Combining Deep Learning and Radiomics for Automated, Objective, Comprehensive Bone Marrow Characterization From Whole-Body MRI: A Multicentric Feasibility Study

From the Divisions of ∗Radiology

†Medical Image Computing, German Cancer Research Center

‡Medical Faculty, University of Heidelberg, Heidelberg, Germany

§Department of Biomedical Engineering, Faculty of Electrical Engineering and Communication, Brno University of Technology, Brno, Czech Republic

∥Department of Diagnostic and Interventional Radiology, University Hospital Heidelberg

¶Department of Medicine V, Multiple Myeloma Section, University Hospital Heidelberg

#Division of Biostatistics, German Cancer Research Center, Heidelberg

∗∗Department of Diagnostic and Interventional Radiology, Experimental Radiology Section, University Hospital Ulm, Ulm

††Pattern Analysis and Learning Group, Department of Radiation Oncology, Heidelberg University Hospital

‡‡Heidelberg Institute of Radiation Oncology, National Center for Radiation Research in Oncology, Heidelberg, Germany

§§Department of Medicine, Roswell Park Comprehensive Cancer Center, Elm and Carlton Streets, Buffalo, NY

∥∥Institute for AI in Medicine, University Medicine Essen, Essen

¶¶National Center for Tumor Diseases, University Hospital Heidelberg, Heidelberg, Germany.

Received for publication February 15, 2022; and accepted for publication, after revision, April 16, 2022.

M.W. and A.K. equally contributed to the study. K.M.-H. and H.-P.S. equally contributed to the study.

Conflicts of interest and sources of funding: This study was supported by a grant from the Black Swan Research Initiative of the International Myeloma Foundation. This work was partially funded by the Helmholtz Association within the project “Trustworthy Federated Data Analytics” (funding number ZT-I-OO1 4), and partially funded by the Helmholtz Association within the project “Helmholtz Analytic Framework” (funding number ZT-I-OOO3).

Data availability statement: The data sets generated during and/or analyzed during the current study are not publicly available, but are available from the corresponding author on reasonable request, under the condition that all legal requirements for data transfer and data usage, as for example set by the general data protection regulation of the EU and the institutional review board, are fulfilled.

Correspondence to: Markus Wennmann, MD, Division of Radiology, German Cancer Research Center, Im Neuenheimer Feld 280, 69120 Heidelberg, Germany. E-mail: [email protected].

Supplemental digital contents are available for this article. Direct URL citations appear in the printed text and are provided in the HTML and PDF versions of this article on the journal’s Web site (www.investigativeradiology.com).

留言 (0)

沒有登入
gif