Non-invasive preoperative imaging differential diagnosis of pineal region tumor: A novel developed and validated multiparametric MRI-based clinicoradiomic model

  • Author Footnotes
    1 Contributed equally to this work.
    Yanghua Fan
    Footnotes
    1 Contributed equally to this work.
    Affiliations
    Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, China
    Search for articles by this author
  • Author Footnotes
    1 Contributed equally to this work.
    Xulei Huo
    Footnotes
    1 Contributed equally to this work.
    Affiliations
    Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, China
    Search for articles by this author
  • Xiaojie Li
    Affiliations
    Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, China
    Search for articles by this author
  • Liang Wang
    Correspondence
    Corresponding author at: Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing 100070, China.
    Affiliations
    Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, China
    Search for articles by this author
  • Zhen Wu
    Correspondence
    Corresponding author at: Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing 100070, China.
    Affiliations
    Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, China
    Search for articles by this author
  • Author Footnotes
    1 Contributed equally to this work.
Published:January 13, 2022DOI:https://doi.org/10.1016/j.radonc.2022.01.005

      Highlights

      • Radiomic features have high performance in differential diagnosis of pineal region tumors.
      • Multi-step selection and clinicopathologic information improved prediction power.
      • Demonstrated superior capability in aiding decision making for Neurooncologist.

      Abstract

      Background

      Preoperative differential diagnosis of pineal region tumor can greatly assist clinical decision-making and avoid economic costs and complications caused by unnecessary radiotherapy or invasive procedures. The present study was performed to pre-operatively distinguish pineal region germinoma and pinealoblastoma using a clinicoradiomic model by incorporating radiomic and clinical features.

      Methods

      134 pineal region tumor patients (germinoma, 69; pinealoblastoma, 65) with complete clinic-radiological and histopathological data from Tiantan hospital were retrospectively reviewed and randomly assigned to training and validation sets. Radiomic features were extracted from MR images, then the elastic net and recursive feature elimination algorithms were applied to select radiomic features for constructing a fusion radiomic model. Subsequently, multivariable logistic regression analysis was used to select the clinical features, and a clinicoradiomic model incorporating the fusion radiomic model and selected clinical features was constructed for individual predictions. The calibration, discriminating capacity, and clinical usefulness were also evaluated.

      Results

      Seven significant radiomic features were selected to construct a fusion radiomic model that achieved an area under the curve (AUC) value of 0.920 and 0.880 in the training and validation sets, respectively. A clinicoradiomic model that incorporated the radiomic model and four selected clinical features was constructed and showed good discrimination and calibration, with an AUC of 0.950 in the training set and 0.940 in the validation set. The analysis of the decision curve showed that the radiomic model and clinicoradiomic model were clinically useful for patients with pineal region tumor.

      Conclusions

      Our clinicoradiomic model showed great performance and high sensitivity in the differential diagnosis of germinoma and pinealoblastoma, and could contribute to non-invasive development of individualized diagnosis and treatment of patients with pineal region tumor.

      Abbreviations:

      β-HCG (β-chorionic gonadotropin), AFP (blood alpha fetoprotein), CEA (blood carcinoembryonic antigen), T2WI (T2-weighted imaging), CE-T1WI (contrast-enhanced T1-weighted imaging), ROI (regions of interest), GLCM (gray level co-occurrence matrix), GLRLM (gray level run-length matrix), LASSO (least absolute shrinkage and selection operator), RFE (recursive feature elimination), ROC (receiver operating characteristic), AIC (Akaike information criterion), AUC (area under curve), DCA (decision curve analysis), ACC (accuracy), PPV (positive predictive value), NPV (negative predictive value)

      Keywords

      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic and Personal
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Radiotherapy and Oncology
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Samadian M.
        • Maloumeh E.N.
        • Shiravand S.
        • Ebrahimzadeh K.
        • Sharifi G.
        • Mousavinejad A.
        • et al.
        Pineal region tumors: Long-term results of endoscopic third ventriculostomy and concurrent tumor biopsy with a single entry approach in a series of 64 cases.
        Clin Neurol Neurosurg. 2019; 184: 105418https://doi.org/10.1016/j.clineuro.2019.105418
        • Bruce J.N.
        • Ogden A.T.
        Surgical strategies for treating patients with pineal region tumors.
        J Neurooncol. 2004; 69: 221-236
        • Constantini S.
        • Mohanty A.
        • Zymberg S.
        • Cavalheiro S.
        • Mallucci C.
        • Hellwig D.
        • et al.
        Safety and diagnostic accuracy of neuroendoscopic biopsies: an international multicenter study.
        J Neurosurg Pediatr. 2013; 11: 704-709
        • Dhall G.
        • Khatua S.
        • Finlay J.L.
        Pineal region tumors in children.
        Curr Opin Neurol. 2010; 23: 576-582
        • Radovanovic I.
        • Dizdarevic K.
        • de Tribolet N.
        • Masic T.
        • Muminagic S.
        Pineal region tumors–neurosurgical review.
        Med Arh. 2009; 63: 171-173
        • Konovalov A.N.
        • Pitskhelauri D.I.
        Principles of treatment of the pineal region tumors.
        Surg Neurol. 2003; 59: 250-268
        • Iorio-Morin C.
        • Kano H.
        • Huang M.
        • Lunsford L.D.
        • Simonová G.
        • Liscak R.
        • et al.
        Histology-Stratified Tumor Control and Patient Survival After Stereotactic Radiosurgery for Pineal Region Tumors: A Report From the International Gamma Knife Research Foundation.
        World Neurosurg. 2017; 107: 974-982
        • Fauchon F.
        • Jouvet A.
        • Paquis P.
        • Saint-Pierre G.
        • Mottolese C.
        • Ben Hassel M.
        • et al.
        Parenchymal pineal tumors: a clinicopathological study of 76 cases.
        Int J Radiat Oncol Biol Phys. 2000; 46: 959-968
        • Sonabend A.M.
        • Bowden S.
        • Bruce J.N.
        Microsurgical resection of pineal region tumors.
        J Neurooncol. 2016; 130: 351-366
        • Abay 2nd, E.O.
        • Laws Jr., E.R.
        • Grado G.L.
        • Bruckman J.E.
        • Forbes G.S.
        • Gomez M.R.
        • et al.
        Pineal tumors in children and adolescents. Treatment by CSF shunting and radiotherapy.
        J Neurosurg. 1981; 55: 889-895
        • Jenkin D.
        • Berry M.
        • Chan H.
        • Greenberg M.
        • Hendrick B.
        • Hoffman H.
        • et al.
        Pineal region germinomas in childhood treatment considerations.
        Int J Radiat Oncol Biol Phys. 1990; 18: 541-545
        • Awa R.
        • Campos F.
        • Arita K.
        • Sugiyama K.
        • Tominaga A.
        • Kurisu K.
        • et al.
        Neuroimaging diagnosis of pineal region tumors-quest for pathognomonic finding of germinoma.
        Neuroradiology. 2014; 56: 525-534
        • Reis F.
        • Faria A.V.
        • Zanardi V.A.
        • Menezes J.R.
        • Cendes F.
        • Queiroz L.S.
        Neuroimaging in pineal tumors.
        J Neuroimaging. 2006; 16: 52-58
        • Carr C.
        • O'Neill B.E.
        • Hochhalter C.B.
        • Strong M.J.
        • Ware M.L.
        Biomarkers of Pineal Region Tumors: A Review.
        Ochsner J. 2019; 19: 26-31
        • Blakeley J.O.
        • Grossman S.A.
        Management of pineal region tumors.
        Curr Treat Options Oncol. 2006; 7: 505-516
        • Gillies R.J.
        • Kinahan P.E.
        • Hricak H.
        Radiomics: Images Are More than Pictures.
        They Are Data Radiology. 2016; 278: 563-577
        • Lambin P.
        • Leijenaar R.T.H.
        • Deist T.M.
        • Peerlings J.
        • de Jong E.E.C.
        • van Timmeren J.
        • et al.
        Radiomics: the bridge between medical imaging and personalized medicine.
        Nat Rev Clin Oncol. 2017; 14: 749-762
      1. D. Kang J.E. Park Y.-H. Kim J.H. Kim J.Y. Oh J. Kim et al. Diffusion radiomics as a diagnostic model for atypical manifestation of primary central nervous system lymphoma: development and multicenter external validation Neuro Oncol. 20 9 2018 2018 1251 1261

        • Zhou H.
        • Vallières M.
        • Bai H.X.
        • Su C.
        • Tang H.
        • Oldridge D.
        • et al.
        MRI features predict survival and molecular markers in diffuse lower-grade gliomas.
        Neuro Oncol. 2017; 19: 862-870
        • Fan Y.
        • Hua M.
        • Mou A.
        • Wu M.
        • Liu X.
        • Bao X.
        • et al.
        Preoperative Noninvasive Radiomics Approach Predicts Tumor Consistency in Patients With Acromegaly: Development and Multicenter Prospective Validation.
        Front Endocrinol (Lausanne). 2019; 10https://doi.org/10.3389/fendo.2019.00403
        • van Griethuysen J.J.M.
        • Fedorov A.
        • Parmar C.
        • Hosny A.
        • Aucoin N.
        • Narayan V.
        • et al.
        Computational Radiomics System to Decode the Radiographic Phenotype.
        Cancer Res. 2017; 77: e104-e107
        • Aerts H.J.W.L.
        • Velazquez E.R.
        • Leijenaar R.T.H.
        • Parmar C.
        • Grossmann P.
        • Carvalho S.
        • et al.
        Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach.
        Nat Commun. 2014; 5https://doi.org/10.1038/ncomms5006
        • Fan Y.
        • Chai Y.
        • Li K.
        • Fang H.
        • Mou A.
        • Feng S.
        • et al.
        Non-invasive and real-time proliferative activity estimation based on a quantitative radiomics approach for patients with acromegaly: a multicenter study.
        J Endocrinol Invest. 2020; 43: 755-765
        • Wang Q.
        • Li Q.
        • Mi R.
        • Ye H.
        • Zhang H.
        • Chen B.
        • et al.
        Radiomics Nomogram Building From Multiparametric MRI to Predict Grade in Patients With Glioma: A Cohort Study.
        J Magn Reson Imaging. 2019; 49: 825-833
        • Qu J.
        • Shen C.
        • Qin J.
        • Wang Z.
        • Liu Z.
        • Guo J.
        • et al.
        The MR radiomic signature can predict preoperative lymph node metastasis in patients with esophageal cancer.
        Eur Radiol. 2019; 29: 906-914
        • Zinn P.O.
        • Singh S.K.
        • Kotrotsou A.
        • Hassan I.
        • Thomas G.
        • Luedi M.M.
        • et al.
        A Coclinical Radiogenomic Validation Study: Conserved Magnetic Resonance Radiomic Appearance of Periostin-Expressing Glioblastoma in Patients and Xenograft Models.
        Clin Cancer Res. 2018; 24: 6288-6299
      2. S.M. Erturk Receiver operating characteristic analysis AJR Am J Roentgenol. 197 4 2011 W784 W784

        • Pan W.
        Akaike's information criterion in generalized estimating equations.
        Biometrics. 2001; 57: 120-125
        • Kramer A.A.
        • Zimmerman J.E.
        Assessing the calibration of mortality benchmarks in critical care: The Hosmer-Lemeshow test revisited.
        Crit Care Med. 2007; 35: 2052-2056
        • Vickers A.J.
        • Cronin A.M.
        • Elkin E.B.
        • Gonen M.
        Extensions to decision curve analysis, a novel method for evaluating diagnostic tests, prediction models and molecular markers.
        BMC Med Inform Decis Mak. 2008; 8: 53
        • Ahn E.S.
        • Goumnerova L.
        Endoscopic biopsy of brain tumors in children: diagnostic success and utility in guiding treatment strategies.
        J Neurosurg Pediatr. 2010; 5: 255-262
        • Mathieu D.
        • Iorio-Morin C.
        Stereotactic Radiosurgery for Pineal Region Tumors.
        Prog Neurol Surg. 2019; 34: 173-183
        • Park J.E.
        • Kim H.S.
        Radiomics as a Quantitative Imaging Biomarker: Practical Considerations and the Current Standpoint in Neuro-oncologic Studies.
        Nucl Med Mol Imaging. 2018; 52: 99-108
        • Zhou M.
        • Scott J.
        • Chaudhury B.
        • Hall L.
        • Goldgof D.
        • Yeom K.W.
        • et al.
        Radiomics in Brain Tumor: Image Assessment, Quantitative Feature Descriptors, and Machine-Learning Approaches.
        AJNR Am J Neuroradiol. 2018; 39: 208-216