Skip to main content
Erschienen in:

27.06.2024 | Scientific Article

Whole-body low-dose computed tomography in patients with newly diagnosed multiple myeloma predicts cytogenetic risk: a deep learning radiogenomics study

verfasst von: Shahriar Faghani, Mana Moassefi, Udit Yadav, Francis K. Buadi, Shaji K. Kumar, Bradley J. Erickson, Wilson I. Gonsalves, Francis I. Baffour

Erschienen in: Skeletal Radiology | Ausgabe 2/2025

Einloggen, um Zugang zu erhalten

Abstract

Objective

To develop a whole-body low-dose CT (WBLDCT) deep learning model and determine its accuracy in predicting the presence of cytogenetic abnormalities in multiple myeloma (MM).

Materials and methods

WBLDCTs of MM patients performed within a year of diagnosis were included. Cytogenetic assessments of clonal plasma cells via fluorescent in situ hybridization (FISH) were used to risk-stratify patients as high-risk (HR) or standard-risk (SR). Presence of any of del(17p), t(14;16), t(4;14), and t(14;20) on FISH was defined as HR. The dataset was evenly divided into five groups (folds) at the individual patient level for model training. Mean and standard deviation (SD) of the area under the receiver operating curve (AUROC) across the folds were recorded.

Results

One hundred fifty-one patients with MM were included in the study. The model performed best for t(4;14), mean (SD) AUROC of 0.874 (0.073). The lowest AUROC was observed for trisomies: AUROC of 0.717 (0.058). Two- and 5-year survival rates for HR cytogenetics were 87% and 71%, respectively, compared to 91% and 79% for SR cytogenetics. Survival predictions by the WBLDCT deep learning model revealed 2- and 5-year survival rates for patients with HR cytogenetics as 87% and 71%, respectively, compared to 92% and 81% for SR cytogenetics.

Conclusion

A deep learning model trained on WBLDCT scans predicted the presence of cytogenetic abnormalities used for risk stratification in MM. Assessment of the model’s performance revealed good to excellent classification of the various cytogenetic abnormalities.
Anhänge
Nur mit Berechtigung zugänglich
Literatur
1.
Zurück zum Zitat Siegel RL, Giaquinto AN, Jemal A. Cancer statistics, 2024. CA Cancer J Clin. 2024;74(1):12–49.CrossRefPubMed Siegel RL, Giaquinto AN, Jemal A. Cancer statistics, 2024. CA Cancer J Clin. 2024;74(1):12–49.CrossRefPubMed
2.
Zurück zum Zitat Kumar SK, Rajkumar SV. The multiple myelomas - current concepts in cytogenetic classification and therapy. Nat Rev Clin Oncol. 2018;15(7):409–21.CrossRefPubMed Kumar SK, Rajkumar SV. The multiple myelomas - current concepts in cytogenetic classification and therapy. Nat Rev Clin Oncol. 2018;15(7):409–21.CrossRefPubMed
3.
Zurück zum Zitat Abdallah NH, Binder M, Rajkumar SV, Greipp PT, Kapoor P, Dispenzieri A, et al. A simple additive staging system for newly diagnosed multiple myeloma. Blood Cancer J. 2022;12(1):21.CrossRefPubMedPubMedCentral Abdallah NH, Binder M, Rajkumar SV, Greipp PT, Kapoor P, Dispenzieri A, et al. A simple additive staging system for newly diagnosed multiple myeloma. Blood Cancer J. 2022;12(1):21.CrossRefPubMedPubMedCentral
4.
Zurück zum Zitat Chng WJ, Dispenzieri A, Chim CS, Fonseca R, Goldschmidt H, Lentzsch S, et al. IMWG consensus on risk stratification in multiple myeloma. Leukemia. 2014;28(2):269–77.CrossRefPubMed Chng WJ, Dispenzieri A, Chim CS, Fonseca R, Goldschmidt H, Lentzsch S, et al. IMWG consensus on risk stratification in multiple myeloma. Leukemia. 2014;28(2):269–77.CrossRefPubMed
5.
Zurück zum Zitat Rasche L, Chavan SS, Stephens OW, Patel PH, Tytarenko R, Ashby C, et al. Spatial genomic heterogeneity in multiple myeloma revealed by multi-region sequencing. Nat Commun. 2017;8(1):268.CrossRefPubMedPubMedCentral Rasche L, Chavan SS, Stephens OW, Patel PH, Tytarenko R, Ashby C, et al. Spatial genomic heterogeneity in multiple myeloma revealed by multi-region sequencing. Nat Commun. 2017;8(1):268.CrossRefPubMedPubMedCentral
6.
Zurück zum Zitat Yadav U, Kumar SK, Baughn LB, Dispenzieri A, Greipp P, Ketterling R, et al. Impact of cytogenetic abnormalities on the risk of disease progression in solitary bone plasmacytomas. Blood. 2023;142(22):1871–8.CrossRefPubMedPubMedCentral Yadav U, Kumar SK, Baughn LB, Dispenzieri A, Greipp P, Ketterling R, et al. Impact of cytogenetic abnormalities on the risk of disease progression in solitary bone plasmacytomas. Blood. 2023;142(22):1871–8.CrossRefPubMedPubMedCentral
7.
Zurück zum Zitat Katodritou E, Kastritis E, Gatt M, Cohen YC, Avivi I, Pouli A, et al. Real-world data on incidence, clinical characteristics and outcome of patients with macrofocal multiple myeloma (MFMM) in the era of novel therapies: a study of the Greco-Israeli collaborative myeloma working group. Am J Hematol. 2020;95(5):465–71.CrossRefPubMed Katodritou E, Kastritis E, Gatt M, Cohen YC, Avivi I, Pouli A, et al. Real-world data on incidence, clinical characteristics and outcome of patients with macrofocal multiple myeloma (MFMM) in the era of novel therapies: a study of the Greco-Israeli collaborative myeloma working group. Am J Hematol. 2020;95(5):465–71.CrossRefPubMed
8.
Zurück zum Zitat Moulopoulos LA, Koutoulidis V, Hillengass J, Zamagni E, Aquerreta JD, Roche CL, et al. Recommendations for acquisition, interpretation and reporting of whole body low dose CT in patients with multiple myeloma and other plasma cell disorders: a report of the IMWG Bone Working Group. Blood Cancer J. 2018;8(10):95.CrossRefPubMedPubMedCentral Moulopoulos LA, Koutoulidis V, Hillengass J, Zamagni E, Aquerreta JD, Roche CL, et al. Recommendations for acquisition, interpretation and reporting of whole body low dose CT in patients with multiple myeloma and other plasma cell disorders: a report of the IMWG Bone Working Group. Blood Cancer J. 2018;8(10):95.CrossRefPubMedPubMedCentral
9.
Zurück zum Zitat Rajkumar SV, Dimopoulos MA, Palumbo A, Blade J, Merlini G, Mateos MV, et al. International Myeloma Working Group updated criteria for the diagnosis of multiple myeloma. Lancet Oncol. 2014;15(12):e538-548.CrossRefPubMed Rajkumar SV, Dimopoulos MA, Palumbo A, Blade J, Merlini G, Mateos MV, et al. International Myeloma Working Group updated criteria for the diagnosis of multiple myeloma. Lancet Oncol. 2014;15(12):e538-548.CrossRefPubMed
11.
Zurück zum Zitat Rouzrokh P, Khosravi B, Faghani S, Moassefi M, Vera Garcia DV, Singh Y, et al. Mitigating bias in radiology machine learning: 1. Data handling. Radiol Artif Intell. 2022;4(5): e210290.CrossRefPubMedPubMedCentral Rouzrokh P, Khosravi B, Faghani S, Moassefi M, Vera Garcia DV, Singh Y, et al. Mitigating bias in radiology machine learning: 1. Data handling. Radiol Artif Intell. 2022;4(5): e210290.CrossRefPubMedPubMedCentral
12.
Zurück zum Zitat Zhang K, Khosravi B, Vahdati S, Faghani S, Nugen F, Rassoulinejad-Mousavi SM, et al. Mitigating bias in radiology machine learning: 2. Model development. Radiol Artif Intell. 2022;4(5): e220010.CrossRefPubMedPubMedCentral Zhang K, Khosravi B, Vahdati S, Faghani S, Nugen F, Rassoulinejad-Mousavi SM, et al. Mitigating bias in radiology machine learning: 2. Model development. Radiol Artif Intell. 2022;4(5): e220010.CrossRefPubMedPubMedCentral
13.
Zurück zum Zitat Faghani S, Khosravi B, Moassefi M, Conte GM, Erickson BJ. A Comparison of three different deep learning-based models to predict the MGMT promoter methylation status in glioblastoma using brain MRI. J Digit Imaging. 2023;36(3):837–46.CrossRefPubMedPubMedCentral Faghani S, Khosravi B, Moassefi M, Conte GM, Erickson BJ. A Comparison of three different deep learning-based models to predict the MGMT promoter methylation status in glioblastoma using brain MRI. J Digit Imaging. 2023;36(3):837–46.CrossRefPubMedPubMedCentral
14.
Zurück zum Zitat Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2017 21–26 July 2017; 2017. p. 2261–2269. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2017 21–26 July 2017; 2017. p. 2261–2269.
15.
Zurück zum Zitat Moassefi M, Faghani S, Conte GM, Kowalchuk RO, Vahdati S, Crompton DJ, et al. A deep learning model for discriminating true progression from pseudoprogression in glioblastoma patients. J Neurooncol. 2022;159(2):447–55.CrossRefPubMed Moassefi M, Faghani S, Conte GM, Kowalchuk RO, Vahdati S, Crompton DJ, et al. A deep learning model for discriminating true progression from pseudoprogression in glioblastoma patients. J Neurooncol. 2022;159(2):447–55.CrossRefPubMed
16.
Zurück zum Zitat Singh Y, Kelm ZS, Faghani S, Erickson D, Yalon T, Bancos I, et al. Deep learning approach for differentiating indeterminate adrenal masses using CT imaging. Abdom Radiol (NY). 2023;48(10):3189–94.CrossRefPubMed Singh Y, Kelm ZS, Faghani S, Erickson D, Yalon T, Bancos I, et al. Deep learning approach for differentiating indeterminate adrenal masses using CT imaging. Abdom Radiol (NY). 2023;48(10):3189–94.CrossRefPubMed
17.
Zurück zum Zitat Loshchilov I, Hutter F. Decoupled weight decay regularization. International Conference on Learning Representations; 2017; 2017. Loshchilov I, Hutter F. Decoupled weight decay regularization. International Conference on Learning Representations; 2017; 2017.
18.
Zurück zum Zitat Gotmare A, Keskar NS, Xiong C, Socher R. A closer look at deep learning heuristics: learning rate restarts, warmup and distillation. arXiv preprint arXiv:181013243. 2018. Gotmare A, Keskar NS, Xiong C, Socher R. A closer look at deep learning heuristics: learning rate restarts, warmup and distillation. arXiv preprint arXiv:181013243. 2018.
19.
Zurück zum Zitat Ho Y, Wookey S. The real-world-weight cross-entropy loss function: modeling the costs of mislabeling. IEEE Access. 2020;8:4806–13.CrossRef Ho Y, Wookey S. The real-world-weight cross-entropy loss function: modeling the costs of mislabeling. IEEE Access. 2020;8:4806–13.CrossRef
20.
Zurück zum Zitat Faghani S. shahriar-faghani/MM_radgen. GitHub 2024. Faghani S. shahriar-faghani/MM_radgen. GitHub 2024.
21.
Zurück zum Zitat Faghani S, Khosravi B, Zhang K, Moassefi M, Jagtap JM, Nugen F, et al. Mitigating bias in radiology machine learning: 3. Performance metrics. Radiol Artif Intell. 2022;4(5): e220061.CrossRefPubMedPubMedCentral Faghani S, Khosravi B, Zhang K, Moassefi M, Jagtap JM, Nugen F, et al. Mitigating bias in radiology machine learning: 3. Performance metrics. Radiol Artif Intell. 2022;4(5): e220061.CrossRefPubMedPubMedCentral
22.
Zurück zum Zitat Binder M, Rajkumar SV, Ketterling RP, Dispenzieri A, Lacy MQ, Gertz MA, et al. Substratification of patients with newly diagnosed standard-risk multiple myeloma. Br J Haematol. 2019;185(2):254–60.CrossRefPubMed Binder M, Rajkumar SV, Ketterling RP, Dispenzieri A, Lacy MQ, Gertz MA, et al. Substratification of patients with newly diagnosed standard-risk multiple myeloma. Br J Haematol. 2019;185(2):254–60.CrossRefPubMed
23.
Zurück zum Zitat Ni B, Huang G, Huang H, Wang T, Han X, Shen L, et al. Machine learning model based on optimized radiomics feature from (18)F-FDG-PET/CT and clinical characteristics predicts prognosis of multiple myeloma: a preliminary study. J Clin Med. 2023;12(6). Ni B, Huang G, Huang H, Wang T, Han X, Shen L, et al. Machine learning model based on optimized radiomics feature from (18)F-FDG-PET/CT and clinical characteristics predicts prognosis of multiple myeloma: a preliminary study. J Clin Med. 2023;12(6).
24.
Zurück zum Zitat Sachpekidis C, Enqvist O, Ulén J, Kopp-Schneider A, Pan L, Mai EK, et al. Artificial intelligence-based, volumetric assessment of the bone marrow metabolic activity in [(18)F]FDG PET/CT predicts survival in multiple myeloma. Eur J Nucl Med Mol Imaging. 2024. Sachpekidis C, Enqvist O, Ulén J, Kopp-Schneider A, Pan L, Mai EK, et al. Artificial intelligence-based, volumetric assessment of the bone marrow metabolic activity in [(18)F]FDG PET/CT predicts survival in multiple myeloma. Eur J Nucl Med Mol Imaging. 2024.
25.
Zurück zum Zitat Zhong H, Huang D, Wu J, Chen X, Chen Y, Huang C. (18)F-FDG PET/CT based radiomics features improve prediction of prognosis: multiple machine learning algorithms and multimodality applications for multiple myeloma. BMC Med Imaging. 2023;23(1):87.CrossRefPubMedPubMedCentral Zhong H, Huang D, Wu J, Chen X, Chen Y, Huang C. (18)F-FDG PET/CT based radiomics features improve prediction of prognosis: multiple machine learning algorithms and multimodality applications for multiple myeloma. BMC Med Imaging. 2023;23(1):87.CrossRefPubMedPubMedCentral
26.
Zurück zum Zitat Liu J, Wang C, Guo W, Zeng P, Liu Y, Lang N, et al. A preliminary study using spinal MRI-based radiomics to predict high-risk cytogenetic abnormalities in multiple myeloma. Radiol Med. 2021;126(9):1226–35.CrossRefPubMed Liu J, Wang C, Guo W, Zeng P, Liu Y, Lang N, et al. A preliminary study using spinal MRI-based radiomics to predict high-risk cytogenetic abnormalities in multiple myeloma. Radiol Med. 2021;126(9):1226–35.CrossRefPubMed
Metadaten
Titel
Whole-body low-dose computed tomography in patients with newly diagnosed multiple myeloma predicts cytogenetic risk: a deep learning radiogenomics study
verfasst von
Shahriar Faghani
Mana Moassefi
Udit Yadav
Francis K. Buadi
Shaji K. Kumar
Bradley J. Erickson
Wilson I. Gonsalves
Francis I. Baffour
Publikationsdatum
27.06.2024
Verlag
Springer Berlin Heidelberg
Erschienen in
Skeletal Radiology / Ausgabe 2/2025
Print ISSN: 0364-2348
Elektronische ISSN: 1432-2161
DOI
https://doi.org/10.1007/s00256-024-04733-0

Neu im Fachgebiet Radiologie

Ab sofort gelten die neuen Verordnungsausnahmen für Lipidsenker

Freie Fahrt für Lipidsenker? Das nicht, doch mit niedrigerem Schwellenwert fürs Infarktrisiko und neuen Indikationen hat der G-BA die Verordnungs-Handbremse ein gutes Stück weit gelockert.

Abdominale CT bei Kindern: 40% mit Zufallsbefunden

Wird bei Kindern mit stumpfem Trauma eine CT des Bauchraums veranlasst, sind in rund 40% der Fälle Auffälligkeiten zu sehen, die nichts mit dem Trauma zu tun haben. Die allerwenigsten davon sind klinisch relevant.

Genügt die biparametrische MRT für die Prostatadiagnostik?

Die multiparametrische Magnetresonanztomografie hat einen festen Platz im Screening auf klinisch signifikante Prostatakarzinome. Ob auch ein biparametrisches Vorgehen ausreicht, ist in einer Metaanalyse untersucht worden.

Höhere Trefferquoten bei Brustkrebsscreening dank KI?

Künstliche Intelligenz unterstützt bei der Auswertung von Mammografie-Screenings und senkt somit den radiologischen Arbeitsaufwand. Wie wirken sich diese Technologien auf die Trefferquote und die Falsch-positiv-Rate aus? Das hat jetzt eine Studie aus Schweden untersucht.

Update Radiologie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.