Detail publikace

Prediction of Bone Marrow Biopsy Results From MRI in Multiple Myeloma Patients Using Deep Learning and Radiomics

WENNMANN, M. MING, W. BAUER, F. CHMELIK, J. KLEIN, A. UHLENBROCK, C. GROZINGER, M. KIM-CELINE, K. NONNENMACHER, T. DEBIC, M. HIELSCHER, T. THIERJUNG, H. ROTKOPF, L. STANZCYK, N. SAUER, S. JAUCH, A. GOTZ, M. KURZ, F. SCHLAMP, K. HORGER, M. AFAT, S. BESEMER, B. HOFFMANN, M. HOFFEND, J. KRAEMER, D. GRAEVEN, U. RINGELSTEIN, A. BONEKAMP, D. KLEESIEK, J. FLOCA, R. HILLENGASS, J. MAI, E. WEINHOLD, N. WEBER, T. GOLDSCHMIDT, H. SCHLEMMER, H. MAIER-HEIN, K. DELORME, S. NEHER, P.

Originální název

Prediction of Bone Marrow Biopsy Results From MRI in Multiple Myeloma Patients Using Deep Learning and Radiomics

Typ

článek v časopise ve Web of Science, Jimp

Jazyk

angličtina

Originální abstrakt

ObjectivesIn 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 MethodsThis 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.ResultsA 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 & LE; 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.ConclusionsThe 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.

Klíčová slova

deep learning; segmentation; radiomics; MRI; bone marrow; biopsy; plasma cell infiltration; cytogenetic aberrations; multiple myeloma; multicenter

Autoři

WENNMANN, M.; MING, W.; BAUER, F.; CHMELIK, J.; KLEIN, A.; UHLENBROCK, C.; GROZINGER, M.; KIM-CELINE, K.; NONNENMACHER, T.; DEBIC, M.; HIELSCHER, T.; THIERJUNG, H.; ROTKOPF, L.; STANZCYK, N.; SAUER, S.; JAUCH, A.; GOTZ, M.; KURZ, F.; SCHLAMP, K.; HORGER, M.; AFAT, S.; BESEMER, B.; HOFFMANN, M.; HOFFEND, J.; KRAEMER, D.; GRAEVEN, U.; RINGELSTEIN, A.; BONEKAMP, D.; KLEESIEK, J.; FLOCA, R.; HILLENGASS, J.; MAI, E.; WEINHOLD, N.; WEBER, T.; GOLDSCHMIDT, H.; SCHLEMMER, H.; MAIER-HEIN, K.; DELORME, S.; NEHER, P.

Vydáno

8. 9. 2023

Nakladatel

Wolters Kluwer Health, Inc.

ISSN

0020-9996

Periodikum

INVESTIGATIVE RADIOLOGY

Ročník

58

Číslo

10

Stát

Spojené státy americké

Strany od

754

Strany do

765

Strany počet

12

URL

BibTex

@article{BUT183581,
  author="Markus {Wennmann} and Wenlong {Ming} and Fabian {Bauer} and Jiří {Chmelík} and André {Klein} and Charlotte {Uhlenbrock} and Martin {Grözinger} and Kahl {Kim-Celine} and Tobias {Nonnenmacher} and Manuel {Debic} and Thomas {Hielscher} and Heidi {Thierjung} and Lukas {Rotkopf} and Nikolas {Stanzcyk} and Sandra {Sauer} and Anna {Jauch} and Michael {Gotz} and Felix {Kurz} and Kai {Schlamp} and Marius {Horger} and Saif {Afat} and Britta {Besemer} and Martin {Hoffmann} and Johanes {Hoffend} and Doris {Kraemer} and Ullrich {Graeven} and Adrian {Ringelstein} and David {Bonekamp} and Jens {Kleesiek} and Ralf {Floca} and Jens {Hillengass} and Elias {Mai} and Niels {Weinhold} and Tim {Weber} and Hartmut {Goldschmidt} and Heinz-Peter {Schlemmer} and Klaus {Maier-Hein} and Stefan {Delorme} and Peter {Neher}",
  title="Prediction of Bone Marrow Biopsy Results From MRI in Multiple Myeloma Patients Using Deep Learning and Radiomics",
  journal="INVESTIGATIVE RADIOLOGY",
  year="2023",
  volume="58",
  number="10",
  pages="754--765",
  doi="10.1097/RLI.0000000000000986",
  issn="0020-9996",
  url="https://journals.lww.com/investigativeradiology/fulltext/2023/10000/prediction_of_bone_marrow_biopsy_results_from_mri.7.aspx"
}