• Je něco špatně v tomto záznamu ?

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

M. Wennmann, W. Ming, F. Bauer, J. Chmelik, A. Klein, C. Uhlenbrock, M. Grözinger, KC. Kahl, T. Nonnenmacher, M. Debic, T. Hielscher, H. Thierjung, LT. Rotkopf, N. Stanczyk, S. Sauer, A. Jauch, M. Götz, FT. Kurz, K. Schlamp, M. Horger, S. Afat,...

. 2023 ; 58 (10) : 754-765. [pub] 20230522

Jazyk angličtina Země Spojené státy americké

Typ dokumentu multicentrická studie, časopisecké články, práce podpořená grantem

Perzistentní odkaz   https://www.medvik.cz/link/bmc23016165

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.

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc23016165
003      
CZ-PrNML
005      
20250507102512.0
007      
ta
008      
231013s2023 xxu f 000 0|eng||
009      
AR
024    7_
$a 10.1097/RLI.0000000000000986 $2 doi
035    __
$a (PubMed)37222527
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a xxu
100    1_
$a Wennmann, Markus $u From 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.)
245    10
$a Prediction of Bone Marrow Biopsy Results From MRI in Multiple Myeloma Patients Using Deep Learning and Radiomics / $c M. Wennmann, W. Ming, F. Bauer, J. Chmelik, A. Klein, C. Uhlenbrock, M. Grözinger, KC. Kahl, T. Nonnenmacher, M. Debic, T. Hielscher, H. Thierjung, LT. Rotkopf, N. Stanczyk, S. Sauer, A. Jauch, M. Götz, FT. Kurz, K. Schlamp, M. Horger, S. Afat, B. Besemer, M. Hoffmann, J. Hoffend, D. Kraemer, U. Graeven, A. Ringelstein, D. Bonekamp, J. Kleesiek, RO. Floca, J. Hillengass, EK. Mai, N. Weinhold, TF. Weber, H. Goldschmidt, HP. Schlemmer, K. Maier-Hein, S. Delorme, P. Neher
520    9_
$a 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.
650    _2
$a mužské pohlaví $7 D008297
650    _2
$a lidé $7 D006801
650    _2
$a lidé středního věku $7 D008875
650    12
$a mnohočetný myelom $x diagnostické zobrazování $x genetika $7 D009101
650    _2
$a kostní dřeň $x diagnostické zobrazování $7 D001853
650    12
$a deep learning $7 D000077321
650    _2
$a retrospektivní studie $7 D012189
650    _2
$a magnetická rezonanční tomografie $x metody $7 D008279
650    _2
$a biopsie $7 D001706
650    _2
$a chromozomální aberace $7 D002869
655    _2
$a multicentrická studie $7 D016448
655    _2
$a časopisecké články $7 D016428
655    _2
$a práce podpořená grantem $7 D013485
700    1_
$a Ming, Wenlong
700    1_
$a Bauer, Fabian
700    1_
$a Chmelík, Jiří $7 xx0331819
700    1_
$a Klein, André
700    1_
$a Uhlenbrock, Charlotte
700    1_
$a Grözinger, Martin
700    1_
$a Kahl, Kim-Celine
700    1_
$a Nonnenmacher, Tobias
700    1_
$a Debic, Manuel
700    1_
$a Hielscher, Thomas
700    1_
$a Thierjung, Heidi
700    1_
$a Rotkopf, Lukas T
700    1_
$a Stanczyk, Nikolas
700    1_
$a Sauer, Sandra
700    1_
$a Jauch, Anna
700    1_
$a Götz, Michael
700    1_
$a Kurz, Felix T
700    1_
$a Schlamp, Kai
700    1_
$a Horger, Marius
700    1_
$a Afat, Saif
700    1_
$a Besemer, Britta
700    1_
$a Hoffmann, Martin
700    1_
$a Hoffend, Johannes
700    1_
$a Kraemer, Doris
700    1_
$a Graeven, Ullrich
700    1_
$a Ringelstein, Adrian
700    1_
$a Bonekamp, David
700    1_
$a Kleesiek, Jens
700    1_
$a Floca, Ralf O
700    1_
$a Hillengass, Jens
700    1_
$a Mai, Elias K
700    1_
$a Weinhold, Niels
700    1_
$a Weber, Tim F
700    1_
$a Goldschmidt, Hartmut
700    1_
$a Schlemmer, Heinz-Peter
700    1_
$a Maier-Hein, Klaus
700    1_
$a Delorme, Stefan
700    1_
$a Neher, Peter
773    0_
$w MED00002405 $t Investigative radiology $x 1536-0210 $g Roč. 58, č. 10 (2023), s. 754-765
856    41
$u https://pubmed.ncbi.nlm.nih.gov/37222527 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y - $z 0
990    __
$a 20231013 $b ABA008
991    __
$a 20250507102509 $b ABA008
999    __
$a ok $b bmc $g 1999973 $s 1202527
BAS    __
$a 3
BAS    __
$a PreBMC-MEDLINE
BMC    __
$a 2023 $b 58 $c 10 $d 754-765 $e 20230522 $i 1536-0210 $m Investigative radiology $n Invest Radiol $x MED00002405
LZP    __
$a Pubmed-20231013

Najít záznam

Citační ukazatele

Pouze přihlášení uživatelé

Možnosti archivace