Multi-Parameter Molecular MRI Quantification using Physics-Informed Self-Supervised Learning Article Swipe

PDF

Alex Finkelstein , Nikita Vladimirov , Moritz Zaiß , Or Perlman ·

YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2411.06447

Biophysical model fitting plays a key role in obtaining quantitative parameters from physiological signals and images. However, the model complexity for molecular magnetic resonance imaging (MRI) often translates into excessive computation time, which makes clinical use impractical. Here, we present a generic computational approach for solving the parameter extraction inverse problem posed by ordinary differential equation (ODE) modeling coupled with experimental measurement of the system dynamics. This is achieved by formulating a numerical ODE solver to function as a step-wise analytical one, thereby making it compatible with automatic differentiation-based optimization. This enables efficient gradient-based model fitting, and provides a new approach to parameter quantification based on self-supervised learning from a single data observation. The neural-network-based train-by-fit pipeline was used to quantify semisolid magnetization transfer (MT) and chemical exchange saturation transfer (CEST) amide proton exchange parameters in the human brain, in an in-vivo molecular MRI study (n = 4). The entire pipeline of the first whole brain quantification was completed in 18.3 $\pm$ 8.3 minutes. Reusing the single-subject-trained network for inference in new subjects took 1.0 $\pm$ 0.2 s, to provide results in agreement with literature values and scan-specific fit results.

Related Topics

Artificial Intelligence

Machine Learning

Computer Science

Physics

Concepts

Artificial intelligence Medical physics Machine learning Computer science Physics

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2411.06447
PDF: https://arxiv.org/pdf/2411.06447
OA Status: green
Related Works: 10
OpenAlex ID: https://openalex.org/W4404401707

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4404401707

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2411.06447

Digital Object Identifier
Title: Multi-Parameter Molecular MRI Quantification using Physics-Informed Self-Supervised Learning

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2024

Year of publication
Publication date: 2024-11-10

Full publication date if available
Authors: Alex Finkelstein, Nikita Vladimirov, Moritz Zaiß, Or Perlman

List of authors in order
Landing page: https://arxiv.org/abs/2411.06447

Publisher landing page
PDF URL: https://arxiv.org/pdf/2411.06447

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2411.06447

Direct OA link when available
Concepts: Artificial intelligence, Medical physics, Machine learning, Computer science, Physics

Top concepts (fields/topics) attached by OpenAlex
Cited by: 0

Total citation count in OpenAlex
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4404401707
doi	https://doi.org/10.48550/arxiv.2411.06447
ids.doi	https://doi.org/10.48550/arxiv.2411.06447
ids.openalex	https://openalex.org/W4404401707
fwci	0.0
type	preprint
title	Multi-Parameter Molecular MRI Quantification using Physics-Informed Self-Supervised Learning
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T10378
topics[0].field.id	https://openalex.org/fields/27
topics[0].field.display_name	Medicine
topics[0].score	0.9672999978065491
topics[0].domain.id	https://openalex.org/domains/4
topics[0].domain.display_name	Health Sciences
topics[0].subfield.id	https://openalex.org/subfields/2741
topics[0].subfield.display_name	Radiology, Nuclear Medicine and Imaging
topics[0].display_name	Advanced MRI Techniques and Applications
topics[1].id	https://openalex.org/T12603
topics[1].field.id	https://openalex.org/fields/31
topics[1].field.display_name	Physics and Astronomy
topics[1].score	0.9549999833106995
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/3106
topics[1].subfield.display_name	Nuclear and High Energy Physics
topics[1].display_name	NMR spectroscopy and applications
topics[2].id	https://openalex.org/T11809
topics[2].field.id	https://openalex.org/fields/16
topics[2].field.display_name	Chemistry
topics[2].score	0.9368000030517578
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/1607
topics[2].subfield.display_name	Spectroscopy
topics[2].display_name	Advanced NMR Techniques and Applications
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C154945302
concepts[0].level	1
concepts[0].score	0.43860578536987305
concepts[0].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[0].display_name	Artificial intelligence
concepts[1].id	https://openalex.org/C19527891
concepts[1].level	1
concepts[1].score	0.41063442826271057
concepts[1].wikidata	https://www.wikidata.org/wiki/Q1120908
concepts[1].display_name	Medical physics
concepts[2].id	https://openalex.org/C119857082
concepts[2].level	1
concepts[2].score	0.3690810203552246
concepts[2].wikidata	https://www.wikidata.org/wiki/Q2539
concepts[2].display_name	Machine learning
concepts[3].id	https://openalex.org/C41008148
concepts[3].level	0
concepts[3].score	0.36317718029022217
concepts[3].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[3].display_name	Computer science
concepts[4].id	https://openalex.org/C121332964
concepts[4].level	0
concepts[4].score	0.34007394313812256
concepts[4].wikidata	https://www.wikidata.org/wiki/Q413
concepts[4].display_name	Physics
keywords[0].id	https://openalex.org/keywords/artificial-intelligence
keywords[0].score	0.43860578536987305
keywords[0].display_name	Artificial intelligence
keywords[1].id	https://openalex.org/keywords/medical-physics
keywords[1].score	0.41063442826271057
keywords[1].display_name	Medical physics
keywords[2].id	https://openalex.org/keywords/machine-learning
keywords[2].score	0.3690810203552246
keywords[2].display_name	Machine learning
keywords[3].id	https://openalex.org/keywords/computer-science
keywords[3].score	0.36317718029022217
keywords[3].display_name	Computer science
keywords[4].id	https://openalex.org/keywords/physics
keywords[4].score	0.34007394313812256
keywords[4].display_name	Physics
language	en
locations[0].id	pmh:oai:arXiv.org:2411.06447
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2411.06447
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2411.06447
locations[1].id	doi:10.48550/arxiv.2411.06447
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license	cc-by
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article-journal
locations[1].license_id	https://openalex.org/licenses/cc-by
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2411.06447
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5068062672
authorships[0].author.orcid
authorships[0].author.display_name	Alex Finkelstein
authorships[0].author_position	first
authorships[0].raw_author_name	Finkelstein, Alex
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5078478374
authorships[1].author.orcid	https://orcid.org/0000-0002-1159-0689
authorships[1].author.display_name	Nikita Vladimirov
authorships[1].author_position	middle
authorships[1].raw_author_name	Vladimirov, Nikita
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5054149506
authorships[2].author.orcid	https://orcid.org/0000-0001-9780-3616
authorships[2].author.display_name	Moritz Zaiß
authorships[2].author_position	middle
authorships[2].raw_author_name	Zaiss, Moritz
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5027178832
authorships[3].author.orcid	https://orcid.org/0000-0002-3566-569X
authorships[3].author.display_name	Or Perlman
authorships[3].author_position	last
authorships[3].raw_author_name	Perlman, Or
authorships[3].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2411.06447
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Multi-Parameter Molecular MRI Quantification using Physics-Informed Self-Supervised Learning
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T10378
primary_topic.field.id	https://openalex.org/fields/27
primary_topic.field.display_name	Medicine
primary_topic.score	0.9672999978065491
primary_topic.domain.id	https://openalex.org/domains/4
primary_topic.domain.display_name	Health Sciences
primary_topic.subfield.id	https://openalex.org/subfields/2741
primary_topic.subfield.display_name	Radiology, Nuclear Medicine and Imaging
primary_topic.display_name	Advanced MRI Techniques and Applications
related_works	https://openalex.org/W4391375266, https://openalex.org/W2961085424, https://openalex.org/W4306674287, https://openalex.org/W3046775127, https://openalex.org/W4394896187, https://openalex.org/W3170094116, https://openalex.org/W4386462264, https://openalex.org/W3107602296, https://openalex.org/W4364306694, https://openalex.org/W4312192474
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2411.06447
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2411.06447
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2411.06447
primary_location.id	pmh:oai:arXiv.org:2411.06447
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2411.06447
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2411.06447
publication_date	2024-11-10
publication_year	2024
referenced_works_count	0
abstract_inverted_index.=	146
abstract_inverted_index.a	4, 40, 71, 78, 98, 109
abstract_inverted_index.(n	145
abstract_inverted_index.an	140
abstract_inverted_index.as	77
abstract_inverted_index.by	52, 69
abstract_inverted_index.in	7, 135, 139, 159, 170, 181
abstract_inverted_index.is	67
abstract_inverted_index.it	84
abstract_inverted_index.of	62, 151
abstract_inverted_index.on	105
abstract_inverted_index.s,	177
abstract_inverted_index.to	75, 101, 119, 178
abstract_inverted_index.we	38
abstract_inverted_index.0.2	176
abstract_inverted_index.1.0	174
abstract_inverted_index.4).	147
abstract_inverted_index.8.3	162
abstract_inverted_index.MRI	143
abstract_inverted_index.ODE	73
abstract_inverted_index.The	113, 148
abstract_inverted_index.and	14, 96, 125, 186
abstract_inverted_index.fit	188
abstract_inverted_index.for	20, 44, 168
abstract_inverted_index.key	5
abstract_inverted_index.new	99, 171
abstract_inverted_index.the	17, 46, 63, 136, 152, 165
abstract_inverted_index.use	35
abstract_inverted_index.was	117, 157
abstract_inverted_index.(MT)	124
abstract_inverted_index.18.3	160
abstract_inverted_index.This	66, 90
abstract_inverted_index.data	111
abstract_inverted_index.from	11, 108
abstract_inverted_index.into	28
abstract_inverted_index.one,	81
abstract_inverted_index.role	6
abstract_inverted_index.took	173
abstract_inverted_index.used	118
abstract_inverted_index.with	59, 86, 183
abstract_inverted_index.$\pm$	161, 175
abstract_inverted_index.(MRI)	25
abstract_inverted_index.(ODE)	56
abstract_inverted_index.Here,	37
abstract_inverted_index.amide	131
abstract_inverted_index.based	104
abstract_inverted_index.brain	155
abstract_inverted_index.first	153
abstract_inverted_index.human	137
abstract_inverted_index.makes	33
abstract_inverted_index.model	1, 18, 94
abstract_inverted_index.often	26
abstract_inverted_index.plays	3
abstract_inverted_index.posed	51
abstract_inverted_index.study	144
abstract_inverted_index.time,	31
abstract_inverted_index.which	32
abstract_inverted_index.whole	154
abstract_inverted_index.(CEST)	130
abstract_inverted_index.brain,	138
abstract_inverted_index.entire	149
abstract_inverted_index.making	83
abstract_inverted_index.proton	132
abstract_inverted_index.single	110
abstract_inverted_index.solver	74
abstract_inverted_index.system	64
abstract_inverted_index.values	185
abstract_inverted_index.Reusing	164
abstract_inverted_index.coupled	58
abstract_inverted_index.enables	91
abstract_inverted_index.fitting	2
abstract_inverted_index.generic	41
abstract_inverted_index.images.	15
abstract_inverted_index.imaging	24
abstract_inverted_index.in-vivo	141
abstract_inverted_index.inverse	49
abstract_inverted_index.network	167
abstract_inverted_index.present	39
abstract_inverted_index.problem	50
abstract_inverted_index.provide	179
abstract_inverted_index.results	180
abstract_inverted_index.signals	13
abstract_inverted_index.solving	45
abstract_inverted_index.thereby	82
abstract_inverted_index.However,	16
abstract_inverted_index.achieved	68
abstract_inverted_index.approach	43, 100
abstract_inverted_index.chemical	126
abstract_inverted_index.clinical	34
abstract_inverted_index.equation	55
abstract_inverted_index.exchange	127, 133
abstract_inverted_index.fitting,	95
abstract_inverted_index.function	76
abstract_inverted_index.learning	107
abstract_inverted_index.magnetic	22
abstract_inverted_index.minutes.	163
abstract_inverted_index.modeling	57
abstract_inverted_index.ordinary	53
abstract_inverted_index.pipeline	116, 150
abstract_inverted_index.provides	97
abstract_inverted_index.quantify	120
abstract_inverted_index.results.	189
abstract_inverted_index.subjects	172
abstract_inverted_index.transfer	123, 129
abstract_inverted_index.agreement	182
abstract_inverted_index.automatic	87
abstract_inverted_index.completed	158
abstract_inverted_index.dynamics.	65
abstract_inverted_index.efficient	92
abstract_inverted_index.excessive	29
abstract_inverted_index.inference	169
abstract_inverted_index.molecular	21, 142
abstract_inverted_index.numerical	72
abstract_inverted_index.obtaining	8
abstract_inverted_index.parameter	47, 102
abstract_inverted_index.resonance	23
abstract_inverted_index.semisolid	121
abstract_inverted_index.step-wise	79
abstract_inverted_index.analytical	80
abstract_inverted_index.compatible	85
abstract_inverted_index.complexity	19
abstract_inverted_index.extraction	48
abstract_inverted_index.literature	184
abstract_inverted_index.parameters	10, 134
abstract_inverted_index.saturation	128
abstract_inverted_index.translates	27
abstract_inverted_index.Biophysical	0
abstract_inverted_index.computation	30
abstract_inverted_index.formulating	70
abstract_inverted_index.measurement	61
abstract_inverted_index.differential	54
abstract_inverted_index.experimental	60
abstract_inverted_index.impractical.	36
abstract_inverted_index.observation.	112
abstract_inverted_index.quantitative	9
abstract_inverted_index.train-by-fit	115
abstract_inverted_index.computational	42
abstract_inverted_index.magnetization	122
abstract_inverted_index.optimization.	89
abstract_inverted_index.physiological	12
abstract_inverted_index.scan-specific	187
abstract_inverted_index.gradient-based	93
abstract_inverted_index.quantification	103, 156
abstract_inverted_index.self-supervised	106
abstract_inverted_index.neural-network-based	114
abstract_inverted_index.differentiation-based	88
abstract_inverted_index.single-subject-trained	166
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	4
citation_normalized_percentile.value	0.37742876
citation_normalized_percentile.is_in_top_1_percent	False
citation_normalized_percentile.is_in_top_10_percent	False