Machine learning decision tree models for multiclass classification of common malignant brain tumors using perfusion and spectroscopy MRI data

Rodolphe Vallée; Jean-Noël Vallée; Carole Guillevin; Athéna Lallouette; Clément Thomas; Guillaume Rittano; Michel Wager; Rémy Guillevin; Alexandre Vallée

doi:10.3389/fonc.2023.1089998

Machine learning decision tree models for multiclass classification of common malignant brain tumors using perfusion and spectroscopy MRI data

Front Oncol. 2023 Aug 8:13:1089998. doi: 10.3389/fonc.2023.1089998. eCollection 2023.

Authors

Rodolphe Vallée^{1

2

3}, Jean-Noël Vallée^{2

4}, Carole Guillevin^{2

5}, Athéna Lallouette⁶, Clément Thomas^{2

4}, Guillaume Rittano⁷, Michel Wager⁸, Rémy Guillevin^{2

5}, Alexandre Vallée⁹

Affiliations

¹ Interdisciplinary Laboratory in Neurosciences, Physiology and Psychology (LINP2), Université Paris Lumière (UPL), Paris Nanterre University, Nanterre, France.
² Laboratory of Mathematics and Applications (LMA) Centre National de la Recherche Scientifique - Unité Mixte de Recherche (CNRS UMR)7348, i3M-DACTIM-MIH (Data Analysis and Computations Through Imaging Modeling - Mathematics, Image, Health), Poitiers University, Poitiers, France.
³ Glaucoma Research Center, Swiss Visio Network, Lausanne, Switzerland.
⁴ Diagnostic and Functional Neuroradiology and Brain stimulation Department, 15-20 National Vision Hospital of Paris - Paris University Hospital Center, University of PARIS-SACLAY - UVSQ, Paris, France.
⁵ Radiology Department, Poitiers University Hospital, Poitiers University, Poitiers, France.
⁶ Center of Genève Ophtalmologie, Geneve, Switzerland.
⁷ Radiology Department, Hopital Riveira Chablais, Rennaz, Switzerland.
⁸ Neurosurgery Department, Poitiers University Hospital, Poitiers University, Poitiers, France.
⁹ Department of Epidemiology and Public Health, Foch Hospital, Suresnes, France.

Abstract

Background: To investigate the contribution of machine learning decision tree models applied to perfusion and spectroscopy MRI for multiclass classification of lymphomas, glioblastomas, and metastases, and then to bring out the underlying key pathophysiological processes involved in the hierarchization of the decision-making algorithms of the models.

Methods: From 2013 to 2020, 180 consecutive patients with histopathologically proved lymphomas (n = 77), glioblastomas (n = 45), and metastases (n = 58) were included in machine learning analysis after undergoing MRI. The perfusion parameters (rCBV_max, PSR_max) and spectroscopic concentration ratios (lac/Cr, Cho/NAA, Cho/Cr, and lip/Cr) were applied to construct Classification and Regression Tree (CART) models for multiclass classification of these brain tumors. A 5-fold random cross validation was performed on the dataset.

Results: The decision tree model thus constructed successfully classified all 3 tumor types with a performance (AUC) of 0.98 for PCNSLs, 0.98 for GBM and 1.00 for METs. The model accuracy was 0.96 with a RSquare of 0.887. Five rules of classifier combinations were extracted with a predicted probability from 0.907 to 0.989 for that end nodes of the decision tree for tumor multiclass classification. In hierarchical order of importance, the root node (Cho/NAA) in the decision tree algorithm was primarily based on the proliferative, infiltrative, and neuronal destructive characteristics of the tumor, the internal node (PSRmax), on tumor tissue capillary permeability characteristics, and the end node (Lac/Cr or Cho/Cr), on tumor energy glycolytic (Warburg effect), or on membrane lipid tumor metabolism.

Conclusion: Our study shows potential implementation of machine learning decision tree model algorithms based on a hierarchical, convenient, and personalized use of perfusion and spectroscopy MRI data for multiclass classification of these brain tumors.

Keywords: classification and regression tree (CART); glioblastoma; lymphoma; metastasis; multiclass classification.