Salvato in:
Dettagli Bibliografici
Autori principali: Nguyen, Cong Huy, Nguyen, Son Dinh, Li, Guanlin, Nguyen, Tuan Dung, Sankaran, Aditya Narayan, Thong, Mai Huy, Nguyen, Thanh Trung, Son, Mai Hong, Farahbakhsh, Reza, Nguyen, Phi Le, Crespi, Noel
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.18145
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909047541727232
author Nguyen, Cong Huy
Nguyen, Son Dinh
Li, Guanlin
Nguyen, Tuan Dung
Sankaran, Aditya Narayan
Thong, Mai Huy
Nguyen, Thanh Trung
Son, Mai Hong
Farahbakhsh, Reza
Nguyen, Phi Le
Crespi, Noel
author_facet Nguyen, Cong Huy
Nguyen, Son Dinh
Li, Guanlin
Nguyen, Tuan Dung
Sankaran, Aditya Narayan
Thong, Mai Huy
Nguyen, Thanh Trung
Son, Mai Hong
Farahbakhsh, Reza
Nguyen, Phi Le
Crespi, Noel
contents Automated medical report generation for 3D PET/CT imaging is fundamentally challenged by the high-dimensional nature of volumetric data and a critical scarcity of annotated datasets, particularly for low-resource languages. Current black-box methods map whole volumes to reports, ignoring the clinical workflow of analyzing localized Regions of Interest (RoIs) to derive diagnostic conclusions. In this paper, we bridge this gap by introducing VietPET-RoI, the first large-scale 3D PET/CT dataset with fine-grained RoI annotation for a low-resource language, comprising 600 PET/CT samples and 1,960 manually annotated RoIs, paired with corresponding clinical reports. Furthermore, to demonstrate the utility of this dataset, we propose HiRRA, a novel framework that mimics the professional radiologist diagnostic workflow by employing graph-based relational modules to capture dependencies between RoI attributes. This approach shifts from global pattern matching toward localized clinical findings. Additionally, we introduce new clinical evaluation metrics, namely RoI Coverage and RoI Quality Index, that measure both RoI localization accuracy and attribute description fidelity using LLM-based extraction. Extensive evaluation demonstrates that our framework achieves SOTA performance, surpassing existing models by 19.7% in BLEU and 4.7% in ROUGE-L, while achieving a remarkable 45.8% improvement in clinical metrics, indicating enhanced clinical reliability and reduced hallucination. Our code and dataset are available on GitHub.
format Preprint
id arxiv_https___arxiv_org_abs_2604_18145
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Region-Grounded Report Generation for 3D Medical Imaging: A Fine-Grained Dataset and Graph-Enhanced Framework
Nguyen, Cong Huy
Nguyen, Son Dinh
Li, Guanlin
Nguyen, Tuan Dung
Sankaran, Aditya Narayan
Thong, Mai Huy
Nguyen, Thanh Trung
Son, Mai Hong
Farahbakhsh, Reza
Nguyen, Phi Le
Crespi, Noel
Computer Vision and Pattern Recognition
Artificial Intelligence
Automated medical report generation for 3D PET/CT imaging is fundamentally challenged by the high-dimensional nature of volumetric data and a critical scarcity of annotated datasets, particularly for low-resource languages. Current black-box methods map whole volumes to reports, ignoring the clinical workflow of analyzing localized Regions of Interest (RoIs) to derive diagnostic conclusions. In this paper, we bridge this gap by introducing VietPET-RoI, the first large-scale 3D PET/CT dataset with fine-grained RoI annotation for a low-resource language, comprising 600 PET/CT samples and 1,960 manually annotated RoIs, paired with corresponding clinical reports. Furthermore, to demonstrate the utility of this dataset, we propose HiRRA, a novel framework that mimics the professional radiologist diagnostic workflow by employing graph-based relational modules to capture dependencies between RoI attributes. This approach shifts from global pattern matching toward localized clinical findings. Additionally, we introduce new clinical evaluation metrics, namely RoI Coverage and RoI Quality Index, that measure both RoI localization accuracy and attribute description fidelity using LLM-based extraction. Extensive evaluation demonstrates that our framework achieves SOTA performance, surpassing existing models by 19.7% in BLEU and 4.7% in ROUGE-L, while achieving a remarkable 45.8% improvement in clinical metrics, indicating enhanced clinical reliability and reduced hallucination. Our code and dataset are available on GitHub.
title Region-Grounded Report Generation for 3D Medical Imaging: A Fine-Grained Dataset and Graph-Enhanced Framework
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2604.18145