Skip to main content
SpringerLink
Log in

Shape and texture analyses based on conventional MRI for the preoperative prediction of the aggressiveness of pituitary adenomas

  • Magnetic Resonance
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objectives

Pituitary adenomas can exhibit aggressive behavior, characterized by rapid growth, resistance to conventional treatment, and early recurrence. This study aims to evaluate the clinical value of shape-related features combined with textural features based on conventional MRI in evaluating the aggressiveness of pituitary adenomas and develop the best diagnostic model.

Methods

Two hundred forty-six pituitary adenoma patients (84 aggressive, 162 non-aggressive) who underwent preoperative MRI were retrospectively reviewed. The patients were divided into training (n = 193) and testing (n = 53) sets. Clinical information, shape-related, and textural features extracted from the tumor volume on contrast-enhanced T1-weighted images (CE-T1WI), were compared between aggressive and non-aggressive groups. Variables with significant differences were enrolled into Pearson’s correlation analysis to weaken multicollinearity. Logistic regression models based on the selected features were constructed to predict tumor aggressiveness under fivefold cross-validation.

Results

Sixty-five imaging features, including five shape-related and sixty textural features, were extracted from volumetric CE-T1WI. Forty-seven features were significantly different between aggressive and non-aggressive groups (all p values < 0.05). After feature selection, four features (SHAPE_Sphericity, SHAPE_Compacity, DISCRETIZED_Q3, and DISCRETIZED_Kurtosis) were put into logistic regression analysis. Based on the combination of these features and Knosp grade, the model yielded an area under the curve value of 0.935, with a sensitivity of 94.4% and a specificity of 82.9%, to discriminate between aggressive and non-aggressive pituitary adenomas in the testing set.

Conclusion

The radiomic model based on tumor shape and textural features study from CE-T1WI might potentially assist in the preoperative aggressiveness diagnosis of pituitary adenomas.

Key Points

• Pituitary adenomas with aggressive behavior exhibit rapid growth, resistance to conventional treatment, and early recurrence despite gross resection and may require multiline treatments.

• Shape-related features and texture features based on CE-T1WI were significantly correlated with the Ki-67 labeling index, mitotic count, and p53 expression, and the proposed model achieved a favorable prediction of the aggressiveness of PAs with an AUC value of 0.935.

• The prediction model might provide valuable guidance for individualized treatment in patients with PAs.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Abbreviations

AUC:

Area under the curve

CE-T1WI:

Contrast-enhanced T1-weighted image

ESE:

European Society of Endocrinology

PAs:

Pituitary adenomas

ROC:

Receiver operating characteristic

WHO:

World Health Organization

References

  1. Di Ieva A, Rotondo F, Syro LV, Cusimano MD, Kovacs K (2014) Aggressive pituitary adenomas—diagnosis and emerging treatments. Nat Rev Endocrinol. https://doi.org/10.1038/nrendo.2014.64

    Article  PubMed  Google Scholar 

  2. Dekkers OM, Karavitaki N, Pereira AM (2020) The epidemiology of aggressive pituitary tumors (and its challenges). Rev Endocr Metab Disord. https://doi.org/10.1007/s11154-020-09556-7

    Article  PubMed  PubMed Central  Google Scholar 

  3. Raverot G, Burman P, McCormack A et al (2018) European Society of Endocrinology Clinical Practice Guidelines for the management of aggressive pituitary tumours and carcinomas. Eur J Endocrinol. https://doi.org/10.1530/eje-17-0796

    Article  PubMed  Google Scholar 

  4. Salehi F, Agur A, Scheithauer BW et al (2009) Ki-67 in pituitary neoplasms: a review–part I. Neurosurgery. https://doi.org/10.1227/01.Neu.0000349930.66434.82

    Article  PubMed  Google Scholar 

  5. Jaffrain-Rea ML, Di Stefano D, Minniti G et al (2002) A critical reappraisal of MIB-1 labelling index significance in a large series of pituitary tumours: secreting versus non-secreting adenomas. Endocr Relat Cancer. https://doi.org/10.1677/erc.0.0090103

    Article  PubMed  Google Scholar 

  6. Gejman R, Swearingen B, Hedley-Whyte ET (2008) Role of Ki-67 proliferation index and p53 expression in predicting progression of pituitary adenomas. Hum Pathol. https://doi.org/10.1016/j.humpath.2007.10.004

    Article  PubMed  Google Scholar 

  7. Hasanov R, Aydoğan B, Kiremitçi S, Erden E, Güllü S (2019) The prognostic roles of the Ki-67 proliferation index, P53 expression, mitotic index, and radiological tumor invasion in pituitary adenomas. Endocr Pathol. https://doi.org/10.1007/s12022-018-9563-2

    Article  PubMed  Google Scholar 

  8. Raverot G, Dantony E, Beauvy J et al (2017) Risk of recurrence in pituitary neuroendocrine tumors: a prospective study using a five-tiered classification. J Clin Endocrinol Metab. https://doi.org/10.1210/jc.2017-00773

    Article  PubMed  Google Scholar 

  9. Trouillas J, Roy P, Sturm N et al (2013) A new prognostic clinicopathological classification of pituitary adenomas: a multicentric case-control study of 410 patients with 8 years post-operative follow-up. Acta Neuropathol. https://doi.org/10.1007/s00401-013-1084-y

    Article  PubMed  Google Scholar 

  10. Raverot G, Ilie M, Lasolle H et al (2021) Aggressive pituitary tumours and pituitary carcinomas. Nat Rev Endocrinol. https://doi.org/10.1038/s41574-021-00550-w

    Article  PubMed  Google Scholar 

  11. Smirniotopoulos JG, Murphy FM, Rushing EJ, Rees JH, Schroeder JW (2007) Patterns of contrast enhancement in the brain and meninges. Radiographics. https://doi.org/10.1148/rg.272065155

  12. Ingrisch M, Schneider MJ, Nörenberg D et al (2017) Radiomic analysis reveals prognostic information in T1-weighted baseline magnetic resonance imaging in patients with glioblastoma. Invest Radiol. https://doi.org/10.1097/rli.0000000000000349

    Article  PubMed  Google Scholar 

  13. Danieli L, Riccitelli GC, Distefano D et al (2019) Brain tumor-enhancement visualization and morphometric assessment: a comparison of MPRAGE, SPACE, and VIBE MRI techniques. AJNR Am J Neuroradiol. https://doi.org/10.3174/ajnr.A6096

    Article  PubMed  PubMed Central  Google Scholar 

  14. Li N, Mo Y, Huang C et al (2021) A clinical semantic and radiomics nomogram for predicting brain invasion in WHO grade II meningioma based on tumor and tumor-to-brain interface features. Front Oncol. https://doi.org/10.3389/fonc.2021.752158

    Article  PubMed  PubMed Central  Google Scholar 

  15. Galm BP, Martinez-Salazar EL, Swearingen B et al (2018) MRI texture analysis as a predictor of tumor recurrence or progression in patients with clinically non-functioning pituitary adenomas. Eur J Endocrinol. https://doi.org/10.1530/eje-18-0291

    Article  PubMed  Google Scholar 

  16. Ong T, Bharatha A, Alsufayan R, Das S, Lin AW (2021) MRI predictors for brain invasion in meningiomas. Neuroradiol J. https://doi.org/10.1177/1971400920953417

    Article  PubMed  Google Scholar 

  17. P L, E R-V, R L, et al (2012) Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer. https://doi.org/10.1016/j.ejca.2011.11.036

    Article  Google Scholar 

  18. Lambin P, Leijenaar RTH, Deist TM et al (2017) Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol. https://doi.org/10.1038/nrclinonc.2017.141

    Article  PubMed  Google Scholar 

  19. Kniep HC, Madesta F, Schneider T et al (2019) Radiomics of brain MRI: utility in prediction of metastatic tumor type. Radiology. https://doi.org/10.1148/radiol.2018180946

    Article  PubMed  Google Scholar 

  20. Sun Q, Chen Y, Liang C, et al. Biologic pathways underlying prognostic radiomics phenotypes from paired MRI and RNA sequencing in glioblastoma. Radiology. doi:https://doi.org/10.1148/radiol.2021203281

  21. Rui W, Qiao N, Wu Y et al (2022) Radiomics analysis allows for precise prediction of silent corticotroph adenoma among non-functioning pituitary adenomas. Eur Radiol. https://doi.org/10.1007/s00330-021-08361-3

    Article  PubMed  Google Scholar 

  22. Ugga L, Cuocolo R, Solari D et al (2019) Prediction of high proliferative index in pituitary macroadenomas using MRI-based radiomics and machine learning. Neuroradiology. https://doi.org/10.1007/s00234-019-02266-1

    Article  PubMed  Google Scholar 

  23. Niu J, Zhang S, Ma S et al (2019) Preoperative prediction of cavernous sinus invasion by pituitary adenomas using a radiomics method based on magnetic resonance images. Eur Radiol. https://doi.org/10.1007/s00330-018-5725-3

    Article  PubMed  PubMed Central  Google Scholar 

  24. Li Y, Yan C, Weng S et al (2019) Texture analysis of multi-phase MRI images to detect expression of Ki67 in hepatocellular carcinoma. Clin Radiol. https://doi.org/10.1016/j.crad.2019.06.024

    Article  PubMed  Google Scholar 

  25. Blanchet L, Krooshof PWT, Postma GJ et al (2011) Discrimination between metastasis and glioblastoma multiforme based on morphometric analysis of MR images. AJNR Am J Neuroradiol. https://doi.org/10.3174/ajnr.A2269

    Article  PubMed  PubMed Central  Google Scholar 

  26. Cui Y, Tha KK, Terasaka S et al (2016) Prognostic imaging biomarkers in glioblastoma: development and independent validation on the basis of multiregion and quantitative analysis of MR images. Radiology. https://doi.org/10.1148/radiol.2015150358

    Article  PubMed  Google Scholar 

  27. Stoyanova R, Takhar M, Tschudi Y et al (2016) Prostate cancer radiomics and the promise of radiogenomics. Transl Cancer Res. https://doi.org/10.21037/tcr.2016.06.20

    Article  PubMed  Google Scholar 

  28. Yang G, Jones TL, Howe FA, Barrick TR (2016) Morphometric model for discrimination between glioblastoma multiforme and solitary metastasis using three-dimensional shape analysis. Magn Reson Med. https://doi.org/10.1002/mrm.25845

    Article  PubMed  PubMed Central  Google Scholar 

  29. Aerts HJ, Velazquez ER, Leijenaar RT et al (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun. https://doi.org/10.1038/ncomms5006

    Article  PubMed  PubMed Central  Google Scholar 

  30. Pérez-Beteta J, Molina-García D, Ortiz-Alhambra JA et al (2018) Tumor surface regularity at MR imaging predicts survival and response to surgery in patients with glioblastoma. Radiology. https://doi.org/10.1148/radiol.2018171051

    Article  PubMed  Google Scholar 

  31. Liu YQ, Gao BB, Dong B et al (2020) Preoperative vascular heterogeneity and aggressiveness assessment of pituitary macroadenoma based on dynamic contrast-enhanced MRI texture analysis. Eur J Radiol. https://doi.org/10.1016/j.ejrad.2020.109125

    Article  PubMed  PubMed Central  Google Scholar 

  32. Knosp E, Steiner E, Kitz K, Matula C (1993) Pituitary adenomas with invasion of the cavernous sinus space: a magnetic resonance imaging classification compared with surgical findings. Neurosurgery. https://doi.org/10.1227/00006123-199310000-00008

    Article  PubMed  Google Scholar 

  33. Micko ASG, Wöhrer A, Höftberger R et al (2017) MGMT and MSH6 immunoexpression for functioning pituitary macroadenomas. Pituitary. https://doi.org/10.1007/s11102-017-0829-3

    Article  PubMed  PubMed Central  Google Scholar 

  34. Nioche C, Orlhac F, Boughdad S et al (2018) LIFEx: a freeware for radiomic feature calculation in multimodality imaging to accelerate advances in the characterization of tumor heterogeneity. Cancer Res. https://doi.org/10.1158/0008-5472.Can-18-0125

    Article  PubMed  Google Scholar 

  35. Zwanenburg A, Vallières M, Abdalah MA, et al. (2020) The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping. Radiology 295:328–338

  36. Sollini M, Cozzi L, Antunovic L, Chiti A, Kirienko M (2017) PET radiomics in NSCLC: state of the art and a proposal for harmonization of methodology. Sci Rep. https://doi.org/10.1038/s41598-017-00426-y

    Article  PubMed  PubMed Central  Google Scholar 

  37. Deisboeck TS, Guiot C, Delsanto PP, Pugno N (2006) Does cancer growth depend on surface extension? Med Hypotheses 67:1338–1341

  38. Caruana G, Pessini LM, Cannella R et al (2020) Texture analysis in susceptibility-weighted imaging may be useful to differentiate acute from chronic multiple sclerosis lesions. Eur Radiol. https://doi.org/10.1007/s00330-020-06995-3

    Article  PubMed  Google Scholar 

  39. Lopes MBS (2017) The 2017 World Health Organization classification of tumors of the pituitary gland: a summary. Acta Neuropathol. https://doi.org/10.1007/s00401-017-1769-8

    Article  PubMed  Google Scholar 

  40. Madsen H, Borges TM, Knox AJ et al (2011) Giant pituitary adenomas: pathologic-radiographic correlations and lack of role for p53 and MIB-1 labeling. Am J Surg Pathol. https://doi.org/10.1097/PAS.0b013e31821e8c96

    Article  PubMed  Google Scholar 

  41. Batista GE, Prati RC, Monard MC (2004) A study of the behavior of several methods for balancing machine learning training data. ACM SIGKDD explorations newsletter.

  42. Song Y, Zhang J, Zhang YD et al (2020) FeAture Explorer (FAE): a tool for developing and comparing radiomics models. PLoS One. https://doi.org/10.1371/journal.pone.0237587

    Article  PubMed  PubMed Central  Google Scholar 

  43. George DH, Scheithauer BW, Kovacs K et al (2003) Crooke’s cell adenoma of the pituitary: an aggressive variant of corticotroph adenoma. Am J Surg Pathol. https://doi.org/10.1097/00000478-200310000-00005

    Article  PubMed  Google Scholar 

  44. Raverot G, Castinetti F, Jouanneau E et al (2012) Pituitary carcinomas and aggressive pituitary tumours: merits and pitfalls of temozolomide treatment. Clin Endocrinol. https://doi.org/10.1111/j.1365-2265.2012.04381.x

    Article  Google Scholar 

  45. Conficoni A, Feraco P, Mazzatenta D et al (2020) Biomarkers of pituitary macroadenomas aggressive behaviour: a conventional MRI and DWI 3T study. Br J Radiol. https://doi.org/10.1259/bjr.20200321

    Article  PubMed  PubMed Central  Google Scholar 

  46. Giesel FL, Mehndiratta A, Essig M (2010) High-relaxivity contrast-enhanced magnetic resonance neuroimaging: a review. Eur Radiol. https://doi.org/10.1007/s00330-010-1805-8

    Article  PubMed  Google Scholar 

  47. Lu CF, Hsu FT, Hsieh KL et al (2018) Machine Learning-Based Radiomics for Molecular Subtyping of Gliomas. Clin Cancer Res. https://doi.org/10.1158/1078-0432.Ccr-17-3445

    Article  PubMed  PubMed Central  Google Scholar 

  48. Zhou H, Vallières M, Bai HX et al (2017) MRI features predict survival and molecular markers in diffuse lower-grade gliomas. Neuro Oncol. https://doi.org/10.1093/neuonc/now256

    Article  PubMed  PubMed Central  Google Scholar 

  49. Yang G, Jones TL, Barrick TR, Howe FA (2014) Discrimination between glioblastoma multiforme and solitary metastasis using morphological features derived from the p:q tensor decomposition of diffusion tensor imaging. NMR Biomed. https://doi.org/10.1002/nbm.3163

    Article  PubMed  PubMed Central  Google Scholar 

  50. Berkmann S, Lattmann J, Schuetz P et al (2021) The Shape grading system: a classification for growth patterns of pituitary adenomas. Acta Neurochir. https://doi.org/10.1007/s00701-021-04912-1

    Article  PubMed  Google Scholar 

  51. Asano D, Kudo A, Akahoshi K et al (2020) Curative surgery and Ki-67 value rather than tumor differentiation predict the survival of patients with high-grade neuroendocrine neoplasms. Ann Surg. https://doi.org/10.1097/sla.0000000000004495

    Article  PubMed  Google Scholar 

  52. Sav A, Rotondo F, Syro LV, Scheithauer BW, Kovacs K (2012) Biomarkers of pituitary neoplasms. Anticancer Res 32:4639–4654

  53. Frieboes HB, Zheng X, Sun CH et al (2006) An integrated computational/experimental model of tumor invasion. Cancer Res. https://doi.org/10.1158/0008-5472.Can-05-3166

    Article  PubMed  Google Scholar 

  54. Zou H (2013) Variable selection. Editorial. Stat Methods Med Res. https://doi.org/10.1177/0962280213506395

  55. Cozzi L, Dinapoli N, Fogliata A et al (2017) Radiomics based analysis to predict local control and survival in hepatocellular carcinoma patients treated with volumetric modulated arc therapy. BMC Cancer. https://doi.org/10.1186/s12885-017-3847-7

    Article  PubMed  PubMed Central  Google Scholar 

  56. Lam KY (2017) Update on Adrenal Tumours in 2017 World Health Organization (WHO) of Endocrine Tumours. Endocrine pathology.

  57. Delgrange E, Trouillas J, Maiter D, Donckier J, Tourniaire J (1997) Sex-related difference in the growth of prolactinomas: a clinical and proliferation marker study. J Clin Endocrinol Metab. https://doi.org/10.1210/jcem.82.7.4088

    Article  PubMed  Google Scholar 

  58. Obari A, Sano T, Ohyama K et al (2008) Clinicopathological features of growth hormone-producing pituitary adenomas: difference among various types defined by cytokeratin distribution pattern including a transitional form. Endocr Pathol. https://doi.org/10.1007/s12022-008-9029-z

    Article  PubMed  Google Scholar 

Download references

Funding

This study has received funding by the National Natural Science Foundation of China (grant no.82171885), Shanghai Science and Technology Committee Project (Natural Science Funding; grant no.20ZR1433200), and Shanghai Science and Technology Committee Project (the Explorer Project Funding; grant no. 21TS1400700).

Author information

Authors and Affiliations

  1. Department of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China

    Xiaoqing Wang, Jiahui Cheng, Yiming Zhang, Mengqiu Cao & Yan Zhou

  2. Central Research Institute, United Imaging Healthcare, Shanghai, China

    Yongming Dai & Hai Lin

Authors
  1. Xiaoqing Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yongming Dai
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hai Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jiahui Cheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yiming Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Mengqiu Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Yan Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Mengqiu Cao or Yan Zhou.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Yan Zhou.

Conflict of interest

The authors (Yongming Dai and Hai Lin) of this manuscript declare relationships with the following companies: United Imaging Healthcare. The remaining authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.

Methodology

• retrospective

• case–control study

• performed at one institution

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 41 kb)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, X., Dai, Y., Lin, H. et al. Shape and texture analyses based on conventional MRI for the preoperative prediction of the aggressiveness of pituitary adenomas. Eur Radiol 33, 3312–3321 (2023). https://doi.org/10.1007/s00330-023-09412-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-023-09412-7

Keywords

Search

Navigation