A large open access dataset of brain metastasis 3D segmentations on MRI with clinical and imaging information.

Autor: Ramakrishnan D; Yale School of Medicine, Department of Radiology and Biomedical Imaging, New Haven, CT, USA. divya.ramakrishnan@yale.edu., Jekel L; Yale School of Medicine, Department of Radiology and Biomedical Imaging, New Haven, CT, USA.; University of Essen School of Medicine, Essen, Germany., Chadha S; Yale School of Medicine, Department of Radiology and Biomedical Imaging, New Haven, CT, USA., Janas A; Yale School of Medicine, Department of Radiology and Biomedical Imaging, New Haven, CT, USA.; Charité University School of Medicine, Berlin, Germany., Moy H; Yale School of Medicine, Department of Radiology and Biomedical Imaging, New Haven, CT, USA.; Wesleyan University, Middletown, CT, USA., Maleki N; Yale School of Medicine, Department of Radiology and Biomedical Imaging, New Haven, CT, USA., Sala M; Yale School of Medicine, Department of Radiology and Biomedical Imaging, New Haven, CT, USA.; Tulane University School of Medicine, New Orleans, LA, USA., Kaur M; Yale School of Medicine, Department of Radiology and Biomedical Imaging, New Haven, CT, USA.; Ludwig Maximilian University School of Medicine, Munich, Germany., Petersen GC; Yale School of Medicine, Department of Radiology and Biomedical Imaging, New Haven, CT, USA.; University of Göttingen School of Medicine, Göttingen, Germany., Merkaj S; Yale School of Medicine, Department of Radiology and Biomedical Imaging, New Haven, CT, USA.; Ulm University School of Medicine, Ulm, Germany., von Reppert M; Yale School of Medicine, Department of Radiology and Biomedical Imaging, New Haven, CT, USA.; University of Leipzig School of Medicine, Leipzig, Germany., Baid U; Division of Computational Pathology, Department of Pathology & Laboratory Medicine, Indiana University School of Medicine, Indianapolis, IN, USA.; Department of Radiology and Department of Pathology & Laboratory Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA., Bakas S; Division of Computational Pathology, Department of Pathology & Laboratory Medicine, Indiana University School of Medicine, Indianapolis, IN, USA.; Department of Radiology and Department of Pathology & Laboratory Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA., Kirsch C; Yale School of Medicine, Department of Radiology and Biomedical Imaging, New Haven, CT, USA.; School of Clinical Dentistry, University of Sheffield, Sheffield, England.; Diagnostic, Molecular and Interventional Radiology, Biomedical Engineering Imaging, Mount Sinai Hospital, New York City, NY, USA., Davis M; Yale School of Medicine, Department of Radiology and Biomedical Imaging, New Haven, CT, USA., Bousabarah K; Visage Imaging, GmbH, Berlin, Germany., Holler W; Visage Imaging, GmbH, Berlin, Germany., Lin M; Yale School of Medicine, Department of Radiology and Biomedical Imaging, New Haven, CT, USA.; Visage Imaging, Inc., San Diego, CA, USA., Westerhoff M; Visage Imaging, GmbH, Berlin, Germany., Aneja S; Department of Therapeutic Radiology, Yale School of Medicine, New Haven, CT, USA.; Center for Outcomes Research and Evaluation (CORE), Yale School of Medicine, New Haven, CT, USA., Memon F; Yale School of Medicine, Department of Radiology and Biomedical Imaging, New Haven, CT, USA., Aboian MS; Yale School of Medicine, Department of Radiology and Biomedical Imaging, New Haven, CT, USA.
Jazyk: angličtina
Zdroj: Scientific data [Sci Data] 2024 Feb 29; Vol. 11 (1), pp. 254. Date of Electronic Publication: 2024 Feb 29.
DOI: 10.1038/s41597-024-03021-9
Abstrakt: Resection and whole brain radiotherapy (WBRT) are standard treatments for brain metastases (BM) but are associated with cognitive side effects. Stereotactic radiosurgery (SRS) uses a targeted approach with less side effects than WBRT. SRS requires precise identification and delineation of BM. While artificial intelligence (AI) algorithms have been developed for this, their clinical adoption is limited due to poor model performance in the clinical setting. The limitations of algorithms are often due to the quality of 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. 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 peritumoral edema 3D segmentations on FLAIR. Our dataset contains 975 contrast-enhancing lesions, many of which are sub centimeter, along with clinical and imaging information. We used a streamlined approach to database-building through a PACS-integrated segmentation workflow.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz: