Assessing the impact of ultrasound image standardization in deep learning-based segmentation of carotid plaque types

IF 4.9 2区 医学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS Computer methods and programs in biomedicine Pub Date : 2024-10-10 DOI:10.1016/j.cmpb.2024.108460
Georgia D. Liapi , Christos P. Loizou , Constantinos S. Pattichis , Marios S. Pattichis , Andrew N. Nicolaides , Maura Griffin , Efthyvoulos Kyriacou
{"title":"Assessing the impact of ultrasound image standardization in deep learning-based segmentation of carotid plaque types","authors":"Georgia D. Liapi ,&nbsp;Christos P. Loizou ,&nbsp;Constantinos S. Pattichis ,&nbsp;Marios S. Pattichis ,&nbsp;Andrew N. Nicolaides ,&nbsp;Maura Griffin ,&nbsp;Efthyvoulos Kyriacou","doi":"10.1016/j.cmpb.2024.108460","DOIUrl":null,"url":null,"abstract":"<div><h3>Background and objective</h3><div>Carotid B-mode ultrasound (CBUS) imaging is often used to detect and assess atherosclerotic plaques. Doctors often need to segment plaques in the CBUS images to further examine them. Multiple studies have proposed two-dimensional CBUS plaque segmentation deep learning (DL)-based solutions, achieving promising results. In most of these studies, image standardization is not reported, while not all plaque types are represented. However, prior multiple studies have highlighted the importance of data standardization in computerized CBUS plaque classification or segmentation solutions. In this study, we propose and separately evaluate three progressive preprocessing schemes, to discover the most optimal to standardize CBUS images for DL-based carotid plaque segmentation, while we also assess the effect of each preprocessing in the segmentation performance per echodensity-based plaque type (I, II, III, IV and V).</div></div><div><h3>Methods</h3><div>We included three CBUS image datasets (276 CBUS images, from three medical centres), with which we produced 3 data folds (with the best possible equal inclusion of images from all centers per fold), to perform 3-fold cross validation-based training and evaluation of the pre-released Channel-wise Feature Pyramid Network for Medicine (CFPNet-M) model, in carotid plaque type segmentation. We included the three data folds in their original version (O), generating also three preprocessed versions of them, namely, the resolution-normalized (R), the resolution- and intensity-normalized (RN), and the resolution- and intensity-normalized combined with despeckling (RND) versions. The samples were cropped to the plaque level, and the intersection over union (IoU) and the Dice Similarity Coefficient (DSC), along with other metrics, were used to measure the model's performance. In each training round, 12 % of the images in the 2 training folds was used for internal validation (last fold was used in evaluation). Two experienced ultrasonographers manually delineated plaques in the dataset, to provide us with ground truths, while the plaque types (I to V) were extracted according to the Gray-Weale and Geroulakos classification system. We measured the mean±standard deviation of DSC within and across the three evaluated folds, per preprocessing scheme and per plaque type.</div></div><div><h3>Results</h3><div>CFPNet-M segmented the plaques in the CBUS images in all the data preprocessing versions, yielding progressively improved performances (mean DSC at 81.9 ± 9.1 %, 83.6 ± 9.0 %, 84.1 ± 8.3 %, and 84.4 ± 8.1 % for the O, R, RN and RND 3-fold cross validation processes, respectively), irrespective of the plaque type. Interestingly, CFPNet_M yielded improved performances, for all plaque types (I, II, III, IV and V), when trained and tested with the RND data versus the O version, achieving an 80.6 ± 11 % versus 77.6 ± 17 % DSC for type I, an 84.3 ± 8 % versus 81.2 ± 9 % DSC for type II, an 84.9 ± 7 % versus 82.6 ± 7 % for type III, an 85.3 ± 8 % versus 83.9 ± 7 % for type IV, and a 84.8 ± 8 % versus 81.8 ± 2 % for type V. The best increase in DSC, from the O to the RND CBUS images, was found for the plaque type I (3.86 % increase), with types II and V, following.</div></div><div><h3>Conclusions</h3><div>In this study, we investigated the impact of CBUS standardization in DL-based carotid plaque type segmentation and showed that indeed normalization of the image resolution and intensity, combined with speckle noise removal, prior to model training and testing, enhances the DL model's performance, across all plaque types. Based on the findings in this study, CBUS images should be standardized when destined for DL-based segmentation tasks, while all plaque types should be considered, as in a plethora of existing relevant studies, uniformly echolucent plaques or heavily calcified plaques with acoustic shadow are notably underrepresented.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"257 ","pages":"Article 108460"},"PeriodicalIF":4.9000,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer methods and programs in biomedicine","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S016926072400453X","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0

Abstract

Background and objective

Carotid B-mode ultrasound (CBUS) imaging is often used to detect and assess atherosclerotic plaques. Doctors often need to segment plaques in the CBUS images to further examine them. Multiple studies have proposed two-dimensional CBUS plaque segmentation deep learning (DL)-based solutions, achieving promising results. In most of these studies, image standardization is not reported, while not all plaque types are represented. However, prior multiple studies have highlighted the importance of data standardization in computerized CBUS plaque classification or segmentation solutions. In this study, we propose and separately evaluate three progressive preprocessing schemes, to discover the most optimal to standardize CBUS images for DL-based carotid plaque segmentation, while we also assess the effect of each preprocessing in the segmentation performance per echodensity-based plaque type (I, II, III, IV and V).

Methods

We included three CBUS image datasets (276 CBUS images, from three medical centres), with which we produced 3 data folds (with the best possible equal inclusion of images from all centers per fold), to perform 3-fold cross validation-based training and evaluation of the pre-released Channel-wise Feature Pyramid Network for Medicine (CFPNet-M) model, in carotid plaque type segmentation. We included the three data folds in their original version (O), generating also three preprocessed versions of them, namely, the resolution-normalized (R), the resolution- and intensity-normalized (RN), and the resolution- and intensity-normalized combined with despeckling (RND) versions. The samples were cropped to the plaque level, and the intersection over union (IoU) and the Dice Similarity Coefficient (DSC), along with other metrics, were used to measure the model's performance. In each training round, 12 % of the images in the 2 training folds was used for internal validation (last fold was used in evaluation). Two experienced ultrasonographers manually delineated plaques in the dataset, to provide us with ground truths, while the plaque types (I to V) were extracted according to the Gray-Weale and Geroulakos classification system. We measured the mean±standard deviation of DSC within and across the three evaluated folds, per preprocessing scheme and per plaque type.

Results

CFPNet-M segmented the plaques in the CBUS images in all the data preprocessing versions, yielding progressively improved performances (mean DSC at 81.9 ± 9.1 %, 83.6 ± 9.0 %, 84.1 ± 8.3 %, and 84.4 ± 8.1 % for the O, R, RN and RND 3-fold cross validation processes, respectively), irrespective of the plaque type. Interestingly, CFPNet_M yielded improved performances, for all plaque types (I, II, III, IV and V), when trained and tested with the RND data versus the O version, achieving an 80.6 ± 11 % versus 77.6 ± 17 % DSC for type I, an 84.3 ± 8 % versus 81.2 ± 9 % DSC for type II, an 84.9 ± 7 % versus 82.6 ± 7 % for type III, an 85.3 ± 8 % versus 83.9 ± 7 % for type IV, and a 84.8 ± 8 % versus 81.8 ± 2 % for type V. The best increase in DSC, from the O to the RND CBUS images, was found for the plaque type I (3.86 % increase), with types II and V, following.

Conclusions

In this study, we investigated the impact of CBUS standardization in DL-based carotid plaque type segmentation and showed that indeed normalization of the image resolution and intensity, combined with speckle noise removal, prior to model training and testing, enhances the DL model's performance, across all plaque types. Based on the findings in this study, CBUS images should be standardized when destined for DL-based segmentation tasks, while all plaque types should be considered, as in a plethora of existing relevant studies, uniformly echolucent plaques or heavily calcified plaques with acoustic shadow are notably underrepresented.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
评估超声图像标准化对基于深度学习的颈动脉斑块类型分割的影响。
背景和目的:颈动脉 B 型超声(CBUS)成像通常用于检测和评估动脉粥样硬化斑块。医生通常需要对 CBUS 图像中的斑块进行分割,以便进一步检查。多项研究提出了基于深度学习(DL)的二维 CBUS 斑块分割解决方案,并取得了可喜的成果。在大多数这些研究中,都没有报告图像标准化的情况,也没有代表所有斑块类型。然而,之前的多项研究都强调了数据标准化在计算机化 CBUS 斑块分类或分割解决方案中的重要性。在本研究中,我们提出并分别评估了三种渐进式预处理方案,以发现最佳的CBUS图像标准化方案,用于基于DL的颈动脉斑块分割,同时我们还评估了每种预处理对基于回声密度的斑块类型(I、II、III、IV和V)分割性能的影响:我们纳入了三个 CBUS 图像数据集(来自三个医疗中心的 276 幅 CBUS 图像),并利用这些数据集生成了 3 个数据折叠(每个折叠尽可能平等地包含来自所有中心的图像),以便在颈动脉斑块类型分割中对预先发布的医学通道特征金字塔网络(CFPNet-M)模型进行基于 3 倍交叉验证的训练和评估。我们在原始版本(O)中包含了三个数据折叠,并生成了三个预处理版本,即分辨率归一化版本(R)、分辨率和强度归一化版本(RN)以及分辨率和强度归一化结合去斑版本(RND)。样本被裁剪到斑块水平,并使用交集大于联合(IoU)和骰子相似系数(DSC)以及其他指标来衡量模型的性能。在每一轮训练中,2 个训练折叠中的 12% 图像用于内部验证(最后一个折叠用于评估)。两名经验丰富的超声波技师手动划分数据集中的斑块,为我们提供基本事实,而斑块类型(I 至 V)则根据 Gray-Weale 和 Geroulakos 分类系统提取。我们测量了每个预处理方案和每种斑块类型在三个评估折叠内和折叠间的 DSC 平均值(± 标准偏差):无论斑块类型如何,CFPNet-M 在所有数据预处理版本中都对 CBUS 图像中的斑块进行了分割,性能逐步提高(O、R、RN 和 RND 3 倍交叉验证过程的平均 DSC 分别为 81.9 ± 9.1 %、83.6 ± 9.0 %、84.1 ± 8.3 % 和 84.4 ± 8.1 %)。有趣的是,对于所有斑块类型(I、II、III、IV 和 V),使用 RND 数据进行训练和测试时,CFPNet_M 的性能都比 O 版本有所提高,I 型的 DSC 为 80.6 ± 11 % 对 77.6 ± 17 %,II 型的 DSC 为 84.3 ± 8 % 对 81.2 ± 9 %,III 型的 DSC 为 84.9 ± 7 % 对 82.6 ± 7 %,IV 型的 DSC 为 84.3 ± 8 % 对 81.2 ± 9 %。从 O 型到 RND CBUS 图像,斑块 I 型的 DSC 增幅最大(3.86%),其次是 II 型和 V 型:在这项研究中,我们研究了 CBUS 标准化对基于 DL 的颈动脉斑块类型分割的影响,结果表明,在模型训练和测试之前,图像分辨率和强度的归一化,以及斑点噪声的去除,确实提高了 DL 模型在所有斑块类型中的性能。根据这项研究的结果,CBUS 图像在用于基于 DL 的分割任务时应标准化,同时应考虑所有斑块类型,因为在现有的大量相关研究中,均匀回声斑块或带有声影的严重钙化斑块的代表性明显不足。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Computer methods and programs in biomedicine
Computer methods and programs in biomedicine 工程技术-工程:生物医学
CiteScore
12.30
自引率
6.60%
发文量
601
审稿时长
135 days
期刊介绍: To encourage the development of formal computing methods, and their application in biomedical research and medical practice, by illustration of fundamental principles in biomedical informatics research; to stimulate basic research into application software design; to report the state of research of biomedical information processing projects; to report new computer methodologies applied in biomedical areas; the eventual distribution of demonstrable software to avoid duplication of effort; to provide a forum for discussion and improvement of existing software; to optimize contact between national organizations and regional user groups by promoting an international exchange of information on formal methods, standards and software in biomedicine. Computer Methods and Programs in Biomedicine covers computing methodology and software systems derived from computing science for implementation in all aspects of biomedical research and medical practice. It is designed to serve: biochemists; biologists; geneticists; immunologists; neuroscientists; pharmacologists; toxicologists; clinicians; epidemiologists; psychiatrists; psychologists; cardiologists; chemists; (radio)physicists; computer scientists; programmers and systems analysts; biomedical, clinical, electrical and other engineers; teachers of medical informatics and users of educational software.
期刊最新文献
Computational hemodynamic indices to identify Transcatheter Aortic Valve Implantation degeneration One-class classification with confound control for cognitive screening in older adults using gait, fingertapping, cognitive, and dual tasks A porohyperelastic scheme targeted at High-Performance Computing frameworks for the simulation of the intervertebral disc CIMIL-CRC: A clinically-informed multiple instance learning framework for patient-level colorectal cancer molecular subtypes classification from H&E stained images Dynamic evolution analysis and parameter optimization design of data-driven network infectious disease model
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1