Resection and whole brain radiotherapy (WBRT) are the standards of care for the treatment of patients with brain metastases (BM) but are often associated with cognitive side effects. Stereotactic radiosurgery (SRS) involves a more targeted treatment approach and has been shown to avoid the side effects associated with WBRT. However, SRS requires precise identification and delineation of BM. While many AI algorithms have been developed for this purpose, their clinical adoption has been limited due to poor model performance in the clinical setting. Major reasons for non-generalizable algorithms are the limitations in the datasets used for training the AI network. The purpose of this study was to create a large, heterogenous, annotated BM dataset for training and validation of AI models to improve generalizability. We present a BM dataset of 200 patients with pretreatment T1, T1 post-contrast, T2, and FLAIR MR images. The dataset includes contrast-enhancing and necrotic 3D segmentations on T1 post-contrast and whole tumor (including peritumoral edema) 3D segmentations on FLAIR. Our dataset contains 975 contrast-enhancing lesions, many of which are sub centimeter, along with clinical and imaging feature information. We used a streamlined approach to database-building leveraging a PACS-integrated segmentation workflow.
@article{arxiv.2309.05053,
title = {A Large Open Access Dataset of Brain Metastasis 3D Segmentations with Clinical and Imaging Feature Information},
author = {Divya Ramakrishnan and Leon Jekel and Saahil Chadha and Anastasia Janas and Harrison Moy and Nazanin Maleki and Matthew Sala and Manpreet Kaur and Gabriel Cassinelli Petersen and Sara Merkaj and Marc von Reppert and Ujjwal Baid and Spyridon Bakas and Claudia Kirsch and Melissa Davis and Khaled Bousabarah and Wolfgang Holler and MingDe Lin and Malte Westerhoff and Sanjay Aneja and Fatima Memon and Mariam S. Aboian},
journal= {arXiv preprint arXiv:2309.05053},
year = {2023}
}