Transformer and Attention-Based Architectures for Segmentation of Coronary Arterial Walls in Intravascular Ultrasound: A Narrative Review

<b>Background:</b> The leading global cause of death is coronary artery disease (CAD), necessitating early and precise diagnosis. Intravascular ultrasound (IVUS) is a sophisticated imaging technique that provides detailed visualization of coronary arteries. However, the methods for segme...

Full description

Saved in:
Bibliographic Details
Main Authors: Vandana Kumari, Alok Katiyar, Mrinalini Bhagawati, Mahesh Maindarkar, Siddharth Gupta, Sudip Paul, Tisha Chhabra, Alberto Boi, Ekta Tiwari, Vijay Rathore, Inder M. Singh, Mustafa Al-Maini, Vinod Anand, Luca Saba, Jasjit S. Suri
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/15/7/848
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849739456103317504
author Vandana Kumari
Alok Katiyar
Mrinalini Bhagawati
Mahesh Maindarkar
Siddharth Gupta
Sudip Paul
Tisha Chhabra
Alberto Boi
Ekta Tiwari
Vijay Rathore
Inder M. Singh
Mustafa Al-Maini
Vinod Anand
Luca Saba
Jasjit S. Suri
author_facet Vandana Kumari
Alok Katiyar
Mrinalini Bhagawati
Mahesh Maindarkar
Siddharth Gupta
Sudip Paul
Tisha Chhabra
Alberto Boi
Ekta Tiwari
Vijay Rathore
Inder M. Singh
Mustafa Al-Maini
Vinod Anand
Luca Saba
Jasjit S. Suri
author_sort Vandana Kumari
collection DOAJ
description <b>Background:</b> The leading global cause of death is coronary artery disease (CAD), necessitating early and precise diagnosis. Intravascular ultrasound (IVUS) is a sophisticated imaging technique that provides detailed visualization of coronary arteries. However, the methods for segmenting walls in the IVUS scan into internal wall structures and quantifying plaque are still evolving. This study explores the use of transformers and attention-based models to improve diagnostic accuracy for wall segmentation in IVUS scans. Thus, the objective is to explore the application of transformer models for wall segmentation in IVUS scans to assess their inherent biases in artificial intelligence systems for improving diagnostic accuracy. <b>Methods:</b> By employing the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework, we pinpointed and examined the top strategies for coronary wall segmentation using transformer-based techniques, assessing their traits, scientific soundness, and clinical relevancy. Coronary artery wall thickness is determined by using the boundaries (inner: lumen-intima and outer: media-adventitia) through cross-sectional IVUS scans. Additionally, it is the first to investigate biases in deep learning (DL) systems that are associated with IVUS scan wall segmentation. Finally, the study incorporates explainable AI (XAI) concepts into the DL structure for IVUS scan wall segmentation. <b>Findings:</b> Because of its capacity to automatically extract features at numerous scales in encoders, rebuild segmented pictures via decoders, and fuse variations through skip connections, the UNet and transformer-based model stands out as an efficient technique for segmenting coronary walls in IVUS scans. <b>Conclusions:</b> The investigation underscores a deficiency in incentives for embracing XAI and pruned AI (PAI) models, with no UNet systems attaining a bias-free configuration. Shifting from theoretical study to practical usage is crucial to bolstering clinical evaluation and deployment.
format Article
id doaj-art-261c4994c8a44fefbfce942fe1b8719c
institution DOAJ
issn 2075-4418
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-261c4994c8a44fefbfce942fe1b8719c2025-08-20T03:06:16ZengMDPI AGDiagnostics2075-44182025-03-0115784810.3390/diagnostics15070848Transformer and Attention-Based Architectures for Segmentation of Coronary Arterial Walls in Intravascular Ultrasound: A Narrative ReviewVandana Kumari0Alok Katiyar1Mrinalini Bhagawati2Mahesh Maindarkar3Siddharth Gupta4Sudip Paul5Tisha Chhabra6Alberto Boi7Ekta Tiwari8Vijay Rathore9Inder M. Singh10Mustafa Al-Maini11Vinod Anand12Luca Saba13Jasjit S. Suri14School of Computer Science and Engineering, Galgotias University, Greater Noida 201310, IndiaSchool of Computer Science and Engineering, Galgotias University, Greater Noida 201310, IndiaDepartment of Biomedical Engineering, North Eastern Hill University, Shillong 793022, IndiaSchool of Bioengineering Research and Sciences, MIT Art, Design and Technology University, Pune 412021, IndiaDepartment of Computer Science and Engineering, Bharati Vidyapeeth’s College of Engineering, New Delhi 110063, IndiaDepartment of Biomedical Engineering, North Eastern Hill University, Shillong 793022, IndiaDepartment of Information Technology, Bharati Vidyapeeth’s College of Engineering, New Delhi 110063, IndiaDepartment of Cardiology, University of Cagliari, 09124 Cagliari, ItalyDepartment of Computer Science, Visvesvaraya National Institute of Technology (VNIT), Nagpur 440010, IndiaStroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA 95661, USAStroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA 95661, USAAllergy, Clinical Immunology and Rheumatology Institute, Toronto, ON M5G 1N8, CanadaStroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA 95661, USADepartment of Cardiology, University of Cagliari, 09124 Cagliari, ItalyStroke Monitoring and Diagnostic Division, AtheroPoint™, Roseville, CA 95661, USA<b>Background:</b> The leading global cause of death is coronary artery disease (CAD), necessitating early and precise diagnosis. Intravascular ultrasound (IVUS) is a sophisticated imaging technique that provides detailed visualization of coronary arteries. However, the methods for segmenting walls in the IVUS scan into internal wall structures and quantifying plaque are still evolving. This study explores the use of transformers and attention-based models to improve diagnostic accuracy for wall segmentation in IVUS scans. Thus, the objective is to explore the application of transformer models for wall segmentation in IVUS scans to assess their inherent biases in artificial intelligence systems for improving diagnostic accuracy. <b>Methods:</b> By employing the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework, we pinpointed and examined the top strategies for coronary wall segmentation using transformer-based techniques, assessing their traits, scientific soundness, and clinical relevancy. Coronary artery wall thickness is determined by using the boundaries (inner: lumen-intima and outer: media-adventitia) through cross-sectional IVUS scans. Additionally, it is the first to investigate biases in deep learning (DL) systems that are associated with IVUS scan wall segmentation. Finally, the study incorporates explainable AI (XAI) concepts into the DL structure for IVUS scan wall segmentation. <b>Findings:</b> Because of its capacity to automatically extract features at numerous scales in encoders, rebuild segmented pictures via decoders, and fuse variations through skip connections, the UNet and transformer-based model stands out as an efficient technique for segmenting coronary walls in IVUS scans. <b>Conclusions:</b> The investigation underscores a deficiency in incentives for embracing XAI and pruned AI (PAI) models, with no UNet systems attaining a bias-free configuration. Shifting from theoretical study to practical usage is crucial to bolstering clinical evaluation and deployment.https://www.mdpi.com/2075-4418/15/7/848coronary artery diseaseIVUSwall segmentationDLUNettransformer
spellingShingle Vandana Kumari
Alok Katiyar
Mrinalini Bhagawati
Mahesh Maindarkar
Siddharth Gupta
Sudip Paul
Tisha Chhabra
Alberto Boi
Ekta Tiwari
Vijay Rathore
Inder M. Singh
Mustafa Al-Maini
Vinod Anand
Luca Saba
Jasjit S. Suri
Transformer and Attention-Based Architectures for Segmentation of Coronary Arterial Walls in Intravascular Ultrasound: A Narrative Review
Diagnostics
coronary artery disease
IVUS
wall segmentation
DL
UNet
transformer
title Transformer and Attention-Based Architectures for Segmentation of Coronary Arterial Walls in Intravascular Ultrasound: A Narrative Review
title_full Transformer and Attention-Based Architectures for Segmentation of Coronary Arterial Walls in Intravascular Ultrasound: A Narrative Review
title_fullStr Transformer and Attention-Based Architectures for Segmentation of Coronary Arterial Walls in Intravascular Ultrasound: A Narrative Review
title_full_unstemmed Transformer and Attention-Based Architectures for Segmentation of Coronary Arterial Walls in Intravascular Ultrasound: A Narrative Review
title_short Transformer and Attention-Based Architectures for Segmentation of Coronary Arterial Walls in Intravascular Ultrasound: A Narrative Review
title_sort transformer and attention based architectures for segmentation of coronary arterial walls in intravascular ultrasound a narrative review
topic coronary artery disease
IVUS
wall segmentation
DL
UNet
transformer
url https://www.mdpi.com/2075-4418/15/7/848
work_keys_str_mv AT vandanakumari transformerandattentionbasedarchitecturesforsegmentationofcoronaryarterialwallsinintravascularultrasoundanarrativereview
AT alokkatiyar transformerandattentionbasedarchitecturesforsegmentationofcoronaryarterialwallsinintravascularultrasoundanarrativereview
AT mrinalinibhagawati transformerandattentionbasedarchitecturesforsegmentationofcoronaryarterialwallsinintravascularultrasoundanarrativereview
AT maheshmaindarkar transformerandattentionbasedarchitecturesforsegmentationofcoronaryarterialwallsinintravascularultrasoundanarrativereview
AT siddharthgupta transformerandattentionbasedarchitecturesforsegmentationofcoronaryarterialwallsinintravascularultrasoundanarrativereview
AT sudippaul transformerandattentionbasedarchitecturesforsegmentationofcoronaryarterialwallsinintravascularultrasoundanarrativereview
AT tishachhabra transformerandattentionbasedarchitecturesforsegmentationofcoronaryarterialwallsinintravascularultrasoundanarrativereview
AT albertoboi transformerandattentionbasedarchitecturesforsegmentationofcoronaryarterialwallsinintravascularultrasoundanarrativereview
AT ektatiwari transformerandattentionbasedarchitecturesforsegmentationofcoronaryarterialwallsinintravascularultrasoundanarrativereview
AT vijayrathore transformerandattentionbasedarchitecturesforsegmentationofcoronaryarterialwallsinintravascularultrasoundanarrativereview
AT indermsingh transformerandattentionbasedarchitecturesforsegmentationofcoronaryarterialwallsinintravascularultrasoundanarrativereview
AT mustafaalmaini transformerandattentionbasedarchitecturesforsegmentationofcoronaryarterialwallsinintravascularultrasoundanarrativereview
AT vinodanand transformerandattentionbasedarchitecturesforsegmentationofcoronaryarterialwallsinintravascularultrasoundanarrativereview
AT lucasaba transformerandattentionbasedarchitecturesforsegmentationofcoronaryarterialwallsinintravascularultrasoundanarrativereview
AT jasjitssuri transformerandattentionbasedarchitecturesforsegmentationofcoronaryarterialwallsinintravascularultrasoundanarrativereview