Zongyu Li, Yixuan Jia, Xiaojian Xu, Jason Hu, Jeffrey A Fessler, Yuni K Dewaraja
{"title":"更短的SPECT扫描使用自监督坐标学习合成跳过的投影视图。","authors":"Zongyu Li, Yixuan Jia, Xiaojian Xu, Jason Hu, Jeffrey A Fessler, Yuni K Dewaraja","doi":"10.1186/s40658-025-00762-3","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>This study addresses the challenge of extended SPECT imaging duration under low-count conditions, as encountered in Lu-177 SPECT imaging, by developing a self-supervised learning approach to synthesize skipped SPECT projection views, thus shortening scan times in clinical settings.</p><p><strong>Methods: </strong>We developed SpeRF, a SPECT reconstruction pipeline that integrates synthesized and measured projections, using a self-supervised coordinate-based learning framework inspired by Neural Radiance Fields (NeRF). For each single scan, SpeRF independently trains a multi-layer perceptron (MLP) to estimate skipped SPECT projection views. SpeRF was tested with various down-sampling factors (DFs = 2, 4, 8) on both Lu-177 phantom SPECT/CT measurements and clinical SPECT/CT datasets, from 11 patients undergoing [177Lu]Lu-DOTATATE and 6 patients undergoing [177Lu]Lu-PSMA-617 radiopharmaceutical therapy. Performance was evaluated both in projection space and by comparing reconstructed images using (1) all measured views (\"Full\"), (2) down-sampled measured views only (\"Partial\"), and partially measured views combined with skipped views (3) generated by linear interpolation (\"LinInt\") and (4) synthesized by our method (\"SpeRF\").</p><p><strong>Results: </strong>SpeRF projections demonstrated lower Normalized Root Mean Squared Difference (NRMSD) compared to the measured projections, than LinInt projections. Across various DFs, the NRMSD for SpeRF projections averaged 7% vs. 10% in phantom studies, 18% vs. 26% in DOTATATE patient studies, and 20% vs. 21% in PSMA-617 patient studies, compared to LinInt projections. For SPECT reconstructions, DF = 4 is recommended as the best trade-off between acquisition time and image quality. At DF = 4, in terms of Contrast-to-Noise Ratio relative to Full, SpeRF outperformed LinInt and Partial: (1) DOTATATE: 88% vs. 69% vs. 69% for lesions and 88% vs. 73% vs. 67% for kidney, (2) PSMA-617: 78% vs. 71% vs. 69% for lesions and 78% vs. 57% vs. 67% for organs, including kidneys, lacrimal glands, parotid glands, and submandibular glands. SpeRF slightly underestimated count recovery relative to Full, compared to Partial but still outperformed LinInt: (1) DOTATATE: 98% vs. 100% vs. 88% for lesions and 98% vs. 100% vs. 94% for kidney, (2) PSMA-617: 98% vs. 101% vs. 94% for lesions and 96% vs. 101% vs. 78% for organs.</p><p><strong>Conclusion: </strong>The proposed method, SpeRF, shows potential for significant reduction in acquisition time (up to a factor of 4) while maintaining quantitative accuracy in clinical SPECT protocols by allowing for the collection of fewer projections. The self-supervised nature of SpeRF, with data processed independently on each patient's projection data, eliminates the need for extensive training datasets. The reduction in acquisition time is particularly relevant for imaging under low-count conditions and for protocols that require multiple-bed positions such as whole-body imaging.</p>","PeriodicalId":11559,"journal":{"name":"EJNMMI Physics","volume":"12 1","pages":"47"},"PeriodicalIF":3.0000,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12092854/pdf/","citationCount":"0","resultStr":"{\"title\":\"Shorter SPECT scans using self-supervised coordinate learning to synthesize skipped projection views.\",\"authors\":\"Zongyu Li, Yixuan Jia, Xiaojian Xu, Jason Hu, Jeffrey A Fessler, Yuni K Dewaraja\",\"doi\":\"10.1186/s40658-025-00762-3\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Purpose: </strong>This study addresses the challenge of extended SPECT imaging duration under low-count conditions, as encountered in Lu-177 SPECT imaging, by developing a self-supervised learning approach to synthesize skipped SPECT projection views, thus shortening scan times in clinical settings.</p><p><strong>Methods: </strong>We developed SpeRF, a SPECT reconstruction pipeline that integrates synthesized and measured projections, using a self-supervised coordinate-based learning framework inspired by Neural Radiance Fields (NeRF). For each single scan, SpeRF independently trains a multi-layer perceptron (MLP) to estimate skipped SPECT projection views. SpeRF was tested with various down-sampling factors (DFs = 2, 4, 8) on both Lu-177 phantom SPECT/CT measurements and clinical SPECT/CT datasets, from 11 patients undergoing [177Lu]Lu-DOTATATE and 6 patients undergoing [177Lu]Lu-PSMA-617 radiopharmaceutical therapy. Performance was evaluated both in projection space and by comparing reconstructed images using (1) all measured views (\\\"Full\\\"), (2) down-sampled measured views only (\\\"Partial\\\"), and partially measured views combined with skipped views (3) generated by linear interpolation (\\\"LinInt\\\") and (4) synthesized by our method (\\\"SpeRF\\\").</p><p><strong>Results: </strong>SpeRF projections demonstrated lower Normalized Root Mean Squared Difference (NRMSD) compared to the measured projections, than LinInt projections. Across various DFs, the NRMSD for SpeRF projections averaged 7% vs. 10% in phantom studies, 18% vs. 26% in DOTATATE patient studies, and 20% vs. 21% in PSMA-617 patient studies, compared to LinInt projections. For SPECT reconstructions, DF = 4 is recommended as the best trade-off between acquisition time and image quality. At DF = 4, in terms of Contrast-to-Noise Ratio relative to Full, SpeRF outperformed LinInt and Partial: (1) DOTATATE: 88% vs. 69% vs. 69% for lesions and 88% vs. 73% vs. 67% for kidney, (2) PSMA-617: 78% vs. 71% vs. 69% for lesions and 78% vs. 57% vs. 67% for organs, including kidneys, lacrimal glands, parotid glands, and submandibular glands. SpeRF slightly underestimated count recovery relative to Full, compared to Partial but still outperformed LinInt: (1) DOTATATE: 98% vs. 100% vs. 88% for lesions and 98% vs. 100% vs. 94% for kidney, (2) PSMA-617: 98% vs. 101% vs. 94% for lesions and 96% vs. 101% vs. 78% for organs.</p><p><strong>Conclusion: </strong>The proposed method, SpeRF, shows potential for significant reduction in acquisition time (up to a factor of 4) while maintaining quantitative accuracy in clinical SPECT protocols by allowing for the collection of fewer projections. The self-supervised nature of SpeRF, with data processed independently on each patient's projection data, eliminates the need for extensive training datasets. The reduction in acquisition time is particularly relevant for imaging under low-count conditions and for protocols that require multiple-bed positions such as whole-body imaging.</p>\",\"PeriodicalId\":11559,\"journal\":{\"name\":\"EJNMMI Physics\",\"volume\":\"12 1\",\"pages\":\"47\"},\"PeriodicalIF\":3.0000,\"publicationDate\":\"2025-05-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12092854/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"EJNMMI Physics\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1186/s40658-025-00762-3\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"EJNMMI Physics","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s40658-025-00762-3","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0
摘要
目的:本研究通过开发一种自我监督学习方法来合成跳过的SPECT投影视图,从而缩短临床扫描时间,解决了在低计数条件下延长SPECT成像时间的挑战,如在Lu-177 SPECT成像中遇到的问题。方法:我们开发了SpeRF,这是一个集成了合成和测量投影的SPECT重建管道,使用受神经辐射场(NeRF)启发的基于自监督坐标的学习框架。对于每次扫描,SpeRF独立训练一个多层感知器(MLP)来估计跳过的SPECT投影视图。对11名接受[177Lu]Lu-DOTATATE治疗的患者和6名接受[177Lu]Lu-PSMA-617放射药物治疗的患者的Lu-177幻影SPECT/CT测量数据和临床SPECT/CT数据集进行了SpeRF的各种降采样因子(DFs = 2、4、8)测试。在投影空间中,通过比较(1)所有测量视图(“完整”)、(2)仅下采样测量视图(“部分”)和部分测量视图结合跳过视图(3)由线性插值生成(“LinInt”)和(4)由我们的方法合成(“SpeRF”)的重建图像来评估性能。结果:与测量结果相比,SpeRF预测显示出较低的归一化均方根差(NRMSD)。在各种df中,与LinInt预测相比,SpeRF预测的NRMSD在幻影研究中平均为7%对10%,在DOTATATE患者研究中为18%对26%,在PSMA-617患者研究中为20%对21%。对于SPECT重建,推荐DF = 4作为采集时间和图像质量之间的最佳折衷。在DF = 4时,就相对于Full的对比噪声比而言,SpeRF优于LinInt和Partial:(1) DOTATATE:病变88% vs. 69% vs.肾脏88% vs. 73% vs. 67%, (2) PSMA-617:病变78% vs. 71% vs. 69%,器官78% vs. 57% vs. 67%,包括肾脏、泪腺、腮腺和下颌下腺。SpeRF与Full相比略微低估了计数恢复,但仍然优于LinInt:(1) DOTATATE:病变98% vs 100% vs 88%,肾脏98% vs 100% vs 94%, (2) PSMA-617:病变98% vs 101% vs 94%,器官96% vs 101% vs 78%。结论:提出的方法,SpeRF,显示出显著减少采集时间(高达4倍)的潜力,同时通过允许收集更少的投影,保持临床SPECT方案的定量准确性。SpeRF的自我监督性质,对每个患者的投影数据进行独立处理,消除了对大量训练数据集的需要。减少采集时间对于低计数条件下的成像和需要多床位置(如全身成像)的方案尤其重要。
Shorter SPECT scans using self-supervised coordinate learning to synthesize skipped projection views.
Purpose: This study addresses the challenge of extended SPECT imaging duration under low-count conditions, as encountered in Lu-177 SPECT imaging, by developing a self-supervised learning approach to synthesize skipped SPECT projection views, thus shortening scan times in clinical settings.
Methods: We developed SpeRF, a SPECT reconstruction pipeline that integrates synthesized and measured projections, using a self-supervised coordinate-based learning framework inspired by Neural Radiance Fields (NeRF). For each single scan, SpeRF independently trains a multi-layer perceptron (MLP) to estimate skipped SPECT projection views. SpeRF was tested with various down-sampling factors (DFs = 2, 4, 8) on both Lu-177 phantom SPECT/CT measurements and clinical SPECT/CT datasets, from 11 patients undergoing [177Lu]Lu-DOTATATE and 6 patients undergoing [177Lu]Lu-PSMA-617 radiopharmaceutical therapy. Performance was evaluated both in projection space and by comparing reconstructed images using (1) all measured views ("Full"), (2) down-sampled measured views only ("Partial"), and partially measured views combined with skipped views (3) generated by linear interpolation ("LinInt") and (4) synthesized by our method ("SpeRF").
Results: SpeRF projections demonstrated lower Normalized Root Mean Squared Difference (NRMSD) compared to the measured projections, than LinInt projections. Across various DFs, the NRMSD for SpeRF projections averaged 7% vs. 10% in phantom studies, 18% vs. 26% in DOTATATE patient studies, and 20% vs. 21% in PSMA-617 patient studies, compared to LinInt projections. For SPECT reconstructions, DF = 4 is recommended as the best trade-off between acquisition time and image quality. At DF = 4, in terms of Contrast-to-Noise Ratio relative to Full, SpeRF outperformed LinInt and Partial: (1) DOTATATE: 88% vs. 69% vs. 69% for lesions and 88% vs. 73% vs. 67% for kidney, (2) PSMA-617: 78% vs. 71% vs. 69% for lesions and 78% vs. 57% vs. 67% for organs, including kidneys, lacrimal glands, parotid glands, and submandibular glands. SpeRF slightly underestimated count recovery relative to Full, compared to Partial but still outperformed LinInt: (1) DOTATATE: 98% vs. 100% vs. 88% for lesions and 98% vs. 100% vs. 94% for kidney, (2) PSMA-617: 98% vs. 101% vs. 94% for lesions and 96% vs. 101% vs. 78% for organs.
Conclusion: The proposed method, SpeRF, shows potential for significant reduction in acquisition time (up to a factor of 4) while maintaining quantitative accuracy in clinical SPECT protocols by allowing for the collection of fewer projections. The self-supervised nature of SpeRF, with data processed independently on each patient's projection data, eliminates the need for extensive training datasets. The reduction in acquisition time is particularly relevant for imaging under low-count conditions and for protocols that require multiple-bed positions such as whole-body imaging.
期刊介绍:
EJNMMI Physics is an international platform for scientists, users and adopters of nuclear medicine with a particular interest in physics matters. As a companion journal to the European Journal of Nuclear Medicine and Molecular Imaging, this journal has a multi-disciplinary approach and welcomes original materials and studies with a focus on applied physics and mathematics as well as imaging systems engineering and prototyping in nuclear medicine. This includes physics-driven approaches or algorithms supported by physics that foster early clinical adoption of nuclear medicine imaging and therapy.