Quantitative imaging of apoptosis following oncolytic virotherapy by magnetic resonance fingerprinting aided by deep learning.

in Nature biomedical engineering by Or Perlman, Hirotaka Ito, Kai Herz, Naoyuki Shono, Hiroshi Nakashima, Moritz Zaiss, E Antonio Chiocca, Ouri Cohen, Matthew S Rosen, Christian T Farrar

TLDR

  • Researchers developed a non-invasive imaging method using CEST-MRF and deep learning to detect early apoptotic responses to oncolytic virotherapy in glioblastoma multiforme.
  • The method generates quantitative maps of intratumoral pH, protein, and lipid concentrations without exogenous contrast agents.
  • This technology has the potential to improve cancer treatment outcomes by enabling rapid and non-invasive monitoring of treatment response and host responses.

Abstract

Non-invasive imaging methods for detecting intratumoural viral spread and host responses to oncolytic virotherapy are either slow, lack specificity or require the use of radioactive or metal-based contrast agents. Here we show that in mice with glioblastoma multiforme, the early apoptotic responses to oncolytic virotherapy (characterized by decreased cytosolic pH and reduced protein synthesis) can be rapidly detected via chemical-exchange-saturation-transfer magnetic resonance fingerprinting (CEST-MRF) aided by deep learning. By leveraging a deep neural network trained with simulated magnetic resonance fingerprints, CEST-MRF can generate quantitative maps of intratumoural pH and of protein and lipid concentrations by selectively labelling the exchangeable amide protons of endogenous proteins and the exchangeable macromolecule protons of lipids, without requiring exogenous contrast agents. We also show that in a healthy volunteer, CEST-MRF yielded molecular parameters that are in good agreement with values from the literature. Deep-learning-aided CEST-MRF may also be amenable to the characterization of host responses to other cancer therapies and to the detection of cardiac and neurological pathologies.

Overview

  • The study aims to develop a non-invasive imaging method to detect intratumoral viral spread and host responses to oncolytic virotherapy using chemical-exchange-saturation-transfer magnetic resonance fingerprinting (CEST-MRF) aided by deep learning.
  • The study uses a deep neural network trained with simulated magnetic resonance fingerprints to generate quantitative maps of intratumoral pH, protein, and lipid concentrations without exogenous contrast agents.
  • The primary objective of the study is to develop a rapid and non-invasive imaging method to detect early apoptotic responses to oncolytic virotherapy in mice with glioblastoma multiforme.

Comparative Analysis & Findings

  • The study shows that CEST-MRF can detect early apoptotic responses to oncolytic virotherapy in mice with glioblastoma multiforme by rapidly detecting changes in cytosolic pH and reduced protein synthesis.
  • The study reports that CEST-MRF can generate quantitative maps of intratumoral pH, protein, and lipid concentrations without requiring exogenous contrast agents.
  • The study also shows that CEST-MRF can be used to detect molecular parameters in a healthy volunteer that agree with values from the literature, indicating its potential for use in clinical settings.

Implications and Future Directions

  • The study's findings have implications for the development of non-invasive imaging methods for detecting intratumoral viral spread and host responses to oncolytic virotherapy, reducing the need for invasive procedures or exogenous contrast agents.
  • Future studies could explore the use of CEST-MRF to characterize host responses to other cancer therapies and to detect cardiac and neurological pathologies.
  • Deep-learning-aided CEST-MRF may also enable the detection of biomarkers for early cancer diagnosis and monitoring, improving treatment outcomes and patient care.
Read Full Article