Embedding MRI information into MRSI data source extraction improves brain tumour delineation in animal models

Abstract

Glioblastoma is the most frequent malignant intra-cranial tumour. Magnetic resonance imaging is the modality of choice in diagnosis, aggressiveness assessment, and follow-up. However, there are examples where it lacks diagnostic accuracy. Magnetic resonance spectroscopy enables the identification of molecules present in the tissue, providing a precise metabolomic signature. Previous research shows that combining imaging and spectroscopy information results in more accurate outcomes and superior diagnostic value. This study proposes a method to combine them, which builds upon a previous methodology whose main objective is to guide the extraction of sources. To this aim, prior knowledge about class-specific information is integrated into the methodology by setting the metric of a latent variable space where Non-negative Matrix Factorisation is performed. The former methodology, which only used spectroscopy and involved combining spectra from different subjects, was adapted to use selected areas of interest that arise from segmenting the T2-weighted image. Results showed that embedding imaging information into the source extraction (the proposed semi-supervised analysis) improved the quality of the tumour delineation, as compared to those obtained without this information (unsupervised analysis). Both approaches were applied to pre-clinical data, involving thirteen brain tumour-bearing mice, and tested against histopathological data. On results of twenty-eight images, the proposed Semi-Supervised Source Extraction (SSSE) method greatly outperformed the unsupervised one, as well as an alternative semi-supervised approach from the literature, with differences being statistically significant. SSSE has proven successful in the delineation of the tumour, while bringing benefits such as 1) not constricting the metabolomic-based prediction to the image-segmented area, 2) ability to deal with signal-to-noise issues, 3) opportunity to answer specific questions by allowing researchers/radiologists define areas of interest that guide the source extraction, 4) creation of an intra-subject model and avoiding contamination from inter-subject overlaps, and 5) extraction of meaningful, good-quality sources that adds interpretability, conferring validation and better understanding of each case.

Brain Tumor Segmentation and Classification using hybrid Deep CNN with LuNet Classifier

“…Para el desarrollo de nuestra investigación se optará por esta última opción, para lo cual se cuenta con las bases de datos generada a partir de los estudios previos realizados por (Ortega-Martorell et al, 2019) en los años 2012, 2013 y 2016, reseñados en la bibliografía de esta propuesta.…”

Implementation of Trusted Traceability Query Using Blockchain and Deep Reinforcement Learning in Resource Management

“…One reason is that the PROV data model has strong scenario applicability. The other reason is that the PROV data model has relatively complete open-source codes [ 23 , 24 ].…”

Tracking Therapy Response in Glioblastoma Using 1D Convolutional Neural Networks

“…Our groups have been working in the preclinical scenario in order to explore, interpret, analyse and validate the potential of the spectroscopic approaches, especially spectroscopic imaging (MRSI), in the early assessment of therapy responses [7][8][9]. Also, for several years now, machine learning (ML) and deep learning (DL) methods have been consistently shown to be able to help with tasks such as brain tumour detection [10][11][12], diagnosis and grading [13][14][15], classification [16][17][18][19], segmentation of the affected/tumour area [20][21][22] and therapy response prediction to distinguish post-treatment effects and tumour progression [23][24][25][26][27], among others. Hence, we firmly believe that ML and DL methods applied to such metabolomic datasets using whole pattern inputs may help to unravel its potential in a way that would not be possible with a single metabolite or ratio quantitation.…”