Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Predicting Hypoxia in Brain Tumors from Multiparametric MRI

Daniele Perlo, Georgia Kanli, Selma Boudissa, Olivier Keunen

TL;DR

This work tackles the challenge of non-invasively predicting tumor hypoxia in brain cancers by translating multi-parametric MRI into FMISO PET signals. It introduces a 3D ResViT framework that ingests four MRI sequences to estimate FMISO uptake, using a tumor-focused loss to emphasize prediction accuracy in clinically relevant regions. The approach achieves high overall similarity metrics (PSNR > 29.6, SSIM > 0.94 in the abstract) and demonstrates superior tumor-area fidelity compared to 2D models and baselines, signaling MRI's potential as an accessible surrogate for FMISO-based hypoxia assessment. If validated on larger cohorts and extended with functional imaging, this method could enable more timely, targeted radiotherapy planning for brain tumor patients.

Abstract

This research paper presents a novel approach to the prediction of hypoxia in brain tumors, using multi-parametric Magnetic Resonance Imaging (MRI). Hypoxia, a condition characterized by low oxygen levels, is a common feature of malignant brain tumors associated with poor prognosis. Fluoromisonidazole Positron Emission Tomography (FMISO PET) is a well-established method for detecting hypoxia in vivo, but it is expensive and not widely available. Our study proposes the use of MRI, a more accessible and cost-effective imaging modality, to predict FMISO PET signals. We investigate deep learning models (DL) trained on the ACRIN 6684 dataset, a resource that contains paired MRI and FMISO PET images from patients with brain tumors. Our trained models effectively learn the complex relationships between the MRI features and the corresponding FMISO PET signals, thereby enabling the prediction of hypoxia from MRI scans alone. The results show a strong correlation between the predicted and actual FMISO PET signals, with an overall PSNR score above 29.6 and a SSIM score greater than 0.94, confirming MRI as a promising option for hypoxia prediction in brain tumors. This approach could significantly improve the accessibility of hypoxia detection in clinical settings, with the potential for more timely and targeted treatments.

Predicting Hypoxia in Brain Tumors from Multiparametric MRI

TL;DR

This work tackles the challenge of non-invasively predicting tumor hypoxia in brain cancers by translating multi-parametric MRI into FMISO PET signals. It introduces a 3D ResViT framework that ingests four MRI sequences to estimate FMISO uptake, using a tumor-focused loss to emphasize prediction accuracy in clinically relevant regions. The approach achieves high overall similarity metrics (PSNR > 29.6, SSIM > 0.94 in the abstract) and demonstrates superior tumor-area fidelity compared to 2D models and baselines, signaling MRI's potential as an accessible surrogate for FMISO-based hypoxia assessment. If validated on larger cohorts and extended with functional imaging, this method could enable more timely, targeted radiotherapy planning for brain tumor patients.

Abstract

This research paper presents a novel approach to the prediction of hypoxia in brain tumors, using multi-parametric Magnetic Resonance Imaging (MRI). Hypoxia, a condition characterized by low oxygen levels, is a common feature of malignant brain tumors associated with poor prognosis. Fluoromisonidazole Positron Emission Tomography (FMISO PET) is a well-established method for detecting hypoxia in vivo, but it is expensive and not widely available. Our study proposes the use of MRI, a more accessible and cost-effective imaging modality, to predict FMISO PET signals. We investigate deep learning models (DL) trained on the ACRIN 6684 dataset, a resource that contains paired MRI and FMISO PET images from patients with brain tumors. Our trained models effectively learn the complex relationships between the MRI features and the corresponding FMISO PET signals, thereby enabling the prediction of hypoxia from MRI scans alone. The results show a strong correlation between the predicted and actual FMISO PET signals, with an overall PSNR score above 29.6 and a SSIM score greater than 0.94, confirming MRI as a promising option for hypoxia prediction in brain tumors. This approach could significantly improve the accessibility of hypoxia detection in clinical settings, with the potential for more timely and targeted treatments.
Paper Structure (11 sections, 2 equations, 2 figures, 1 table)

This paper contains 11 sections, 2 equations, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Method
  4. Dataset description
  5. FMISO Dataset
  6. FDG Dataset
  7. Data Preprocessing
  8. Model
  9. Results
  10. Conclusions
  11. Acknowledgment

Figures (2)

  • Figure 1: Data preparation workflow for FMISO and FDG images.
  • Figure 2: Axial view of cancer region FMISO signal reconstruction from our 3D ResViT trained with Tumor Focus.