A radiogenomics application for prognostic profiling of endometrial cancer.
Journal
Communications biology
ISSN: 2399-3642
Titre abrégé: Commun Biol
Pays: England
ID NLM: 101719179
Informations de publication
Date de publication:
06 12 2021
06 12 2021
Historique:
received:
02
05
2021
accepted:
09
11
2021
entrez:
7
12
2021
pubmed:
8
12
2021
medline:
28
12
2021
Statut:
epublish
Résumé
Prognostication is critical for accurate diagnosis and tailored treatment in endometrial cancer (EC). We employed radiogenomics to integrate preoperative magnetic resonance imaging (MRI, n = 487 patients) with histologic-, transcriptomic- and molecular biomarkers (n = 550 patients) aiming to identify aggressive tumor features in a study including 866 EC patients. Whole-volume tumor radiomic profiling from manually (radiologists) segmented tumors (n = 138 patients) yielded clusters identifying patients with high-risk histological features and poor survival. Radiomic profiling by a fully automated machine learning (ML)-based tumor segmentation algorithm (n = 336 patients) reproduced the same radiomic prognostic groups. From these radiomic risk-groups, an 11-gene high-risk signature was defined, and its prognostic role was reproduced in orthologous validation cohorts (n = 554 patients) and aligned with The Cancer Genome Atlas (TCGA) molecular class with poor survival (copy-number-high/p53-altered). We conclude that MRI-based integrated radiogenomics profiling provides refined tumor characterization that may aid in prognostication and guide future treatment strategies in EC.
Identifiants
pubmed: 34873276
doi: 10.1038/s42003-021-02894-5
pii: 10.1038/s42003-021-02894-5
pmc: PMC8648740
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
1363Informations de copyright
© 2021. The Author(s).
Références
Sung, H. et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J. Clin. 71, 209–249 (2021).
pubmed: 33538338
doi: 10.3322/caac.21660
Lu, K. H. & Broaddus, R. R. Endometrial cancer. N. Engl. J. Med. 383, 2053–2064 (2020).
pubmed: 33207095
doi: 10.1056/NEJMra1514010
Colombo, N. et al. ESMO-ESGO-ESTRO consensus conference on endometrial cancer: diagnosis, treatment and follow-up. Ann. Oncol. 27, 16–41 (2017).
doi: 10.1093/annonc/mdv484
Marnitz, S. et al. A modern approach to endometrial carcinoma: will molecular classification improve precision medicine in the future? Cancers 12, 2577 (2020).
pmcid: 7564776
doi: 10.3390/cancers12092577
Haldorsen, I. S. & Salvesen, H. B. What is the best preoperative imaging for endometrial cancer? Curr. Oncol. Rep. 18, 25 (2016).
pubmed: 26922331
pmcid: 4769723
doi: 10.1007/s11912-016-0506-0
Expert Panel on GYN and OB Imaging, Reinhold, C. et al. ACR Appropriateness Criteria® pretreatment evaluation and follow-up of endometrial cancer. J. Am. Coll. Radiol. 17, S472–S486 (2020).
doi: 10.1016/j.jacr.2020.09.001
Lambin, P. et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat. Rev. Clin. Oncol. 14, 749–762 (2017).
pubmed: 28975929
doi: 10.1038/nrclinonc.2017.141
Lo Gullo, R., Daimiel, I., Morris, E. A. & Pinker, K. Combining molecular and imaging metrics in cancer: radiogenomics. Insights Imaging 11, 1 (2020).
pubmed: 31901171
pmcid: 6942081
doi: 10.1186/s13244-019-0795-6
Aerts, H. J. et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat. Commun. 5, 4006 (2014).
pubmed: 24892406
doi: 10.1038/ncomms5006
Lu, H. et al. A mathematical-descriptor of tumor-mesoscopic-structure from computed-tomography images annotates prognostic- and molecular-phenotypes of epithelial ovarian cancer. Nat. Commun. 10, 764 (2019).
pubmed: 30770825
pmcid: 6377605
doi: 10.1038/s41467-019-08718-9
Fan, M., Xia, P., Clarke, R., Wang, Y. & Li, L. Radiogenomic signatures reveal multiscale intratumour heterogeneity associated with biological functions and survival in breast cancer. Nat. Commun. 11, 4861 (2020).
pubmed: 32978398
pmcid: 7519071
doi: 10.1038/s41467-020-18703-2
Moussa, A. M. & Ziv, E. Radiogenomics in interventional oncology. Curr. Oncol. Rep. 23, 9 (2021).
pubmed: 33387095
doi: 10.1007/s11912-020-00994-9
Shiri, I. et al. Next-generation radiogenomics sequencing for prediction of EGFR and KRAS mutation status in NSCLC patients using multimodal imaging and machine learning algorithms. Mol. Imaging Biol. 22, 1132–1148 (2020).
pubmed: 32185618
doi: 10.1007/s11307-020-01487-8
Veeraraghavan, H. et al. Machine learning-based prediction of microsatellite instability and high tumor mutation burden from contrast-enhanced computed tomography in endometrial cancers. Sci. Rep. 10, 17769 (2020).
pubmed: 33082371
pmcid: 7575573
doi: 10.1038/s41598-020-72475-9
Ytre-Hauge, S. et al. Preoperative tumor size at MRI predicts deep myometrial invasion, lymph node metastases, and patient outcome in endometrial carcinomas. Int J. Gynecol. Cancer 25, 459–466 (2015).
pubmed: 25628109
pmcid: 4340601
doi: 10.1097/IGC.0000000000000367
Ytre-Hauge, S. et al. Preoperative tumor texture analysis on MRI predicts high-risk disease and reduced survival in endometrial cancer. J. Magn. Reson. Imaging 48, 1637–1647 (2018).
pubmed: 30102441
doi: 10.1002/jmri.26184
Ytre-Hauge, S., Salvesen, Ø. O., Krakstad, C., Trovik, J. & Haldorsen, I. S. Tumour texture features from preoperative CT predict high-risk disease in endometrial cancer. Clin. Radiol. 76, e13–79.e20 (2021).
doi: 10.1016/j.crad.2020.07.037
Jacob, H. et al. An MRI-based radiomic prognostic index predicts poor outcome and specific genetic alterations in endometrial cancer. J. Clin. Med. 10, 538 (2021).
pubmed: 33540589
pmcid: 7867221
doi: 10.3390/jcm10030538
Ueno, Y. et al. Endometrial carcinoma: MR imaging–based texture model for preoperative risk stratification—A preliminary analysis. Radiology 284, 748–757 (2017).
pubmed: 28493790
doi: 10.1148/radiol.2017161950
Chen, J. et al. MRI-based radiomic model for preoperative risk stratification in stage I endometrial cancer. J. Cancer 12, 726–734 (2021).
pubmed: 33403030
pmcid: 7778535
doi: 10.7150/jca.50872
Yan, B. C. et al. Preoperative assessment for high-risk endometrial cancer by developing an MRI- and clinical-based radiomics nomogram: a multicenter study. J. Magn. Reson. Imaging 52, 1872–1882 (2020).
pubmed: 32681608
doi: 10.1002/jmri.27289
Fasmer, K. E. et al. Whole-volume tumor MRI radiomics for prognostic modeling in endometrial cancer. J. Magn. Reson. Imaging 53, 928–937 (2020).
pubmed: 33200420
pmcid: 7894560
doi: 10.1002/jmri.27444
De Bernardi, E. et al. Radiomics of the primary tumor as a tool to improve
pubmed: 30136163
pmcid: 6104464
doi: 10.1186/s13550-018-0441-1
Xu, X. et al. Multiplanar MRI-based predictive model for preoperative assessment of lymph node metastasis in endometrial cancer. Front. Oncol. 9, 1007 (2019).
pubmed: 31649877
pmcid: 6794606
doi: 10.3389/fonc.2019.01007
Yan, B. C. et al. Radiologists with MRI-based radiomics aids to predict the pelvic lymph node metastasis in endometrial cancer: a multicenter study. Eur. Radiol. Epub. 31, 411–422 (2020).
doi: 10.1007/s00330-020-07099-8
Hodneland, E. et al. Automated segmentation of endometrial cancer on MR images using deep learning. Sci. Rep. 11, 179 (2021).
pubmed: 33420205
pmcid: 7794479
doi: 10.1038/s41598-020-80068-9
Dong, H. C., Dong, H. K., Yu, M. H., Lin, Y. H. & Chang, C. C. Using deep learning with convolutional neural network approach to identify the invasion depth of endometrial cancer in myometrium using MR images: a pilot study. Int J. Environ. Res. Public Health 17, 5993 (2020).
pmcid: 7460520
doi: 10.3390/ijerph17165993
Chen, X. et al. Deep learning for the determination of myometrial invasion depth and automatic lesion identification in endometrial cancer MR imaging: a preliminary study in a single institution. Eur. Radiol. 30, 4985–4994 (2020).
pubmed: 32337640
doi: 10.1007/s00330-020-06870-1
Guo, S. et al. PGK1 and GRP78 overexpression correlates with clinical significance and poor prognosis in Chinese endometrial cancer patients. Oncotarget 9, 680–690 (2017).
pubmed: 29416645
pmcid: 5787500
doi: 10.18632/oncotarget.23090
Teng, Y., Ai, Z., Wang, Y., Wang, J. & Luo, L. Proteomic identification of PKM2 and HSPA5 as potential biomarkers for predicting high-risk endometrial carcinoma. J. Obstet. Gynaecol. Res. 39, 317–325 (2013).
pubmed: 22889453
doi: 10.1111/j.1447-0756.2012.01970.x
Cancer Genome Atlas Research Network, Kandoth, C. et al. Integrated genomic characterization of endometrial carcinoma. Nature 497, 67–73 (2013).
doi: 10.1038/nature12113
Lin, Y. G. et al. Targeting the glucose-regulated protein-78 abrogates Pten-null driven AKT activation and endometrioid tumorigenesis. Oncogene 34, 5418–5426 (2015).
pubmed: 25684138
pmcid: 4537850
doi: 10.1038/onc.2015.4
Zhang, Y. et al. Cancer cells resistant to therapy promote cell surface relocalization of GRP78 which complexes with PI3K and enhances PI(3,4,5)P3 production. PLoS ONE 8, e80071 (2013).
pubmed: 24244613
pmcid: 3823711
doi: 10.1371/journal.pone.0080071
Hance, M. W. et al. Secreted Hsp90 is a novel regulator of the epithelial to mesenchymal transition (EMT) in prostate cancer. J. Biol. Chem. 287, 37732–37744 (2012).
pubmed: 22989880
pmcid: 3488049
doi: 10.1074/jbc.M112.389015
Wik, E. et al. Lack of estrogen receptor-α is associated with epithelial-mesenchymal transition and PI3K alterations in endometrial carcinoma. Clin. Cancer Res. 19, 1094–1105 (2013).
pubmed: 23319822
doi: 10.1158/1078-0432.CCR-12-3039
Jiang, G. et al. Cooperativity of co-factor NR2F2 with Pioneer Factors GATA3, FOXA1 in promoting ERα function. Theranostics 9, 6501–6516 (2019).
pubmed: 31588232
pmcid: 6771234
doi: 10.7150/thno.34874
Li, J., Xu, W. & Zhu, Y. Mammaglobin B may be a prognostic biomarker of uterine corpus endometrial cancer. Oncol. Lett. 20, 255 (2020).
pubmed: 32994818
pmcid: 7509766
doi: 10.3892/ol.2020.12118
Zhou, H. et al. Decreased secretoglobin family 2A member 1expression is associated with poor outcomes in endometrial cancer. Oncol. Lett. 20, 24 (2020).
pubmed: 32774497
pmcid: 7406884
Ao, X. et al. PBX1 is a valuable prognostic biomarker for patients with breast cancer. Exp. Ther. Med. 20, 385–394 (2020).
pubmed: 32565927
pmcid: 7286203
doi: 10.3892/etm.2020.8705
Thakur, V. S., Aguila, B., Brett-Morris, A., Creighton, C. J. & Welford, S. M. Spermidine/spermine N1-acetyltransferase 1 is a gene-specific transcriptional regulator that drives brain tumor aggressiveness. Oncogene 38, 6794–6800 (2019).
pubmed: 31399646
pmcid: 6786946
doi: 10.1038/s41388-019-0917-0
Wischhusen, J., Melero, I. & Fridman, W. H. Growth/differentiation factor-15 (GDF-15): from biomarker to novel targetable immune checkpoint. Front. Immunol. 11, 951 (2020).
pubmed: 32508832
pmcid: 7248355
doi: 10.3389/fimmu.2020.00951
Raulf, N. et al. Annexin A1 regulates EGFR activity and alters EGFR-containing tumour-derived exosomes in head and neck cancers. Eur. J. Cancer 102, 52–68 (2018).
pubmed: 30142511
doi: 10.1016/j.ejca.2018.07.123
Zhang, Z. et al. Underexpressed CNDP2 participates in gastric cancer growth inhibition through activating the MAPK signaling pathway. Mol. Med. 20, 17–28 (2014).
pubmed: 24395568
doi: 10.2119/molmed.2013.00102
Liao, H. Y., Da, C. M., Liao, B. & Zhang, H. H. Roles of matrix metalloproteinase-7 (MMP-7) in cancer. Clin. Biochem. 92, 9–18 (2021).
pubmed: 33713636
doi: 10.1016/j.clinbiochem.2021.03.003
Kong, Z. et al.
pubmed: 31426864
pmcid: 6701097
doi: 10.1186/s40644-019-0246-0
Tangen, I. L. et al. Loss of progesterone receptor links to high proliferation and increases from primary to metastatic endometrial cancer lesions. Eur. J. Cancer 50, 3003–3010 (2014).
pubmed: 25281525
doi: 10.1016/j.ejca.2014.09.003
Tangen, I. L. et al. Androgen receptor as potential therapeutic target in metastatic endometrial cancer. Oncotarget 7, 49289–49298 (2016).
pubmed: 27384477
pmcid: 5226508
doi: 10.18632/oncotarget.10334
Talhouk, A. et al. Confirmation of ProMisE: a simple, genomics-based clinical classifier for endometrial cancer. Cancer 123, 802–813 (2017).
pubmed: 28061006
doi: 10.1002/cncr.30496
Cox, R. W. et al. A (sort of) new Image data format standard: Nifti-1. we 150. Neuroimage 22, e1440 (2004).
Dale, A. M., Fischl, B. & Sereno, M. I. Cortical surface-based analysis. I. Segmentation and surface reconstruction. Neuroimage 9, 179–194 (1999).
doi: 10.1006/nimg.1998.0395
Woolrich, M. W. et al. Bayesian analysis of neuroimaging data in FSL. Neuroimage 45, S173–S186 (2009).
pubmed: 19059349
doi: 10.1016/j.neuroimage.2008.10.055
Çiçek, Ö. et al. 3D U-Net: learning dense volumetric segmentation from sparse annotation. In International Conference on Medical Image Computing and Computer-Assisted Intervention 424–432 (Springer, 2016).
Oliphant, T. Python for scientific computing. Comput. Sci. Eng. 9, 10–20 (2007).
doi: 10.1109/MCSE.2007.58
van der Walt, S. et al. scikit-image: image processing in Python. PeerJ 2, e453 (2014).
pubmed: 25024921
pmcid: 4081273
doi: 10.7717/peerj.453
Griethuysen, J. J. M. et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res. 77, e104–e107 (2017). 2017.
pubmed: 29092951
pmcid: 5672828
doi: 10.1158/0008-5472.CAN-17-0339
Lloyd, S. P. Least Squares Quantization in PCM. Report No. RR-5497 (Bell Lab, 1957).
Subramanian, A. et al. A next generation connectivity map: L1000 platform and the first 1,000,000 profiles. Cell 171, 1437–1452 (2017).
pubmed: 29195078
pmcid: 5990023
doi: 10.1016/j.cell.2017.10.049
Engerud, H. et al. High degree of heterogeneity of PD-L1 and PD-1 from primary to metastatic endometrial cancer. Gynecol Oncol. 157, 260–267 (2020).
León-Castillo, A. et al. Interpretation of somatic POLE mutations in endometrial carcinoma. J. Pathol. 250, 323–335 (2020).
pubmed: 31829442
pmcid: 7065171
doi: 10.1002/path.5372
Cerami, E. et al. The cBio cancer genomics portal: an open platform for exploring multidimensional cancer genomics data. Cancer Discov. 2, 401–404 (2012).
pubmed: 22588877
doi: 10.1158/2159-8290.CD-12-0095
Gao, J. et al. Integrative analysis of complex cancer genomics and clinical profiles using the cBioPortal. Sci. Signal. 6, 269 (2013).
doi: 10.1126/scisignal.2004088
Kusonmano, K. et al. Identification of highly connected and differentially expressed gene subnetworks in metastasizing endometrial cancer. PLoS ONE 13, e0206665 (2018).
pubmed: 30383835
pmcid: 6211718
doi: 10.1371/journal.pone.0206665
Berg, H. F. et al. Patient-derived organoids reflect the genetic profile of endometrial tumors and predict patient prognosis. Commun. Med. 1, 20 (2021).
doi: 10.1038/s43856-021-00019-x