Advertisement

Predicting Meningioma Resection Status: Use of Deep Learning

Published:October 30, 2022DOI:https://doi.org/10.1016/j.acra.2022.10.004
      Meningiomas are the most common primary benign intracranial brain tumors (
      • Goldbrunner R
      • Stavrinou P
      • Jenkinson MD
      • et al.
      EANO guideline on the diagnosis and management of meningiomas.
      ). While the majority of meningiomas are classified World Health Organization (WHO) grade 1 tumors, a minority is classified as grade 2 or 3 lesions, based on features of cellular atypia and invasive growth (
      • Louis DN
      • Perry A
      • Wesseling P
      • et al.
      The 2021 WHO Classification of Tumors of the Central Nervous System: a summary.
      ). Surgical resection remains the treatment of choice for progressive, space-occupying and/ or symptomatic lesions, especially in favourable locations such as convexity meningiomas (
      • Goldbrunner R
      • Stavrinou P
      • Jenkinson MD
      • et al.
      EANO guideline on the diagnosis and management of meningiomas.
      ). While the aim of surgery is gross total resection (GTR), the extent of resection depends on factors such as tumor location, size and involvement of critical tissue (
      • Goldbrunner R
      • Stavrinou P
      • Jenkinson MD
      • et al.
      EANO guideline on the diagnosis and management of meningiomas.
      ). Gross total resection and subtotal resection (STR) are defined according to the Simpson classification: Simpson grade I – III constitute gross total resection and Simpson grades IV – V form the group of subtotal resection. (
      • Jenkinson MD
      • Javadpour M
      • Haylock BJ
      • et al.
      The ROAM/EORTC-1308 trial: radiation vs. observation following surgical resection of Atypical Meningioma: study protocol for a randomised controlled trial.
      ,
      • Simpson D.
      The recurrence of intracranial meningiomas after surgical treatment.
      )

      Keywords

      Abbreviations:

      AI (Artificial Intelligence), CNN (Convolutional Neural Network), CNS (Central Nervous System), DL (Deep Learning), FU (Follow up), GTR (Gross Total Resection), IRB (Institutional Review Board), ML (Machine Learning), MRI (Magnetic Resonance Imaging), NPV (Negative Predictive Value), PPV (Positive Predictive Value), STR (Subtotal Resection), WHO (World Health Organization)
      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      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 Academic Radiology
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Goldbrunner R
        • Stavrinou P
        • Jenkinson MD
        • et al.
        EANO guideline on the diagnosis and management of meningiomas.
        Neuro Oncol. 2021; 23: 1821-1834https://doi.org/10.1093/neuonc/noab150
        • Louis DN
        • Perry A
        • Wesseling P
        • et al.
        The 2021 WHO Classification of Tumors of the Central Nervous System: a summary.
        Neuro Oncol. 2021; 23: 1231-1251https://doi.org/10.1093/neuonc/noab106
        • Jenkinson MD
        • Javadpour M
        • Haylock BJ
        • et al.
        The ROAM/EORTC-1308 trial: radiation vs. observation following surgical resection of Atypical Meningioma: study protocol for a randomised controlled trial.
        Trials. 2015; 16: 519https://doi.org/10.1186/s13063-015-1040-3
        • Simpson D.
        The recurrence of intracranial meningiomas after surgical treatment.
        J Neurol Neurosurg Psychiatry. 1957; 20: 22-39https://doi.org/10.1136/jnnp.20.1.22
        • Ehresman JS
        • Garzon-Muvdi T
        • Rogers D
        • et al.
        The relevance of simpson grade resections in modern neurosurgical treatment of World Health Organization Grade1, 2, and 3Meningiomas.
        World Neurosurg. 2018; 109: e588-e593https://doi.org/10.1016/j.wneu.2017.10.028
        • Rydzewski NR
        • Lesniak MS
        • Chandler JP
        • et al.
        Gross total resection and adjuvant radiotherapy most significant predictors of improved survival in patients with atypical meningioma.
        Cancer. 2018; 124: 734-742https://doi.org/10.1002/cncr.31088
        • Luthge S
        • Spille DC
        • Steinbicker AU
        • et al.
        The applicability of established clinical and histopathological risk factors for tumor recurrence during long-term postoperative care in meningioma patients.
        Neurosurg Rev. 2021; https://doi.org/10.1007/s10143-021-01697-w
        • Aerts HJ
        • Velazquez ER
        • Leijenaar RT
        • et al.
        Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach.
        Nat Commun. 2014; 5: 4006https://doi.org/10.1038/ncomms5006
        • Coroller TP
        • Bi WL
        • Huynh E
        • et al.
        Radiographic prediction of meningioma grade by semantic and radiomic features.
        PLoS One. 2017; 12e0187908https://doi.org/10.1371/journal.pone.0187908
        • Hu J
        • Zhao Y
        • Li M
        • et al.
        Machine learning-based radiomics analysis in predicting the meningioma grade using multiparametric MRI.
        Eur J Radiol. 2020; 131109251.https://doi.org/10.1016/j.ejrad.2020.109251
        • Park YW
        • Oh J
        • You SC
        • et al.
        Radiomics and machine learning may accurately predict the grade and histological subtype in meningiomas using conventional and diffusion tensor imaging.
        Eur Radiol. 2019; 29: 4068-4076https://doi.org/10.1007/s00330-018-5830-3
        • Zhu Y
        • Man C
        • Gong L
        • et al.
        A deep learning radiomics model for preoperative grading in meningioma.
        Eur J Radiol. 2019; 116: 128-134https://doi.org/10.1016/j.ejrad.2019.04.022
        • Zhang Y
        • Chen JH
        • Chen TY
        • et al.
        Radiomics approach for prediction of recurrence in skull base meningiomas.
        Neuroradiology. 2019; 61: 1355-1364https://doi.org/10.1007/s00234-019-02259-0
        • Laukamp KR
        • Thiele F
        • Shakirin G
        • et al.
        Fully automated detection and segmentation of meningiomas using deep learning on routine multiparametric MRI.
        Eur Radiol. 2019; 29: 124-132https://doi.org/10.1007/s00330-018-5595-8
        • Deepak S
        • Ameer PM.
        Brain tumor classification using deep CNN features via transfer learning.
        Comput Biol Med. 2019; 111103345.https://doi.org/10.1016/j.compbiomed.2019.103345
        • Swati ZNK
        • Zhao Q
        • Kabir M
        • et al.
        Brain tumor classification for MR images using transfer learning and fine-tuning.
        Comput Med Imaging Graph. 2019; 75: 34-46https://doi.org/10.1016/j.compmedimag.2019.05.001
        • Laukamp KR
        • Pennig L
        • Thiele F
        • et al.
        Automated meningioma segmentation in multiparametric MRI: comparable effectiveness of a deep learning model and manual segmentation.
        Clin Neuroradiol. 2021; 31: 357-366https://doi.org/10.1007/s00062-020-00884-4
        • Banzato T
        • Causin F
        • Della Puppa A
        Accuracy of deep learning to differentiate the histopathological grading of meningiomas on MR images: a preliminary study.
        J Magn Reson Imaging. 2019; 50: 1152-1159https://doi.org/10.1002/jmri.26723
        • Hale AT
        • Stonko DP
        • Wang L
        • et al.
        Machine learning analyses can differentiate meningioma grade by features on magnetic resonance imaging.
        Neurosurg Focus. 2018; 45: E4https://doi.org/10.3171/2018.8.FOCUS18191
        • Joo L
        • Park JE
        • Park SY
        • et al.
        Extensive peritumoral edema and brain-to-tumor interface MR imaging features enable prediction of brain invasion in meningioma: development and validation.
        Neuro Oncol. 2020; https://doi.org/10.1093/neuonc/noaa190
        • Kandemirli SG
        • Chopra S
        • Priya S
        • et al.
        Presurgical detection of brain invasion status in meningiomas based on first-order histogram based texture analysis of contrast enhanced imaging.
        Clin Neurol Neurosurg. 2020; 198106205.https://doi.org/10.1016/j.clineuro.2020.106205
        • Niu L
        • Zhou X
        • Duan C
        • et al.
        Differentiation researches on the meningioma subtypes by radiomics from contrast-enhanced magnetic resonance imaging: apreliminary study.
        World Neurosurg. 2019; 126: e646-e652https://doi.org/10.1016/j.wneu.2019.02.109
        • Yan PF
        • Yan L
        • Hu TT
        • et al.
        The potential value of preoperative MRI texture and shape analysis in grading meningiomas: apreliminary investigation.
        Transl Oncol. 2017; 10: 570-577https://doi.org/10.1016/j.tranon.2017.04.006
        • Zhang J
        • Yao K
        • Liu P
        • et al.
        A radiomics model for preoperative prediction of brain invasion in meningioma non-invasively based on MRI: amulticentre study.
        EBioMedicine. 2020; 58102933.https://doi.org/10.1016/j.ebiom.2020.102933
        • Rogers L
        • Barani I
        • Chamberlain M
        • et al.
        Meningiomas: knowledge base, treatment outcomes, and uncertainties. A RANO review.
        J Neurosurg. 2015; 122: 4-23https://doi.org/10.3171/2014.7.JNS131644
        • Fu J
        • Zeng J
        • Huang M
        • et al.
        Primary vs. postoperative gamma knife radiosurgery for intracranial benign meningiomas: a matched cohort retrospective study.
        BMC Cancer. 2022; 22: 206https://doi.org/10.1186/s12885-022-09321-w
        • Staartjes VE
        • Serra C
        • Muscas G
        • et al.
        Utility of deep neural networks in predicting gross-total resection after transsphenoidal surgery for pituitary adenoma: a pilot study.
        Neurosurg Focus. 2018; 45: E12https://doi.org/10.3171/2018.8.FOCUS18243
        • Musigmann M
        • Akkurt BH
        • Krahling H
        • et al.
        Assessing preoperative risk of STR in skull meningiomas using MR radiomics and machine learning.
        Sci Rep. 2022; 12: 14043https://doi.org/10.1038/s41598-022-18458-4