, Volume 61, Issue 12, pp 1365–1373 | Cite as

Prediction of high proliferative index in pituitary macroadenomas using MRI-based radiomics and machine learning

  • Lorenzo Ugga
  • Renato CuocoloEmail author
  • Domenico Solari
  • Elia Guadagno
  • Alessandra D’Amico
  • Teresa Somma
  • Paolo Cappabianca
  • Maria Laura del Basso de Caro
  • Luigi Maria Cavallo
  • Arturo Brunetti
Diagnostic Neuroradiology



Pituitary adenomas are among the most frequent intracranial tumors. They may exhibit clinically aggressive behavior, with recurrent disease and resistance to multimodal therapy. The ki-67 labeling index represents a proliferative marker which correlates with pituitary adenoma aggressiveness. Aim of our study was to assess the accuracy of machine learning analysis of texture-derived parameters from pituitary adenomas preoperative MRI for the prediction of ki-67 proliferation index class.


A total of 89 patients who underwent an endoscopic endonasal procedure for pituitary adenoma removal with available ki-67 labeling index were included. From T2w MR images, 1128 quantitative imaging features were extracted. To select the most informative features, different supervised feature selection methods were employed. Subsequently, a k-nearest neighbors (k-NN) classifier was employed to predict macroadenoma high or low proliferation index. Algorithm validation was performed with a train-test approach.


Of the 12 subsets derived from feature selection, the best performing one was constituted by the 4 highest correlating parameters at Pearson’s test. These all showed very good (ICC ≥ 0.85) inter-observer reproducibility. The overall accuracy of the k-NN in the test group was of 91.67% (33/36) of correctly classified patients.


Machine learning analysis of texture-derived parameters from preoperative T2 MRI has proven to be effective for the prediction of pituitary macroadenomas ki-67 proliferation index class. This might aid the surgical strategy making a more accurate preoperative lesion classification and allow for a more focused and cost-effective follow-up and long-term management.


Machine learning Magnetic resonance imaging Pituitary adenoma 



No funding was received for this study.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

All procedures performed in the studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards.

Informed consent

Requirement for informed consent was waived by the local IRB.


  1. 1.
    Daly AF, Rixhon M, Adam C, Dempegioti A, Tichomirowa MA, Beckers A (2006) High prevalence of pituitary adenomas: a cross-sectional study in the province of Liège, Belgium. J Clin Endocrinol Metab 91:4769–4775. CrossRefPubMedGoogle Scholar
  2. 2.
    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 126:123–135. CrossRefPubMedGoogle Scholar
  3. 3.
    Paek K-I, Kim S-H, Song S-H, Choi SW, Koh HS, Youm JY, Kim Y (2005) Clinical significance of Ki-67 labeling index in pituitary macroadenoma. J Korean Med Sci 20:489. CrossRefPubMedPubMedCentralGoogle Scholar
  4. 4.
    Chatzellis E, Alexandraki KI, Androulakis II, Kaltsas G (2015) Aggressive pituitary tumors. Neuroendocrinology 101:87–104. CrossRefPubMedGoogle Scholar
  5. 5.
    Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577. CrossRefPubMedGoogle Scholar
  6. 6.
    Senders JT, Zaki MM, Karhade AV, Chang B, Gormley WB, Broekman ML, Smith TR, Arnaout O (2018) An introduction and overview of machine learning in neurosurgical care. Acta Neurochir 160:29–38. CrossRefPubMedGoogle Scholar
  7. 7.
    Stanzione A, Cuocolo R, Cocozza S, Romeo V, Persico F, Fusco F, Longo N, Brunetti A, Imbriaco M (2019) Detection of extraprostatic extension of cancer on biparametric MRI combining texture analysis and machine learning: preliminary results. Acad Radiol:1–7. CrossRefGoogle Scholar
  8. 8.
    Romeo V, Maurea S, Cuocolo R, Petretta M, Mainenti PP, Verde F, Coppola M, Dell’Aversana S, Brunetti A (2018) Characterization of adrenal lesions on unenhanced MRI using texture analysis: a machine-learning approach. J Magn Reson Imaging 48:198–204. CrossRefPubMedGoogle Scholar
  9. 9.
    Kadir T, Gleeson F (2018) Lung cancer prediction using machine learning and advanced imaging techniques. Transl Lung Cancer Res 7:304–312. CrossRefPubMedPubMedCentralGoogle Scholar
  10. 10.
    Fan M, Cheng H, Zhang P, Gao X, Zhang J, Shao G, Li L (2018) DCE-MRI texture analysis with tumor subregion partitioning for predicting Ki-67 status of estrogen receptor-positive breast cancers. J Magn Reson Imaging 48:237–247. CrossRefPubMedGoogle Scholar
  11. 11.
    Imbriaco M, Cuocolo R (2018) Does texture analysis of MR images of breast tumors help predict response to treatment? Radiology 286:421–423. CrossRefPubMedGoogle Scholar
  12. 12.
    Liu S, Zheng H, Zhang Y, Chen L, Guan W, Guan Y, Ge Y, He J, Zhou Z (2018) Whole-volume apparent diffusion coefficient-based entropy parameters for assessment of gastric cancer aggressiveness. J Magn Reson Imaging 47:168–175. CrossRefPubMedGoogle Scholar
  13. 13.
    Cuocolo R, Stanzione A, Ponsiglione A, Romeo V, Verde F, Creta M, la Rocca R, Longo N, Pace L, Imbriaco M (2019) Clinically significant prostate cancer detection on MRI: a radiomic shape features study. Eur J Radiol 116:144–149. CrossRefPubMedGoogle Scholar
  14. 14.
    Romeo V, Ricciardi C, Cuocolo R, Stanzione A, Verde F, Sarno L, Improta G, Mainenti PP, D’Armiento M, Brunetti A, Maurea S (2019) Machine learning analysis of MRI-derived texture features to predict placenta accreta spectrum in patients with placenta previa. Magn Reson Imaging.
  15. 15.
    Cappabianca P, Cavallo LM, Solari D, Stagno V, Esposito F, de Angelis M (2014) Endoscopic endonasal surgery for pituitary adenomas. World Neurosurg 82:S3–S11. CrossRefPubMedGoogle Scholar
  16. 16.
    de Notaris M, Solari D, Cavallo LM, D’Enza AI, Enseñat J, Berenguer J, Ferrer E, Prats-Galino A, Cappabianca P (2012) The “suprasellar notch,” or the tuberculum sellae as seen from below: definition, features, and clinical implications from an endoscopic endonasal perspective. J Neurosurg 116:622–629. CrossRefPubMedGoogle Scholar
  17. 17.
    Kassam A, Snyderman CH, Mintz A, et al (2005) Expanded endonasal approach: the rostrocaudal axis. Part I. Crista galli to the sella turcica. Neurosurg FocusGoogle Scholar
  18. 18.
    Solari D, Cavallo LM, Cappabianca P (2014) Surgical approach to pituitary tumors. Handb Clin Neurol 124:291–301. CrossRefPubMedGoogle Scholar
  19. 19.
    Cappabianca P, Cavallo LM, Esposito F, de Divitiis O, Messina A, de Divitiis E (2008) Extended endoscopic endonasal approach to the midline skull base: the evolving role of transsphenoidal surgery. In: Pickard JD, Akalan N, Di Rocco C et al (eds) Advances and technical standards in neurosurgery. Springer Vienna, Vienna, pp 151–199CrossRefGoogle Scholar
  20. 20.
    Yushkevich PA, Piven J, Hazlett HC, Smith RG, Ho S, Gee JC, Gerig G (2006) User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. Neuroimage 31:1116–1128. CrossRefPubMedGoogle Scholar
  21. 21.
    van Griethuysen JJM, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V, Beets-Tan RGH, Fillion-Robin JC, Pieper S, Aerts HJWL (2017) Computational radiomics system to decode the radiographic phenotype. Cancer Res 77:e104–e107. CrossRefPubMedPubMedCentralGoogle Scholar
  22. 22.
    Leijenaar RTH, Nalbantov G, Carvalho S, van Elmpt WJC, Troost EGC, Boellaard R, Aerts HJWL, Gillies RJ, Lambin P (2015) The effect of SUV discretization in quantitative FDG-PET Radiomics: the need for standardized methodology in tumor texture analysis. Sci Rep 5:11075. CrossRefPubMedPubMedCentralGoogle Scholar
  23. 23.
    Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern SMC-3:610–621. CrossRefGoogle Scholar
  24. 24.
    THIBAULT G, FERTIL B, NAVARRO C, PEREIRA S, CAU P, LEVY N, SEQUEIRA J, MARI JL (2013) Shape and texture indexes application to cell nuclei classification. Int J Pattern Recognit Artif Intell 27:1357002. CrossRefGoogle Scholar
  25. 25.
    Galloway MM (1975) Texture analysis using gray level run lengths. Comput Graph Image Process 4:172–179. CrossRefGoogle Scholar
  26. 26.
    Amadasun M, King R (1989) Textural features corresponding to textural properties. IEEE Trans Syst Man Cybern 19:1264–1274. CrossRefGoogle Scholar
  27. 27.
    Sun C, Wee WG (1983) Neighboring gray level dependence matrix for texture classification. Comput Vision, Graph Image Process 23:341–352. CrossRefGoogle Scholar
  28. 28.
    Cai J, Luo J, Wang S, Yang S (2018) Feature selection in machine learning: a new perspective. Neurocomputing 300:70–79. CrossRefGoogle Scholar
  29. 29.
    Eibe F, Hall MA, Witten IH (2016) The WEKA Workbench. Online Appendix for “Data Mining: Practical Machine Learning Tools and Techniques,” Fourth Edi. Morgan KaufmannGoogle Scholar
  30. 30.
    Juntu J, Sijbers J, De Backer S et al (2010) Machine learning study of several classifiers trained with texture analysis features to differentiate benign from malignant soft-tissue tumors in T1-MRI images. J Magn Reson Imaging 31:680–689. CrossRefPubMedGoogle Scholar
  31. 31.
    Siva Kumar N (1996) An affinity method for the purification of mannose 6-phosphate receptor proteins (MPR 215) from rat tissues and goat liver. J Biochem Biophys Methods 31:181–184. CrossRefGoogle Scholar
  32. 32.
    Aha DW, Kibler D, Albert MK (1991) Instance-based learning algorithms. Mach Learn 6:37–66. CrossRefGoogle Scholar
  33. 33.
    Thapar K, Kovacs K, Scheithauer BW, Stefaneanu L, Horvath E, Peter J. P, Murray D, Laws ER Jr (1996) Proliferative activity and invasiveness among pituitary adenomas and carcinomas: an analysis using the MIB-1 antibody. Neurosurgery 38:99–107. CrossRefPubMedGoogle Scholar
  34. 34.
    Brennan P, Silman A (1992) Statistical methods for assessing observer variability in clinical measures. BMJ 304:1491–1494. CrossRefPubMedPubMedCentralGoogle Scholar
  35. 35.
    Del Basso De Caro M, Solari D, Pagliuca F et al (2017) Atypical pituitary adenomas: clinical characteristics and role of ki-67 and p53 in prognostic and therapeutic evaluation. A series of 50 patients. Neurosurg Rev 40:105–114. CrossRefGoogle Scholar
  36. 36.
    Vasiljevic A, Jouanneau E, Trouillas J, Raverot G (2016) Clinicopathological prognostic and theranostic markers in pituitary tumors. Minerva Endocrinol 41:377–389PubMedGoogle Scholar
  37. 37.
    Mete O, Lopes MB (2017) Overview of the 2017 WHO classification of pituitary tumors. Endocr Pathol 28:228–243. CrossRefPubMedGoogle Scholar
  38. 38.
    Inoshita N, Nishioka H (2018) The 2017 WHO classification of pituitary adenoma: overview and comments. Brain Tumor Pathol 35:51–56. CrossRefPubMedGoogle Scholar
  39. 39.
    Hollon TC, Parikh A, Pandian B, Tarpeh J, Orringer DA, Barkan AL, McKean EL, Sullivan SE (2018) A machine learning approach to predict early outcomes after pituitary adenoma surgery. Neurosurg Focus 45:1–9. CrossRefGoogle Scholar
  40. 40.
    Staartjes VE, Serra C, Muscas G, et al (2018) Utility of deep neural networks in predicting gross-total resection after transsphenoidal surgery for pituitary adenoma: a pilot study 45:1–7 . doi: CrossRefGoogle Scholar
  41. 41.
    Zhang S, Song G, Zang Y, Jia J, Wang C, Li C, Tian J, Dong D, Zhang Y (2018) Non-invasive radiomics approach potentially predicts non-functioning pituitary adenomas subtypes before surgery. Eur Radiol 28:3692–3701. CrossRefPubMedGoogle Scholar
  42. 42.
    Niu J, Tian J, Zhou W et al (2018) Preoperative prediction of cavernous sinus invasion by pituitary adenomas using a radiomics method based on magnetic resonance images. Eur Radiol 29:1625–1634. CrossRefPubMedPubMedCentralGoogle Scholar
  43. 43.
    Tamrazi B, Pekmezci M, Aboian M, Tihan T, Glastonbury CM (2017) Apparent diffusion coefficient and pituitary macroadenomas: pre-operative assessment of tumor atypia. Pituitary 20:195–200. CrossRefPubMedGoogle Scholar
  44. 44.
    Hua J, Xiong Z, Lowey J, Suh E, Dougherty ER (2005) Optimal number of features as a function of sample size for various classification rules. Bioinformatics 21:1509–1515. CrossRefPubMedGoogle Scholar
  45. 45.
    Zaharchuk G, Gong E, Wintermark M, Rubin D, Langlotz CP (2018) Deep learning in neuroradiology. Am J Neuroradiol 39:1776–1784. CrossRefPubMedGoogle Scholar
  46. 46.
    Sanei Taheri M, Kimia F, Mehrnahad M, Saligheh Rad H, Haghighatkhah H, Moradi A, Kazerooni AF, Alviri M, Absalan A (2019) Accuracy of diffusion-weighted imaging-magnetic resonance in differentiating functional from non-functional pituitary macro-adenoma and classification of tumor consistency. Neuroradiol J 32:74–85. CrossRefPubMedGoogle Scholar
  47. 47.
    Wei L, Lin S-A, Fan K et al (2015) Relationship between pituitary adenoma texture and collagen content revealed by comparative study of MRI and pathology analysis. Int J Clin Exp Med 8:12898–12905PubMedPubMedCentralGoogle Scholar
  48. 48.
    Zeynalova A, Kocak B, Durmaz ES, Comunoglu N, Ozcan K, Ozcan G, Turk O, Tanriover N, Kocer N, Kizilkilic O, Islak C (2019) Preoperative evaluation of tumour consistency in pituitary macroadenomas: a machine learning-based histogram analysis on conventional T2-weighted MRI. Neuroradiology 61:767–774. CrossRefPubMedGoogle Scholar
  49. 49.
    Heck A, Emblem KE, Casar-Borota O, Bollerslev J, Ringstad G (2016) Quantitative analyses of T2-weighted MRI as a potential marker for response to somatostatin analogs in newly diagnosed acromegaly. Endocrine 52:333–343. CrossRefPubMedGoogle Scholar
  50. 50.
    Kocak B, Durmaz ES, Kadioglu P, Polat Korkmaz O, Comunoglu N, Tanriover N, Kocer N, Islak C, Kizilkilic O (2019) Predicting response to somatostatin analogues in acromegaly: machine learning-based high-dimensional quantitative texture analysis on T2-weighted MRI. Eur Radiol 29:2731–2739. CrossRefPubMedGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  • Lorenzo Ugga
    • 1
  • Renato Cuocolo
    • 1
    Email author
  • Domenico Solari
    • 2
  • Elia Guadagno
    • 3
  • Alessandra D’Amico
    • 1
  • Teresa Somma
    • 2
  • Paolo Cappabianca
    • 2
  • Maria Laura del Basso de Caro
    • 3
  • Luigi Maria Cavallo
    • 2
  • Arturo Brunetti
    • 1
  1. 1.Department of Advanced Biomedical SciencesUniversity of Naples “Federico II”NaplesItaly
  2. 2.Department of Neurosciences, Reproductive and Odontostomatological Sciences, Division of NeurosurgeryUniversity of Naples “Federico II”NaplesItaly
  3. 3.Department of Advanced Biomedical Sciences, Pathology SectionUniversity of Naples “Federico II”NaplesItaly

Personalised recommendations