Multi-Scale Transformer Architecture for Accurate Medical Image Classification Article Swipe

PDF

Jiacheng Hu , Yun Xiang , Lin Yang , Junliang Du , Hanchao Zhang , Houze Liu ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2502.06243

This study introduces an AI-driven skin lesion classification algorithm built on an enhanced Transformer architecture, addressing the challenges of accuracy and robustness in medical image analysis. By integrating a multi-scale feature fusion mechanism and refining the self-attention process, the model effectively extracts both global and local features, enhancing its ability to detect lesions with ambiguous boundaries and intricate structures. Performance evaluation on the ISIC 2017 dataset demonstrates that the improved Transformer surpasses established AI models, including ResNet50, VGG19, ResNext, and Vision Transformer, across key metrics such as accuracy, AUC, F1-Score, and Precision. Grad-CAM visualizations further highlight the interpretability of the model, showcasing strong alignment between the algorithm's focus areas and actual lesion sites. This research underscores the transformative potential of advanced AI models in medical imaging, paving the way for more accurate and reliable diagnostic tools. Future work will explore the scalability of this approach to broader medical imaging tasks and investigate the integration of multimodal data to enhance AI-driven diagnostic frameworks for intelligent healthcare.

Related Topics

Architecture

Transformer

Computer Science

Artificial Intelligence

Electrical Engineering

Archaeology

Voltage

Concepts

Architecture Transformer Computer science Scale (ratio) Artificial intelligence Computer vision Pattern recognition (psychology) Cartography Geography Engineering Electrical engineering Archaeology Voltage

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2502.06243
PDF: https://arxiv.org/pdf/2502.06243
OA Status: green
Related Works: 10
OpenAlex ID: https://openalex.org/W4407358677

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4407358677

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2502.06243

Digital Object Identifier
Title: Multi-Scale Transformer Architecture for Accurate Medical Image Classification

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-02-10

Full publication date if available
Authors: Jiacheng Hu, Yun Xiang, Lin Yang, Junliang Du, Hanchao Zhang, Houze Liu

List of authors in order
Landing page: https://arxiv.org/abs/2502.06243

Publisher landing page
PDF URL: https://arxiv.org/pdf/2502.06243

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/2502.06243

Direct OA link when available
Concepts: Architecture, Transformer, Computer science, Scale (ratio), Artificial intelligence, Computer vision, Pattern recognition (psychology), Cartography, Geography, Engineering, Electrical engineering, Archaeology, Voltage

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/W4407358677
doi	https://doi.org/10.48550/arxiv.2502.06243
ids.doi	https://doi.org/10.48550/arxiv.2502.06243
ids.openalex	https://openalex.org/W4407358677
fwci
type	preprint
title	Multi-Scale Transformer Architecture for Accurate Medical Image Classification
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T12702
topics[0].field.id	https://openalex.org/fields/28
topics[0].field.display_name	Neuroscience
topics[0].score	0.9146999716758728
topics[0].domain.id	https://openalex.org/domains/1
topics[0].domain.display_name	Life Sciences
topics[0].subfield.id	https://openalex.org/subfields/2808
topics[0].subfield.display_name	Neurology
topics[0].display_name	Brain Tumor Detection and Classification
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C123657996
concepts[0].level	2
concepts[0].score	0.6988918781280518
concepts[0].wikidata	https://www.wikidata.org/wiki/Q12271
concepts[0].display_name	Architecture
concepts[1].id	https://openalex.org/C66322947
concepts[1].level	3
concepts[1].score	0.5696316957473755
concepts[1].wikidata	https://www.wikidata.org/wiki/Q11658
concepts[1].display_name	Transformer
concepts[2].id	https://openalex.org/C41008148
concepts[2].level	0
concepts[2].score	0.5254860520362854
concepts[2].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[2].display_name	Computer science
concepts[3].id	https://openalex.org/C2778755073
concepts[3].level	2
concepts[3].score	0.4819459915161133
concepts[3].wikidata	https://www.wikidata.org/wiki/Q10858537
concepts[3].display_name	Scale (ratio)
concepts[4].id	https://openalex.org/C154945302
concepts[4].level	1
concepts[4].score	0.4696587324142456
concepts[4].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[4].display_name	Artificial intelligence
concepts[5].id	https://openalex.org/C31972630
concepts[5].level	1
concepts[5].score	0.3419865369796753
concepts[5].wikidata	https://www.wikidata.org/wiki/Q844240
concepts[5].display_name	Computer vision
concepts[6].id	https://openalex.org/C153180895
concepts[6].level	2
concepts[6].score	0.3364945650100708
concepts[6].wikidata	https://www.wikidata.org/wiki/Q7148389
concepts[6].display_name	Pattern recognition (psychology)
concepts[7].id	https://openalex.org/C58640448
concepts[7].level	1
concepts[7].score	0.23918548226356506
concepts[7].wikidata	https://www.wikidata.org/wiki/Q42515
concepts[7].display_name	Cartography
concepts[8].id	https://openalex.org/C205649164
concepts[8].level	0
concepts[8].score	0.2383863925933838
concepts[8].wikidata	https://www.wikidata.org/wiki/Q1071
concepts[8].display_name	Geography
concepts[9].id	https://openalex.org/C127413603
concepts[9].level	0
concepts[9].score	0.20443293452262878
concepts[9].wikidata	https://www.wikidata.org/wiki/Q11023
concepts[9].display_name	Engineering
concepts[10].id	https://openalex.org/C119599485
concepts[10].level	1
concepts[10].score	0.1359201967716217
concepts[10].wikidata	https://www.wikidata.org/wiki/Q43035
concepts[10].display_name	Electrical engineering
concepts[11].id	https://openalex.org/C166957645
concepts[11].level	1
concepts[11].score	0.05908012390136719
concepts[11].wikidata	https://www.wikidata.org/wiki/Q23498
concepts[11].display_name	Archaeology
concepts[12].id	https://openalex.org/C165801399
concepts[12].level	2
concepts[12].score	0.0
concepts[12].wikidata	https://www.wikidata.org/wiki/Q25428
concepts[12].display_name	Voltage
keywords[0].id	https://openalex.org/keywords/architecture
keywords[0].score	0.6988918781280518
keywords[0].display_name	Architecture
keywords[1].id	https://openalex.org/keywords/transformer
keywords[1].score	0.5696316957473755
keywords[1].display_name	Transformer
keywords[2].id	https://openalex.org/keywords/computer-science
keywords[2].score	0.5254860520362854
keywords[2].display_name	Computer science
keywords[3].id	https://openalex.org/keywords/scale
keywords[3].score	0.4819459915161133
keywords[3].display_name	Scale (ratio)
keywords[4].id	https://openalex.org/keywords/artificial-intelligence
keywords[4].score	0.4696587324142456
keywords[4].display_name	Artificial intelligence
keywords[5].id	https://openalex.org/keywords/computer-vision
keywords[5].score	0.3419865369796753
keywords[5].display_name	Computer vision
keywords[6].id	https://openalex.org/keywords/pattern-recognition
keywords[6].score	0.3364945650100708
keywords[6].display_name	Pattern recognition (psychology)
keywords[7].id	https://openalex.org/keywords/cartography
keywords[7].score	0.23918548226356506
keywords[7].display_name	Cartography
keywords[8].id	https://openalex.org/keywords/geography
keywords[8].score	0.2383863925933838
keywords[8].display_name	Geography
keywords[9].id	https://openalex.org/keywords/engineering
keywords[9].score	0.20443293452262878
keywords[9].display_name	Engineering
keywords[10].id	https://openalex.org/keywords/electrical-engineering
keywords[10].score	0.1359201967716217
keywords[10].display_name	Electrical engineering
keywords[11].id	https://openalex.org/keywords/archaeology
keywords[11].score	0.05908012390136719
keywords[11].display_name	Archaeology
language	en
locations[0].id	pmh:oai:arXiv.org:2502.06243
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/2502.06243
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/2502.06243
locations[1].id	doi:10.48550/arxiv.2502.06243
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.2502.06243
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5107194762
authorships[0].author.orcid	https://orcid.org/0009-0003-6588-2868
authorships[0].author.display_name	Jiacheng Hu
authorships[0].author_position	first
authorships[0].raw_author_name	Hu, Jiacheng
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5007650182
authorships[1].author.orcid	https://orcid.org/0000-0003-2982-425X
authorships[1].author.display_name	Yun Xiang
authorships[1].author_position	middle
authorships[1].raw_author_name	Xiang, Yanlin
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5101659750
authorships[2].author.orcid	https://orcid.org/0000-0002-9698-8222
authorships[2].author.display_name	Lin Yang
authorships[2].author_position	middle
authorships[2].raw_author_name	Lin, Yang
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5010332378
authorships[3].author.orcid	https://orcid.org/0000-0002-2794-2327
authorships[3].author.display_name	Junliang Du
authorships[3].author_position	middle
authorships[3].raw_author_name	Du, Junliang
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5101843084
authorships[4].author.orcid	https://orcid.org/0000-0001-9610-408X
authorships[4].author.display_name	Hanchao Zhang
authorships[4].author_position	middle
authorships[4].raw_author_name	Zhang, Hanchao
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5104250303
authorships[5].author.orcid
authorships[5].author.display_name	Houze Liu
authorships[5].author_position	last
authorships[5].raw_author_name	Liu, Houze
authorships[5].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/2502.06243
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Multi-Scale Transformer Architecture for Accurate Medical Image Classification
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T12702
primary_topic.field.id	https://openalex.org/fields/28
primary_topic.field.display_name	Neuroscience
primary_topic.score	0.9146999716758728
primary_topic.domain.id	https://openalex.org/domains/1
primary_topic.domain.display_name	Life Sciences
primary_topic.subfield.id	https://openalex.org/subfields/2808
primary_topic.subfield.display_name	Neurology
primary_topic.display_name	Brain Tumor Detection and Classification
related_works	https://openalex.org/W2588198209, https://openalex.org/W1909006023, https://openalex.org/W4205824991, https://openalex.org/W3200723557, https://openalex.org/W4312713546, https://openalex.org/W2362195430, https://openalex.org/W2347494122, https://openalex.org/W2567983276, https://openalex.org/W2802298219, https://openalex.org/W2393996461
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2502.06243
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/2502.06243
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/2502.06243
primary_location.id	pmh:oai:arXiv.org:2502.06243
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/2502.06243
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/2502.06243
publication_date	2025-02-10
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	28
abstract_inverted_index.AI	73, 121
abstract_inverted_index.By	26
abstract_inverted_index.an	3, 11
abstract_inverted_index.as	86
abstract_inverted_index.in	22, 123
abstract_inverted_index.of	18, 98, 119, 142, 154
abstract_inverted_index.on	10, 61
abstract_inverted_index.to	50, 145, 157
abstract_inverted_index.and	20, 33, 44, 56, 79, 90, 109, 132, 150
abstract_inverted_index.for	129, 162
abstract_inverted_index.its	48
abstract_inverted_index.key	83
abstract_inverted_index.the	16, 35, 38, 62, 68, 96, 99, 105, 116, 127, 140, 152
abstract_inverted_index.way	128
abstract_inverted_index.2017	64
abstract_inverted_index.AUC,	88
abstract_inverted_index.ISIC	63
abstract_inverted_index.This	0, 113
abstract_inverted_index.both	42
abstract_inverted_index.data	156
abstract_inverted_index.more	130
abstract_inverted_index.skin	5
abstract_inverted_index.such	85
abstract_inverted_index.that	67
abstract_inverted_index.this	143
abstract_inverted_index.will	138
abstract_inverted_index.with	53
abstract_inverted_index.work	137
abstract_inverted_index.areas	108
abstract_inverted_index.built	9
abstract_inverted_index.focus	107
abstract_inverted_index.image	24
abstract_inverted_index.local	45
abstract_inverted_index.model	39
abstract_inverted_index.study	1
abstract_inverted_index.tasks	149
abstract_inverted_index.Future	136
abstract_inverted_index.VGG19,	77
abstract_inverted_index.Vision	80
abstract_inverted_index.across	82
abstract_inverted_index.actual	110
abstract_inverted_index.detect	51
abstract_inverted_index.fusion	31
abstract_inverted_index.global	43
abstract_inverted_index.lesion	6, 111
abstract_inverted_index.model,	100
abstract_inverted_index.models	122
abstract_inverted_index.paving	126
abstract_inverted_index.sites.	112
abstract_inverted_index.strong	102
abstract_inverted_index.tools.	135
abstract_inverted_index.ability	49
abstract_inverted_index.between	104
abstract_inverted_index.broader	146
abstract_inverted_index.dataset	65
abstract_inverted_index.enhance	158
abstract_inverted_index.explore	139
abstract_inverted_index.feature	30
abstract_inverted_index.further	94
abstract_inverted_index.imaging	148
abstract_inverted_index.lesions	52
abstract_inverted_index.medical	23, 124, 147
abstract_inverted_index.metrics	84
abstract_inverted_index.models,	74
abstract_inverted_index.Grad-CAM	92
abstract_inverted_index.ResNext,	78
abstract_inverted_index.accuracy	19
abstract_inverted_index.accurate	131
abstract_inverted_index.advanced	120
abstract_inverted_index.approach	144
abstract_inverted_index.enhanced	12
abstract_inverted_index.extracts	41
abstract_inverted_index.imaging,	125
abstract_inverted_index.improved	69
abstract_inverted_index.process,	37
abstract_inverted_index.refining	34
abstract_inverted_index.reliable	133
abstract_inverted_index.research	114
abstract_inverted_index.AI-driven	4, 159
abstract_inverted_index.F1-Score,	89
abstract_inverted_index.ResNet50,	76
abstract_inverted_index.accuracy,	87
abstract_inverted_index.algorithm	8
abstract_inverted_index.alignment	103
abstract_inverted_index.ambiguous	54
abstract_inverted_index.analysis.	25
abstract_inverted_index.enhancing	47
abstract_inverted_index.features,	46
abstract_inverted_index.highlight	95
abstract_inverted_index.including	75
abstract_inverted_index.intricate	57
abstract_inverted_index.mechanism	32
abstract_inverted_index.potential	118
abstract_inverted_index.surpasses	71
abstract_inverted_index.Precision.	91
abstract_inverted_index.addressing	15
abstract_inverted_index.boundaries	55
abstract_inverted_index.challenges	17
abstract_inverted_index.diagnostic	134, 160
abstract_inverted_index.evaluation	60
abstract_inverted_index.frameworks	161
abstract_inverted_index.introduces	2
abstract_inverted_index.multimodal	155
abstract_inverted_index.robustness	21
abstract_inverted_index.showcasing	101
abstract_inverted_index.Performance	59
abstract_inverted_index.Transformer	13, 70
abstract_inverted_index.algorithm's	106
abstract_inverted_index.effectively	40
abstract_inverted_index.established	72
abstract_inverted_index.healthcare.	164
abstract_inverted_index.integrating	27
abstract_inverted_index.integration	153
abstract_inverted_index.intelligent	163
abstract_inverted_index.investigate	151
abstract_inverted_index.multi-scale	29
abstract_inverted_index.scalability	141
abstract_inverted_index.structures.	58
abstract_inverted_index.underscores	115
abstract_inverted_index.Transformer,	81
abstract_inverted_index.demonstrates	66
abstract_inverted_index.architecture,	14
abstract_inverted_index.classification	7
abstract_inverted_index.self-attention	36
abstract_inverted_index.transformative	117
abstract_inverted_index.visualizations	93
abstract_inverted_index.interpretability	97
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	6
citation_normalized_percentile