A comparison of non‐negative matrix underapproximation methods for the decomposition of magnetic resonance spectroscopy data from human brain tumors

Abstract

Magnetic resonance spectroscopy (MRS) is an MR technique that provides information about the biochemistry of tissues in a noninvasive way. MRS has been widely used for the study of brain tumors, both preoperatively and during follow‐up. In this study, we investigated the performance of a range of variants of unsupervised matrix factorization methods of the non‐negative matrix underapproximation (NMU) family, namely, sparse NMU, global NMU, and recursive NMU, and compared them with convex non‐negative matrix factorization (C‐NMF), which has previously shown a good performance on brain tumor diagnostic support problems using MRS data. The purpose of the investigation was 2‐fold: first, to ascertain the differences among the sources extracted by these methods; and second, to compare the influence of each method in the diagnostic accuracy of the classification of brain tumors, using them as feature extractors. We discovered that, first, NMU variants found meaningful sources in terms of biological interpretability, but representing parts of the spectrum, in contrast to C‐NMF; and second, that NMU methods achieved better classification accuracy than C‐NMF for the classification tasks when one class was not meningioma.

Advances in the Use of Deep Learning for the Analysis of Magnetic Resonance Image in Neuro-Oncology

“…Data are still approximated by linear combinations of factors. Although NMF and variants of this family of methods have extensively been used for the pre-processing and analysis of MRS and MRS imaging (MRSI) signal [38,39], they have only scarcely been used for the pre-processing of MRI. Some outstanding exceptions include the work in [40] with hierarchical NMF for multi-parametric MRI and the recent proposal of a whole new architecture based on NMF called Factorizer [41], constructed by replacing the self-attention layer of a Vision Transformer (ViT, [42]) block with NMF-based modules.…”