An accessible deep learning tool for voxel-wise classification of brain malignancies from perfusion MRI

Abstract

Deep learning; Glioblastoma; Perfusion MRI

Aprenentatge profund; Glioblastoma; Ressonància magnètica de perfusió

Aprendizaje profundo; Glioblastoma; Resonancia magnética de perfusión

Noninvasive differential diagnosis of brain tumors is currently based on the assessment of magnetic resonance imaging (MRI) coupled with dynamic susceptibility contrast (DSC). However, a definitive diagnosis often requires neurosurgical interventions that compromise patients' quality of life. We apply deep learning on DSC images from histology-confirmed patients with glioblastoma, metastasis, or lymphoma. The convolutional neural network trained on ∼50,000 voxels from 40 patients provides intratumor probability maps that yield clinical-grade diagnosis. Performance is tested in 400 additional cases and an external validation cohort of 128 patients. The tool reaches a three-way accuracy of 0.78, superior to the conventional MRI metrics cerebral blood volume (0.55) and percentage of signal recovery (0.59), showing high value as a support diagnostic tool. Our open-access software, Diagnosis In Susceptibility Contrast Enhancing Regions for Neuro-oncology (DISCERN), demonstrates its potential in aiding medical decisions for brain tumor diagnosis using standard-of-care MRI.

This project was supported by “La Caixa” Foundation (RTI2018-095209-B-C21) and the Spanish Ministry of Science and Innovation (FIS-G64384969). R.P.-L. is supported by the Prostate Cancer Foundation Young Investigator Award, the FERO Foundation, the CRIS Foundation Talent Award (TALENT19-05), the Instituto de Salud Carlos III Investigacion en Salud (PI21/01019), and the Asociacion Espanola Contra el Cancer (PRYCO211023SERR). F.G. was funded by the Government of Catalonia (Beatriu de Pinos 2020 00117 BP) and by the Fundacio LaCaixa (ID 100010434, code LCF/BQ/PR22/11920010). C.M. and A.P.-E. acknowledge support from the Instituto de Salud Carlos III-Investigación en Salud (PI20/00360). We would like to express our sincere appreciation to Javier Carmona for his valuable support and assistance in reviewing the manuscript.