The accuracy of deep learning models for diagnosing maxillary fungal ball rhinosinusitis.

IF 1.9 3区 医学 Q2 OTORHINOLARYNGOLOGY
Pakapoom Sukswai, Narit Hnoohom, Minh Phuoc Hoang, Songklot Aeumjaturapat, Supinda Chusakul, Jesada Kanjanaumporn, Kachorn Seresirikachorn, Kornkiat Snidvongs
{"title":"The accuracy of deep learning models for diagnosing maxillary fungal ball rhinosinusitis.","authors":"Pakapoom Sukswai, Narit Hnoohom, Minh Phuoc Hoang, Songklot Aeumjaturapat, Supinda Chusakul, Jesada Kanjanaumporn, Kachorn Seresirikachorn, Kornkiat Snidvongs","doi":"10.1007/s00405-024-08948-8","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>To assess the accuracy of deep learning models for the diagnosis of maxillary fungal ball rhinosinusitis (MFB) and to compare the accuracy, sensitivity, specificity, precision, and F1-score with a rhinologist.</p><p><strong>Methods: </strong>Data from 1539 adult chronic rhinosinusitis (CRS) patients who underwent paranasal sinus computed tomography (CT) were collected. The overall dataset consisted of 254 MFB cases and 1285 non-MFB cases. The CT images were constructed and labeled to form the deep learning models. Seventy percent of the images were used for training the deep-learning models, and 30% were used for testing. Whole image analysis and instance segmentation analysis were performed using three different architectures: MobileNetv3, ResNet50, and ResNet101 for whole image analysis, and YOLOv5X-SEG, YOLOv8X-SEG, and YOLOv9-C-SEG for instance segmentation analysis. The ROC curve was assessed. Accuracy, sensitivity (recall), specificity, precision, and F1-score were compared between the models and a rhinologist. Kappa agreement was evaluated.</p><p><strong>Results: </strong>Whole image analysis showed lower precision, recall, and F1-score compared to instance segmentation. The models exhibited an area under the ROC curve of 0.86 for whole image analysis and 0.88 for instance segmentation. In the testing dataset for whole images, the MobileNet V3 model showed 81.00% accuracy, 47.40% sensitivity, 87.90% specificity, 66.80% precision, and a 67.20% F1 score. Instance segmentation yielded the best evaluation with YOLOv8X-SEG showing 94.10% accuracy, 85.90% sensitivity, 95.80% specificity, 88.90% precision, and an 89.80% F1-score. The rhinologist achieved 93.5% accuracy, 84.6% sensitivity, 95.3% specificity, 78.6% precision, and an 81.5% F1-score.</p><p><strong>Conclusion: </strong>Utilizing paranasal sinus CT imaging with enhanced localization and constructive instance segmentation in deep learning models can be the practical promising deep learning system in assisting physicians for diagnosing maxillary fungal ball.</p>","PeriodicalId":11952,"journal":{"name":"European Archives of Oto-Rhino-Laryngology","volume":" ","pages":"6485-6492"},"PeriodicalIF":1.9000,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Archives of Oto-Rhino-Laryngology","FirstCategoryId":"92","ListUrlMain":"https://doi.org/10.1007/s00405-024-08948-8","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/9/4 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"OTORHINOLARYNGOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Purpose: To assess the accuracy of deep learning models for the diagnosis of maxillary fungal ball rhinosinusitis (MFB) and to compare the accuracy, sensitivity, specificity, precision, and F1-score with a rhinologist.

Methods: Data from 1539 adult chronic rhinosinusitis (CRS) patients who underwent paranasal sinus computed tomography (CT) were collected. The overall dataset consisted of 254 MFB cases and 1285 non-MFB cases. The CT images were constructed and labeled to form the deep learning models. Seventy percent of the images were used for training the deep-learning models, and 30% were used for testing. Whole image analysis and instance segmentation analysis were performed using three different architectures: MobileNetv3, ResNet50, and ResNet101 for whole image analysis, and YOLOv5X-SEG, YOLOv8X-SEG, and YOLOv9-C-SEG for instance segmentation analysis. The ROC curve was assessed. Accuracy, sensitivity (recall), specificity, precision, and F1-score were compared between the models and a rhinologist. Kappa agreement was evaluated.

Results: Whole image analysis showed lower precision, recall, and F1-score compared to instance segmentation. The models exhibited an area under the ROC curve of 0.86 for whole image analysis and 0.88 for instance segmentation. In the testing dataset for whole images, the MobileNet V3 model showed 81.00% accuracy, 47.40% sensitivity, 87.90% specificity, 66.80% precision, and a 67.20% F1 score. Instance segmentation yielded the best evaluation with YOLOv8X-SEG showing 94.10% accuracy, 85.90% sensitivity, 95.80% specificity, 88.90% precision, and an 89.80% F1-score. The rhinologist achieved 93.5% accuracy, 84.6% sensitivity, 95.3% specificity, 78.6% precision, and an 81.5% F1-score.

Conclusion: Utilizing paranasal sinus CT imaging with enhanced localization and constructive instance segmentation in deep learning models can be the practical promising deep learning system in assisting physicians for diagnosing maxillary fungal ball.

Abstract Image

深度学习模型诊断上颌真菌球鼻炎的准确性。
目的:评估深度学习模型诊断上颌真菌球鼻炎(MFB)的准确性,并将其准确性、灵敏度、特异性、精确度和 F1 分数与鼻科医师进行比较:方法: 收集了 1539 名接受鼻旁窦计算机断层扫描(CT)的成年慢性鼻炎(CRS)患者的数据。整个数据集包括 254 个 MFB 病例和 1285 个非 MFB 病例。CT 图像经过构建和标记后形成深度学习模型。70%的图像用于训练深度学习模型,30%用于测试。使用三种不同的架构进行全图分析和实例分割分析:全图分析使用 MobileNetv3、ResNet50 和 ResNet101,实例分割分析使用 YOLOv5X-SEG、YOLOv8X-SEG 和 YOLOv9-C-SEG。对 ROC 曲线进行了评估。比较了模型与鼻科医生之间的准确度、灵敏度(召回)、特异性、精确度和 F1 分数。对 Kappa 一致性进行了评估:结果:与实例分割相比,全图分析的精确度、召回率和 F1 分数都较低。全图分析模型的 ROC 曲线下面积为 0.86,实例分割模型的 ROC 曲线下面积为 0.88。在整个图像的测试数据集中,MobileNet V3 模型显示出 81.00% 的准确率、47.40% 的灵敏度、87.90% 的特异性、66.80% 的精确度和 67.20% 的 F1 分数。YOLOv8X-SEG 的实例分割评估结果最佳,准确率为 94.10%,灵敏度为 85.90%,特异度为 95.80%,精确度为 88.90%,F1 分数为 89.80%。鼻科医生的准确率为 93.5%,灵敏度为 84.6%,特异性为 95.3%,精确度为 78.6%,F1 分数为 81.5%:结论:在深度学习模型中利用鼻旁窦 CT 成像增强定位和建构实例分割,可以成为协助医生诊断上颌真菌球的实用而有前途的深度学习系统。
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 求助全文
来源期刊
CiteScore
5.30
自引率
7.70%
发文量
537
审稿时长
2-4 weeks
期刊介绍: Official Journal of European Union of Medical Specialists – ORL Section and Board Official Journal of Confederation of European Oto-Rhino-Laryngology Head and Neck Surgery "European Archives of Oto-Rhino-Laryngology" publishes original clinical reports and clinically relevant experimental studies, as well as short communications presenting new results of special interest. With peer review by a respected international editorial board and prompt English-language publication, the journal provides rapid dissemination of information by authors from around the world. This particular feature makes it the journal of choice for readers who want to be informed about the continuing state of the art concerning basic sciences and the diagnosis and management of diseases of the head and neck on an international level. European Archives of Oto-Rhino-Laryngology was founded in 1864 as "Archiv für Ohrenheilkunde" by A. von Tröltsch, A. Politzer and H. Schwartze.
×
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