_version_ 1866915578391822336
author Baharoon, Mohammed
Luo, Luyang
Moritz, Michael
Kumar, Abhinav
Kim, Sung Eun
Zhang, Xiaoman
Zhu, Miao
Alabbad, Mahmoud Hussain
Alhazmi, Maha Sbayel
Mistry, Neel P.
Bijnens, Lucas
Kleinschmidt, Kent Ryan
Chrisler, Brady
Suryadevara, Sathvik
Jaliparthi, Sri Sai Dinesh
Prudlo, Noah Michael
Marino, Mark David
Palacio, Jeremy
Akula, Rithvik
Zhou, Di
Zhou, Hong-Yu
Hamamci, Ibrahim Ethem
Adams, Scott J.
AlOmaish, Hassan Rayhan
Rajpurkar, Pranav
author_facet Baharoon, Mohammed
Luo, Luyang
Moritz, Michael
Kumar, Abhinav
Kim, Sung Eun
Zhang, Xiaoman
Zhu, Miao
Alabbad, Mahmoud Hussain
Alhazmi, Maha Sbayel
Mistry, Neel P.
Bijnens, Lucas
Kleinschmidt, Kent Ryan
Chrisler, Brady
Suryadevara, Sathvik
Jaliparthi, Sri Sai Dinesh
Prudlo, Noah Michael
Marino, Mark David
Palacio, Jeremy
Akula, Rithvik
Zhou, Di
Zhou, Hong-Yu
Hamamci, Ibrahim Ethem
Adams, Scott J.
AlOmaish, Hassan Rayhan
Rajpurkar, Pranav
contents We introduce ReXGroundingCT, the first publicly available dataset linking free-text findings to pixel-level 3D segmentations in chest CT scans. The dataset includes 3,142 non-contrast chest CT scans paired with standardized radiology reports from CT-RATE. Construction followed a structured three-stage pipeline. First, GPT-4 was used to extract and standardize findings, descriptors, and metadata from reports originally written in Turkish and machine-translated into English. Second, GPT-4o-mini categorized each finding into a hierarchical ontology of lung and pleural abnormalities. Third, 3D annotations were produced for all CT volumes: the training set was quality-assured by board-certified radiologists, and the validation and test sets were fully annotated by board-certified radiologists. Additionally, a complementary chain-of-thought dataset was created to provide step-by-step hierarchical anatomical reasoning for localizing findings within the CT volume, using GPT-4o and localization coordinates derived from organ segmentation models. ReXGroundingCT contains 16,301 annotated entities across 8,028 text-to-3D-segmentation pairs, covering diverse radiological patterns from 3,142 non-contrast CT scans. About 79% of findings are focal abnormalities and 21% are non-focal. The dataset includes a public validation set of 50 cases and a private test set of 100 cases, both annotated by board-certified radiologists. The dataset establishes a foundation for enabling free-text finding segmentation and grounded radiology report generation in CT imaging. Model performance on the private test set is hosted on a public leaderboard at https://rexrank.ai/ReXGroundingCT. The dataset is available at https://huggingface.co/datasets/rajpurkarlab/ReXGroundingCT.
format Preprint
id arxiv_https___arxiv_org_abs_2507_22030
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ReXGroundingCT: A 3D Chest CT Dataset for Segmentation of Findings from Free-Text Reports
Baharoon, Mohammed
Luo, Luyang
Moritz, Michael
Kumar, Abhinav
Kim, Sung Eun
Zhang, Xiaoman
Zhu, Miao
Alabbad, Mahmoud Hussain
Alhazmi, Maha Sbayel
Mistry, Neel P.
Bijnens, Lucas
Kleinschmidt, Kent Ryan
Chrisler, Brady
Suryadevara, Sathvik
Jaliparthi, Sri Sai Dinesh
Prudlo, Noah Michael
Marino, Mark David
Palacio, Jeremy
Akula, Rithvik
Zhou, Di
Zhou, Hong-Yu
Hamamci, Ibrahim Ethem
Adams, Scott J.
AlOmaish, Hassan Rayhan
Rajpurkar, Pranav
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
We introduce ReXGroundingCT, the first publicly available dataset linking free-text findings to pixel-level 3D segmentations in chest CT scans. The dataset includes 3,142 non-contrast chest CT scans paired with standardized radiology reports from CT-RATE. Construction followed a structured three-stage pipeline. First, GPT-4 was used to extract and standardize findings, descriptors, and metadata from reports originally written in Turkish and machine-translated into English. Second, GPT-4o-mini categorized each finding into a hierarchical ontology of lung and pleural abnormalities. Third, 3D annotations were produced for all CT volumes: the training set was quality-assured by board-certified radiologists, and the validation and test sets were fully annotated by board-certified radiologists. Additionally, a complementary chain-of-thought dataset was created to provide step-by-step hierarchical anatomical reasoning for localizing findings within the CT volume, using GPT-4o and localization coordinates derived from organ segmentation models. ReXGroundingCT contains 16,301 annotated entities across 8,028 text-to-3D-segmentation pairs, covering diverse radiological patterns from 3,142 non-contrast CT scans. About 79% of findings are focal abnormalities and 21% are non-focal. The dataset includes a public validation set of 50 cases and a private test set of 100 cases, both annotated by board-certified radiologists. The dataset establishes a foundation for enabling free-text finding segmentation and grounded radiology report generation in CT imaging. Model performance on the private test set is hosted on a public leaderboard at https://rexrank.ai/ReXGroundingCT. The dataset is available at https://huggingface.co/datasets/rajpurkarlab/ReXGroundingCT.
title ReXGroundingCT: A 3D Chest CT Dataset for Segmentation of Findings from Free-Text Reports
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.22030