Tracking Therapy Response in Glioblastoma Using 1D Convolutional Neural Networks

Simple Summary Glioblastoma (GB) is a malignant brain tumour with no cure, even after the best treatment. The evaluation of a therapy response is usually based on magnetic resonance imaging (MRI), but it lacks precision in early stages, and doctors must wait several weeks until they are confident information is produced, facing an uncertain time window. Magnetic resonance spectroscopy (MRS/MRSI) can provide additional information about tumours and their environment but is not widely used in clinical settings since the spectroscopy format is not standardised as MRI is, and doctors are not familiarised with outputs/interpretation. This study aims to improve the assessment of the treatment response in GB using MRSI data and machine learning, including state-of-the-art one-dimensional convolutional neural networks. Preclinical (murine) GB data were used for developing models that successfully identified tumour regions regarding their response to treatment (or the lack thereof). These models were accurate and outperformed previous methods, potentially providing new opportunities for GB patient management. Background: Glioblastoma (GB) is a malignant brain tumour that is challenging to treat, often relapsing even after aggressive therapy. Evaluating therapy response relies on magnetic resonance imaging (MRI) following the Response Assessment in Neuro-Oncology (RANO) criteria. However, early assessment is hindered by phenomena such as pseudoprogression and pseudoresponse. Magnetic resonance spectroscopy (MRS/MRSI) provides metabolomics information but is underutilised due to a lack of familiarity and standardisation. Methods: This study explores the potential of spectroscopic imaging (MRSI) in combination with several machine learning approaches, including one-dimensional convolutional neural networks (1D-CNNs), to improve therapy response assessment. Preclinical GB (GL261-bearing mice) were studied for method optimisation and validation. Results: The proposed 1D-CNN models successfully identify different regions of tumours sampled by MRSI, i.e., normal brain (N), control/unresponsive tumour (T), and tumour responding to treatment (R). Class activation maps using Grad-CAM enabled the study of the key areas relevant to the models, providing model explainability. The generated colour-coded maps showing the N, T and R regions were highly accurate (according to Dice scores) when compared against ground truth and outperformed our previous method. Conclusions: The proposed methodology may provide new and better opportunities for therapy response assessment, potentially providing earlier hints of tumour relapsing stages.