Parisa Salemi YolgunluUniversity of Bern, Jules BlomUniversity of Twente, Naiara Korta MartiartuUniversity of Bern, Michael JaegerUniversity of Bern
{"title":"脉冲回波声速定量成像的学习正则化","authors":"Parisa Salemi YolgunluUniversity of Bern, Jules BlomUniversity of Twente, Naiara Korta MartiartuUniversity of Bern, Michael JaegerUniversity of Bern","doi":"arxiv-2408.11471","DOIUrl":null,"url":null,"abstract":"Computed ultrasound tomography in echo mode generates maps of tissue speed of\nsound (SoS) from the shift of echoes when detected under varying steering\nangles. It solves a linearized inverse problem that requires regularization to\ncomplement the echo shift data with a priori constraints. Spatial gradient\nregularization has been used to enforce smooth solutions, but SoS estimates\nwere found to be biased depending on tissue layer geometry. Here, we propose to\ntrain a linear operator to minimize SoS errors on average over a large number\nof random tissue models that sample the distribution of geometries and SoS\nvalues expected in vivo. In an extensive simulation study on liver imaging, we\ndemonstrate that biases are strongly reduced, with residual biases being the\nresult of a partial non-linearity in the actual physical problem. This approach\ncan either be applied directly to echo-shift data or to the SoS maps estimated\nwith gradient regularization, where the former shows slightly better\nperformance, but the latter is computationally more efficient. Experimental\nphantom results confirm the transferability of our results to real ultrasound\ndata.","PeriodicalId":501378,"journal":{"name":"arXiv - PHYS - Medical Physics","volume":"59 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Learned Regularization for Quantitative Pulse-Echo Speed-of-Sound Imaging\",\"authors\":\"Parisa Salemi YolgunluUniversity of Bern, Jules BlomUniversity of Twente, Naiara Korta MartiartuUniversity of Bern, Michael JaegerUniversity of Bern\",\"doi\":\"arxiv-2408.11471\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Computed ultrasound tomography in echo mode generates maps of tissue speed of\\nsound (SoS) from the shift of echoes when detected under varying steering\\nangles. It solves a linearized inverse problem that requires regularization to\\ncomplement the echo shift data with a priori constraints. Spatial gradient\\nregularization has been used to enforce smooth solutions, but SoS estimates\\nwere found to be biased depending on tissue layer geometry. Here, we propose to\\ntrain a linear operator to minimize SoS errors on average over a large number\\nof random tissue models that sample the distribution of geometries and SoS\\nvalues expected in vivo. In an extensive simulation study on liver imaging, we\\ndemonstrate that biases are strongly reduced, with residual biases being the\\nresult of a partial non-linearity in the actual physical problem. This approach\\ncan either be applied directly to echo-shift data or to the SoS maps estimated\\nwith gradient regularization, where the former shows slightly better\\nperformance, but the latter is computationally more efficient. Experimental\\nphantom results confirm the transferability of our results to real ultrasound\\ndata.\",\"PeriodicalId\":501378,\"journal\":{\"name\":\"arXiv - PHYS - Medical Physics\",\"volume\":\"59 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Medical Physics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2408.11471\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Medical Physics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.11471","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
在回波模式下,超声计算机断层扫描可根据在不同转向角下检测到的回波位移生成组织声速(SoS)图。它解决的是一个线性化的逆问题,需要通过正则化将回波位移数据与先验约束条件相结合。空间梯度正则化已被用于执行平滑解,但 SoS 估计值会因组织层的几何形状而产生偏差。在此,我们建议训练一个线性算子,以平均最小化大量随机组织模型的 SoS 误差,这些组织模型采样了体内预期的几何分布和 SoS 值。在对肝脏成像进行的大量模拟研究中,我们证明偏差已大大减少,残余偏差是实际物理问题中部分非线性的结果。这种方法既可以直接应用于回波平移数据,也可以应用于梯度正则化估算的 SoS 地图,前者的性能略好,但后者的计算效率更高。实验结果证实了我们的方法可以应用于真实的超声数据。
Learned Regularization for Quantitative Pulse-Echo Speed-of-Sound Imaging
Computed ultrasound tomography in echo mode generates maps of tissue speed of
sound (SoS) from the shift of echoes when detected under varying steering
angles. It solves a linearized inverse problem that requires regularization to
complement the echo shift data with a priori constraints. Spatial gradient
regularization has been used to enforce smooth solutions, but SoS estimates
were found to be biased depending on tissue layer geometry. Here, we propose to
train a linear operator to minimize SoS errors on average over a large number
of random tissue models that sample the distribution of geometries and SoS
values expected in vivo. In an extensive simulation study on liver imaging, we
demonstrate that biases are strongly reduced, with residual biases being the
result of a partial non-linearity in the actual physical problem. This approach
can either be applied directly to echo-shift data or to the SoS maps estimated
with gradient regularization, where the former shows slightly better
performance, but the latter is computationally more efficient. Experimental
phantom results confirm the transferability of our results to real ultrasound
data.