Download PDF
J Neurol Surg B Skull Base
DOI: 10.1055/a-2607-0735
Original Article

Radiomics for Preoperative Assessment of Pituitary Adenoma Consistency with T2-Weighted MRI: A Multicenter Study

Edoardo Agosti
1   Division of Neurosurgery, Department of Medical and Surgical Specialties, Radiological Sciences and Public Health, University of Brescia, Brescia, Italy
,
Renato Cuocolo
2   Department of Medicine, Surgery and Dentistry, University of Salerno, Baronissi, Italy
,
Marcello Mangili
1   Division of Neurosurgery, Department of Medical and Surgical Specialties, Radiological Sciences and Public Health, University of Brescia, Brescia, Italy
,
Vittorio Rampinelli
3   Unit of Otorhinolaryngology - Head and Neck Surgery, ASST Spedali Civili, Department of Surgical and Medical Specialties, Radiological Sciences, and Public Health, University of Brescia, School of Medicine, Brescia, Italy
,
Pierlorenzo Veiceschi 
4   Unit of Neurosurgery, ARNAS Ospedale Civico of Palermo, Palermo, Italy
,
Martina Cappelletti
5   Unit of Neurosurgery, Ospedale Ca' Foncello, Treffviso, Italy
,
Pier Paolo Panciani
1   Division of Neurosurgery, Department of Medical and Surgical Specialties, Radiological Sciences and Public Health, University of Brescia, Brescia, Italy
,
Amedeo Piazza
6   Neurosurgery Division, Department of Neuroscience, “Sapienza” University of Rome, Rome, Italy
,
Ilaria Bove
7   Division of Neurosurgery, Department of Neurosciences, Reproductive and Odontostomatological Sciences, Università degli Studi di Napoli Federico II, Naples, Italy
,
Domenico Solari
7   Division of Neurosurgery, Department of Neurosciences, Reproductive and Odontostomatological Sciences, Università degli Studi di Napoli Federico II, Naples, Italy
,
Luigi Maria Cavallo
7   Division of Neurosurgery, Department of Neurosciences, Reproductive and Odontostomatological Sciences, Università degli Studi di Napoli Federico II, Naples, Italy
,
Davide Locatelli
8   Division of Neurological Surgery, Department of Biotechnology and Life Sciences, University of Insubria-Varese, ASST Sette Laghi, Ospedale di Circolo e Fondazione Macchi, Varese, Italy
,
Francesco Doglietto
9   Facoltà di Medicina e Chirurgia, Università Cattolica del Sacro Cuore, Rome, Italy
10   Division of Neurosurgery, Department of Neuroscience, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy
,
Alessandro Fiorindi
1   Division of Neurosurgery, Department of Medical and Surgical Specialties, Radiological Sciences and Public Health, University of Brescia, Brescia, Italy
,
Marco Maria Fontanella
1   Division of Neurosurgery, Department of Medical and Surgical Specialties, Radiological Sciences and Public Health, University of Brescia, Brescia, Italy
,
Lorenzo Ugga
11   Department of Advanced Medical and Surgical Sciences, University of Campania “Luigi Vanvitelli,” Naples, Italy
› Author Affiliations
Funding This work was supported in part by the “Centro di ricerche per gli adenomi ipofisari e le patologie sellari” of the Insubria University in Varese, Italy.
› Further Information
Also available at
   Permissions and Reprints

Abstract

Introduction

Pituitary adenoma (PA) consistency significantly influences the outcomes of endoscopic endonasal surgery. Radiomics represents a promising tool for objective and quantitative assessment using T2-weighted magnetic resonance imaging (MRI).

Methods

A multicenter retrospective database was collected (2012–2023), including 394 patients with preoperative T2-weighted MRI and histologically confirmed PAs after endoscopic endonasal surgical removal. Tumor segmentation was performed manually on coronal T2-weighted images using ITK-SNAP software. Radiomic features were extracted with Pyradiomics. A 60:40 dataset split was used to train an Extra Trees classifier, and recursive feature elimination was used to select features. Model performance was assessed using sensitivity, specificity, and the area under the curve of receiver operating characteristic (AUC-ROC) curve metrics.

Results

From 1,106 extracted radiomic features, 65 were identified as most predictive following variance and correlation filtering. The sensitivity, specificity, and accuracy of the ET classifier were 74%, 74%, and 63% (±10%), respectively. The AUC-ROC curve was 0.59.

Conclusion

Despite its moderate accuracy and AUC-ROC curve, the ET model showed promising performance to predict preoperative PA consistency, underlying the power of radiomics-driven models in PA surgical planning.

Keywords

pituitary adenoma - consistency - preoperative MRI - radiomics - machine learning

Ethical Approval

This retrospective chart review study involving human participants was in accordance with the ethical standards of the institutional and national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards. The IRB approved this study.


Supplementary Material



Publication History

Received: 20 February 2025

Accepted: 12 May 2025

Accepted Manuscript online:
13 May 2025

Article published online:
04 June 2025

© 2025. Thieme. All rights reserved.

Georg Thieme Verlag KG
Oswald-Hesse-Straße 50, 70469 Stuttgart, Germany

 

  • References

  • 1 Acitores Cancela A, Rodríguez Berrocal V, Pian H, Martínez San Millán JS, Díez JJ, Iglesias P. Clinical relevance of tumor consistency in pituitary adenoma. Hormones (Athens) 2021; 20 (03) 463-473
    Search in Google Scholar
  • 2 De Alcubierre D, Puliani G, Cozzolino A. et al. Pituitary adenoma consistency affects postoperative hormone function: a retrospective study. BMC Endocr Disord 2023; 23 (01) 92
    Search in Google Scholar
  • 3 Smith KA, Leever JD, Chamoun RB. Prediction of consistency of pituitary adenomas by magnetic resonance imaging. J Neurol Surg B Skull Base 2015; 76 (05) 340-343
    Search in Google Scholar
  • 4 Pierallini A, Caramia F, Falcone C. et al. Pituitary macroadenomas: preoperative evaluation of consistency with diffusion-weighted MR imaging–initial experience. Radiology 2006; 239 (01) 223-231
    Search in Google Scholar
  • 5 Su CQ, Zhang X, Pan T. et al. Texture analysis of high b-value diffusion-weighted imaging for evaluating consistency of pituitary macroadenomas. J Magn Reson Imaging 2020; 51 (05) 1507-1513
    Search in Google Scholar
  • 6 Najjar R. Redefining radiology: A review of artificial intelligence integration in medical imaging. Diagnostics (Basel) 2023; 13 (17) 2760
    Search in Google Scholar
  • 7 Bioletto F, Prencipe N, Berton AM. et al. Radiomic analysis in pituitary tumors: Current knowledge and future perspectives. J Clin Med 2024; 13 (02) 336
    Search in Google Scholar
  • 8 Ibrahim A, Primakov S, Beuque M. et al. Radiomics for precision medicine: Current challenges, future prospects, and the proposal of a new framework. Methods 2021; 188: 20-29
    Search in Google Scholar
  • 9 Wang H, Chang J, Zhang W. et al. Radiomics model and clinical scale for the preoperative diagnosis of silent corticotroph adenomas. J Endocrinol Invest 2023; 46 (09) 1843-1854
    Search in Google Scholar
  • 10 Wan T, Wu C, Meng M. et al. Radiomic features on multiparametric MRI for preoperative evaluation of pituitary macroadenomas consistency: Preliminary findings. J Magn Reson Imaging 2022; 55 (05) 1491-1503
    Search in Google Scholar
  • 11 Fang Y, Wang H, Cao D. et al. Multi-center application of a convolutional neural network for preoperative detection of cavernous sinus invasion in pituitary adenomas. Neuroradiology 2024; 66 (03) 353-360
    Search in Google Scholar
  • 12 Zhang W, Sun M, Fan Y. et al. Machine learning in preoperative prediction of postoperative immediate remission of histology-positive Cushing's disease. Front Endocrinol (Lausanne) 2021; 12: 635795
    Search in Google Scholar
  • 13 Park YW, Eom J, Kim S. et al. Radiomics with ensemble machine learning predicts dopamine agonist response in patients with prolactinoma. J Clin Endocrinol Metab 2021; 106 (08) e3069-e3077
    Search in Google Scholar
  • 14 Fan Y, Jiang S, Hua M, Feng S, Feng M, Wang R. Machine learning-based radiomics predicts radiotherapeutic response in patients with acromegaly. Front Endocrinol (Lausanne) 2019; 10: 588
    Search in Google Scholar
  • 15 Zhang Y, Huang Z, Zhao Y, Xu J, Chen C, Xu J. Radiomics using multiparametric magnetic resonance imaging to predict postoperative visual outcomes of patients with pituitary adenoma. Asian J Surg 2024:S1015-9584(24)01504-5
  • 16 Chen YJ, Hsieh HP, Hung KC. et al. Deep learning for prediction of progression and recurrence in nonfunctioning pituitary macroadenomas: Combination of clinical and MRI features. Front Oncol 2022; 12: 813806
    Search in Google Scholar
  • 17 Resneck Jr JS. Revisions to the Declaration of Helsinki on its 60th anniversary: A modernized set of ethical principles to promote and ensure respect for participants in a rapidly innovating medical research ecosystem. JAMA 2025; 333 (01) 15-17
    Search in Google Scholar
  • 18 Ugga L, Cuocolo R, Solari D. et al. Prediction of high proliferative index in pituitary macroadenomas using MRI-based radiomics and machine learning. Neuroradiology 2019; 61 (12) 1365-1373
    Search in Google Scholar
  • 19 Černý M, Netuka D. Radiomic analysis of T2-weighted MRI scans for prediction of pituitary adenoma consistency and gross total resection: preliminary results. Brain Spine 2025; 5: 104237
    Search in Google Scholar
  • 20 Cuocolo R, Ugga L, Solari D. et al. Prediction of pituitary adenoma surgical consistency: radiomic data mining and machine learning on T2-weighted MRI. Neuroradiology 2020; 62 (12) 1649-1656
    Search in Google Scholar
  • 21 Cappabianca P, Cavallo LM, de Divitiis O, Solari D, Esposito F, Colao A. Endoscopic pituitary surgery. Pituitary 2008; 11 (04) 385-390
    Search in Google Scholar
  • 22 Cappabianca P, Cavallo LM, Solari D, Stagno V, Esposito F, de Angelis M. Endoscopic endonasal surgery for pituitary adenomas. World Neurosurg 2014; 82 (6, Suppl): S3-S11
    Search in Google Scholar
  • 23 Solari D, Pivonello R, Caggiano C. et al. Pituitary adenomas: What are the key features? What are the current treatments? Where is the future taking us?. World Neurosurg 2019; 127: 695-709
    Search in Google Scholar
  • 24 Di Maio S, Cavallo LM, Esposito F, Stagno V, Corriero OV, Cappabianca P. Extended endoscopic endonasal approach for selected pituitary adenomas: early experience. J Neurosurg 2011; 114 (02) 345-353
    Search in Google Scholar
  • 25 Rutkowski MJ, Chang KE, Cardinal T. et al. Development and clinical validation of a grading system for pituitary adenoma consistency. J Neurosurg 2020; 134 (06) 1800-1807
    Search in Google Scholar
  • 26 Fiore G, Bertani GA, Conte G. et al. Predicting tumor consistency and extent of resection in non-functioning pituitary tumors. Pituitary 2023; 26 (02) 209-220
    Search in Google Scholar
  • 27 Rui W, Wu Y, Ma Z. et al. MR textural analysis on contrast enhanced 3D-SPACE images in assessment of consistency of pituitary macroadenoma. Eur J Radiol 2019; 110: 219-224
    Search in Google Scholar
  • 28 Černý M, Sedlák V, Lesáková V, Francůz P, Netuka D. Methods of preoperative prediction of pituitary adenoma consistency: a systematic review. Neurosurg Rev 2022; 46 (01) 11
    Search in Google Scholar
  • 29 Mastorakos P, Mehta GU, Chatrath A. et al. Tumor to cerebellar peduncle T2-weighted imaging intensity ratio fails to predict pituitary adenoma consistency. J Neurol Surg B Skull Base 2019; 80 (03) 252-257
    Search in Google Scholar
  • 30 Li P, Zhang D, Ma S. et al. Consistency of pituitary adenomas: Amounts of collagen types I and III and the predictive value of T2WI MRI. Exp Ther Med 2021; 22 (05) 1255
    Search in Google Scholar
  • 31 Kamimura K, Nakajo M, Bohara M. et al. Consistency of pituitary adenoma: prediction by pharmacokinetic dynamic contrast-enhanced MRI and comparison with histologic collagen content. Cancers (Basel) 2021; 13 (15) 3914
    Search in Google Scholar
  • 32 Guinto-Nishimura GY, Ramirez J, Ortega-Porcayo LA. et al. Accuracy of preoperative MRI for predicting tumor consistency in non-functioning pituitary adenomas. Neurosurgery 2020; 87 (01) (Supplement_1)
    Search in Google Scholar
  • 33 Hughes JD, Fattahi N, Van Gompel J, Arani A, Ehman R, Huston III J. Magnetic resonance elastography detects tumoral consistency in pituitary macroadenomas. Pituitary 2016; 19 (03) 286-292
    Search in Google Scholar
  • 34 Cohen-Cohen S, Helal A, Yin Z. et al. Predicting pituitary adenoma consistency with preoperative magnetic resonance elastography. J Neurosurg 2021; 136 (05) 1356-1363
    Search in Google Scholar
  • 35 Zeynalova A, Kocak B, Durmaz ES. et al. Preoperative evaluation of tumour consistency in pituitary macroadenomas: a machine learning-based histogram analysis on conventional T2-weighted MRI. Neuroradiology 2019; 61 (07) 767-774
    Search in Google Scholar
  • 36 Wang H, Zhang W, Li S, Fan Y, Feng M, Wang R. Development and evaluation of deep learning-based automated segmentation of pituitary adenoma in clinical task. J Clin Endocrinol Metab 2021; 106 (09) 2535-2546
    Search in Google Scholar
  • 37 Eche T, Schwartz LH, Mokrane FZ, Dercle L. Toward generalizability in the deployment of artificial intelligence in radiology: Role of computation stress testing to overcome underspecification. Radiol Artif Intell 2021; 3 (06) e210097
    Search in Google Scholar
  • 38 Cuocolo R, Imbriaco M. Machine learning solutions in radiology: does the emperor have no clothes?. Eur Radiol 2021; 31 (06) 3783-3785
    Search in Google Scholar
  • 39 Yao A, Rutland JW, Verma G. et al. Pituitary adenoma consistency: Direct correlation of ultrahigh field 7T MRI with histopathological analysis. Eur J Radiol 2020; 126: 108931
    Search in Google Scholar
  • 40 Zheng B, Zhao Z, Zheng P. et al. The current state of MRI-based radiomics in pituitary adenoma: promising but challenging. Front Endocrinol (Lausanne) 2024; 15: 1426781
    Search in Google Scholar
  • 41 Guerra GA, Kashif Z, Cote DJ. et al. Association between pituitary adenoma consistency, resection techniques, and patient outcomes: a single-institution experience. J Neurosurg 2025; 24: 1-8
    Search in Google Scholar
  • 42 Romano A, Coppola V, Lombardi M. et al. Predictive role of dynamic contrast enhanced T1-weighted MR sequences in pre-surgical evaluation of macroadenomas consistency. Pituitary 2017; 20 (02) 201-209
    Search in Google Scholar
  • 43 Fan Y, Liu Z, Hou B. et al. Development and validation of an MRI-based radiomic signature for the preoperative prediction of treatment response in patients with invasive functional pituitary adenoma. Eur J Radiol 2019; 121: 108647
    Search in Google Scholar
  • 44 Ugga L, Perillo T, Capasso S, Negroni D, Cuocolo R. Radiomics in Meningiomas: Pathological and Biomolecular Correlation. In: Maiuri F, Del Basso De Caro M. eds. Meningiomas: From Pathology to Clinics. Springer Nature Switzerland; 2024: 121-130
    Search in Google Scholar
  • 45 Liu CX, Heng LJ, Han Y. et al. Usefulness of the texture signatures based on multiparametric MRI in predicting growth hormone pituitary adenoma subtypes. Front Oncol 2021; 11: 640375
    Search in Google Scholar