改进放射科医师对欠采样、深度学习重建膝关节MRI半月板异常的检测。

Radiology advances Pub Date : 2025-04-04 eCollection Date: 2025-03-01 DOI:10.1093/radadv/umaf015
Natalia Konovalova, Aniket Tolpadi, Felix Liu, Zehra Akkaya, Johanna Luitjens, Felix Gassert, Paula Giesler, Rupsa Bhattacharjee, Misung Han, Emma Bahroos, Sharmila Majumdar, Valentina Pedoia
{"title":"改进放射科医师对欠采样、深度学习重建膝关节MRI半月板异常的检测。","authors":"Natalia Konovalova, Aniket Tolpadi, Felix Liu, Zehra Akkaya, Johanna Luitjens, Felix Gassert, Paula Giesler, Rupsa Bhattacharjee, Misung Han, Emma Bahroos, Sharmila Majumdar, Valentina Pedoia","doi":"10.1093/radadv/umaf015","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Accurate interpretation of meniscal anomalies on knee MRI is critical for diagnosis and treatment planning, with artificial intelligence emerging as a promising tool to support and enhance this process through automated anomaly detection.</p><p><strong>Purpose: </strong>To evaluate the impact of an artificial intelligence (AI) anomaly detection assistant on radiologists' interpretation of meniscal anomalies in undersampled, deep learning (DL)-reconstructed knee MRI and assess the relationship between reconstruction quality metrics and anomaly detection performance.</p><p><strong>Materials and methods: </strong>This retrospective study included 947 knee MRI examinations; 51 were excluded for poor image quality, leaving 896 participants (mean age, 44.7 ± 15.3 years; 472 women). Using 8-fold undersampled data, DL-based reconstructed images were generated. An object detection model was trained on original, fully sampled images and evaluated on 1 original and 14 DL-reconstructed test sets to identify meniscal lesions. Standard reconstruction metrics (normalized root mean square error, peak signal-to-noise ratio, and structural similarity index) and anomaly detection metrics (mean average precision, F1 score) were quantified and compared. Two radiologists independently reviewed a stratified sample of 50 examinations unassisted and assisted with AI-predicted anomaly boxes. McNemar's test evaluated differences in diagnostic performance; Cohen's kappa assessed interrater agreement.</p><p><strong>Results: </strong>On the original images, the anomaly detection model achieved the following: 70.53% precision, 72.17% recall, 63.09% mAP, and a 71.34% F1 score. Comparing performance among the undersampled reconstruction datasets, box-based reconstruction metrics showed better correlation with detection performance than traditional image-based metrics (mAP to box-based SSIM, <i>r</i> = 0.81, <i>P</i> < .01; mAP to image-based SSIM, <i>r</i> = 0.64, <i>P</i> = .01). In 50 participants, AI assistance improved radiologists' accuracy on reconstructed images. Sensitivity increased from 77.27% (95% CI, 65.83-85.72; 51/66) to 80.30% (95% CI, 69.16-88.11; 53/66), and specificity improved from 88.46% (95% CI, 83.73-91.95; 207/234) to 90.60% (95% CI, 86.18-93.71; 212/234) (<i>P</i> < .05).</p><p><strong>Conclusion: </strong>AI-assisted meniscal anomaly detection enhanced radiologists' interpretation of undersampled, DL-reconstructed knee MRI. Anomaly detection may serve as a complementary tool alongside other reconstruction metrics to assess the preservation of clinically important features in reconstructed images, warranting further investigation.</p>","PeriodicalId":519940,"journal":{"name":"Radiology advances","volume":"2 2","pages":"umaf015"},"PeriodicalIF":0.0000,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12021832/pdf/","citationCount":"0","resultStr":"{\"title\":\"Improving radiologist detection of meniscal abnormality on undersampled, deep learning reconstructed knee MRI.\",\"authors\":\"Natalia Konovalova, Aniket Tolpadi, Felix Liu, Zehra Akkaya, Johanna Luitjens, Felix Gassert, Paula Giesler, Rupsa Bhattacharjee, Misung Han, Emma Bahroos, Sharmila Majumdar, Valentina Pedoia\",\"doi\":\"10.1093/radadv/umaf015\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Accurate interpretation of meniscal anomalies on knee MRI is critical for diagnosis and treatment planning, with artificial intelligence emerging as a promising tool to support and enhance this process through automated anomaly detection.</p><p><strong>Purpose: </strong>To evaluate the impact of an artificial intelligence (AI) anomaly detection assistant on radiologists' interpretation of meniscal anomalies in undersampled, deep learning (DL)-reconstructed knee MRI and assess the relationship between reconstruction quality metrics and anomaly detection performance.</p><p><strong>Materials and methods: </strong>This retrospective study included 947 knee MRI examinations; 51 were excluded for poor image quality, leaving 896 participants (mean age, 44.7 ± 15.3 years; 472 women). Using 8-fold undersampled data, DL-based reconstructed images were generated. An object detection model was trained on original, fully sampled images and evaluated on 1 original and 14 DL-reconstructed test sets to identify meniscal lesions. Standard reconstruction metrics (normalized root mean square error, peak signal-to-noise ratio, and structural similarity index) and anomaly detection metrics (mean average precision, F1 score) were quantified and compared. Two radiologists independently reviewed a stratified sample of 50 examinations unassisted and assisted with AI-predicted anomaly boxes. McNemar's test evaluated differences in diagnostic performance; Cohen's kappa assessed interrater agreement.</p><p><strong>Results: </strong>On the original images, the anomaly detection model achieved the following: 70.53% precision, 72.17% recall, 63.09% mAP, and a 71.34% F1 score. Comparing performance among the undersampled reconstruction datasets, box-based reconstruction metrics showed better correlation with detection performance than traditional image-based metrics (mAP to box-based SSIM, <i>r</i> = 0.81, <i>P</i> < .01; mAP to image-based SSIM, <i>r</i> = 0.64, <i>P</i> = .01). In 50 participants, AI assistance improved radiologists' accuracy on reconstructed images. Sensitivity increased from 77.27% (95% CI, 65.83-85.72; 51/66) to 80.30% (95% CI, 69.16-88.11; 53/66), and specificity improved from 88.46% (95% CI, 83.73-91.95; 207/234) to 90.60% (95% CI, 86.18-93.71; 212/234) (<i>P</i> < .05).</p><p><strong>Conclusion: </strong>AI-assisted meniscal anomaly detection enhanced radiologists' interpretation of undersampled, DL-reconstructed knee MRI. Anomaly detection may serve as a complementary tool alongside other reconstruction metrics to assess the preservation of clinically important features in reconstructed images, warranting further investigation.</p>\",\"PeriodicalId\":519940,\"journal\":{\"name\":\"Radiology advances\",\"volume\":\"2 2\",\"pages\":\"umaf015\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2025-04-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12021832/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Radiology advances\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1093/radadv/umaf015\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/3/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Radiology advances","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1093/radadv/umaf015","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/3/1 0:00:00","PubModel":"eCollection","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

背景:在膝关节MRI上准确解释半月板异常对于诊断和治疗计划至关重要,人工智能正在成为一种有前途的工具,通过自动异常检测来支持和增强这一过程。目的:评估人工智能(AI)异常检测助手对放射科医生在欠采样、深度学习(DL)重建的膝关节MRI中半月板异常的解释的影响,并评估重建质量指标与异常检测性能之间的关系。材料和方法:本回顾性研究包括947例膝关节MRI检查;51例因图像质量差被排除,共896例(平均年龄44.7±15.3岁;472名女性)。利用8倍欠采样数据,生成基于dl的重构图像。目标检测模型在原始的、完全采样的图像上进行训练,并在1个原始图像和14个dl重建的测试集上进行评估,以识别半月板病变。对标准重构指标(归一化均方根误差、峰值信噪比和结构相似性指数)和异常检测指标(平均平均精度、F1评分)进行量化和比较。两名放射科医生独立审查了50次检查的分层样本,并协助人工智能预测异常框。McNemar的测试评估了诊断表现的差异;科恩的kappa评估了译员之间的协议。结果:在原始图像上,异常检测模型的准确率为70.53%,召回率为72.17%,mAP为63.09%,F1得分为71.34%。对比欠采样重建数据集的性能,基于盒的重建指标与检测性能的相关性优于传统的基于图像的指标(mAP与基于盒的SSIM, r = 0.81, P r = 0.64, P = 0.01)。在50名参与者中,人工智能帮助提高了放射科医生重建图像的准确性。敏感性从77.27%增加(95% CI, 65.83-85.72;51/66)至80.30% (95% CI, 69.16-88.11;53/66),特异性从88.46%提高(95% CI, 83.73-91.95;207/234)至90.60% (95% CI, 86.18-93.71;212/234) (p < 0.05)。结论:人工智能辅助半月板异常检测增强了放射科医生对采样不足、dl重建的膝关节MRI的解释。异常检测可以作为一种补充工具,与其他重建指标一起评估重建图像中临床重要特征的保存情况,值得进一步研究。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Improving radiologist detection of meniscal abnormality on undersampled, deep learning reconstructed knee MRI.

Improving radiologist detection of meniscal abnormality on undersampled, deep learning reconstructed knee MRI.

Improving radiologist detection of meniscal abnormality on undersampled, deep learning reconstructed knee MRI.

Improving radiologist detection of meniscal abnormality on undersampled, deep learning reconstructed knee MRI.

Background: Accurate interpretation of meniscal anomalies on knee MRI is critical for diagnosis and treatment planning, with artificial intelligence emerging as a promising tool to support and enhance this process through automated anomaly detection.

Purpose: To evaluate the impact of an artificial intelligence (AI) anomaly detection assistant on radiologists' interpretation of meniscal anomalies in undersampled, deep learning (DL)-reconstructed knee MRI and assess the relationship between reconstruction quality metrics and anomaly detection performance.

Materials and methods: This retrospective study included 947 knee MRI examinations; 51 were excluded for poor image quality, leaving 896 participants (mean age, 44.7 ± 15.3 years; 472 women). Using 8-fold undersampled data, DL-based reconstructed images were generated. An object detection model was trained on original, fully sampled images and evaluated on 1 original and 14 DL-reconstructed test sets to identify meniscal lesions. Standard reconstruction metrics (normalized root mean square error, peak signal-to-noise ratio, and structural similarity index) and anomaly detection metrics (mean average precision, F1 score) were quantified and compared. Two radiologists independently reviewed a stratified sample of 50 examinations unassisted and assisted with AI-predicted anomaly boxes. McNemar's test evaluated differences in diagnostic performance; Cohen's kappa assessed interrater agreement.

Results: On the original images, the anomaly detection model achieved the following: 70.53% precision, 72.17% recall, 63.09% mAP, and a 71.34% F1 score. Comparing performance among the undersampled reconstruction datasets, box-based reconstruction metrics showed better correlation with detection performance than traditional image-based metrics (mAP to box-based SSIM, r = 0.81, P < .01; mAP to image-based SSIM, r = 0.64, P = .01). In 50 participants, AI assistance improved radiologists' accuracy on reconstructed images. Sensitivity increased from 77.27% (95% CI, 65.83-85.72; 51/66) to 80.30% (95% CI, 69.16-88.11; 53/66), and specificity improved from 88.46% (95% CI, 83.73-91.95; 207/234) to 90.60% (95% CI, 86.18-93.71; 212/234) (P < .05).

Conclusion: AI-assisted meniscal anomaly detection enhanced radiologists' interpretation of undersampled, DL-reconstructed knee MRI. Anomaly detection may serve as a complementary tool alongside other reconstruction metrics to assess the preservation of clinically important features in reconstructed images, warranting further investigation.

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
自引率
0.00%
发文量
0
×
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:604180095
Book学术官方微信