Machine Assist for Pediatric Posterior Fossa Tumor Diagnosis: A Multinational Study

Michael Zhang, Samuel W. Wong, Jason N. Wright, Sebastian Toescu, Maryam Mohammadzadeh, Michelle Han, Seth Lummus, Matthias W. Wagner, Derek Yecies, Hollie Lai, Azam Eghbal, Alireza Radmanesh, Jordan Nemelka, Stephen Harward, Michael Malinzak, Suzanne Laughlin, Sebastien Perreault, Kristina R.M. Braun, Arastoo Vossough, Tina PoussaintRobert Goetti, Birgit Ertl-Wagner, Chang Y. Ho, Ozgur Oztekin, Vijay Ramaswamy, Kshitij Mankad, Nicholas A. Vitanza, Samuel H. Cheshier, Mourad Said, Kristian Aquilina, Eric Thompson, Alok Jaju, Gerald A. Grant, Robert M. Lober, Kristen W. Yeom*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

BACKGROUND: Clinicians and machine classifiers reliably diagnose pilocytic astrocytoma (PA) on magnetic resonance imaging (MRI) but less accurately distinguish medulloblastoma (MB) from ependymoma (EP). One strategy is to first rule out the most identifiable diagnosis. OBJECTIVE: To hypothesize a sequential machine-learning classifier could improve diagnostic performance by mimicking a clinician's strategy of excluding PA before distinguishing MB from EP. METHODS: We extracted 1800 total Image Biomarker Standardization Initiative (IBSI)-based features from T2- and gadolinium-enhanced T1-weighted images in a multinational cohort of 274 MB, 156 PA, and 97 EP. We designed a 2-step sequential classifier - first ruling out PA, and next distinguishing MB from EP. For each step, we selected the best performing model from 6-candidate classifier using a reduced feature set, and measured performance on a holdout test set with the microaveraged F1 score. RESULTS: Optimal diagnostic performance was achieved using 2 decision steps, each with its own distinct imaging features and classifier method. A 3-way logistic regression classifier first distinguished PA from non-PA, with T2 uniformity and T1 contrast as the most relevant IBSI features (F1 score 0.8809). A 2-way neural net classifier next distinguished MB from EP, with T2 sphericity and T1 flatness as most relevant (F1 score 0.9189). The combined, sequential classifier was with F1 score 0.9179. CONCLUSION: An MRI-based sequential machine-learning classifiers offer high-performance prediction of pediatric posterior fossa tumors across a large, multinational cohort. Optimization of this model with demographic, clinical, imaging, and molecular predictors could provide significant advantages for family counseling and surgical planning.

Original languageEnglish (US)
Pages (from-to)892-900
Number of pages9
JournalNeurosurgery
Volume89
Issue number5
DOIs
StatePublished - Nov 1 2021
Externally publishedYes

Keywords

  • Artificial intelligence
  • Ependymoma
  • Machine learning
  • Medulloblastoma
  • Pilocytic astrocytoma
  • Posterior fossa tumors
  • Radiomics

ASJC Scopus subject areas

  • Surgery
  • Clinical Neurology

Fingerprint

Dive into the research topics of 'Machine Assist for Pediatric Posterior Fossa Tumor Diagnosis: A Multinational Study'. Together they form a unique fingerprint.

Cite this