Saahil Islam, Venkatesh N Murthy, Dominik Neumann, Badhan Kumar Das, Puneet Sharma, Andreas Maier, Dorin Comaniciu, Florin C Ghesu
{"title":"介入性图像分析的自我监督学习:实现稳健的设备跟踪器。","authors":"Saahil Islam, Venkatesh N Murthy, Dominik Neumann, Badhan Kumar Das, Puneet Sharma, Andreas Maier, Dorin Comaniciu, Florin C Ghesu","doi":"10.1117/1.JMI.11.3.035001","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>The accurate detection and tracking of devices, such as guiding catheters in live X-ray image acquisitions, are essential prerequisites for endovascular cardiac interventions. This information is leveraged for procedural guidance, e.g., directing stent placements. To ensure procedural safety and efficacy, there is a need for high robustness/no failures during tracking. To achieve this, one needs to efficiently tackle challenges, such as device obscuration by the contrast agent or other external devices or wires and changes in the field-of-view or acquisition angle, as well as the continuous movement due to cardiac and respiratory motion.</p><p><strong>Approach: </strong>To overcome the aforementioned challenges, we propose an approach to learn spatio-temporal features from a very large data cohort of over 16 million interventional X-ray frames using self-supervision for image sequence data. Our approach is based on a masked image modeling technique that leverages frame interpolation-based reconstruction to learn fine inter-frame temporal correspondences. The features encoded in the resulting model are fine-tuned downstream in a light-weight model.</p><p><strong>Results: </strong>Our approach achieves state-of-the-art performance, in particular for robustness, compared to ultra optimized reference solutions (that use multi-stage feature fusion or multi-task and flow regularization). The experiments show that our method achieves a 66.31% reduction in the maximum tracking error against the reference solutions (23.20% when flow regularization is used), achieving a success score of 97.95% at a <math><mrow><mn>3</mn><mo>×</mo></mrow></math> faster inference speed of 42 frames-per-second (on GPU). In addition, we achieve a 20% reduction in the standard deviation of errors, which indicates a much more stable tracking performance.</p><p><strong>Conclusions: </strong>The proposed data-driven approach achieves superior performance, particularly in robustness and speed compared with the frequently used multi-modular approaches for device tracking. The results encourage the use of our approach in various other tasks within interventional image analytics that require effective understanding of spatio-temporal semantics.</p>","PeriodicalId":47707,"journal":{"name":"Journal of Medical Imaging","volume":"11 3","pages":"035001"},"PeriodicalIF":1.9000,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11094643/pdf/","citationCount":"0","resultStr":"{\"title\":\"Self-supervised learning for interventional image analytics: toward robust device trackers.\",\"authors\":\"Saahil Islam, Venkatesh N Murthy, Dominik Neumann, Badhan Kumar Das, Puneet Sharma, Andreas Maier, Dorin Comaniciu, Florin C Ghesu\",\"doi\":\"10.1117/1.JMI.11.3.035001\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Purpose: </strong>The accurate detection and tracking of devices, such as guiding catheters in live X-ray image acquisitions, are essential prerequisites for endovascular cardiac interventions. This information is leveraged for procedural guidance, e.g., directing stent placements. To ensure procedural safety and efficacy, there is a need for high robustness/no failures during tracking. To achieve this, one needs to efficiently tackle challenges, such as device obscuration by the contrast agent or other external devices or wires and changes in the field-of-view or acquisition angle, as well as the continuous movement due to cardiac and respiratory motion.</p><p><strong>Approach: </strong>To overcome the aforementioned challenges, we propose an approach to learn spatio-temporal features from a very large data cohort of over 16 million interventional X-ray frames using self-supervision for image sequence data. Our approach is based on a masked image modeling technique that leverages frame interpolation-based reconstruction to learn fine inter-frame temporal correspondences. The features encoded in the resulting model are fine-tuned downstream in a light-weight model.</p><p><strong>Results: </strong>Our approach achieves state-of-the-art performance, in particular for robustness, compared to ultra optimized reference solutions (that use multi-stage feature fusion or multi-task and flow regularization). The experiments show that our method achieves a 66.31% reduction in the maximum tracking error against the reference solutions (23.20% when flow regularization is used), achieving a success score of 97.95% at a <math><mrow><mn>3</mn><mo>×</mo></mrow></math> faster inference speed of 42 frames-per-second (on GPU). In addition, we achieve a 20% reduction in the standard deviation of errors, which indicates a much more stable tracking performance.</p><p><strong>Conclusions: </strong>The proposed data-driven approach achieves superior performance, particularly in robustness and speed compared with the frequently used multi-modular approaches for device tracking. The results encourage the use of our approach in various other tasks within interventional image analytics that require effective understanding of spatio-temporal semantics.</p>\",\"PeriodicalId\":47707,\"journal\":{\"name\":\"Journal of Medical Imaging\",\"volume\":\"11 3\",\"pages\":\"035001\"},\"PeriodicalIF\":1.9000,\"publicationDate\":\"2024-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11094643/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Medical Imaging\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1117/1.JMI.11.3.035001\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/5/15 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q3\",\"JCRName\":\"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Medical Imaging","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1117/1.JMI.11.3.035001","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/5/15 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0
摘要
目的:在实时 X 射线图像采集中准确检测和跟踪导引导管等装置是进行血管内心脏介入治疗的必要前提。这些信息可用于手术指导,如引导支架植入。为确保手术的安全性和有效性,需要在跟踪过程中实现高稳健性/无故障。为此,我们需要有效地应对各种挑战,如造影剂或其他外部设备或导线对设备的遮挡、视场或采集角度的变化,以及心脏和呼吸运动引起的持续移动:为了克服上述挑战,我们提出了一种方法,利用图像序列数据的自我监督,从超过 1600 万个介入 X 光帧的超大数据群中学习时空特征。我们的方法基于掩蔽图像建模技术,该技术利用基于帧插值的重建来学习帧间的精细时空对应关系。结果:与超优化参考解决方案(使用多阶段特征融合或多任务和流正则化)相比,我们的方法达到了最先进的性能,特别是在鲁棒性方面。实验表明,我们的方法与参考方案相比,最大跟踪误差减少了 66.31%(使用流正则化时减少了 23.20%),在每秒 42 帧(GPU)的推理速度提高 3 倍的情况下,成功率达到 97.95%。此外,我们还将误差标准差降低了 20%,这表明跟踪性能更加稳定:结论:与常用的多模块设备跟踪方法相比,所提出的数据驱动方法性能优越,尤其是在鲁棒性和速度方面。这些结果鼓励将我们的方法用于介入图像分析中需要有效理解时空语义的其他各种任务。
Self-supervised learning for interventional image analytics: toward robust device trackers.
Purpose: The accurate detection and tracking of devices, such as guiding catheters in live X-ray image acquisitions, are essential prerequisites for endovascular cardiac interventions. This information is leveraged for procedural guidance, e.g., directing stent placements. To ensure procedural safety and efficacy, there is a need for high robustness/no failures during tracking. To achieve this, one needs to efficiently tackle challenges, such as device obscuration by the contrast agent or other external devices or wires and changes in the field-of-view or acquisition angle, as well as the continuous movement due to cardiac and respiratory motion.
Approach: To overcome the aforementioned challenges, we propose an approach to learn spatio-temporal features from a very large data cohort of over 16 million interventional X-ray frames using self-supervision for image sequence data. Our approach is based on a masked image modeling technique that leverages frame interpolation-based reconstruction to learn fine inter-frame temporal correspondences. The features encoded in the resulting model are fine-tuned downstream in a light-weight model.
Results: Our approach achieves state-of-the-art performance, in particular for robustness, compared to ultra optimized reference solutions (that use multi-stage feature fusion or multi-task and flow regularization). The experiments show that our method achieves a 66.31% reduction in the maximum tracking error against the reference solutions (23.20% when flow regularization is used), achieving a success score of 97.95% at a faster inference speed of 42 frames-per-second (on GPU). In addition, we achieve a 20% reduction in the standard deviation of errors, which indicates a much more stable tracking performance.
Conclusions: The proposed data-driven approach achieves superior performance, particularly in robustness and speed compared with the frequently used multi-modular approaches for device tracking. The results encourage the use of our approach in various other tasks within interventional image analytics that require effective understanding of spatio-temporal semantics.
期刊介绍:
JMI covers fundamental and translational research, as well as applications, focused on medical imaging, which continue to yield physical and biomedical advancements in the early detection, diagnostics, and therapy of disease as well as in the understanding of normal. The scope of JMI includes: Imaging physics, Tomographic reconstruction algorithms (such as those in CT and MRI), Image processing and deep learning, Computer-aided diagnosis and quantitative image analysis, Visualization and modeling, Picture archiving and communications systems (PACS), Image perception and observer performance, Technology assessment, Ultrasonic imaging, Image-guided procedures, Digital pathology, Biomedical applications of biomedical imaging. JMI allows for the peer-reviewed communication and archiving of scientific developments, translational and clinical applications, reviews, and recommendations for the field.