Rapid Bone Scintigraphy Enhancement via Semantic Prior Distillation from Segment Anything Model Article Swipe

PDF

Pengchen Liang , Lei Shi , Huiping Yao , Bin Pu , Jianguo Chen , Lei Zhao , Haishan Huang , Zhuangzhuang Chen , Zhaozhao Xu , Liming Xu , Qing Chang , Yiwei Li ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2503.02321

Rapid bone scintigraphy is crucial for diagnosing skeletal disorders and detecting tumor metastases in children, as it shortens scan duration and reduces discomfort. However, accelerated acquisition often degrades image quality, impairing the visibility of fine anatomical details and potentially compromising diagnosis. To overcome this limitation, we introduce the first application of SAM-based semantic priors for medical image restoration, utilizing the Segment Anything Model (SAM) to enhance pediatric rapid bone scintigraphy. Our approach employs two cascaded networks, $f^{IR1}$ and $f^{IR2}$, supported by three specialized modules: a Semantic Prior Integration (SPI) module, a Semantic Knowledge Distillation (SKD) module, and a Semantic Consistency Module (SCM). The SPI and SKD modules inject domain-specific semantic cues from a fine-tuned SAM, while the SCM preserves coherent semantic feature representations across both cascaded stages. Moreover, we present RBS, a novel Rapid Bone Scintigraphy dataset comprising paired standard (20 cm/min) and rapid (40 cm/min) scans from 137 pediatric patients aged 0.5 - 16 years, making it the first dataset tailored for pediatric rapid bone scintigraphy restoration. Extensive experiments on both a public endoscopic dataset and our RBS dataset demonstrate that our method consistently surpasses existing techniques in PSNR, SSIM, FID, and LPIPS metrics.

Related Topics

Bone Tomahawk

Bone Thugs-N-Harmony

Rag'N'Bone Man

Shadow And Bone (Tv Series)

Rapid Transit

Delhi–Meerut Regional Rapid Transit System

T Bone Burnett

Children Of Blood And Bone

Bizzy Bone

Winter's Bone

Bone Marrow

Bay Area Rapid Transit

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2503.02321
PDF: https://arxiv.org/pdf/2503.02321
OA Status: green
OpenAlex ID: https://openalex.org/W4415145335

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4415145335

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2503.02321

Digital Object Identifier
Title: Rapid Bone Scintigraphy Enhancement via Semantic Prior Distillation from Segment Anything Model

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-03-04

Full publication date if available
Authors: Pengchen Liang, Lei Shi, Huiping Yao, Bin Pu, Jianguo Chen, Lei Zhao, Haishan Huang, Zhuangzhuang Chen, Zhaozhao Xu, Liming Xu, Qing Chang, Yiwei Li

List of authors in order
Landing page: https://arxiv.org/abs/2503.02321

Publisher landing page
PDF URL: https://arxiv.org/pdf/2503.02321

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/2503.02321

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4415145335
doi	https://doi.org/10.48550/arxiv.2503.02321
ids.doi	https://doi.org/10.48550/arxiv.2503.02321
ids.openalex	https://openalex.org/W4415145335
fwci
type	preprint
title	Rapid Bone Scintigraphy Enhancement via Semantic Prior Distillation from Segment Anything Model
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T12422
topics[0].field.id	https://openalex.org/fields/27
topics[0].field.display_name	Medicine
topics[0].score	0.930899977684021
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	Radiomics and Machine Learning in Medical Imaging
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2503.02321
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/2503.02321
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/2503.02321
locations[1].id	doi:10.48550/arxiv.2503.02321
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
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
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.2503.02321
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5080438062
authorships[0].author.orcid	https://orcid.org/0000-0002-7475-373X
authorships[0].author.display_name	Pengchen Liang
authorships[0].author_position	first
authorships[0].raw_author_name	Liang, Pengchen
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5014936207
authorships[1].author.orcid	https://orcid.org/0009-0002-8383-0757
authorships[1].author.display_name	Lei Shi
authorships[1].author_position	middle
authorships[1].raw_author_name	Shi, Leijun
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5070739987
authorships[2].author.orcid	https://orcid.org/0000-0002-7031-6436
authorships[2].author.display_name	Huiping Yao
authorships[2].author_position	middle
authorships[2].raw_author_name	Yao, Huiping
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5022349009
authorships[3].author.orcid	https://orcid.org/0000-0002-4959-8432
authorships[3].author.display_name	Bin Pu
authorships[3].author_position	middle
authorships[3].raw_author_name	Pu, Bin
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5100435606
authorships[4].author.orcid	https://orcid.org/0000-0002-6838-4309
authorships[4].author.display_name	Jianguo Chen
authorships[4].author_position	middle
authorships[4].raw_author_name	Chen, Jianguo
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5101762938
authorships[5].author.orcid	https://orcid.org/0000-0002-6336-048X
authorships[5].author.display_name	Lei Zhao
authorships[5].author_position	middle
authorships[5].raw_author_name	Zhao, Lei
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5058283876
authorships[6].author.orcid
authorships[6].author.display_name	Haishan Huang
authorships[6].author_position	middle
authorships[6].raw_author_name	Huang, Haishan
authorships[6].is_corresponding	False
authorships[7].author.id	https://openalex.org/A5008344915
authorships[7].author.orcid	https://orcid.org/0000-0002-0336-1181
authorships[7].author.display_name	Zhuangzhuang Chen
authorships[7].author_position	middle
authorships[7].raw_author_name	Chen, Zhuangzhuang
authorships[7].is_corresponding	False
authorships[8].author.id	https://openalex.org/A5046193582
authorships[8].author.orcid	https://orcid.org/0000-0002-7811-3799
authorships[8].author.display_name	Zhaozhao Xu
authorships[8].author_position	middle
authorships[8].raw_author_name	Xu, Zhaozhao
authorships[8].is_corresponding	False
authorships[9].author.id	https://openalex.org/A5055320676
authorships[9].author.orcid	https://orcid.org/0000-0002-2974-2097
authorships[9].author.display_name	Liming Xu
authorships[9].author_position	middle
authorships[9].raw_author_name	Xu, Lite
authorships[9].is_corresponding	False
authorships[10].author.id	https://openalex.org/A5070457572
authorships[10].author.orcid	https://orcid.org/0000-0001-7568-4070
authorships[10].author.display_name	Qing Chang
authorships[10].author_position	middle
authorships[10].raw_author_name	Chang, Qing
authorships[10].is_corresponding	False
authorships[11].author.id	https://openalex.org/A5101551084
authorships[11].author.orcid	https://orcid.org/0009-0008-2043-9842
authorships[11].author.display_name	Yiwei Li
authorships[11].author_position	last
authorships[11].raw_author_name	Li, Yiwei
authorships[11].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/2503.02321
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-14T00:00:00
display_name	Rapid Bone Scintigraphy Enhancement via Semantic Prior Distillation from Segment Anything Model
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T12422
primary_topic.field.id	https://openalex.org/fields/27
primary_topic.field.display_name	Medicine
primary_topic.score	0.930899977684021
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	Radiomics and Machine Learning in Medical Imaging
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2503.02321
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/2503.02321
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/2503.02321
primary_location.id	pmh:oai:arXiv.org:2503.02321
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/2503.02321
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/2503.02321
publication_date	2025-03-04
publication_year	2025
referenced_works_count	0
abstract_inverted_index.-	153
abstract_inverted_index.a	84, 90, 97, 112, 131, 172
abstract_inverted_index.16	154
abstract_inverted_index.To	41
abstract_inverted_index.as	15
abstract_inverted_index.by	80
abstract_inverted_index.in	13, 188
abstract_inverted_index.is	3
abstract_inverted_index.it	16, 157
abstract_inverted_index.of	33, 50
abstract_inverted_index.on	170
abstract_inverted_index.to	64
abstract_inverted_index.we	45, 128
abstract_inverted_index.(20	140
abstract_inverted_index.(40	144
abstract_inverted_index.0.5	152
abstract_inverted_index.137	148
abstract_inverted_index.Our	70
abstract_inverted_index.RBS	178
abstract_inverted_index.SCM	117
abstract_inverted_index.SKD	105
abstract_inverted_index.SPI	103
abstract_inverted_index.The	102
abstract_inverted_index.and	9, 20, 37, 77, 96, 104, 142, 176, 192
abstract_inverted_index.for	5, 54, 162
abstract_inverted_index.our	177, 182
abstract_inverted_index.the	31, 47, 59, 116, 158
abstract_inverted_index.two	73
abstract_inverted_index.Bone	134
abstract_inverted_index.FID,	191
abstract_inverted_index.RBS,	130
abstract_inverted_index.SAM,	114
abstract_inverted_index.aged	151
abstract_inverted_index.bone	1, 68, 165
abstract_inverted_index.both	124, 171
abstract_inverted_index.cues	110
abstract_inverted_index.fine	34
abstract_inverted_index.from	111, 147
abstract_inverted_index.scan	18
abstract_inverted_index.that	181
abstract_inverted_index.this	43
abstract_inverted_index.(SAM)	63
abstract_inverted_index.(SKD)	94
abstract_inverted_index.(SPI)	88
abstract_inverted_index.LPIPS	193
abstract_inverted_index.Model	62
abstract_inverted_index.PSNR,	189
abstract_inverted_index.Prior	86
abstract_inverted_index.Rapid	0, 133
abstract_inverted_index.SSIM,	190
abstract_inverted_index.first	48, 159
abstract_inverted_index.image	28, 56
abstract_inverted_index.novel	132
abstract_inverted_index.often	26
abstract_inverted_index.rapid	67, 143, 164
abstract_inverted_index.scans	146
abstract_inverted_index.three	81
abstract_inverted_index.tumor	11
abstract_inverted_index.while	115
abstract_inverted_index.(SCM).	101
abstract_inverted_index.Module	100
abstract_inverted_index.across	123
abstract_inverted_index.inject	107
abstract_inverted_index.making	156
abstract_inverted_index.method	183
abstract_inverted_index.paired	138
abstract_inverted_index.priors	53
abstract_inverted_index.public	173
abstract_inverted_index.years,	155
abstract_inverted_index.Segment	60
abstract_inverted_index.cm/min)	141, 145
abstract_inverted_index.crucial	4
abstract_inverted_index.dataset	136, 160, 175, 179
abstract_inverted_index.details	36
abstract_inverted_index.employs	72
abstract_inverted_index.enhance	65
abstract_inverted_index.feature	121
abstract_inverted_index.medical	55
abstract_inverted_index.module,	89, 95
abstract_inverted_index.modules	106
abstract_inverted_index.present	129
abstract_inverted_index.reduces	21
abstract_inverted_index.stages.	126
abstract_inverted_index.Anything	61
abstract_inverted_index.However,	23
abstract_inverted_index.Semantic	85, 91, 98
abstract_inverted_index.approach	71
abstract_inverted_index.cascaded	74, 125
abstract_inverted_index.coherent	119
abstract_inverted_index.degrades	27
abstract_inverted_index.duration	19
abstract_inverted_index.existing	186
abstract_inverted_index.metrics.	194
abstract_inverted_index.modules:	83
abstract_inverted_index.overcome	42
abstract_inverted_index.patients	150
abstract_inverted_index.quality,	29
abstract_inverted_index.semantic	52, 109, 120
abstract_inverted_index.shortens	17
abstract_inverted_index.skeletal	7
abstract_inverted_index.standard	139
abstract_inverted_index.tailored	161
abstract_inverted_index.$f^{IR1}$	76
abstract_inverted_index.Extensive	168
abstract_inverted_index.Knowledge	92
abstract_inverted_index.Moreover,	127
abstract_inverted_index.SAM-based	51
abstract_inverted_index.children,	14
abstract_inverted_index.detecting	10
abstract_inverted_index.disorders	8
abstract_inverted_index.impairing	30
abstract_inverted_index.introduce	46
abstract_inverted_index.networks,	75
abstract_inverted_index.pediatric	66, 149, 163
abstract_inverted_index.preserves	118
abstract_inverted_index.supported	79
abstract_inverted_index.surpasses	185
abstract_inverted_index.utilizing	58
abstract_inverted_index.$f^{IR2}$,	78
abstract_inverted_index.anatomical	35
abstract_inverted_index.comprising	137
abstract_inverted_index.diagnosing	6
abstract_inverted_index.diagnosis.	40
abstract_inverted_index.endoscopic	174
abstract_inverted_index.fine-tuned	113
abstract_inverted_index.metastases	12
abstract_inverted_index.techniques	187
abstract_inverted_index.visibility	32
abstract_inverted_index.Consistency	99
abstract_inverted_index.Integration	87
abstract_inverted_index.accelerated	24
abstract_inverted_index.acquisition	25
abstract_inverted_index.application	49
abstract_inverted_index.demonstrate	180
abstract_inverted_index.discomfort.	22
abstract_inverted_index.experiments	169
abstract_inverted_index.limitation,	44
abstract_inverted_index.potentially	38
abstract_inverted_index.specialized	82
abstract_inverted_index.Distillation	93
abstract_inverted_index.Scintigraphy	135
abstract_inverted_index.compromising	39
abstract_inverted_index.consistently	184
abstract_inverted_index.restoration,	57
abstract_inverted_index.restoration.	167
abstract_inverted_index.scintigraphy	2, 166
abstract_inverted_index.scintigraphy.	69
abstract_inverted_index.domain-specific	108
abstract_inverted_index.representations	122
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	12
citation_normalized_percentile