Prediction of therapy response of breast cancer patients with machine learning based on clinical data and imaging data derived from breast [
Breast cancer
Machine learning
PET/MRI
Therapy response
Journal
European journal of nuclear medicine and molecular imaging
ISSN: 1619-7089
Titre abrégé: Eur J Nucl Med Mol Imaging
Pays: Germany
ID NLM: 101140988
Informations de publication
Date de publication:
Apr 2024
Apr 2024
Historique:
received:
11
07
2023
accepted:
06
11
2023
pubmed:
22
12
2023
medline:
22
12
2023
entrez:
22
12
2023
Statut:
ppublish
Résumé
To evaluate if a machine learning prediction model based on clinical and easily assessable imaging features derived from baseline breast [ Altogether 143 women with newly diagnosed breast cancer (54 ± 12 years) were retrospectively enrolled. All women underwent a breast [ Nested-cross-validation yielded a mean ROC-AUC of 80.4 ± 6.0% for prediction of pCR. Mean sensitivity, specificity, PPV, and NPV of 54.5 ± 21.3%, 83.6 ± 4.2%, 63.6 ± 8.5%, and 77.6 ± 8.1% could be achieved. Histopathological data were the most important features for classification of the XGBoost model followed by PET, MRI, and sociodemographic/anthropometric features. The evaluated multi-source XGBoost model shows promising results for reliably predicting pathological complete response in breast cancer patients prior to NAST. However, yielded performance is yet insufficient to be implemented in the clinical decision-making process.
Identifiants
pubmed: 38133687
doi: 10.1007/s00259-023-06513-9
pii: 10.1007/s00259-023-06513-9
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
1451-1461Subventions
Organisme : Deutsche Forschungsgemeinschaft
ID : BU3075/2‑1
Organisme : Deutsche Forschungsgemeinschaft
ID : KI2434/1-2
Informations de copyright
© 2023. The Author(s).
Références
Sung H, Ferlay J, Siegel RL, Laversanne M, Soerjomataram I, Jemal A, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2021;71:209–49. https://doi.org/10.3322/caac.21660 .
doi: 10.3322/caac.21660
pubmed: 33538338
Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2018;68:394–424. https://doi.org/10.3322/caac.21492 .
doi: 10.3322/caac.21492
pubmed: 30207593
Rose J, Puckett Y. Breast Reconstruction Free Flaps. StatPearls. Treasure Island (FL): StatPearls Publishing Copyright © 2022, StatPearls Publishing LLC.; 2022.
Leitlinienprogramm Onkologie (Deutsche Krebsgesellschaft DK, AWMF). S3-Leitlinie Früherkennung, Diagnose, Therapie und Nachsorge des Mammakarzinoms. 2021; Version 4.4. AWMF Registernummer: 032-045OL. http://www.leitlinienprogramm-onkologie.de/leitlinien/mammakarzinom/ . (abgerufen am: 11.11.2023)
Bruckmann NM, Morawitz J, Fendler WP, Ruckhäberle E, Bittner AK, Giesel FL, et al. A role of PET/MR in breast cancer? Semin Nucl Med. 2022. https://doi.org/10.1053/j.semnuclmed.2022.01.003 .
doi: 10.1053/j.semnuclmed.2022.01.003
pubmed: 35260243
Murthy V, Sonni I, Jariwala N, Juarez R, Reiter RE, Raman SS, et al. The role of PSMA PET/CT and PET/MRI in the initial staging of prostate cancer. Eur Urol Focus. 2021;7:258–66. https://doi.org/10.1016/j.euf.2021.01.016 .
doi: 10.1016/j.euf.2021.01.016
pubmed: 33541838
Heacock L, Weissbrot J, Raad R, Campbell N, Friedman KP, Ponzo F, et al. PET/MRI for the evaluation of patients with lymphoma: initial observations. AJR Am J Roentgenol. 2015;204:842–8. https://doi.org/10.2214/AJR.14.13181 .
doi: 10.2214/AJR.14.13181
pubmed: 25794075
pmcid: 4465553
Kirchner J, Grueneisen J, Martin O, Oehmigen M, Quick HH, Bittner A-K, et al. Local and whole-body staging in patients with primary breast cancer: a comparison of one-step to two-step staging utilizing 18F-FDG-PET/MRI. Eur J Nucl Med Mol Imaging. 2018;45:2328–37. https://doi.org/10.1007/s00259-018-4102-4 .
doi: 10.1007/s00259-018-4102-4
pubmed: 30056547
Bruckmann NM, Kirchner J, Morawitz J, Umutlu L, Herrmann K, Bittner AK, et al. Prospective comparison of CT and 18F-FDG PET/MRI in N and M staging of primary breast cancer patients: initial results. PLoS ONE. 2021;16: e0260804. https://doi.org/10.1371/journal.pone.0260804 .
doi: 10.1371/journal.pone.0260804
pubmed: 34855886
pmcid: 8638872
Bruckmann NM, Kirchner J, Umutlu L, Fendler WP, Seifert R, Herrmann K, et al. Prospective comparison of the diagnostic accuracy of 18F-FDG PET/MRI, MRI, CT, and bone scintigraphy for the detection of bone metastases in the initial staging of primary breast cancer patients. Eur Radiol. 2021;31:8714–24. https://doi.org/10.1007/s00330-021-07956-0 .
doi: 10.1007/s00330-021-07956-0
pubmed: 33912991
pmcid: 8523471
Cardoso F, Paluch-Shimon S, Senkus E, Curigliano G, Aapro MS, André F, et al. 5th ESO-ESMO international consensus guidelines for advanced breast cancer (ABC 5). Ann Oncol. 2020;31:1623–49. https://doi.org/10.1016/j.annonc.2020.09.010 .
doi: 10.1016/j.annonc.2020.09.010
pubmed: 32979513
Mougalian SS, Hernandez M, Lei X, Lynch S, Kuerer HM, Symmans WF, et al. Ten-year outcomes of patients with breast cancer with cytologically confirmed axillary lymph node metastases and pathologic complete response after primary systemic chemotherapy. JAMA Oncol. 2016;2:508–16. https://doi.org/10.1001/jamaoncol.2015.4935 .
doi: 10.1001/jamaoncol.2015.4935
pubmed: 26720612
pmcid: 4845895
Fayanju OM, Ren Y, Thomas SM, Greenup RA, Plichta JK, Rosenberger LH, et al. The clinical significance of breast-only and node-only pathologic complete response (pCR) after neoadjuvant chemotherapy (NACT): a review of 20,000 breast cancer patients in the National Cancer Data Base (NCDB). Ann Surg. 2018;268:591–601. https://doi.org/10.1097/sla.0000000000002953 .
doi: 10.1097/sla.0000000000002953
pubmed: 30048319
Gu YL, Pan SM, Ren J, Yang ZX, Jiang GQ. Role of magnetic resonance imaging in detection of pathologic complete remission in breast cancer patients treated with neoadjuvant chemotherapy: a meta-analysis. Clin Breast Cancer. 2017;17:245–55. https://doi.org/10.1016/j.clbc.2016.12.010 .
doi: 10.1016/j.clbc.2016.12.010
pubmed: 28209330
Urso L, Evangelista L, Alongi P, Quartuccio N, Cittanti C, Rambaldi I, et al. The value of semiquantitative parameters derived from (18)F-FDG PET/CT for predicting response to neoadjuvant chemotherapy in a cohort of patients with different molecular subtypes of breast cancer. Cancers (Basel). 2022;14(23):5869. https://doi.org/10.3390/cancers14235869 .
Park SH, Moon WK, Cho N, Chang JM, Im S-A, Park I, et al. Comparison of diffusion-weighted MR imaging and FDG PET/CT to predict pathological complete response to neoadjuvant chemotherapy in patients with breast cancer. Eur Radiol. 2012;22:18–25.
doi: 10.1007/s00330-011-2236-x
pubmed: 21845462
Morawitz J, Sigl B, Rubbert C, Bruckmann NM, Dietzel F, Häberle LJ, et al. Clinical decision support for axillary lymph node staging in newly diagnosed breast cancer patients based on (18)F-FDG PET/MRI and machine learning. J Nucl Med. 2023;64:304–11. https://doi.org/10.2967/jnumed.122.264138 .
doi: 10.2967/jnumed.122.264138
pubmed: 36137756
pmcid: 9902847
Pehrson LM, Nielsen MB, Ammitzbøl LC. Automatic pulmonary nodule detection applying deep learning or machine learning algorithms to the LIDC-IDRI database: a systematic review. Diagnostics. 2019;9:29.
doi: 10.3390/diagnostics9010029
pubmed: 30866425
pmcid: 6468920
Rubbert C, Wolf L, Turowski B, Hedderich DM, Gaser C, Dahnke R, et al. Impact of defacing on automated brain atrophy estimation. Insights Imaging. 2022;13:54. https://doi.org/10.1186/s13244-022-01195-7 .
doi: 10.1186/s13244-022-01195-7
pubmed: 35348936
pmcid: 8964867
Morawitz J, Bruckmann N-M, Dietzel F, Ullrich T, Bittner A-K, Hoffmann O, et al. Comparison of nodal staging between CT, MRI, and [(18)F]-FDG PET/MRI in patients with newly diagnosed breast cancer. Eur J Nucl Med Mol Imaging. 2022;49:992–1001. https://doi.org/10.1007/s00259-021-05502-0 .
doi: 10.1007/s00259-021-05502-0
pubmed: 34476552
Atallah D, Moubarak M, Arab W, El Kassis N, Chahine G, Salem C. MRI-based predictive factors of axillary lymph node status in breast cancer. Breast J. 2020;26:2177–82. https://doi.org/10.1111/tbj.14089 .
doi: 10.1111/tbj.14089
pubmed: 33073463
Association WM. World Medical Association Declaration of Helsinki: ethical principles for medical research involving human subjects. JAMA. 2013;310:2191–4. https://doi.org/10.1001/jama.2013.281053 .
doi: 10.1001/jama.2013.281053
Oehmigen M, Lindemann ME, Lanz T, Kinner S, Quick HH. Integrated PET/MR breast cancer imaging: attenuation correction and implementation of a 16-channel RF coil. Med Phys. 2016;43:4808. https://doi.org/10.1118/1.4959546 .
doi: 10.1118/1.4959546
pubmed: 27487899
Martinez-Möller A, Souvatzoglou M, Delso G, Bundschuh RA, Chefd’hotel C, Ziegler SI, et al. Tissue classification as a potential approach for attenuation correction in whole-body PET/MRI: evaluation with PET/CT data. J Nucl Med. 2009;50:520–6. https://doi.org/10.2967/jnumed.108.054726 .
doi: 10.2967/jnumed.108.054726
pubmed: 19289430
Paulus DH, Quick HH, Geppert C, Fenchel M, Zhan Y, Hermosillo G, et al. Whole-body PET/MR imaging: quantitative evaluation of a novel model-based MR attenuation correction method including bone. J Nucl Med. 2015;56:1061–6. https://doi.org/10.2967/jnumed.115.156000 .
doi: 10.2967/jnumed.115.156000
pubmed: 26025957
Lindemann ME, Oehmigen M, Blumhagen JO, Gratz M, Quick HH. MR-based truncation and attenuation correction in integrated PET/MR hybrid imaging using HUGE with continuous table motion. Med Phys. 2017;44:4559–72. https://doi.org/10.1002/mp.12449 .
doi: 10.1002/mp.12449
pubmed: 28675598
Sinn HP, Schmid H, Junkermann H, Huober J, Leppien G, Kaufmann M, et al. Histologic regression of breast cancer after primary (neoadjuvant) chemotherapy. Geburtshilfe Frauenheilkd. 1994;54:552–8. https://doi.org/10.1055/s-2007-1022338 .
doi: 10.1055/s-2007-1022338
pubmed: 8001751
Du Bois D, Du Bois EF. Clinical calorimetry: tenth paper a formula to estimate the approximate surface area if height and weight be known. Arch Intern Med. 1916;XVII:863–71. https://doi.org/10.1001/archinte.1916.00080130010002 .
Bergstra J, Bengio Y. Random search for hyper-parameter optimization. J Mach Learn Res. 2012;13:281–305.
Hurria A, Soto-Perez-de-Celis E, Allred JB, Cohen HJ, Arsenyan A, Ballman K, et al. Functional decline and resilience in older women receiving adjuvant chemotherapy for breast cancer. J Am Geriatr Soc. 2019;67:920–7. https://doi.org/10.1111/jgs.15493 .
doi: 10.1111/jgs.15493
pubmed: 30146695
Heil J, Kümmel S, Schaefgen B, Paepke S, Thomssen C, Rauch G, et al. Diagnosis of pathological complete response to neoadjuvant chemotherapy in breast cancer by minimal invasive biopsy techniques. Br J Cancer. 2015;113:1565–70. https://doi.org/10.1038/bjc.2015.381 .
doi: 10.1038/bjc.2015.381
pubmed: 26554654
pmcid: 4705891
Del Prete S, Caraglia M, Luce A, Montella L, Galizia G, Sperlongano P, et al. Clinical and pathological factors predictive of response to neoadjuvant chemotherapy in breast cancer: a single center experience. Oncol Lett. 2019;18:3873–9. https://doi.org/10.3892/ol.2019.10729 .
doi: 10.3892/ol.2019.10729
pubmed: 31516598
pmcid: 6732960
Wang L, Zhang S, Wang X. The Metabolic Mechanisms of Breast Cancer Metastasis. Front Oncol. 2020;10: 602416. https://doi.org/10.3389/fonc.2020.602416 .
doi: 10.3389/fonc.2020.602416
pubmed: 33489906
Catalano OA, Horn GL, Signore A, Iannace C, Lepore M, Vangel M, et al. PET/MR in invasive ductal breast cancer: correlation between imaging markers and histological phenotype. Br J Cancer. 2017;116:893–902. https://doi.org/10.1038/bjc.2017.26 .
doi: 10.1038/bjc.2017.26
pubmed: 28208155
pmcid: 5379139
Jannusch K, Bittner A-K, Bruckmann NM, Morawitz J, Stieglitz C, Dietzel F, et al. Correlation between imaging markers derived from pet/mri and invasive acquired biomarkers in newly diagnosed breast cancer. Cancers. 2023;15:1651.
doi: 10.3390/cancers15061651
pubmed: 36980537
pmcid: 10046153
Choi JH, Kim H-A, Kim W, Lim I, Lee I, Byun BH, et al. Early prediction of neoadjuvant chemotherapy response for advanced breast cancer using PET/MRI image deep learning. Sci Rep. 2020;10:21149. https://doi.org/10.1038/s41598-020-77875-5 .
doi: 10.1038/s41598-020-77875-5
pubmed: 33273490
pmcid: 7712787
Parvandeh S, Yeh H-W, Paulus MP, McKinney BA. Consensus features nested cross-validation. Bioinformatics. 2020;36:3093–8. https://doi.org/10.1093/bioinformatics/btaa046 .
doi: 10.1093/bioinformatics/btaa046
pubmed: 31985777
pmcid: 7776094
Tsamardinos I, Rakhshani A, Lagani V. Performance-estimation properties of cross-validation-based protocols with simultaneous hyper-parameter optimization. Int J Artif Intell Tools. 2015;24:1540023. https://doi.org/10.1142/s0218213015400230 .
doi: 10.1142/s0218213015400230
Wainer J, Cawley G. Nested cross-validation when selecting classifiers is overzealous for most practical applications. Expert Syst Appl. 2021;182: 115222. https://doi.org/10.1016/j.eswa.2021.115222 .
doi: 10.1016/j.eswa.2021.115222
Varoquaux G, Cheplygina V. Machine learning for medical imaging: methodological failures and recommendations for the future. NPJ Digit Med. 2022;5:48. https://doi.org/10.1038/s41746-022-00592-y .
doi: 10.1038/s41746-022-00592-y
pubmed: 35413988
pmcid: 9005663
Tahmassebi A, Wengert GJ, Helbich TH, Bago-Horvath Z, Alaei S, Bartsch R, et al. Impact of machine learning with multiparametric magnetic resonance imaging of the breast for early prediction of response to neoadjuvant chemotherapy and survival outcomes in breast cancer patients. Invest Radiol. 2019;54:110–7. https://doi.org/10.1097/rli.0000000000000518 .
doi: 10.1097/rli.0000000000000518
pubmed: 30358693
pmcid: 6310100
Syed A, Adam R, Ren T, Lu J, Maldjian T, Duong TQ. Machine learning with textural analysis of longitudinal multiparametric MRI and molecular subtypes accurately predicts pathologic complete response in patients with invasive breast cancer. PLoS ONE. 2023;18: e0280320. https://doi.org/10.1371/journal.pone.0280320 .
doi: 10.1371/journal.pone.0280320
pubmed: 36649274
pmcid: 9844845