Xuejun Wen, Tianzhi Zhao, Hongzhang Yang, Mengqi Shi, Xin Jie Wee, Jiayu Fu, Min Lin, Zhenyue Zhang, Maosheng Zou, David Green, Xiaoming Wu, Xiaoyuan Chen, Jingjing Zhang
{"title":"Development of [225Ac]Ac‑LNC1011 for targeted alpha-radionuclide therapy of prostate cancer","authors":"Xuejun Wen, Tianzhi Zhao, Hongzhang Yang, Mengqi Shi, Xin Jie Wee, Jiayu Fu, Min Lin, Zhenyue Zhang, Maosheng Zou, David Green, Xiaoming Wu, Xiaoyuan Chen, Jingjing Zhang","doi":"10.1007/s00259-025-07155-9","DOIUrl":"https://doi.org/10.1007/s00259-025-07155-9","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Purpose</h3><p>Prostate-specific membrane antigen (PSMA) radioligand therapy (PRLT) has become a promising option for treating metastatic castration-resistant prostate cancer (mCRPC). Radioligands labelled with the <sup>68</sup>Ga/<sup>177</sup>Lu theranostic pair have been most widely used in the clinic for diagnosis and therapy, respectively. This study aims to develop a novel PSMA-targeted radioligand, LNC1011, radiolabeled with alpha-emitter <sup>225</sup>Ac, to optimise pharmacokinetic properties and assess its potential for targeted alpha therapy (TAT) in prostate cancer treatment.</p><h3 data-test=\"abstract-sub-heading\">Methods</h3><p>LNC1011 (Dan-PSMA) was synthesised based on a PSMA-binding ligand with the addition of a dansylated amino acid. Systematic radiochemical analyses were conducted to confirm the successful synthesis and radiolabelling of [<sup>225</sup>Ac]Ac-LNC1011. Cell uptake and competition binding assays were performed in PSMA-positive PC3-PIP tumour cells to evaluate the binding affinity and PSMA targeting specificity. The pharmacokinetics properties and tumour uptake were characterised by biodistribution studies using healthy mice and a PC3-PIP xenograft mouse model injected with [<sup>225</sup>Ac]Ac-LNC1011. Radioligand therapy studies and maximum tolerated dose (MTD) assays were conducted to systematically evaluate the therapeutic efficacy and the safety of [<sup>225</sup>Ac]Ac-LNC1011.</p><h3 data-test=\"abstract-sub-heading\">Results</h3><p>[<sup>225</sup>Ac]Ac-LNC1011 was successfully radiolabelled with high radiochemical purity (> 97%) and high stability within 96 h (radiochemical purity > 96%). The high binding affinity of LNC1011 (IC<sub>50</sub> = 16.28 nM) to PSMA was comparable to that of PSMA-617 (IC<sub>50</sub> = 27.93 nM). Biodistribution studies confirmed that <b>[</b><sup>225</sup>Ac]Ac-LNC1011 had moderate blood elimination half-life (T<sub>1/2z</sub> = 13.4 ± 0.57 h), which was at an optimised level between [<sup>225</sup>Ac]Ac-PSMA-617 (T<sub>1/2z</sub> = 5.19 ± 0.12 h) and [<sup>225</sup>Ac]Ac-PSMA-EB-01 (T<sub>1/2z</sub> = 25.18 ± 2.78 h). In addition, high tumour uptake of [<sup>225</sup>Ac]Ac-LNC1011 was identified to be 38.28 ± 10.04%ID/g at 1 h post-injection. The specific uptake gradually increased and peaked at 24 h (80.57 ± 3.00%ID/g) and persisted at a high level up to 72 h post-injection (50.58 ± 5.37%ID/g). Targeted alpha therapy results showed the complete inhibition of PC3-PIP tumour growth after administration of a single dose of 1 µCi and 0.5 µCi of [<sup>225</sup>Ac]Ac-LNC1011 similar to 0.5 µCi [<sup>225</sup>Ac]Ac-PSMA-617. At the 0.1 µCi dose level, partial remission was observed for [<sup>225</sup>Ac]Ac-LNC1011, as recurrence was found 20 days after administration. In contrast, mice treated with 0.1 µCi [<sup>225</sup>Ac]Ac-PSMA-617 showed incomplete tumour inhibition under the same conditions.</p><h3 data-test=\"abstract-sub-heading\">Conclu","PeriodicalId":11909,"journal":{"name":"European Journal of Nuclear Medicine and Molecular Imaging","volume":"56 1","pages":""},"PeriodicalIF":9.1,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143477473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Christos Sachpekidis, Olof Enqvist, Johannes Ulén, Annette Kopp‑Schneider, Leyun Pan, Elias K. Mai, Marina Hajiyianni, Maximilian Merz, Marc S. Raab, Anna Jauch, Hartmut Goldschmidt, Lars Edenbrandt, Antonia Dimitrakopoulou‑Strauss
{"title":"Correction to: Artificial intelligence–based, volumetric assessment of the bone marrow metabolic activity in [18F]FDG PET/CT predicts survival in multiple myeloma","authors":"Christos Sachpekidis, Olof Enqvist, Johannes Ulén, Annette Kopp‑Schneider, Leyun Pan, Elias K. Mai, Marina Hajiyianni, Maximilian Merz, Marc S. Raab, Anna Jauch, Hartmut Goldschmidt, Lars Edenbrandt, Antonia Dimitrakopoulou‑Strauss","doi":"10.1007/s00259-025-07158-6","DOIUrl":"https://doi.org/10.1007/s00259-025-07158-6","url":null,"abstract":"","PeriodicalId":11909,"journal":{"name":"European Journal of Nuclear Medicine and Molecular Imaging","volume":"23 1","pages":""},"PeriodicalIF":9.1,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143470662","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Solène Malmon, Olivier Casasnovas, Marguerite Fournier, Guillaume Cartron, Salim Kanoun, Anne Ségolène Cottereau, Charles Herbaux, Yassine Al Tabaa
{"title":"Personalized baseline and residual TMTV influence treatment response and outcomes in relapsed/refractory lymphomas: results from the GATA study","authors":"Solène Malmon, Olivier Casasnovas, Marguerite Fournier, Guillaume Cartron, Salim Kanoun, Anne Ségolène Cottereau, Charles Herbaux, Yassine Al Tabaa","doi":"10.1007/s00259-025-07154-w","DOIUrl":"https://doi.org/10.1007/s00259-025-07154-w","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Purpose</h3><p>Total metabolic tumor volume (TMTV) at baseline becomes a key biomarker in several lymphoma subtypes. Variability in segmentation methods such as 41%SUVmax and SUVmax > 4 has limited its clinical application. Additionally, immune-checkpoint-inhibitors introduced challenges in response assessment due to pseudoprogression, complicating the use of traditional metrics. This study investigates the prognostic impact of baseline- and residual-TMTV and introduces a novel personalized-liver-based-threshold (pTMTV<sub>liver</sub>) to enhance precision in patient stratification.</p><h3 data-test=\"abstract-sub-heading\">Methods</h3><p>We analyzed 91 patients with relapsed/refractory diffuse-large-B-cell lymphoma and follicular lymphoma from the GATA trial, comparing patient’s outcome according to three segmentation methods: TMTV<sub>41%</sub>, TMTV<sub>4</sub>, and pTMTV<sub>liver</sub>. pTMTV<sub>liver</sub> used a threshold of 200%SUVmean<sub>liver</sub> aligning with 125%SUVmax<sub>liver</sub> to enhance standardization and reduce variability.</p><h3 data-test=\"abstract-sub-heading\">Results</h3><p>Baseline-TMTV significantly influenced prognosis with higher TMTV correlating with shorter PFS and OS (<i>p</i> < 0.0001 for all methods). Residual-TMTV, particularly with pTMTV<sub>liver</sub> and TMTV<sub>4</sub>, stratified no-CMR patients with the lowest predictive errors and better predictive accuracy compared to TMTV<sub>41%</sub> Multivariate analyses confirmed residual-pTMTV<sub>liver</sub> as superior for prognostic performance for PFS (HR:5.10; C-index:0.724) and OS (HR:4.00; C-index:0.853) compared to TMTV<sub>4</sub> and Deauville Score (DS). The DS alone did not fully capture the heterogeneity of outcomes of DS4-5 patients.</p><h3 data-test=\"abstract-sub-heading\">Conclusion</h3><p>Baseline- and residual-TMTV strongly influence prognosis and response in lymphoma patients. The novel personalized pTMTV<sub>liver</sub> method offers improved accuracy of patient stratification, particularly for those with DS4-5, providing more reliable risk assessment. Larger cohorts are needed to validate these findings and optimize residual-TMTV-based clinical applications.</p>","PeriodicalId":11909,"journal":{"name":"European Journal of Nuclear Medicine and Molecular Imaging","volume":"17 1","pages":""},"PeriodicalIF":9.1,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143470663","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Akram Al-Ibraheem, Serin Moghrabi, Mike Machaba Sathekge, Ahmed Saad Abdlkadir
{"title":"Evaluating Xerostomia as a side effect of [255Ac]Ac-PSMA therapy in prostate cancer: a systematic review and meta-analysis","authors":"Akram Al-Ibraheem, Serin Moghrabi, Mike Machaba Sathekge, Ahmed Saad Abdlkadir","doi":"10.1007/s00259-025-07168-4","DOIUrl":"https://doi.org/10.1007/s00259-025-07168-4","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Purpose</h3><p>This systematic review and meta-analysis evaluates xerostomia occurrence in prostate cancer (PC) patients undergoing [<sup>225</sup>Ac]Ac-prostate-specific membrane antigen ([<sup>225</sup>Ac]Ac-PSMA) therapy.</p><h3 data-test=\"abstract-sub-heading\">Methods</h3><p>Following the Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols (PRISMA-P) guidelines, comprehensive electronic searches were conducted across PubMed, Scopus, and Web of Science. The study included articles addressing xerostomia as a side effect of [<sup>225</sup>Ac]Ac-PSMA therapy in clinical settings, encompassing both tandem and monotherapy strategies. Methodological quality was assessed using the National Institutes of Health (NIH) Assessment Tool. Stata software was employed to perform pooled xerostomia rates, heterogeneity analysis, meta-regression, and publication bias analysis.</p><h3 data-test=\"abstract-sub-heading\">Results</h3><p>Twenty studies met inclusion criteria, comprising 2949 [<sup>225</sup>Ac]Ac-PSMA cycles administered to 1207 PC patients. For [<sup>225</sup>Ac]Ac-PSMA monotherapy, the pooled rate of any-grade xerostomia was 84% (95%CI: 69–94%). Grade 1–2 xerostomia had a pooled rate 83% (95%CI: 71–93%), while therapy discontinuation due to xerostomia was 5% (95%CI: 0–13%). Grade 3 xerostomia was evident in 13% (95%CI: 7–20%). [<sup>225</sup>Ac]Ac/[<sup>177</sup>Lu]Lu-PSMA tandem therapy resulted in lower pooled rate of 68% for grade 1–2 toxicity (95%CI: 17–100%). Indirect comparison revealed a two-fold decrease in xerostomia risk with tandem protocol compared to monotherapy. Significant heterogeneity was observed, primarily influenced by baseline median prostate-specific antigen values (<i>p</i> = 0.04). Publication bias was present in most xerostomia subgroups, with trim-and-fill analysis adjusting for effect size in specific categories.</p><h3 data-test=\"abstract-sub-heading\">Conclusion</h3><p>Xerostomia is most pronounced in patients undergoing [<sup>225</sup>Ac]Ac-PSMA monotherapy. Tandem approach with [<sup>177</sup>Lu]Lu-PSMA could reduce xerostomia rates and improve compliance. Further large-scale, prospective studies are necessary for generalization and result consolidation.</p>","PeriodicalId":11909,"journal":{"name":"European Journal of Nuclear Medicine and Molecular Imaging","volume":"82 2 1","pages":""},"PeriodicalIF":9.1,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143470661","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wei Tang, Ming Zhou, Chenxi Lu, Lin Qi, Ye Zhang, Yongxiang Tang, Xiaomei Gao, Shuo Hu, Yi Cai
{"title":"CD13 as a potential theranostic target for prostate-specific membrane antigen-negative prostate cancer and first-in-human study of [18F]AlF-CD13-L1 PET/CT imaging","authors":"Wei Tang, Ming Zhou, Chenxi Lu, Lin Qi, Ye Zhang, Yongxiang Tang, Xiaomei Gao, Shuo Hu, Yi Cai","doi":"10.1007/s00259-025-07140-2","DOIUrl":"https://doi.org/10.1007/s00259-025-07140-2","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Purpose</h3><p>Approximately 10% of prostate cancer (PCa) are prostate-specific membrane antigen (PSMA)-negative, leading to blind spots in PSMA-based diagnosis. This study aimed to identify a potential target for PSMA-negative PCa and preliminarily evaluate the feasibility of using radionuclide probe targeting the identified target for PCa diagnosis.</p><h3 data-test=\"abstract-sub-heading\">Methods</h3><p>Quantitative protein analysis was performed on eight PSMA-negative PCa and eleven controls to identify a potential molecular target, followed by validation with an expanded cohort using immunohistochemistry. Sixteen participants underwent [<sup>18</sup>F]AlF-CD13-L1 PET/CT scanning, with the PCa pathological tissues used as references to interpret the imaging results.</p><h3 data-test=\"abstract-sub-heading\">Results</h3><p>Quantitative protein analysis revealed CD13 as the most significantly upregulated membrane protein in PSMA-negative PCa. Expanded validation results indicated that CD13 positivity rates were 92.9% (13/14), 82.7% (105/127), 91.7% (11/12), and 70% (14/20) in PSMA-negative PCa, PSMA-positive PCa, ductal adenocarcinoma of the prostate (DAC), and intraductal carcinoma of the prostate (IDC-P), respectively. In PCa participants, the median [<sup>18</sup>F]AlF-CD13-L1 PET/CT maximum standardized uptake value (SUVmax) of tumors and tumor-to-muscle ratio were 4.3 (1.5–5.8) and 4.6 (1.7–6.1), respectively. The SUVmax value of the PCa lesions and the tumor-to-muscle ratio showed a positive correlation with the immunohistochemical score of CD13 of the PCa lesions (r<sub>spearman</sub> = 0.6249, p = 0.025; r<sub>spearman</sub> = 0.6714, <i>p</i> = 0.015, respectively), with CD13-positive tumors showing significant radiotracer accumulation.</p><h3 data-test=\"abstract-sub-heading\">Conclusion</h3><p>CD13 was a potential target for PSMA-negative PCa and also showed high positivity rates in PSMA-positive PCa, DAC, and IDC-P. [<sup>18</sup>F]AlF-CD13-L1 selectively accumulated in CD13-positive PCa, enabling visualization. (Trial registration: ChiCTR2300077817. Registered November 21, 2023).</p>","PeriodicalId":11909,"journal":{"name":"European Journal of Nuclear Medicine and Molecular Imaging","volume":"28 1","pages":""},"PeriodicalIF":9.1,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143470644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Petra Petranović Ovčariček, Alfredo Campennì, Luca Giovanella, Martin W. Huellner
{"title":"Parathyroid carcinoma: a comprehensive analysis with focus on molecular imaging","authors":"Petra Petranović Ovčariček, Alfredo Campennì, Luca Giovanella, Martin W. Huellner","doi":"10.1007/s00259-025-07162-w","DOIUrl":"https://doi.org/10.1007/s00259-025-07162-w","url":null,"abstract":"","PeriodicalId":11909,"journal":{"name":"European Journal of Nuclear Medicine and Molecular Imaging","volume":"127 1","pages":""},"PeriodicalIF":9.1,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143462425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hans J Biersack, Alejandro Rojas-Fernandez, Hong-Hoi Ting, Vasko Kramer, Malik E Juweid, Felix M Mottaghy
{"title":"The promising potential of camelid nanobodies for nuclear medicine.","authors":"Hans J Biersack, Alejandro Rojas-Fernandez, Hong-Hoi Ting, Vasko Kramer, Malik E Juweid, Felix M Mottaghy","doi":"10.1007/s00259-025-07136-y","DOIUrl":"https://doi.org/10.1007/s00259-025-07136-y","url":null,"abstract":"","PeriodicalId":11909,"journal":{"name":"European Journal of Nuclear Medicine and Molecular Imaging","volume":" ","pages":""},"PeriodicalIF":8.6,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143467348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Bieke Lambert, Valérie Vergucht, Sam Dekeyser, Annick De Craene, Filip Ameye, Bieke Van Den Bossche, Dieter Berwouts, Jeroen Mertens, Henk Vanoverschelde, Mieke Coppens, Charlotte Gabriel, Marianne Rottiers, Carole Van Haverbeke, Peter Dekuyper, Pieter De Backer, Kenneth Carels, Tessa Van Oostveldt, Karel Decaestecker
{"title":"Feasibility study on the implementation of a mobile high-resolution PET/CT scanner for surgical specimens: exploring clinical applications and practical considerations","authors":"Bieke Lambert, Valérie Vergucht, Sam Dekeyser, Annick De Craene, Filip Ameye, Bieke Van Den Bossche, Dieter Berwouts, Jeroen Mertens, Henk Vanoverschelde, Mieke Coppens, Charlotte Gabriel, Marianne Rottiers, Carole Van Haverbeke, Peter Dekuyper, Pieter De Backer, Kenneth Carels, Tessa Van Oostveldt, Karel Decaestecker","doi":"10.1007/s00259-025-07143-z","DOIUrl":"https://doi.org/10.1007/s00259-025-07143-z","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Purpose</h3><p>In this trial we explore potential indications of an intra-operative mobile PET/CT camera. The tested device is designed to acquire high quality images of resected tissue specimens from patients who were administered a PET-tracer, shortly before resection. Besides clinical experiences, we will also comment on the practical aspects of the implementation of a safe workflow for intra-operative PET/CT-imaging.</p><h3 data-test=\"abstract-sub-heading\">Methods</h3><p>This investigator driven study involved a 12-month evaluation of the AURA 10 PET/CT camera (XEOS Medical, Belgium). Depending on the tumour type, [<sup>18</sup>F]FDG, [18F]JK-PSMA-7, [<sup>18F</sup>]PSMA-1007 or [<sup>18</sup>F]Choline was injected intravenously 60–90 min prior to the removal of the tumour. The tissue was scanned in the mobile PET/CT-device and 12 min later the surgeon could review the images. Specimen PET/CT-images were confronted with pathology findings. Dose rates were monitored around the patient throughout the procedure.</p><h3 data-test=\"abstract-sub-heading\">Results</h3><p>The technique was tested in 32 surgeries for thyroid carcinomas (<i>n</i> = 5), transitional cell carcinomas (<i>n</i> = 2,) renal cell carcinoma (<i>n</i> = 1), prostate cancer (<i>n</i> = 5), breast carcinoma (<i>n</i> = 7), skin cancer (<i>n</i> = 3), nodal or bone biopsy for oncology work up (<i>n</i> = 6) and parathyroid adenoma (<i>n</i> = 3). Normalized to an injected activity of 1 MBq/kg the estimated median absorbed doses per procedure were 15.6 µSv (range 0,7-140,8) and 14,1 µSv (0,5–46,2) for respectively the surgeons and instrumenting nurses.</p><h3 data-test=\"abstract-sub-heading\">Conclusion</h3><p>The overall experience of intra-operative PET/CT-imaging of surgical specimens was promising in our hospital, with particular added value in case of (para)thyroid, urological surgeries, and oncological work-ups. High quality images were obtained with low activity of tracers, enabling a safe implementation.</p><h3 data-test=\"abstract-sub-heading\">Trial registration number (Belgium)</h3><p>BUN: B0172022000009 (NCT retrospectively submitted).</p>","PeriodicalId":11909,"journal":{"name":"European Journal of Nuclear Medicine and Molecular Imaging","volume":"49 1","pages":""},"PeriodicalIF":9.1,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143451626","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ghasem Hajianfar, Omid Gharibi, Maziar Sabouri, Mobin Mohebi, Mehdi Amini, Mohammad Javad Yasemi, Mohammad Chehreghani, Mehdi Maghsudi, Zahra Mansouri, Mohammad Edalat-Javid, Setareh Valavi, Ahmad Bitarafan Rajabi, Yazdan Salimi, Hossein Arabi, Arman Rahmim, Isaac Shiri, Habib Zaidi
{"title":"Artificial intelligence-powered coronary artery disease diagnosis from SPECT myocardial perfusion imaging: a comprehensive deep learning study","authors":"Ghasem Hajianfar, Omid Gharibi, Maziar Sabouri, Mobin Mohebi, Mehdi Amini, Mohammad Javad Yasemi, Mohammad Chehreghani, Mehdi Maghsudi, Zahra Mansouri, Mohammad Edalat-Javid, Setareh Valavi, Ahmad Bitarafan Rajabi, Yazdan Salimi, Hossein Arabi, Arman Rahmim, Isaac Shiri, Habib Zaidi","doi":"10.1007/s00259-025-07145-x","DOIUrl":"https://doi.org/10.1007/s00259-025-07145-x","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Background</h3><p>Myocardial perfusion imaging (MPI) using single-photon emission computed tomography (SPECT) is a well-established modality for noninvasive diagnostic assessment of coronary artery disease (CAD). However, the time-consuming and experience-dependent visual interpretation of SPECT images remains a limitation in the clinic.</p><h3 data-test=\"abstract-sub-heading\">Purpose</h3><p>We aimed to develop advanced models to diagnose CAD using different supervised and semi-supervised deep learning (DL) algorithms and training strategies, including transfer learning and data augmentation, with SPECT-MPI and invasive coronary angiography (ICA) as standard of reference.</p><h3 data-test=\"abstract-sub-heading\">Materials and methods</h3><p>A total of 940 patients who underwent SPECT-MPI were enrolled (281 patients included ICA). Quantitative perfusion SPECT (QPS) was used to extract polar maps of rest and stress states. We defined two different tasks, including (1) Automated CAD diagnosis with expert reader (ER) assessment of SPECT-MPI as reference, and (2) CAD diagnosis from SPECT-MPI based on reference ICA reports. In task 2, we used 6 strategies for training DL models. We implemented 13 different DL models along with 4 input types with and without data augmentation (WAug and WoAug) to train, validate, and test the DL models (728 models). One hundred patients with ICA as standard of reference (the same patients in task 1) were used to evaluate models per vessel and per patient. Metrics, such as the area under the receiver operating characteristics curve (AUC), accuracy, sensitivity, specificity, precision, and balanced accuracy were reported. DeLong and pairwise Wilcoxon rank sum tests were respectively used to compare models and strategies after 1000 bootstraps on the test data for all models. We also compared the performance of our best DL model to ER’s diagnosis.</p><h3 data-test=\"abstract-sub-heading\">Results</h3><p>In task 1, DenseNet201 Late Fusion (AUC = 0.89) and ResNet152V2 Late Fusion (AUC = 0.83) models outperformed other models in per-vessel and per-patient analyses, respectively. In task 2, the best models for CAD prediction based on ICA were Strategy 3 (a combination of ER- and ICA-based diagnosis in train data), WoAug InceptionResNetV2 EarlyFusion (AUC = 0.71), and Strategy 5 (semi-supervised approach) WoAug ResNet152V2 EarlyFusion (AUC = 0.77) in per-vessel and per-patient analyses, respectively. Moreover, saliency maps showed that models could be helpful for focusing on relevant spots for decision making.</p><h3 data-test=\"abstract-sub-heading\">Conclusion</h3><p>Our study confirmed the potential of DL-based analysis of SPECT-MPI polar maps in CAD diagnosis. In the automation of ER-based diagnosis, models’ performance was promising showing accuracy close to expert-level analysis. It demonstrated that using different strategies of data combination, such as including those with and without ICA,","PeriodicalId":11909,"journal":{"name":"European Journal of Nuclear Medicine and Molecular Imaging","volume":"15 1","pages":""},"PeriodicalIF":9.1,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143451628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xiao Zhang, Yongkang Gai, Ting Ye, Li Fan, Linfeng Xiu, Weiwei Ruan, Fan Hu, Jing Chen, Xiaoli Lan
{"title":"Head-to-head evaluation of [18F]FDG PET/CT and [68Ga]Ga-HX01 PET/MR in sarcoma patients","authors":"Xiao Zhang, Yongkang Gai, Ting Ye, Li Fan, Linfeng Xiu, Weiwei Ruan, Fan Hu, Jing Chen, Xiaoli Lan","doi":"10.1007/s00259-025-07130-4","DOIUrl":"https://doi.org/10.1007/s00259-025-07130-4","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Purpose</h3><p>Tumor-associated neovasculature and energy metabolism reprogramming serve as critical indicators of tumor proliferation, progression, invasion, and metastasis. This study conducted a head-to-head clinical investigation and comparison of [<sup>18</sup>F]FDG and [<sup>68</sup>Ga]Ga-HX01 PET by reflecting neovasculature and glucose metabolism in sarcoma patients, respectively.</p><h3 data-test=\"abstract-sub-heading\">Methods</h3><p>We reviewed the imaging data of sarcoma patients who underwent [<sup>68</sup>Ga]Ga-HX01 PET/MR and [<sup>18</sup>F]FDG PET/CT from June 29, 2022, to December 21, 2023. The two imaging modalities were performed on two separate days within one week of each other. A cohort of 21 patients with an average age of 45.81 ± 19.99 years were enrolled. The location, number and PET characteristics of all lesions were collected. The relationships between the two tracers were evaluated.</p><h3 data-test=\"abstract-sub-heading\">Results</h3><p>Among the 21 patients, 4 underwent imaging for initial disease staging, while the remaining 17 were imaged to detect recurrences. Patient-based analysis revealed that [<sup>68</sup>Ga]Ga-HX01 PET/MR diagnostic performance was equivalent to [<sup>18</sup>F]FDG PET/CT in lesion detection (<i>P</i> = 1.0). The SUVmax value of [<sup>68</sup>Ga]Ga-HX01 (4.64 ± 1.90) was significantly lower than that of [<sup>18</sup>F]FDG (9.43 ± 6.17, <i>P</i> = 0.002) across all patients. In terms of lesion-based analysis, [<sup>68</sup>Ga]Ga-HX01 identified two additional lesions compared to [<sup>18</sup>F]FDG, though this difference was not statistically significant (94 vs. 92, <i>P</i> = 0.678). The SUVmax value for all lesions with [<sup>68</sup>Ga]Ga-HX01 (3.47 ± 1.68) was also lower than that with [<sup>18</sup>F]FDG (5.82 ± 4.81, <i>P</i> = 0.003). Notably, [<sup>68</sup>Ga]Ga-HX01 was preferred in patients receiving hematopoietic cytokines.</p><h3 data-test=\"abstract-sub-heading\">Conclusion</h3><p>[<sup>68</sup>Ga]Ga-HX01 PET offers comparable diagnostic efficacy to [<sup>18</sup>F]FDG PET/CT in sarcoma, with potential advantages in specific clinical scenarios. Larger cohorts are needed to validate these findings.</p><h3 data-test=\"abstract-sub-heading\">Clinical Trial Registration</h3><p>NCT05490849 and NCT06416774.</p>","PeriodicalId":11909,"journal":{"name":"European Journal of Nuclear Medicine and Molecular Imaging","volume":"2 1","pages":""},"PeriodicalIF":9.1,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143451627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}