{"title":"比较深度学习方法在 PET/CT 和 PET/MRI 图像中检测病灶的准确性。","authors":"Lifang Pang, Zheng Zhang, Guobing Liu, Pengcheng Hu, Shuguang Chen, Yushen Gu, Yukun Huang, Jia Zhang, Yuhang Shi, Tuoyu Cao, Yiqiu Zhang, Hongcheng Shi","doi":"10.1007/s11307-024-01943-9","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>Develop a universal lesion recognition algorithm for PET/CT and PET/MRI, validate it, and explore factors affecting performance.</p><p><strong>Procedures: </strong>The 2022 AutoPet Challenge's 1014 PET/CT dataset was used to train the lesion detection model based on 2D and 3D fractional-residual (F-Res) models. To extend this to PET/MRI, a network for converting MR images to synthetic CT (sCT) was developed, using 41 sets of whole-body MR and corresponding CT data. 38 patients' PET/CT and PET/MRI data were used to verify the universal lesion recognition algorithm. Image quality was assessed using signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). Total lesion glycolysis (TLG), metabolic tumor volume (MTV), and lesion count were calculated from the resultant lesion masks. Experienced physicians reviewed and corrected the model's outputs, establishing the ground truth. The performance of the lesion detection deep-learning model on different PET images was assessed by detection accuracy, precision, recall, and dice coefficients. Data with a detection accuracy score (DAS) less than 1 was used for analysis of outliers.</p><p><strong>Results: </strong>Compared to PET/CT, PET/MRI scans had a significantly longer delay time (135 ± 45 min vs 61 ± 12 min) and lower SNR (6.17 ± 1.11 vs 9.27 ± 2.77). However, CNR values were similar (7.37 ± 5.40 vs 5.86 ± 6.69). PET/MRI detected more lesions (with a mean difference of -3.184). TLG and MTV showed no significant differences between PET/CT and PET/MRI (TLG: 119.18 ± 203.15 vs 123.57 ± 151.58, p = 0.41; MTV: 36.58 ± 57.00 vs 39.16 ± 48.34, p = 0.33). A total of 12 PET/CT and 14 PET/MRI datasets were included in the analysis of outliers. Outlier analysis revealed PET/CT anomalies in intestines, ureters, and muscles, while PET/MRI anomalies were in intestines, testicles, and low tracer uptake regions, with false positives in ureters (PET/CT) and intestines/testicles (PET/MRI).</p><p><strong>Conclusion: </strong>The deep learning lesion detection model performs well with both PET/CT and PET/MRI. SNR, CNR and reconstruction parameters minimally impact recognition accuracy, but delay time post-injection is significant.</p>","PeriodicalId":18760,"journal":{"name":"Molecular Imaging and Biology","volume":" ","pages":"802-811"},"PeriodicalIF":3.0000,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Comparison of the Accuracy of a Deep Learning Method for Lesion Detection in PET/CT and PET/MRI Images.\",\"authors\":\"Lifang Pang, Zheng Zhang, Guobing Liu, Pengcheng Hu, Shuguang Chen, Yushen Gu, Yukun Huang, Jia Zhang, Yuhang Shi, Tuoyu Cao, Yiqiu Zhang, Hongcheng Shi\",\"doi\":\"10.1007/s11307-024-01943-9\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Purpose: </strong>Develop a universal lesion recognition algorithm for PET/CT and PET/MRI, validate it, and explore factors affecting performance.</p><p><strong>Procedures: </strong>The 2022 AutoPet Challenge's 1014 PET/CT dataset was used to train the lesion detection model based on 2D and 3D fractional-residual (F-Res) models. To extend this to PET/MRI, a network for converting MR images to synthetic CT (sCT) was developed, using 41 sets of whole-body MR and corresponding CT data. 38 patients' PET/CT and PET/MRI data were used to verify the universal lesion recognition algorithm. Image quality was assessed using signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). Total lesion glycolysis (TLG), metabolic tumor volume (MTV), and lesion count were calculated from the resultant lesion masks. Experienced physicians reviewed and corrected the model's outputs, establishing the ground truth. The performance of the lesion detection deep-learning model on different PET images was assessed by detection accuracy, precision, recall, and dice coefficients. Data with a detection accuracy score (DAS) less than 1 was used for analysis of outliers.</p><p><strong>Results: </strong>Compared to PET/CT, PET/MRI scans had a significantly longer delay time (135 ± 45 min vs 61 ± 12 min) and lower SNR (6.17 ± 1.11 vs 9.27 ± 2.77). However, CNR values were similar (7.37 ± 5.40 vs 5.86 ± 6.69). PET/MRI detected more lesions (with a mean difference of -3.184). TLG and MTV showed no significant differences between PET/CT and PET/MRI (TLG: 119.18 ± 203.15 vs 123.57 ± 151.58, p = 0.41; MTV: 36.58 ± 57.00 vs 39.16 ± 48.34, p = 0.33). A total of 12 PET/CT and 14 PET/MRI datasets were included in the analysis of outliers. Outlier analysis revealed PET/CT anomalies in intestines, ureters, and muscles, while PET/MRI anomalies were in intestines, testicles, and low tracer uptake regions, with false positives in ureters (PET/CT) and intestines/testicles (PET/MRI).</p><p><strong>Conclusion: </strong>The deep learning lesion detection model performs well with both PET/CT and PET/MRI. SNR, CNR and reconstruction parameters minimally impact recognition accuracy, but delay time post-injection is significant.</p>\",\"PeriodicalId\":18760,\"journal\":{\"name\":\"Molecular Imaging and Biology\",\"volume\":\" \",\"pages\":\"802-811\"},\"PeriodicalIF\":3.0000,\"publicationDate\":\"2024-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Molecular Imaging and Biology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1007/s11307-024-01943-9\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/8/14 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q2\",\"JCRName\":\"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Molecular Imaging and Biology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s11307-024-01943-9","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/8/14 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
Comparison of the Accuracy of a Deep Learning Method for Lesion Detection in PET/CT and PET/MRI Images.
Purpose: Develop a universal lesion recognition algorithm for PET/CT and PET/MRI, validate it, and explore factors affecting performance.
Procedures: The 2022 AutoPet Challenge's 1014 PET/CT dataset was used to train the lesion detection model based on 2D and 3D fractional-residual (F-Res) models. To extend this to PET/MRI, a network for converting MR images to synthetic CT (sCT) was developed, using 41 sets of whole-body MR and corresponding CT data. 38 patients' PET/CT and PET/MRI data were used to verify the universal lesion recognition algorithm. Image quality was assessed using signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). Total lesion glycolysis (TLG), metabolic tumor volume (MTV), and lesion count were calculated from the resultant lesion masks. Experienced physicians reviewed and corrected the model's outputs, establishing the ground truth. The performance of the lesion detection deep-learning model on different PET images was assessed by detection accuracy, precision, recall, and dice coefficients. Data with a detection accuracy score (DAS) less than 1 was used for analysis of outliers.
Results: Compared to PET/CT, PET/MRI scans had a significantly longer delay time (135 ± 45 min vs 61 ± 12 min) and lower SNR (6.17 ± 1.11 vs 9.27 ± 2.77). However, CNR values were similar (7.37 ± 5.40 vs 5.86 ± 6.69). PET/MRI detected more lesions (with a mean difference of -3.184). TLG and MTV showed no significant differences between PET/CT and PET/MRI (TLG: 119.18 ± 203.15 vs 123.57 ± 151.58, p = 0.41; MTV: 36.58 ± 57.00 vs 39.16 ± 48.34, p = 0.33). A total of 12 PET/CT and 14 PET/MRI datasets were included in the analysis of outliers. Outlier analysis revealed PET/CT anomalies in intestines, ureters, and muscles, while PET/MRI anomalies were in intestines, testicles, and low tracer uptake regions, with false positives in ureters (PET/CT) and intestines/testicles (PET/MRI).
Conclusion: The deep learning lesion detection model performs well with both PET/CT and PET/MRI. SNR, CNR and reconstruction parameters minimally impact recognition accuracy, but delay time post-injection is significant.
期刊介绍：
Molecular Imaging and Biology (MIB) invites original contributions (research articles, review articles, commentaries, etc.) on the utilization of molecular imaging (i.e., nuclear imaging, optical imaging, autoradiography and pathology, MRI, MPI, ultrasound imaging, radiomics/genomics etc.) to investigate questions related to biology and health. The objective of MIB is to provide a forum to the discovery of molecular mechanisms of disease through the use of imaging techniques. We aim to investigate the biological nature of disease in patients and establish new molecular imaging diagnostic and therapy procedures.
Some areas that are covered are:
Preclinical and clinical imaging of macromolecular targets (e.g., genes, receptors, enzymes) involved in significant biological processes.
The design, characterization, and study of new molecular imaging probes and contrast agents for the functional interrogation of macromolecular targets.
Development and evaluation of imaging systems including instrumentation, image reconstruction algorithms, image analysis, and display.
Development of molecular assay approaches leading to quantification of the biological information obtained in molecular imaging.
Study of in vivo animal models of disease for the development of new molecular diagnostics and therapeutics.
Extension of in vitro and in vivo discoveries using disease models, into well designed clinical research investigations.
Clinical molecular imaging involving clinical investigations, clinical trials and medical management or cost-effectiveness studies.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
