The RSNA Abdominal Traumatic Injury CT (RATIC) Dataset

• Main Authors: Rudie, Jeffrey D, Lin, Hui-Ming, Ball, Robyn L, Jalal, Sabeena, Prevedello, Luciano M, Nicolaou, Savvas, Marinelli, Brett S, Flanders, Adam E, Magudia, Kirti, Shih, George, Davis, Melissa A, Mongan, John, Chang, Peter D, Berger, Ferco H, Hermans, Sebastiaan, Law, Meng, Richards, Tyler, Grunz, Jan-Peter, Kunz, Andreas Steven, Mathur, Shobhit, Galea-Soler, Sandro, Chung, Andrew D, Afat, Saif, Kuo, Chin-Chi, Aweidah, Layal, Campos, Ana Villanueva, Somasundaram, Arjuna, Tijmes, Felipe Antonio Sanchez, Jantarangkoon, Attaporn, Bittencourt, Leonardo Kayat, Brassil, Michael, Hajjami, Ayoub El, Dogan, Hakan, Becircic, Muris, Bharatkumar, Agrahara G, Farina, Eduardo Moreno Júdice de Mattos, Group, Dataset Curator, Group, Dataset Contributor, Group, Dataset Annotator, Colak, Errol
• Format: Journal Article
• Language: English
• Published: 29.05.2024
• Subjects: Computer Science - Computer Vision and Pattern Recognition
• DOI: 10.48550/arxiv.2405.19595

The RSNA Abdominal Traumatic Injury CT (RATIC) dataset is the largest publicly available collection of adult abdominal CT studies annotated for traumatic injuries. This dataset includes 4,274 studies from 23 institutions across 14 countries. The dataset is freely available for non-commercial use via Kaggle at https://www.kaggle.com/competitions/rsna-2023-abdominal-trauma-detection. Created for the RSNA 2023 Abdominal Trauma Detection competition, the dataset encourages the development of advanced machine learning models for detecting abdominal injuries on CT scans. The dataset encompasses detection and classification of traumatic injuries across multiple organs, including the liver, spleen, kidneys, bowel, and mesentery. Annotations were created by expert radiologists from the American Society of Emergency Radiology (ASER) and Society of Abdominal Radiology (SAR). The dataset is annotated at multiple levels, including the presence of injuries in three solid organs with injury grading, image-level annotations for active extravasations and bowel injury, and voxelwise segmentations of each of the potentially injured organs. With the release of this dataset, we hope to facilitate research and development in machine learning and abdominal trauma that can lead to improved patient care and outcomes.