腹主动脉瘤专用卷积神经网络混杂变量的机器学习分析

Q3 Medicine JVS-vascular science Pub Date : 2023-01-01 DOI:10.1016/j.jvssci.2022.11.004
Roger T. Tomihama MD , Justin R. Camara MD , Sharon C. Kiang MD
{"title":"腹主动脉瘤专用卷积神经网络混杂变量的机器学习分析","authors":"Roger T. Tomihama MD ,&nbsp;Justin R. Camara MD ,&nbsp;Sharon C. Kiang MD","doi":"10.1016/j.jvssci.2022.11.004","DOIUrl":null,"url":null,"abstract":"<div><h3>Objective</h3><p>To identify confounding variables influencing the accuracy of a convolutional neural network (CNN) specific for infrarenal abdominal aortic aneurysms (AAAs) on computed tomography angiograms (CTAs).</p></div><div><h3>Methods</h3><p>A Health Insurance Portability and Accountability Act-compliant, institutional review board-approved, retrospective study analyzed abdominopelvic CTA scans from 200 patients with infrarenal AAAs and 200 propensity-matched control patients. An AAA-specific trained CNN was developed by the application of transfer learning to the VGG-16 base model using model training, validation, and testing techniques. Model accuracy and area under the curve were analyzed based on data sets (selected, balanced, or unbalanced), aneurysm size, extra-abdominal extension, dissections, and mural thrombus. Misjudgments were analyzed by review of heatmaps, via gradient weighted class activation, overlaid on CTA images.</p></div><div><h3>Results</h3><p>The trained custom CNN model reported high test group accuracies of 94.1%, 99.1%, and 99.6% and area under the curve of 0.9900, 0.9998, and 0.9993 in selected (n = 120), balanced (n = 3704), and unbalanced image sets (n = 31,899), respectively. Despite an eightfold difference between balanced and unbalanced image sets, the CNN model demonstrated high test group sensitivities (98.7% vs 98.9%) and specificities (99.7% vs 99.3%) in unbalanced and balanced image sets, respectively. For aneurysm size, the CNN model demonstrates decreasing misjudgments as aneurysm size increases: 47% (16/34) for aneurysms &lt;3.3 cm, 32% (11/34) for aneurysms 3.3 to 5 cm, and 20% (7/34) for aneurysms &gt;5 cm. Aneurysms containing measurable mural thrombus were over-represented within type II (false-negative) misjudgments compared with type I (false-positive) misjudgments (71% vs 15%, <em>P</em> &lt; .05). Inclusion of extra-abdominal aneurysm extension (thoracic or iliac artery) or dissection flaps in these imaging sets did not decrease the model's overall accuracy, indicating that the model performance was excellent without the need to clean the data set of confounding or comorbid diagnoses.</p></div><div><h3>Conclusions</h3><p>Analysis of an AAA-specific CNN model can accurately screen and identify infrarenal AAAs on CTA despite varying pathology and quantitative data sets. The highest anatomic misjudgments were with small aneurysms (&lt;3.3 cm) or the presence of mural thrombus. Accuracy of the CNN model is maintained despite the inclusion of extra-abdominal pathology and imbalanced data sets.</p></div>","PeriodicalId":74035,"journal":{"name":"JVS-vascular science","volume":"4 ","pages":"Article 100096"},"PeriodicalIF":0.0000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/a6/a7/main.PMC10245322.pdf","citationCount":"2","resultStr":"{\"title\":\"Machine learning analysis of confounding variables of a convolutional neural network specific for abdominal aortic aneurysms\",\"authors\":\"Roger T. Tomihama MD ,&nbsp;Justin R. Camara MD ,&nbsp;Sharon C. Kiang MD\",\"doi\":\"10.1016/j.jvssci.2022.11.004\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Objective</h3><p>To identify confounding variables influencing the accuracy of a convolutional neural network (CNN) specific for infrarenal abdominal aortic aneurysms (AAAs) on computed tomography angiograms (CTAs).</p></div><div><h3>Methods</h3><p>A Health Insurance Portability and Accountability Act-compliant, institutional review board-approved, retrospective study analyzed abdominopelvic CTA scans from 200 patients with infrarenal AAAs and 200 propensity-matched control patients. An AAA-specific trained CNN was developed by the application of transfer learning to the VGG-16 base model using model training, validation, and testing techniques. Model accuracy and area under the curve were analyzed based on data sets (selected, balanced, or unbalanced), aneurysm size, extra-abdominal extension, dissections, and mural thrombus. Misjudgments were analyzed by review of heatmaps, via gradient weighted class activation, overlaid on CTA images.</p></div><div><h3>Results</h3><p>The trained custom CNN model reported high test group accuracies of 94.1%, 99.1%, and 99.6% and area under the curve of 0.9900, 0.9998, and 0.9993 in selected (n = 120), balanced (n = 3704), and unbalanced image sets (n = 31,899), respectively. Despite an eightfold difference between balanced and unbalanced image sets, the CNN model demonstrated high test group sensitivities (98.7% vs 98.9%) and specificities (99.7% vs 99.3%) in unbalanced and balanced image sets, respectively. For aneurysm size, the CNN model demonstrates decreasing misjudgments as aneurysm size increases: 47% (16/34) for aneurysms &lt;3.3 cm, 32% (11/34) for aneurysms 3.3 to 5 cm, and 20% (7/34) for aneurysms &gt;5 cm. Aneurysms containing measurable mural thrombus were over-represented within type II (false-negative) misjudgments compared with type I (false-positive) misjudgments (71% vs 15%, <em>P</em> &lt; .05). Inclusion of extra-abdominal aneurysm extension (thoracic or iliac artery) or dissection flaps in these imaging sets did not decrease the model's overall accuracy, indicating that the model performance was excellent without the need to clean the data set of confounding or comorbid diagnoses.</p></div><div><h3>Conclusions</h3><p>Analysis of an AAA-specific CNN model can accurately screen and identify infrarenal AAAs on CTA despite varying pathology and quantitative data sets. The highest anatomic misjudgments were with small aneurysms (&lt;3.3 cm) or the presence of mural thrombus. Accuracy of the CNN model is maintained despite the inclusion of extra-abdominal pathology and imbalanced data sets.</p></div>\",\"PeriodicalId\":74035,\"journal\":{\"name\":\"JVS-vascular science\",\"volume\":\"4 \",\"pages\":\"Article 100096\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/a6/a7/main.PMC10245322.pdf\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"JVS-vascular science\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2666350322000840\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"Medicine\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"JVS-vascular science","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2666350322000840","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Medicine","Score":null,"Total":0}
引用次数: 2

摘要

目的确定影响肾下腹主动脉瘤(AAAs)特异性卷积神经网络(CNN)在计算机断层扫描血管造影(CTA)中准确性的混杂变量,这项回顾性研究分析了200名肾下AAAs患者和200名倾向匹配的对照患者的腹部-骨盆CTA扫描结果。通过将迁移学习应用于VGG-16基础模型,使用模型训练、验证和测试技术,开发了AAA特定训练的CNN。根据数据集(选定的、平衡的或不平衡的)、动脉瘤大小、腹外扩张、夹层和附壁血栓分析模型的准确性和曲线下面积。通过回顾热图,通过梯度加权类激活,叠加在CTA图像上,分析误判。结果训练的自定义CNN模型在选定(n=120)、平衡(n=3704)和不平衡图像集(n=31899)中的测试组准确率分别为94.1%、99.1%和99.6%,曲线下面积分别为0.9900、0.9998和0.9993。尽管平衡和不平衡图像集之间存在八倍的差异,但CNN模型在不平衡和平衡图像集中分别表现出较高的测试组敏感性(98.7%对98.9%)和特异性(99.7%对99.3%)。对于动脉瘤大小,CNN模型显示,随着动脉瘤大小的增加,误判减少:47%(16/34)的动脉瘤<;3.3厘米,动脉瘤3.3至5厘米占32%(11/34),动脉瘤占20%(7/34)>;5厘米。与I型(假阳性)误判相比,包含可测量附壁血栓的动脉瘤在II型(假阴性)误判中表现过度(71%对15%,P<;.05)。在这些成像集中包括腹外动脉瘤延伸(胸动脉或髂动脉)或夹层皮瓣并没有降低模型的总体准确性,表明该模型性能优异,而无需清除混杂或共病诊断的数据集。结论尽管病理学和定量数据集各不相同,但对AAA特异性CNN模型的分析可以在CTA上准确筛选和识别肾下AAAs。最高的解剖误判是小动脉瘤(<3.3厘米)或附壁血栓的存在。尽管包含了腹部外病理学和不平衡的数据集,CNN模型的准确性仍然保持不变。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

摘要图片

摘要图片

摘要图片

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
Machine learning analysis of confounding variables of a convolutional neural network specific for abdominal aortic aneurysms

Objective

To identify confounding variables influencing the accuracy of a convolutional neural network (CNN) specific for infrarenal abdominal aortic aneurysms (AAAs) on computed tomography angiograms (CTAs).

Methods

A Health Insurance Portability and Accountability Act-compliant, institutional review board-approved, retrospective study analyzed abdominopelvic CTA scans from 200 patients with infrarenal AAAs and 200 propensity-matched control patients. An AAA-specific trained CNN was developed by the application of transfer learning to the VGG-16 base model using model training, validation, and testing techniques. Model accuracy and area under the curve were analyzed based on data sets (selected, balanced, or unbalanced), aneurysm size, extra-abdominal extension, dissections, and mural thrombus. Misjudgments were analyzed by review of heatmaps, via gradient weighted class activation, overlaid on CTA images.

Results

The trained custom CNN model reported high test group accuracies of 94.1%, 99.1%, and 99.6% and area under the curve of 0.9900, 0.9998, and 0.9993 in selected (n = 120), balanced (n = 3704), and unbalanced image sets (n = 31,899), respectively. Despite an eightfold difference between balanced and unbalanced image sets, the CNN model demonstrated high test group sensitivities (98.7% vs 98.9%) and specificities (99.7% vs 99.3%) in unbalanced and balanced image sets, respectively. For aneurysm size, the CNN model demonstrates decreasing misjudgments as aneurysm size increases: 47% (16/34) for aneurysms <3.3 cm, 32% (11/34) for aneurysms 3.3 to 5 cm, and 20% (7/34) for aneurysms >5 cm. Aneurysms containing measurable mural thrombus were over-represented within type II (false-negative) misjudgments compared with type I (false-positive) misjudgments (71% vs 15%, P < .05). Inclusion of extra-abdominal aneurysm extension (thoracic or iliac artery) or dissection flaps in these imaging sets did not decrease the model's overall accuracy, indicating that the model performance was excellent without the need to clean the data set of confounding or comorbid diagnoses.

Conclusions

Analysis of an AAA-specific CNN model can accurately screen and identify infrarenal AAAs on CTA despite varying pathology and quantitative data sets. The highest anatomic misjudgments were with small aneurysms (<3.3 cm) or the presence of mural thrombus. Accuracy of the CNN model is maintained despite the inclusion of extra-abdominal pathology and imbalanced data sets.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
4.20
自引率
0.00%
发文量
0
审稿时长
28 weeks
期刊最新文献
Toll-Like Receptor 4, a potential therapeutic target of lower limb ischemic myopathy that raises further questions Role of Toll-like Receptor 4 in Skeletal Muscle Damage in Chronic Limb Threatening Ischaemia Predicting Future Occlusion or Stenosis of Lower Extremity Bypass Grafts Using Artificial Intelligence to Simultaneously Analyze All Flow Velocities Collected in Current and Previous Ultrasound Exams A central arteriovenous fistula reduces systemic hypertension in a mouse model Systematic review and meta-analysis of the genetics of peripheral arterial disease
×
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