arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2411.07976eess.IVcs.AIcs.CV
收藏

DINO-LG:通过标签引导增强视觉变换器用于冠状动脉钙化检测

DINO-LG: Enhancing Vision Transformers with Label Guidance for Coronary Artery Calcium Detection

University of Kentucky(肯塔基大学);Department of Software Engineering, Karabuk University(卡拉巴克大学软件工程系)

Mahmut S. Gokmen, Caner Ozcan, Moneera N. Haque, Steve W. Leung, C. Seth Parker, W. Brent Seales, Cody Bumgardner

AI总结:

DINO-LG通过标签引导增强视觉变换器,提升冠状动脉钙化检测的准确性和效率,降低假阳性与假阴性率,提高诊断精度并减少医疗成本。

摘要:

冠状动脉疾病(CAD)是全球导致死亡的主要原因之一,需要有效的风险评估策略,冠状动脉钙化(CAC)评分通过计算机断层扫描(CT)是预防的关键方法。传统方法主要基于UNET架构实现于预构建模型上,面临标注CT扫描中包含CAC的稀缺性和数据集不平衡等问题,导致分割和评分任务性能下降。在本研究中,我们通过引入DINO-LG,一种新的标签引导扩展的DINO(无标签自蒸馏)方法,解决了这些局限性。该方法在自监督预训练过程中对标注的钙化区域进行针对性增强。我们的三阶段流程整合了通过DINO-LG训练的914例CT扫描(包含700例门控和214例非门控采集)提取的视觉变换器(ViT-Base/8)特征,线性分类以识别钙化切片,以及UNET分割用于CAC量化和Agatston评分。DINO-LG在检测含CAC的CT切片上的灵敏度和特异性分别为89%和90%,相比标准DINO的79%和77%,分别将假阴性和假阳性率降低了49%和57%。集成系统在45例测试患者上实现了90%的CAC风险分类准确率,优于单独的UNET分割(76%准确率),同时仅处理相关CT切片的子集。这种针对性方法通过向UNET模型提供相关切片提高了CAC评分的准确性,提高了诊断精度,同时通过减少不必要的测试和治疗降低了医疗成本。

英文摘要:

Coronary artery disease (CAD), one of the leading causes of mortality worldwide, necessitates effective risk assessment strategies, with coronary artery calcium (CAC) scoring via computed tomography (CT) being a key method for prevention. Traditional methods, primarily based on UNET architectures implemented on pre-built models, face challenges like the scarcity of annotated CT scans containing CAC and imbalanced datasets, leading to reduced performance in segmentation and scoring tasks. In this study, we address these limitations by introducing DINO-LG, a novel label-guided extension of DINO (self-distillation with no labels) that incorporates targeted augmentation on annotated calcified regions during self-supervised pre-training. Our three-stage pipeline integrates Vision Transformer (ViT-Base/8) feature extraction via DINO-LG trained on 914 CT scans comprising 700 gated and 214 non-gated acquisitions, linear classification to identify calcified slices, and U-NET segmentation for CAC quantification and Agatston scoring. DINO-LG achieved 89% sensitivity and 90% specificity for detecting CAC-containing CT slices, compared to standard DINO's 79% sensitivity and 77% specificity, reducing false-negative and false-positive rates by 49% and 57% respectively. The integrated system achieves 90% accuracy in CAC risk classification on 45 test patients, outperforming standalone U-NET segmentation (76% accuracy) while processing only the relevant subset of CT slices. This targeted approach enhances CAC scoring accuracy by feeding the UNET model with relevant slices, improving diagnostic precision while lowering healthcare costs by minimizing unnecessary tests and treatments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑