Hierarchical non-negative matrix factorization applied to three-dimensional 3 T MRSI data for automatic tissue characterization of the prostate

Laudadio, Teresa; Sava, Anca R. Croitor; Sima, Diana M.; Wright, Alan J.; Heerschap, Arend; Mastronardi, Nicola; Huffel, Sabine Van

doi:10.1002/nbm.3527

Cited by 15 publications

(20 citation statements)

References 30 publications

(53 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, in [14], a hierarchical approach is proposed which differs from those ones applied to brain data in [10][11][12]. Indeed, since the detection of only two tissue patterns is generally required for prostate data, i.e., tumour and benign tissue, NMF could be directly applied to the MRSI data set by setting k = 2.…”

Section: Nmf Applied To Prostate Mrsi Data For Automatic Detection Anmentioning

confidence: 99%

“…In [13,14], preliminary studies have been carried out on the application of NMF to simulate as well as to in vivo three-dimensional 3 T long-echo MRSI prostate data in order to extract characteristic patterns for tumour and benign tissue and to visualise their spatial distribution. In particular, in [14], a hierarchical approach is proposed which differs from those ones applied to brain data in [10][11][12].…”

Section: Nmf Applied To Prostate Mrsi Data For Automatic Detection Anmentioning

confidence: 99%

“…In particular, the studies described in [7][8][9][10][11][12][13][14] show that the application of NMF allows to overcome some of the main limitations that still affect most tissue segmentation and classification techniques of MRS(I) data available in the literature, i.e., need of prior knowledge, lack of automation and inability to properly describe tissue mixtures since each tissue volume element (or, equivalently, voxel), where the MRS signal is measured, is only labelled as being tumourous or non-tumorous.…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, they do not require massive MRS(I) data pre-processing aimed at removing artefacts, instrumental limitations, noise, etc., since NMF is able to detect the presence of uninteresting components as separate sources [13,14].…”

Section: Introductionmentioning

confidence: 99%

“…Specifically, NMF-based methods for the recovery of constituent spectra in ex vivo and in vivo brain MRS data [7,8], for brain tissue pattern differentiation using MRSI data [9][10][11][12], and for automatic detection and visualisation of prostate tumours [13,14], will be described. Furthermore, since several NMF implementations are available in the literature, a comparison in terms of pattern detection accuracy of some NMF algorithms will be reported and discussed, and the NMF performance for MRS data analysis will be compared with that of other BSS techniques.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

NMF in MR Spectroscopy

Laudadio

Sava

et al. 2015

Signals and Communication Technology

View full text Add to dashboard Cite

Nowadays, magnetic resonance spectroscopy (MRS) represents a powerful nuclear magnetic resonance (NMR) technique in oncology since it provides information on the biochemical profile of tissues, thereby allowing clinicians and radiologists to identify in a non-invasive way the different tissue types characterising the sample under investigation. The main purpose of the present chapter is to provide a review of the most recent and significant applications of non-negative matrix factorisation (NMF) to MRS data in the field of tissue typing methods for tumour diagnosis. Specifically, NMF-based methods for the recovery of constituent spectra in ex vivo and in vivo brain MRS data, for brain tissue pattern differentiation using magnetic resonance spectroscopic imaging (MRSI) data and for automatic detection and visualisation of prostate tumours, will be described. Furthermore, since several NMF implementations are available in the literature, a comparison in terms of pattern detection accuracy of some NMF algorithms will be reported and discussed, and the NMF performance for MRS data analysis will be compared with that of other blind source separation (BSS) techniques.

show abstract

Section: Nmf Applied To Prostate Mrsi Data For Automatic Detection Anmentioning

confidence: 99%

Section: Nmf Applied To Prostate Mrsi Data For Automatic Detection Anmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

NMF in MR Spectroscopy

Laudadio

Sava

et al. 2015

Signals and Communication Technology

View full text Add to dashboard Cite

show abstract

Distributed geometric nonnegative matrix factorization and hierarchical alternating least squares–based nonnegative tensor factorization with the MapReduce paradigm

Zdunek

Fonał

2018

Concurrency and Computation

View full text Add to dashboard Cite

Summary Nonnegative matrix factorization and its multilinear extension known as nonnegative tensor factorization are commonly used methods in machine learning and data analysis for feature extraction and dimensionality reduction for nonnegative high‐dimensional data. Dimensionality reduction for massive amounts of data usually involves distributed computation across multi‐node computer architectures. In this study, we propose various computational strategies for parallel and distributed computation of the latent factors in both factorization models, all of which are based on partitioning the computational tasks according to the MapReduce paradigm. We extend the previously reported distributed hierarchical alternating least squares algorithm to the multi‐way array factorization model, where we assume that the observed multi‐way data can be partitioned into chunks along one mode. Moreover, we propose a new geometry‐based distributed computational strategy for solving nonnegative matrix factorization problems. Numerical experiments performed using various large‐scale data sets demonstrated that these algorithms are efficient and robust to noisy data.

show abstract

Cancer metabolism in a snapshot: MRS(I)

2019

View full text Add to dashboard Cite

The contribution of MRS(I) to the in vivo evaluation of cancer-metabolism-derived metrics, mostly since 2016, is reviewed here. Increased carbon consumption by tumour cells, which are highly glycolytic, is now being sampled by 13 C magnetic resonance spectroscopic imaging (MRSI) following the injection of hyperpolarized [1-13 C] pyruvate (Pyr). Hot-spots of, mostly, increased lactate dehydrogenase activity or flow between Pyr and lactate (Lac) have been seen with cancer progression in prostate (preclinical and in humans), brain and pancreas (both preclinical) tumours. Therapy response is usually signalled by decreased Lac/Pyr 13 C-labelled ratio with respect to untreated or nonresponding tumour. For therapeutic agents inducing tumour hypoxia, the 13 C-labelled Lac/bicarbonate ratio may be a better metric than the Lac/Pyr ratio. 31 P MRSI may sample intracellular pH changes from brain tumours (acidification upon antiangiogenic treatment, basification at fast proliferation and relapse). The steady state tumour metabolome pattern is still in use for cancer evaluation. Metrics used for this range from quantification of single oncometabolites (such as 2-hydroxyglutarate in mutant IDH1 glial brain tumours) to selected metabolite ratios (such as total choline to N-acetylaspartate (plain ratio or CNI index)) or the whole 1 H MRSI(I) pattern through pattern recognition analysis. These approaches have been applied to address different questions such as tumour subtype definition, following/predicting the response to therapy or defining better resection or radiosurgery limits. KEYWORDSanimal model study, cancer, cellular and molecular cancer imaging, hyperpolarized C-13, MRS and MRSI methods, phosphorus MRS/MRSI | TEMPORAL AND THEMATIC BOUNDARIES OF THE TOPICS COVEREDThe authors of this review declare at the outset that there is no intention of being exhaustive or systematic. The temporal boundaries reviewed will be modest: only relevant literature since 2016, chosen according to our bias. Earlier work or reviews will only be referred to in order to put recent findings in due perspective. Authors hope that this summary will give readers a picture of how far cancer metabolism analysis with MRS(I) has advanced and, perhaps, why it is not advancing further.For quite a long time MRS, rather than MRI, has been the only approach able to evaluate cancer metabolism. Nevertheless, the MRI-derived information related to cancer metabolism should not be forgotten: consider for example the chemical exchange saturation transfer (CEST) effect caused by exchangeable protons in water-derived images of glucose uptake and metabolism in tumours. 1,2 However, apart from these CESTrelated studies, we should acknowledge that most information about cancer metabolism using MR still refers to MRS(I) acquisitions, which are the ones dealt with in our text.Supplementary Figure 1 shows a PUBMED search illustrating the different proportions of articles investigating several cancer types through MRS(I) approaches. The retrieved information can help unders...

show abstract

Hierarchical non-negative matrix factorization applied to three-dimensional 3 T MRSI data for automatic tissue characterization of the prostate

Cited by 15 publications

References 30 publications

NMF in MR Spectroscopy

NMF in MR Spectroscopy

Distributed geometric nonnegative matrix factorization and hierarchical alternating least squares–based nonnegative tensor factorization with the MapReduce paradigm

Cancer metabolism in a snapshot: MRS(I)

Contact Info

Product

Resources

About