Hyperpolarized Magnetic Resonance Imaging, Nuclear Magnetic Resonance Metabolomics, and Artificial Intelligence to Interrogate the Metabolic Evolution of Glioblastoma.

in Metabolites by Kang Lin Hsieh, Qing Chen, Travis C Salzillo, Jian Zhang, Xiaoqian Jiang, Pratip K Bhattacharya, Shyan Shams

TLDR

  • The study investigates whether artificial intelligence (A.I.) can detect glioblastoma (GBM) earlier than conventional imaging techniques in glioblastoma murine models. The researchers developed a deep learning model that combines multiple modalities of cancer data to predict tumor progression, assess treatment effects, and to reconstruct in vivo metabolomic information from ex vivo data. The model can detect GBM progression two weeks earlier than conventional MRIs and a week earlier than HPMRS alone. The model accurately predicted in vivo biomarkers from HPMRS, and the results inferred biological relevance. The study highlights the potential of A.I. in analyzing multiple modalities of cancer data and detecting GBM earlier than conventional imaging techniques.

Abstract

Glioblastoma (GBM) is a malignant Grade VI cancer type with a median survival duration of only 8-16 months. Earlier detection of GBM could enable more effective treatment. Hyperpolarized magnetic resonance spectroscopy (HPMRS) could detect GBM earlier than conventional anatomical MRI in glioblastoma murine models. We further investigated whether artificial intelligence (A.I.) could detect GBM earlier than HPMRS. We developed a deep learning model that combines multiple modalities of cancer data to predict tumor progression, assess treatment effects, and to reconstruct in vivo metabolomic information from ex vivo data. Our model can detect GBM progression two weeks earlier than conventional MRIs and a week earlier than HPMRS alone. Our model accurately predicted in vivo biomarkers from HPMRS, and the results inferred biological relevance. Additionally, the model showed potential for examining treatment effects. Our model successfully detected tumor progression two weeks earlier than conventional MRIs and accurately predicted in vivo biomarkers using ex vivo information such as conventional MRIs, HPMRS, and tumor size data. The accuracy of these predictions is consistent with biological relevance.

Overview

  • The study aims to investigate the potential of artificial intelligence (A.I.) to detect glioblastoma (GBM) earlier than hyperpolarized magnetic resonance spectroscopy (HPMRS) in glioblastoma murine models. The study uses a deep learning model that combines multiple modalities of cancer data to predict tumor progression, assess treatment effects, and to reconstruct in vivo metabolomic information from ex vivo data. The primary objective is to determine if the model can detect GBM progression earlier than conventional MRIs and accurately predict in vivo biomarkers using ex vivo information such as conventional MRIs, HPMRS, and tumor size data. The study is a proof-of-concept study to demonstrate the potential of A.I. in detecting GBM earlier than conventional imaging techniques.

Comparative Analysis & Findings

  • The study compares the outcomes observed under different experimental conditions or interventions, specifically the ability of the deep learning model to detect GBM progression earlier than conventional MRIs and HPMRS. The results show that the model can detect GBM progression two weeks earlier than conventional MRIs and a week earlier than HPMRS alone. The model accurately predicted in vivo biomarkers from HPMRS, and the results inferred biological relevance. The study demonstrates the potential of A.I. in detecting GBM earlier than conventional imaging techniques.

Implications and Future Directions

  • The study's findings suggest that A.I. has the potential to detect GBM earlier than conventional imaging techniques, which could lead to more effective treatment. However, the study is a proof-of-concept study, and further research is needed to validate the results and determine the clinical applicability of the model. Future research could focus on developing a more robust model that can detect GBM progression in human patients and integrating the model with clinical workflows. Additionally, the study highlights the potential of A.I. in analyzing multiple modalities of cancer data, which could lead to more accurate and personalized treatment plans.
Read Full Article