-consuming and variable. This paper proposes a novel framework that leverages large language models (LLMs) and foundational vision-language models (VLMs) in a plan-and-execute agentic approach to improve the efficiency and precision of incidental findings detection, classification, and reporting for abdominal CT scans. Given medical guidelines for abdominal organs, the process of managing incidental findings is automated through a planner-executor framework. The planner, based on LLM, generates Python scripts using predefined base functions, while the executor runs these scripts to perform the necessary checks and detections, via VLMs, segmentation models, and image processing subroutines. We demonstrate the effectiveness of our approach through experiments on a CT abdominal benchmark for three organs, in a fully automatic end-to-end manner. Our results show that the proposed framework outperforms existing pure VLM-based approaches in terms of accuracy and efficiency.
title INFORM-CT: INtegrating LLMs and VLMs FOR Incidental Findings Management in Abdominal CT
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2512.14732