使用简单的机器学习方法进行甲状旁腺识别和血管造影分类。

IF 3.5 3区 医学 Q1 SURGERY
BJS Open Pub Date : 2024-09-03 DOI:10.1093/bjsopen/zrae122
Philip D McEntee, Joseph E Greevy, Frédéric Triponez, Marco S Demarchi, Ronan A Cahill
{"title":"使用简单的机器学习方法进行甲状旁腺识别和血管造影分类。","authors":"Philip D McEntee, Joseph E Greevy, Frédéric Triponez, Marco S Demarchi, Ronan A Cahill","doi":"10.1093/bjsopen/zrae122","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Near-infrared indocyanine green angiography allows experienced surgeons to reliably evaluate parathyroid gland vitality during thyroid and parathyroid operations in order to predict postoperative function. To facilitate equal performance between surgeons, we developed an automatic computational quantification method using computer vision that portrays expert interpretation of visualized parathyroid gland near-infrared indocyanine green angiographic fluorescence signals.</p><p><strong>Methods: </strong>Near-infrared indocyanine green-parathyroid gland angiography video recordings (Fluobeam® LX, Fluoptics, Grenoble-part of Getinge-Göteborg) from patients undergoing endocrine cervical surgery in a high-volume unit were used for model development. Computation (MATLAB, Mathworks, Ireland) included segmentation-identification of the parathyroid gland (by autofluorescence), image stabilization (by linear translation) and adjusted time-fluorescence intensity profile generation. Relative upslope and maximum intensity ratios then trained a simple logistic regression model based on expert interpretation and outcome (including hypoparathyroidism), with subsequent unseen testing for validation.</p><p><strong>Results: </strong>The model was trained on 37 patient videos (45 glands, 29 judged well perfused by parathyroid gland angiography experts), achieving feature data separation with 100% accuracy, and tested on 22 unseen videos (27 glands, 15 judged well perfused), including four in real time. Segmentation-guided parathyroid gland detection correctly identified all parathyroid glands during unseen testing along with three additional non-parathyroid gland regions (90% positive predictive value). Subsequent time-fluorescence intensity profile extraction with vitality prediction was shown feasible in all cases within 5 min, with a 96.3% model accuracy (sensitivity and specificity were 93.3 and 100% respectively) when compared with expert judgement.</p><p><strong>Conclusion: </strong>Automatic parathyroid gland perfusion quantification using simple machine learning computational methods discriminates parathyroid gland perfusion in concordance with expert surgeon interpretation, providing a means for near-infrared indocyanine green-parathyroid gland signal evaluation.</p>","PeriodicalId":9028,"journal":{"name":"BJS Open","volume":null,"pages":null},"PeriodicalIF":3.5000,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11518927/pdf/","citationCount":"0","resultStr":"{\"title\":\"Parathyroid gland identification and angiography classification using simple machine learning methods.\",\"authors\":\"Philip D McEntee, Joseph E Greevy, Frédéric Triponez, Marco S Demarchi, Ronan A Cahill\",\"doi\":\"10.1093/bjsopen/zrae122\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Near-infrared indocyanine green angiography allows experienced surgeons to reliably evaluate parathyroid gland vitality during thyroid and parathyroid operations in order to predict postoperative function. To facilitate equal performance between surgeons, we developed an automatic computational quantification method using computer vision that portrays expert interpretation of visualized parathyroid gland near-infrared indocyanine green angiographic fluorescence signals.</p><p><strong>Methods: </strong>Near-infrared indocyanine green-parathyroid gland angiography video recordings (Fluobeam® LX, Fluoptics, Grenoble-part of Getinge-Göteborg) from patients undergoing endocrine cervical surgery in a high-volume unit were used for model development. Computation (MATLAB, Mathworks, Ireland) included segmentation-identification of the parathyroid gland (by autofluorescence), image stabilization (by linear translation) and adjusted time-fluorescence intensity profile generation. Relative upslope and maximum intensity ratios then trained a simple logistic regression model based on expert interpretation and outcome (including hypoparathyroidism), with subsequent unseen testing for validation.</p><p><strong>Results: </strong>The model was trained on 37 patient videos (45 glands, 29 judged well perfused by parathyroid gland angiography experts), achieving feature data separation with 100% accuracy, and tested on 22 unseen videos (27 glands, 15 judged well perfused), including four in real time. Segmentation-guided parathyroid gland detection correctly identified all parathyroid glands during unseen testing along with three additional non-parathyroid gland regions (90% positive predictive value). Subsequent time-fluorescence intensity profile extraction with vitality prediction was shown feasible in all cases within 5 min, with a 96.3% model accuracy (sensitivity and specificity were 93.3 and 100% respectively) when compared with expert judgement.</p><p><strong>Conclusion: </strong>Automatic parathyroid gland perfusion quantification using simple machine learning computational methods discriminates parathyroid gland perfusion in concordance with expert surgeon interpretation, providing a means for near-infrared indocyanine green-parathyroid gland signal evaluation.</p>\",\"PeriodicalId\":9028,\"journal\":{\"name\":\"BJS Open\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.5000,\"publicationDate\":\"2024-09-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11518927/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"BJS Open\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1093/bjsopen/zrae122\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"SURGERY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"BJS Open","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/bjsopen/zrae122","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"SURGERY","Score":null,"Total":0}
引用次数: 0

摘要

背景:在甲状腺和甲状旁腺手术过程中,经验丰富的外科医生可以通过近红外吲哚青绿血管造影术可靠地评估甲状旁腺的活力,从而预测术后功能。为了促进外科医生之间的平等表现,我们开发了一种利用计算机视觉的自动计算量化方法,该方法可描述专家对可视化甲状旁腺近红外吲哚青绿血管造影荧光信号的解释:方法:使用在高容量单位接受颈部内分泌手术的患者的近红外吲哚菁绿-甲状旁腺血管造影视频记录(Fluobeam® LX,Fluoptics,Grenoble-Getinge-Göteborg的一部分)进行模型开发。计算(MATLAB,Mathworks,爱尔兰)包括甲状旁腺的分割识别(通过自发荧光)、图像稳定(通过线性平移)和调整时间-荧光强度曲线生成。然后,根据专家的解释和结果(包括甲状旁腺功能减退)对相对上斜率和最大强度比进行简单的逻辑回归模型训练,并随后进行未见测试进行验证:该模型在 37 个患者视频(45 个腺体,29 个被甲状旁腺血管造影专家判定为灌注良好)上进行了训练,特征数据分离准确率达到 100%,并在 22 个未见视频(27 个腺体,15 个被判定为灌注良好)上进行了测试,其中包括 4 个实时视频。在未见测试中,分割引导的甲状旁腺检测正确识别了所有甲状旁腺以及另外三个非甲状旁腺区域(阳性预测值为 90%)。随后的时间-荧光强度曲线提取和活力预测在 5 分钟内对所有病例都是可行的,与专家判断相比,模型准确率为 96.3%(灵敏度和特异性分别为 93.3% 和 100% ):结论:使用简单的机器学习计算方法自动量化甲状旁腺灌注,与外科医生的专业判断一致,为近红外吲哚青绿-甲状旁腺信号评估提供了一种方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Parathyroid gland identification and angiography classification using simple machine learning methods.

Background: Near-infrared indocyanine green angiography allows experienced surgeons to reliably evaluate parathyroid gland vitality during thyroid and parathyroid operations in order to predict postoperative function. To facilitate equal performance between surgeons, we developed an automatic computational quantification method using computer vision that portrays expert interpretation of visualized parathyroid gland near-infrared indocyanine green angiographic fluorescence signals.

Methods: Near-infrared indocyanine green-parathyroid gland angiography video recordings (Fluobeam® LX, Fluoptics, Grenoble-part of Getinge-Göteborg) from patients undergoing endocrine cervical surgery in a high-volume unit were used for model development. Computation (MATLAB, Mathworks, Ireland) included segmentation-identification of the parathyroid gland (by autofluorescence), image stabilization (by linear translation) and adjusted time-fluorescence intensity profile generation. Relative upslope and maximum intensity ratios then trained a simple logistic regression model based on expert interpretation and outcome (including hypoparathyroidism), with subsequent unseen testing for validation.

Results: The model was trained on 37 patient videos (45 glands, 29 judged well perfused by parathyroid gland angiography experts), achieving feature data separation with 100% accuracy, and tested on 22 unseen videos (27 glands, 15 judged well perfused), including four in real time. Segmentation-guided parathyroid gland detection correctly identified all parathyroid glands during unseen testing along with three additional non-parathyroid gland regions (90% positive predictive value). Subsequent time-fluorescence intensity profile extraction with vitality prediction was shown feasible in all cases within 5 min, with a 96.3% model accuracy (sensitivity and specificity were 93.3 and 100% respectively) when compared with expert judgement.

Conclusion: Automatic parathyroid gland perfusion quantification using simple machine learning computational methods discriminates parathyroid gland perfusion in concordance with expert surgeon interpretation, providing a means for near-infrared indocyanine green-parathyroid gland signal evaluation.

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
BJS Open
BJS Open SURGERY-
CiteScore
6.00
自引率
3.20%
发文量
144
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信