Related Experiment Video
Updated: Jul 29, 2025
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
Prediction of Bone Marrow Biopsy Results From MRI in Multiple Myeloma Patients Using Deep Learning and Radiomics
Markus Wennmann1, Wenlong Ming, Fabian Bauer
1From the Divisions of Radiology (M.W., F.B, C.U., M.G., H.T., L.T.R., N.S., F.T.K., D.B., J.K., H.-K.S., S.D.), and Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany (W.M., J.C., A.K., K.-C.K., M.G., R.O.F., K.M.-H., P.N.); State Key Laboratory of Bioelectronics, School of Biological Science and Medical Engineering, Southeast University, Nanjing, China (W.M.); Medical Faculty, University of Heidelberg, Heidelberg, Germany (F.B., C.U., N.S.); Department of Biomedical Engineering, Faculty of Electrical Engineering and Communication, Brno University of Technology, Brno, Czech Republic (J.C.); Diagnostic and Interventional Radiology, University Hospital Heidelberg (T.N., M.D., T.F.W.); Division of Biostatistics, German Cancer Research Center (DKFZ) (T.H.); Department of Medicine V, Multiple Myeloma Section (S.S., E.K.M., N.W., H.G.), and Institute of Human Genetics, University Hospital Heidelberg, Heidelberg (A.J.); Department of Diagnostic and Interventional Radiology, Experimental Radiology Section, University Hospital Ulm, Ulm (M.G.); Department of Diagnostic and Interventional Radiology With Nuclear Medicine, Thorax Clinic at Heidelberg University Hospital, Heidelberg (K.S.); Department of Diagnostic and Interventional Radiology (M.H., S.A.), and Department of Hematology, Oncology, and Immunology, University Hospital of Tuebingen, Tübingen (B.B.); Medical Clinic A (M.H.), and Department for Radiology, Hospital of Ludwigshafen, Ludwigshafen, Germany (J.H.); Department of Hematology, Oncology, and Palliative Care, St Josefs Hospital Hagen, Hagen (D.K.); Department of Hematology, Oncology, and Gastroenterology (U.G.), and Department of Radiology and Neuroradiology, Mönchengladbach (A.R.); Institute for AI in Medicine, University Medicine Essen, Essen (J.K.); Pattern Analysis and Learning Group, Department of Radiation Oncology, Heidelberg University Hospital (R.O.F., K.M.-H.); Heidelberg Institute of Radiation Oncology, National Center for Radiation Research in Oncology, Heidelberg, Germany (R.O.F.); Department of Medicine, Roswell Park Comprehensive Cancer Center, Buffalo, NY (J.H.); National Center for Tumor Diseases, University Hospital Heidelberg, Heidelberg, Germany (H.G., H.-P.S., K.M.-H., P.N.); German Cancer Consortium (DKTK), Partner Site Heidelberg, Heidelberg, Germany (P.N.).
Objectives:
In multiple myeloma and its precursor stages, plasma cell infiltration (PCI) and cytogenetic aberrations are important for staging, risk stratification, and response assessment. However, invasive bone marrow (BM) biopsies cannot be performed frequently and multifocally to assess the spatially heterogenous tumor tissue. Therefore, the goal of this study was to establish an automated framework to predict local BM biopsy results from magnetic resonance imaging (MRI).
Materials And Methods:
This retrospective multicentric study used data from center 1 for algorithm training and internal testing, and data from center 2 to 8 for external testing. An nnU-Net was trained for automated segmentation of pelvic BM from T1-weighted whole-body MRI. Radiomics features were extracted from these segmentations, and random forest models were trained to predict PCI and the presence or absence of cytogenetic aberrations. Pearson correlation coefficient and the area under the receiver operating characteristic were used to evaluate the prediction performance for PCI and cytogenetic aberrations, respectively.
Results:
A total of 672 MRIs from 512 patients (median age, 61 years; interquartile range, 53-67 years; 307 men) from 8 centers and 370 corresponding BM biopsies were included. The predicted PCI from the best model was significantly correlated ( P ≤ 0.01) to the actual PCI from biopsy in all internal and external test sets (internal test set: r = 0.71 [0.51, 0.83]; center 2, high-quality test set: r = 0.45 [0.12, 0.69]; center 2, other test set: r = 0.30 [0.07, 0.49]; multicenter test set: r = 0.57 [0.30, 0.76]). The areas under the receiver operating characteristic of the prediction models for the different cytogenetic aberrations ranged from 0.57 to 0.76 for the internal test set, but no model generalized well to all 3 external test sets.
Conclusions:
The automated image analysis framework established in this study allows for noninvasive prediction of a surrogate parameter for PCI, which is significantly correlated to the actual PCI from BM biopsy.
More Related Videos
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
05:32Multimodal Bioluminescent and Positronic-emission Tomography/Computational Tomography Imaging of Multiple Myeloma Bone Marrow Xenografts in NOG Mice
Published on: January 7, 2019