基于端到端机器学习的计算机断层扫描肿瘤性和非肿瘤性脑出血鉴别

Q1 Medicine
Jawed Nawabi , Sophia Schulze-Weddige , Georg Lukas Baumgärtner , Tobias Orth , Andrea Dell'Orco , Andrea Morotti , Federico Mazzacane , Helge Kniep , Uta Hanning , Michael Scheel , Jens Fiehler , Tobias Penzkofer
{"title":"基于端到端机器学习的计算机断层扫描肿瘤性和非肿瘤性脑出血鉴别","authors":"Jawed Nawabi ,&nbsp;Sophia Schulze-Weddige ,&nbsp;Georg Lukas Baumgärtner ,&nbsp;Tobias Orth ,&nbsp;Andrea Dell'Orco ,&nbsp;Andrea Morotti ,&nbsp;Federico Mazzacane ,&nbsp;Helge Kniep ,&nbsp;Uta Hanning ,&nbsp;Michael Scheel ,&nbsp;Jens Fiehler ,&nbsp;Tobias Penzkofer","doi":"10.1016/j.imu.2025.101633","DOIUrl":null,"url":null,"abstract":"<div><h3>Purpose</h3><div>To develop and evaluate a fully automated segmentation and classification tool for the discrimination of neoplastic and non-neoplastic intracerebral hemorrhage (ICH) on admission Computed Tomography (CT).</div></div><div><h3>Materials and methods</h3><div>Two models were developed using a retrospective dataset of acute ICH patients with unknown etiology upon admission, based on CT scans from a single institution (January 2016 to May 2020). An nnU-Net segmentation model was trained on manually segmented ICH and perihematomal edema (PHE) masks, alongside a ResNet-34 classification model for differentiating between neoplastic and non-neoplastic ICH. The combined tool was evaluated on the test set and validated on an external cohort. Validation performance was reevaluated after enriching the training data of the segmentation model. Evaluation metrics included accuracy (Acc), area under the curve (AUC), sensitivity, specificity, and Matthews Correlation Coefficient (MCC). Performance was compared to human raters.</div></div><div><h3>Results</h3><div>Among 291 patients, 116 (39.86 %) had neoplastic and 175 (60.14 %) non-neoplastic ICH. The tool achieved an Acc of 86 % and an AUC of 85 % with a sensitivity and specificity of 80 % and 93 % in the test set. On the validation cohort (n = 58), the tool achieved an AUC of 68 % reaching 83 % after retraining of the segmentation model. The tool achieved an MCC of 0.62, compared to 0.47–0.61 for the human raters.</div></div><div><h3>Conclusion</h3><div>The tool demonstrated high diagnostic performance with potential as a decision-aiding tool; however, it relies on multi-vendor data for improved robustness, warranting further validation across diverse datasets.</div></div>","PeriodicalId":13953,"journal":{"name":"Informatics in Medicine Unlocked","volume":"54 ","pages":"Article 101633"},"PeriodicalIF":0.0000,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"End-to-end machine learning based discrimination of neoplastic and non-neoplastic intracerebral hemorrhage on computed tomography\",\"authors\":\"Jawed Nawabi ,&nbsp;Sophia Schulze-Weddige ,&nbsp;Georg Lukas Baumgärtner ,&nbsp;Tobias Orth ,&nbsp;Andrea Dell'Orco ,&nbsp;Andrea Morotti ,&nbsp;Federico Mazzacane ,&nbsp;Helge Kniep ,&nbsp;Uta Hanning ,&nbsp;Michael Scheel ,&nbsp;Jens Fiehler ,&nbsp;Tobias Penzkofer\",\"doi\":\"10.1016/j.imu.2025.101633\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Purpose</h3><div>To develop and evaluate a fully automated segmentation and classification tool for the discrimination of neoplastic and non-neoplastic intracerebral hemorrhage (ICH) on admission Computed Tomography (CT).</div></div><div><h3>Materials and methods</h3><div>Two models were developed using a retrospective dataset of acute ICH patients with unknown etiology upon admission, based on CT scans from a single institution (January 2016 to May 2020). An nnU-Net segmentation model was trained on manually segmented ICH and perihematomal edema (PHE) masks, alongside a ResNet-34 classification model for differentiating between neoplastic and non-neoplastic ICH. The combined tool was evaluated on the test set and validated on an external cohort. Validation performance was reevaluated after enriching the training data of the segmentation model. Evaluation metrics included accuracy (Acc), area under the curve (AUC), sensitivity, specificity, and Matthews Correlation Coefficient (MCC). Performance was compared to human raters.</div></div><div><h3>Results</h3><div>Among 291 patients, 116 (39.86 %) had neoplastic and 175 (60.14 %) non-neoplastic ICH. The tool achieved an Acc of 86 % and an AUC of 85 % with a sensitivity and specificity of 80 % and 93 % in the test set. On the validation cohort (n = 58), the tool achieved an AUC of 68 % reaching 83 % after retraining of the segmentation model. The tool achieved an MCC of 0.62, compared to 0.47–0.61 for the human raters.</div></div><div><h3>Conclusion</h3><div>The tool demonstrated high diagnostic performance with potential as a decision-aiding tool; however, it relies on multi-vendor data for improved robustness, warranting further validation across diverse datasets.</div></div>\",\"PeriodicalId\":13953,\"journal\":{\"name\":\"Informatics in Medicine Unlocked\",\"volume\":\"54 \",\"pages\":\"Article 101633\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2025-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Informatics in Medicine Unlocked\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2352914825000218\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"Medicine\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Informatics in Medicine Unlocked","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2352914825000218","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"Medicine","Score":null,"Total":0}
引用次数: 0

摘要

目的开发一种全自动分割分类工具,用于颅内肿瘤与非肿瘤性脑出血(ICH)的CT鉴别。材料和方法:基于单一机构(2016年1月至2020年5月)的CT扫描,使用入院时病因不明的急性脑出血患者的回顾性数据集开发了两个模型。在人工分割的脑出血和血肿周围水肿(PHE)面具上训练了一个nnU-Net分割模型,并使用ResNet-34分类模型来区分肿瘤性和非肿瘤性脑出血。该组合工具在测试集上进行了评估,并在外部队列中进行了验证。在丰富分割模型的训练数据后,对验证性能进行重新评价。评估指标包括准确性(Acc)、曲线下面积(AUC)、敏感性、特异性和马修斯相关系数(MCC)。他们的表现与人类评分者进行了比较。结果291例患者中有116例(39.86%)为肿瘤性脑出血,175例(60.14%)为非肿瘤性脑出血。该工具在测试集中的Acc为86%,AUC为85%,灵敏度和特异性分别为80%和93%。在验证队列(n = 58)上,该工具在对分割模型进行再训练后实现了68%的AUC,达到83%。该工具的MCC为0.62,而人类评分者的MCC为0.47-0.61。结论该工具具有较高的诊断效能,具有作为决策辅助工具的潜力;然而,它依赖于多供应商的数据来提高鲁棒性,保证跨不同数据集的进一步验证。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
End-to-end machine learning based discrimination of neoplastic and non-neoplastic intracerebral hemorrhage on computed tomography

Purpose

To develop and evaluate a fully automated segmentation and classification tool for the discrimination of neoplastic and non-neoplastic intracerebral hemorrhage (ICH) on admission Computed Tomography (CT).

Materials and methods

Two models were developed using a retrospective dataset of acute ICH patients with unknown etiology upon admission, based on CT scans from a single institution (January 2016 to May 2020). An nnU-Net segmentation model was trained on manually segmented ICH and perihematomal edema (PHE) masks, alongside a ResNet-34 classification model for differentiating between neoplastic and non-neoplastic ICH. The combined tool was evaluated on the test set and validated on an external cohort. Validation performance was reevaluated after enriching the training data of the segmentation model. Evaluation metrics included accuracy (Acc), area under the curve (AUC), sensitivity, specificity, and Matthews Correlation Coefficient (MCC). Performance was compared to human raters.

Results

Among 291 patients, 116 (39.86 %) had neoplastic and 175 (60.14 %) non-neoplastic ICH. The tool achieved an Acc of 86 % and an AUC of 85 % with a sensitivity and specificity of 80 % and 93 % in the test set. On the validation cohort (n = 58), the tool achieved an AUC of 68 % reaching 83 % after retraining of the segmentation model. The tool achieved an MCC of 0.62, compared to 0.47–0.61 for the human raters.

Conclusion

The tool demonstrated high diagnostic performance with potential as a decision-aiding tool; however, it relies on multi-vendor data for improved robustness, warranting further validation across diverse datasets.
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
Informatics in Medicine Unlocked
Informatics in Medicine Unlocked Medicine-Health Informatics
CiteScore
9.50
自引率
0.00%
发文量
282
审稿时长
39 days
期刊介绍: Informatics in Medicine Unlocked (IMU) is an international gold open access journal covering a broad spectrum of topics within medical informatics, including (but not limited to) papers focusing on imaging, pathology, teledermatology, public health, ophthalmological, nursing and translational medicine informatics. The full papers that are published in the journal are accessible to all who visit the website.
×
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