For patients with advanced-stage metastatic castration-resistant prostate cancer (mCRPC) who do not respond to [177Lu]Lu-PSMA therapy, there are limited treatment options. Clinical results obtained with [225Ac]Ac-PSMA are promising. We retrospectively analyzed the outcomes of patients treated with [225Ac]Ac-PSMA between December 2018 and October 2022. Methods: We evaluated the treatment results of 23 patients (mean age, 70.3 ± 8.8 y) with mCRPC who were refractory to treatment with [177Lu]Lu-PSMA (2-9 cycles). The safety profile was assessed according to Common Technology Criteria for Adverse Events version 5.0. Treatment efficacy was assessed using prostate-specific membrane antigen PET progression criteria and prostate-specific antigen (PSA) response according to Prostate Cancer Working Group 2 criteria after the first cycle of [225Ac]Ac-PSMA treatment. Results: All patients received androgen-deprivation therapy, whereas 22 (96%) and 19 (83%) patients received chemotherapy and second-generation antiandrogen therapy, respectively. One patient received 4 cycles, 2 received 3 cycles, 8 received 2 cycles, and 12 received 1 cycle of [225Ac]Ac-PSMA. The median interval between cycles was 13 wk (range, 8-28 wk). [225Ac]Ac-PSMA was administered with a mean activity of 7.6 MBq (range, 6.2-10.0 MBq) in each cycle. Patients were at an advanced stage of disease, and tumor burden was very high. Although the best PSA response was observed in 5 patients (26%) after [225Ac]Ac-PSMA treatment, there was at least some level of decline in PSA observed in 11 patients (58%; n = 19). Treatment response was assessed in patients who underwent [68Ga]Ga-PSMA PET/CT imaging. After the first cycle of treatment (n = 18), 50% of patients (n = 9) showed disease progression according to prostate-specific membrane antigen PET progression criteria, and the disease control rate was calculated to be 50%. Median progression-free survival was 3.1 mo, and median overall survival was 7.7 mo. Grade 3 hematologic toxicity occurred in 1 patient, and grade 3 nephrotoxicity was observed in another patient. Parotid SUVmax decreased by 33%, although all patients complained of dry mouth before treatment. Conclusion: We observed that [225Ac]Ac-PSMA therapy was safe and showed potential even in cases with advanced-stage mCRPC in which all other treatment options were completed.
{"title":"Clinical Experience with [<sup>225</sup>Ac]Ac-PSMA Treatment in Patients with [<sup>177</sup>Lu]Lu-PSMA-Refractory Metastatic Castration-Resistant Prostate Cancer.","authors":"Nalan Alan-Selcuk, Gamze Beydagi, Emre Demirci, Meltem Ocak, Serkan Celik, Bala B Oven, Turkay Toklu, Ipek Karaaslan, Kaan Akcay, Omer Sonmez, Levent Kabasakal","doi":"10.2967/jnumed.123.265546","DOIUrl":"10.2967/jnumed.123.265546","url":null,"abstract":"<p><p>For patients with advanced-stage metastatic castration-resistant prostate cancer (mCRPC) who do not respond to [<sup>177</sup>Lu]Lu-PSMA therapy, there are limited treatment options. Clinical results obtained with [<sup>225</sup>Ac]Ac-PSMA are promising. We retrospectively analyzed the outcomes of patients treated with [<sup>225</sup>Ac]Ac-PSMA between December 2018 and October 2022. <b>Methods:</b> We evaluated the treatment results of 23 patients (mean age, 70.3 ± 8.8 y) with mCRPC who were refractory to treatment with [<sup>177</sup>Lu]Lu-PSMA (2-9 cycles). The safety profile was assessed according to Common Technology Criteria for Adverse Events version 5.0. Treatment efficacy was assessed using prostate-specific membrane antigen PET progression criteria and prostate-specific antigen (PSA) response according to Prostate Cancer Working Group 2 criteria after the first cycle of [<sup>225</sup>Ac]Ac-PSMA treatment. <b>Results:</b> All patients received androgen-deprivation therapy, whereas 22 (96%) and 19 (83%) patients received chemotherapy and second-generation antiandrogen therapy, respectively. One patient received 4 cycles, 2 received 3 cycles, 8 received 2 cycles, and 12 received 1 cycle of [<sup>225</sup>Ac]Ac-PSMA. The median interval between cycles was 13 wk (range, 8-28 wk). [<sup>225</sup>Ac]Ac-PSMA was administered with a mean activity of 7.6 MBq (range, 6.2-10.0 MBq) in each cycle. Patients were at an advanced stage of disease, and tumor burden was very high. Although the best PSA response was observed in 5 patients (26%) after [<sup>225</sup>Ac]Ac-PSMA treatment, there was at least some level of decline in PSA observed in 11 patients (58%; <i>n</i> = 19). Treatment response was assessed in patients who underwent [<sup>68</sup>Ga]Ga-PSMA PET/CT imaging. After the first cycle of treatment (<i>n</i> = 18), 50% of patients (<i>n</i> = 9) showed disease progression according to prostate-specific membrane antigen PET progression criteria, and the disease control rate was calculated to be 50%. Median progression-free survival was 3.1 mo, and median overall survival was 7.7 mo. Grade 3 hematologic toxicity occurred in 1 patient, and grade 3 nephrotoxicity was observed in another patient. Parotid SUV<sub>max</sub> decreased by 33%, although all patients complained of dry mouth before treatment. <b>Conclusion:</b> We observed that [<sup>225</sup>Ac]Ac-PSMA therapy was safe and showed potential even in cases with advanced-stage mCRPC in which all other treatment options were completed.</p>","PeriodicalId":16758,"journal":{"name":"Journal of Nuclear Medicine","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10068799","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}
Pub Date : 2023-10-01Epub Date: 2023-08-24DOI: 10.2967/jnumed.123.266110
Jonathan Herington, Melissa D McCradden, Kathleen Creel, Ronald Boellaard, Elizabeth C Jones, Abhinav K Jha, Arman Rahmim, Peter J H Scott, John J Sunderland, Richard L Wahl, Sven Zuehlsdorff, Babak Saboury
The deployment of artificial intelligence (AI) has the potential to make nuclear medicine and medical imaging faster, cheaper, and both more effective and more accessible. This is possible, however, only if clinicians and patients feel that these AI medical devices (AIMDs) are trustworthy. Highlighting the need to ensure health justice by fairly distributing benefits and burdens while respecting individual patients' rights, the AI Task Force of the Society of Nuclear Medicine and Molecular Imaging has identified 4 major ethical risks that arise during the deployment of AIMD: autonomy of patients and clinicians, transparency of clinical performance and limitations, fairness toward marginalized populations, and accountability of physicians and developers. We provide preliminary recommendations for governing these ethical risks to realize the promise of AIMD for patients and populations.
{"title":"Ethical Considerations for Artificial Intelligence in Medical Imaging: Deployment and Governance.","authors":"Jonathan Herington, Melissa D McCradden, Kathleen Creel, Ronald Boellaard, Elizabeth C Jones, Abhinav K Jha, Arman Rahmim, Peter J H Scott, John J Sunderland, Richard L Wahl, Sven Zuehlsdorff, Babak Saboury","doi":"10.2967/jnumed.123.266110","DOIUrl":"10.2967/jnumed.123.266110","url":null,"abstract":"<p><p>The deployment of artificial intelligence (AI) has the potential to make nuclear medicine and medical imaging faster, cheaper, and both more effective and more accessible. This is possible, however, only if clinicians and patients feel that these AI medical devices (AIMDs) are trustworthy. Highlighting the need to ensure health justice by fairly distributing benefits and burdens while respecting individual patients' rights, the AI Task Force of the Society of Nuclear Medicine and Molecular Imaging has identified 4 major ethical risks that arise during the deployment of AIMD: autonomy of patients and clinicians, transparency of clinical performance and limitations, fairness toward marginalized populations, and accountability of physicians and developers. We provide preliminary recommendations for governing these ethical risks to realize the promise of AIMD for patients and populations.</p>","PeriodicalId":16758,"journal":{"name":"Journal of Nuclear Medicine","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10071259","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}
Pub Date : 2023-10-01Epub Date: 2023-07-27DOI: 10.2967/jnumed.122.264923
Alexandre Chicheportiche, Moshe Sason, Mahmoud Zidan, Jeremy Godefroy, Yodphat Krausz, David J Gross, Simona Grozinsky-Glasberg, Simona Ben-Haim
Dosimetry after 177Lu-DOTATATE peptide receptor radionuclide therapy (PRRT) enables estimation of radiation doses absorbed by normal organs and target lesions. This process is time-consuming and requires multiple posttreatment studies on several subsequent days. In a previous study, we described a newly developed multiple-linear-regression model to predict absorbed doses (ADs) from a single-time-point (STP) posttreatment study acquired 168 h after the first infusion and 24 h after the following ones, with similar results to the standard multiple-time-point (MTP) protocol. The present study aimed to validate this model in a large patient cohort and to assess whether STP dosimetry affects patient management decisions compared with our MTP protocol. Methods: Quantitative 177Lu-DOTATATE SPECT/CT post-PRRT data from 159 consecutive patients (172 therapies, 477 therapy cycles) were retrospectively analyzed. ADs obtained from an STP model were compared with those obtained using an MTP model. We evaluated the impact of the STP model on the decision on whether PRRT should be stopped because of an expected kidney AD exceeding the safety threshold. We hypothesized that patient management based on the STP model does not differ from that based on the MTP model in at least 90% of the cases. Results: There was no difference in management decisions between the MTP and STP models in 170 of 172 therapies (98.8%). A Fisher χ2 test for combined probabilities produced a composite P value of 0.0003. Mean cumulative AD relative differences between the STP and MTP models were 0.8% ± 8.0%, -7.7% ± 4.8%, 0.0% ± 11.4%, -2.8% ± 6.3%, and -2.1% ± 18.4% for kidneys, bone marrow, liver, spleen, and tumors, respectively (Pearson r = 0.99 for all), for patients who underwent 4 therapy cycles. Similar results were obtained with fewer therapy cycles. Conclusion: Estimated radiation ADs and patient management decisions were similar with the STP and MTP models. The STP model can simplify the dosimetry process while also reducing scanner and staff time and improving patient comfort.
{"title":"Impact of Single-Time-Point Estimates of <sup>177</sup>Lu-PRRT Absorbed Doses on Patient Management: Validation of a Trained Multiple-Linear-Regression Model in 159 Patients and 477 Therapy Cycles.","authors":"Alexandre Chicheportiche, Moshe Sason, Mahmoud Zidan, Jeremy Godefroy, Yodphat Krausz, David J Gross, Simona Grozinsky-Glasberg, Simona Ben-Haim","doi":"10.2967/jnumed.122.264923","DOIUrl":"10.2967/jnumed.122.264923","url":null,"abstract":"<p><p>Dosimetry after <sup>177</sup>Lu-DOTATATE peptide receptor radionuclide therapy (PRRT) enables estimation of radiation doses absorbed by normal organs and target lesions. This process is time-consuming and requires multiple posttreatment studies on several subsequent days. In a previous study, we described a newly developed multiple-linear-regression model to predict absorbed doses (ADs) from a single-time-point (STP) posttreatment study acquired 168 h after the first infusion and 24 h after the following ones, with similar results to the standard multiple-time-point (MTP) protocol. The present study aimed to validate this model in a large patient cohort and to assess whether STP dosimetry affects patient management decisions compared with our MTP protocol. <b>Methods:</b> Quantitative <sup>177</sup>Lu-DOTATATE SPECT/CT post-PRRT data from 159 consecutive patients (172 therapies, 477 therapy cycles) were retrospectively analyzed. ADs obtained from an STP model were compared with those obtained using an MTP model. We evaluated the impact of the STP model on the decision on whether PRRT should be stopped because of an expected kidney AD exceeding the safety threshold. We hypothesized that patient management based on the STP model does not differ from that based on the MTP model in at least 90% of the cases. <b>Results:</b> There was no difference in management decisions between the MTP and STP models in 170 of 172 therapies (98.8%). A Fisher χ<sup>2</sup> test for combined probabilities produced a composite <i>P</i> value of 0.0003. Mean cumulative AD relative differences between the STP and MTP models were 0.8% ± 8.0%, -7.7% ± 4.8%, 0.0% ± 11.4%, -2.8% ± 6.3%, and -2.1% ± 18.4% for kidneys, bone marrow, liver, spleen, and tumors, respectively (Pearson <i>r</i> = 0.99 for all), for patients who underwent 4 therapy cycles. Similar results were obtained with fewer therapy cycles. <b>Conclusion:</b> Estimated radiation ADs and patient management decisions were similar with the STP and MTP models. The STP model can simplify the dosimetry process while also reducing scanner and staff time and improving patient comfort.</p>","PeriodicalId":16758,"journal":{"name":"Journal of Nuclear Medicine","volume":null,"pages":null},"PeriodicalIF":9.1,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9883564","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}
Pub Date : 2023-10-01Epub Date: 2023-08-31DOI: 10.2967/jnumed.123.265738
Sanne A M van Lith, Ilanah J Pruis, Nelleke Tolboom, Tom J Snijders, Dylan Henssen, Mark Ter Laan, Maarten Te Dorsthorst, William P J Leenders, Martin Gotthardt, James Nagarajah, Pierre A Robe, Philip De Witt Hamer, Harry Hendrikse, Daniela E Oprea-Lager, Maqsood Yaqub, Ronald Boellaard, Pieter Wesseling, Rutger K Balvers, Frederik A Verburg, Anita A Harteveld, Marion Smits, Martin van den Bent, Sophie E M Veldhuijzen van Zanten, Elsmarieke van de Giessen
Upregulation of prostate-specific membrane antigen (PSMA) in neovasculature has been described in glioblastoma multiforme (GBM), whereas vasculature in nonaffected brain shows hardly any expression of PSMA. It is unclear whether PSMA-targeting tracer uptake on PET is based on PSMA-specific binding to neovasculature or aspecific uptake in tumor. Here, we quantified uptake of various PSMA-targeting tracers in GBM and correlated this with PSMA expression in tumor biopsy samples from the same patients. Methods: Fourteen patients diagnosed with de novo (n = 8) or recurrent (n = 6) GBM underwent a preoperative PET scan after injection of 1.5 MBq/kg [68Ga]Ga-PSMA-11 (n = 7), 200 MBq of [18F]DCFpyl (n = 3), or 200 MBq of [18F]PSMA-1007 (n = 4). Uptake in tumor and tumor-to-background ratios, with contralateral nonaffected brain as background, were determined. In a subset of patients, PSMA expression levels from different regions in the tumor tissue samples (n = 40), determined using immunohistochemistry (n = 35) or RNA sequencing (n = 13), were correlated with tracer uptake on PET. Results: Moderate to high (SUVmax, 1.3-20.0) heterogeneous uptake was found in all tumors irrespective of the tracer type used. Uptake in nonaffected brain was low, resulting in high tumor-to-background ratios (6.1-359.0) calculated by dividing SUVmax of tumor by SUVmax of background. Immunohistochemistry showed variable PSMA expression on endothelial cells of tumor microvasculature, as well as on dispersed individual cells (of unknown origin), and granular staining of the neuropil. No correlation was found between in vivo uptake and PSMA expression levels (for immunohistochemistry, r = -0.173, P = 0.320; for RNA, r = -0.033, P = 0.915). Conclusion: Our results indicate the potential use of various PSMA-targeting tracers in GBM. However, we found no correlation between PSMA expression levels on immunohistochemistry and uptake intensity on PET. Whether this may be explained by methodologic reasons, such as the inability to measure functionally active PSMA with immunohistochemistry, tracer pharmacokinetics, or the contribution of a disturbed blood-brain barrier to tracer retention, should still be investigated.
{"title":"PET Imaging and Protein Expression of Prostate-Specific Membrane Antigen in Glioblastoma: A Multicenter Inventory Study.","authors":"Sanne A M van Lith, Ilanah J Pruis, Nelleke Tolboom, Tom J Snijders, Dylan Henssen, Mark Ter Laan, Maarten Te Dorsthorst, William P J Leenders, Martin Gotthardt, James Nagarajah, Pierre A Robe, Philip De Witt Hamer, Harry Hendrikse, Daniela E Oprea-Lager, Maqsood Yaqub, Ronald Boellaard, Pieter Wesseling, Rutger K Balvers, Frederik A Verburg, Anita A Harteveld, Marion Smits, Martin van den Bent, Sophie E M Veldhuijzen van Zanten, Elsmarieke van de Giessen","doi":"10.2967/jnumed.123.265738","DOIUrl":"10.2967/jnumed.123.265738","url":null,"abstract":"<p><p>Upregulation of prostate-specific membrane antigen (PSMA) in neovasculature has been described in glioblastoma multiforme (GBM), whereas vasculature in nonaffected brain shows hardly any expression of PSMA. It is unclear whether PSMA-targeting tracer uptake on PET is based on PSMA-specific binding to neovasculature or aspecific uptake in tumor. Here, we quantified uptake of various PSMA-targeting tracers in GBM and correlated this with PSMA expression in tumor biopsy samples from the same patients. <b>Methods:</b> Fourteen patients diagnosed with de novo (<i>n</i> = 8) or recurrent (<i>n</i> = 6) GBM underwent a preoperative PET scan after injection of 1.5 MBq/kg [<sup>68</sup>Ga]Ga-PSMA-11 (<i>n</i> = 7), 200 MBq of [<sup>18</sup>F]DCFpyl (<i>n</i> = 3), or 200 MBq of [<sup>18</sup>F]PSMA-1007 (<i>n</i> = 4). Uptake in tumor and tumor-to-background ratios, with contralateral nonaffected brain as background, were determined. In a subset of patients, PSMA expression levels from different regions in the tumor tissue samples (<i>n</i> = 40), determined using immunohistochemistry (<i>n</i> = 35) or RNA sequencing (<i>n</i> = 13), were correlated with tracer uptake on PET. <b>Results:</b> Moderate to high (SUV<sub>max</sub>, 1.3-20.0) heterogeneous uptake was found in all tumors irrespective of the tracer type used. Uptake in nonaffected brain was low, resulting in high tumor-to-background ratios (6.1-359.0) calculated by dividing SUV<sub>max</sub> of tumor by SUV<sub>max</sub> of background. Immunohistochemistry showed variable PSMA expression on endothelial cells of tumor microvasculature, as well as on dispersed individual cells (of unknown origin), and granular staining of the neuropil. No correlation was found between in vivo uptake and PSMA expression levels (for immunohistochemistry, <i>r</i> = -0.173, <i>P</i> = 0.320; for RNA, <i>r</i> = -0.033, <i>P</i> = 0.915). <b>Conclusion:</b> Our results indicate the potential use of various PSMA-targeting tracers in GBM. However, we found no correlation between PSMA expression levels on immunohistochemistry and uptake intensity on PET. Whether this may be explained by methodologic reasons, such as the inability to measure functionally active PSMA with immunohistochemistry, tracer pharmacokinetics, or the contribution of a disturbed blood-brain barrier to tracer retention, should still be investigated.</p>","PeriodicalId":16758,"journal":{"name":"Journal of Nuclear Medicine","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10483759","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}
This study aimed to develop an analytic approach based on [18F]FDG PET radiomics using stacking ensemble learning to improve the outcome prediction in diffuse large B-cell lymphoma (DLBCL). Methods: In total, 240 DLBCL patients from 2 medical centers were divided into the training set (n = 141), internal testing set (n = 61), and external testing set (n = 38). Radiomics features were extracted from pretreatment [18F]FDG PET scans at the patient level using 4 semiautomatic segmentation methods (SUV threshold of 2.5, SUV threshold of 4.0 [SUV4.0], 41% of SUVmax, and SUV threshold of mean liver uptake [PERCIST]). All extracted features were harmonized with the ComBat method. The intraclass correlation coefficient was used to evaluate the reliability of radiomics features extracted by different segmentation methods. Features from the most reliable segmentation method were selected by Pearson correlation coefficient analysis and the LASSO (least absolute shrinkage and selection operator) algorithm. A stacking ensemble learning approach was applied to build radiomics-only and combined clinical-radiomics models for prediction of 2-y progression-free survival and overall survival based on 4 machine learning classifiers (support vector machine, random forests, gradient boosting decision tree, and adaptive boosting). Confusion matrix, receiver-operating-characteristic curve analysis, and survival analysis were used to evaluate the model performance. Results: Among 4 semiautomatic segmentation methods, SUV4.0 segmentation yielded the highest interobserver reliability, with 830 (66.7%) selected radiomics features. The combined model constructed by the stacking method achieved the best discrimination performance. For progression-free survival prediction in the external testing set, the areas under the receiver-operating-characteristic curve and accuracy of the stacking-based combined model were 0.771 and 0.789, respectively. For overall survival prediction, the stacking-based combined model achieved an area under the curve of 0.725 and an accuracy of 0.763 in the external testing set. The combined model also demonstrated a more distinct risk stratification than the International Prognostic Index in all sets (log-rank test, all P < 0.05). Conclusion: The combined model that incorporates [18F]FDG PET radiomics and clinical characteristics based on stacking ensemble learning could enable improved risk stratification in DLBCL.
{"title":"Stacking Ensemble Learning-Based [<sup>18</sup>F]FDG PET Radiomics for Outcome Prediction in Diffuse Large B-Cell Lymphoma.","authors":"Shuilin Zhao, Jing Wang, Chentao Jin, Xiang Zhang, Chenxi Xue, Rui Zhou, Yan Zhong, Yuwei Liu, Xuexin He, Youyou Zhou, Caiyun Xu, Lixia Zhang, Wenbin Qian, Hong Zhang, Xiaohui Zhang, Mei Tian","doi":"10.2967/jnumed.122.265244","DOIUrl":"10.2967/jnumed.122.265244","url":null,"abstract":"<p><p>This study aimed to develop an analytic approach based on [<sup>18</sup>F]FDG PET radiomics using stacking ensemble learning to improve the outcome prediction in diffuse large B-cell lymphoma (DLBCL). <b>Methods:</b> In total, 240 DLBCL patients from 2 medical centers were divided into the training set (<i>n</i> = 141), internal testing set (<i>n</i> = 61), and external testing set (<i>n</i> = 38). Radiomics features were extracted from pretreatment [<sup>18</sup>F]FDG PET scans at the patient level using 4 semiautomatic segmentation methods (SUV threshold of 2.5, SUV threshold of 4.0 [SUV4.0], 41% of SUV<sub>max</sub>, and SUV threshold of mean liver uptake [PERCIST]). All extracted features were harmonized with the ComBat method. The intraclass correlation coefficient was used to evaluate the reliability of radiomics features extracted by different segmentation methods. Features from the most reliable segmentation method were selected by Pearson correlation coefficient analysis and the LASSO (least absolute shrinkage and selection operator) algorithm. A stacking ensemble learning approach was applied to build radiomics-only and combined clinical-radiomics models for prediction of 2-y progression-free survival and overall survival based on 4 machine learning classifiers (support vector machine, random forests, gradient boosting decision tree, and adaptive boosting). Confusion matrix, receiver-operating-characteristic curve analysis, and survival analysis were used to evaluate the model performance. <b>Results:</b> Among 4 semiautomatic segmentation methods, SUV4.0 segmentation yielded the highest interobserver reliability, with 830 (66.7%) selected radiomics features. The combined model constructed by the stacking method achieved the best discrimination performance. For progression-free survival prediction in the external testing set, the areas under the receiver-operating-characteristic curve and accuracy of the stacking-based combined model were 0.771 and 0.789, respectively. For overall survival prediction, the stacking-based combined model achieved an area under the curve of 0.725 and an accuracy of 0.763 in the external testing set. The combined model also demonstrated a more distinct risk stratification than the International Prognostic Index in all sets (log-rank test, all <i>P</i> < 0.05). <b>Conclusion:</b> The combined model that incorporates [<sup>18</sup>F]FDG PET radiomics and clinical characteristics based on stacking ensemble learning could enable improved risk stratification in DLBCL.</p>","PeriodicalId":16758,"journal":{"name":"Journal of Nuclear Medicine","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9883566","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}
Pub Date : 2023-10-01Epub Date: 2023-06-29DOI: 10.2967/jnumed.123.266006
Dale L Bailey
TO THE EDITOR: Sometimes we need to challenge the views of colleagues and friends, especially when their thinking has the effect of muddying the waters rather than providing greater insight and clarity. I believe this to be the case with the opinion piece by Weber et al. in the May 2023 issue of the journal (1). The authors seek to redefine the term theranostic. They assert that this is any molecular imaging probe that provides actionable information for any subsequent therapeutic. This includes medical therapies, radiation therapy, surgery, or cell therapies. I believe that, in doing so, they are losing the very essence of what a theranostic is. I agree with the authors that the therapeutic component of a theranostic pair need not be a radionuclide therapy, but I contend that it mustbe the same(oravery similar)moleculeormoiety. It couldbecarrying a toxic therapeutic or it may be an antibody that targets a protein (e.g., amyloid in the brain), but it has to be the same targeting moiety. What the authors of this article are referring to as a theranostic imaging probe when used with a range of other therapies is more accurately described by the term gatekeeper or companion diagnostic. The imaging study validates the use of a certain therapeutic approach: this is not theranostics but simply a good use of medical imaging. The authors surely would not contend that a ventilation–perfusion lung scan demonstrating a pulmonary embolism that was subsequently treated with anticoagulation was a theranostic approach. Definitions are important and help us to describe and conceptualize the strategy chosen to diagnose and treat diseases. Seeking to dilute the definition of a theranostic in the way the authors have done will have the effect of confusing the basis of the concept and will be unhelpful. The theranostic approach is an extremely powerful one and should be amajor focus of future developments inmolecular imaging and therapy. We need to keep the concepts clear and appreciate the differences between gatekeeper and theranostic approaches. They are both very important, but they are not the same. Not all gatekeepers are theranostics.
{"title":"Not All Gatekeepers Are Theranostics.","authors":"Dale L Bailey","doi":"10.2967/jnumed.123.266006","DOIUrl":"10.2967/jnumed.123.266006","url":null,"abstract":"TO THE EDITOR: Sometimes we need to challenge the views of colleagues and friends, especially when their thinking has the effect of muddying the waters rather than providing greater insight and clarity. I believe this to be the case with the opinion piece by Weber et al. in the May 2023 issue of the journal (1). The authors seek to redefine the term theranostic. They assert that this is any molecular imaging probe that provides actionable information for any subsequent therapeutic. This includes medical therapies, radiation therapy, surgery, or cell therapies. I believe that, in doing so, they are losing the very essence of what a theranostic is. I agree with the authors that the therapeutic component of a theranostic pair need not be a radionuclide therapy, but I contend that it mustbe the same(oravery similar)moleculeormoiety. It couldbecarrying a toxic therapeutic or it may be an antibody that targets a protein (e.g., amyloid in the brain), but it has to be the same targeting moiety. What the authors of this article are referring to as a theranostic imaging probe when used with a range of other therapies is more accurately described by the term gatekeeper or companion diagnostic. The imaging study validates the use of a certain therapeutic approach: this is not theranostics but simply a good use of medical imaging. The authors surely would not contend that a ventilation–perfusion lung scan demonstrating a pulmonary embolism that was subsequently treated with anticoagulation was a theranostic approach. Definitions are important and help us to describe and conceptualize the strategy chosen to diagnose and treat diseases. Seeking to dilute the definition of a theranostic in the way the authors have done will have the effect of confusing the basis of the concept and will be unhelpful. The theranostic approach is an extremely powerful one and should be amajor focus of future developments inmolecular imaging and therapy. We need to keep the concepts clear and appreciate the differences between gatekeeper and theranostic approaches. They are both very important, but they are not the same. Not all gatekeepers are theranostics.","PeriodicalId":16758,"journal":{"name":"Journal of Nuclear Medicine","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9698301","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}
Pub Date : 2023-10-01Epub Date: 2023-08-03DOI: 10.2967/jnumed.123.265782
Marc Pretze, Jörg Kotzerke, Robert Freudenberg, Claudia Brogsitter
{"title":"Potential of <sup>188</sup>Re as an Alternative to <sup>177</sup>Lu and Dosimetric Consequences.","authors":"Marc Pretze, Jörg Kotzerke, Robert Freudenberg, Claudia Brogsitter","doi":"10.2967/jnumed.123.265782","DOIUrl":"10.2967/jnumed.123.265782","url":null,"abstract":"","PeriodicalId":16758,"journal":{"name":"Journal of Nuclear Medicine","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9930928","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}
Pub Date : 2023-10-01Epub Date: 2023-07-20DOI: 10.2967/jnumed.123.265664
David Kersting, Patrick Sandach, Miriam Sraieb, Marcel Wiesweg, Martin Metzenmacher, Kaid Darwiche, Filiz Oezkan, Servet Bölükbas, Martin Stuschke, Lale Umutlu, Michael Nader, Rainer Hamacher, Wolfgang P Fendler, Johannes Wienker, Wilfried E E Eberhardt, Martin Schuler, Ken Herrmann, Hubertus Hautzel
PET imaging using the somatostatin receptor 2 (SSTR2) antagonist satoreotide trizoxetan (SSO-120, previously OPS-202) could offer accurate tumor detection and screening for SSTR2-antagonist radionuclide therapy in patients with SSTR2-expressing small cell lung cancer (SCLC). The aim of this single-center study was to investigate tumor uptake and detection rates of 68Ga-SSO-120 in comparison to 18F-FDG PET in the initial staging of SCLC patients. Methods: Patients with newly diagnosed SCLC who underwent additional whole-body 68Ga-SSO-120 PET/CT during the initial diagnostic workup were retrospectively included. The mean administered activity was 139 MBq, and the mean uptake time was 60 min. Gold-standard staging 18F-FDG PET/CT was evaluated if available within 2 wk before or after 68Ga-SSO-120 PET if morphologic differences in CT images were absent. 68Ga-SSO-120- or 18F-FDG-positive lesions were reported in 7 anatomic regions (primary tumor, thoracic lymph node metastases, and distant metastases including pleural, contralateral pulmonary, liver, bone, and other) according to the TNM classification for lung cancer (eighth edition). Consensus TNM staging (derived from CT, endobronchial ultrasound-guided transbronchial needle aspiration, PET, and brain MRI) by a clinical tumor board served as the reference standard. Results: Thirty-one patients were included, 12 with limited and 19 with extensive disease according to the Veterans Administration Lung Study Group classification. 68Ga-SSO-120-positive tumor was detected in all patients (100%) and in 90 of the 217 evaluated regions (41.5%). Thirteen patients (42.0%) had intense average 68Ga-SSO-120 uptake (region-based mean SUVmax ≥ 10); 28 patients (90.3%) had average 68Ga-SSO-120 uptake greater than liver uptake (region-based mean peak tumor-to-liver ratio > 1). In 25 patients with evaluable 18F-FDG PET, primary tumor, thoracic lymph node metastases, and distant metastases were detected in 100%, 92%, and 64%, respectively, of all investigated patients by 68Ga-SSO-120 and in 100%, 92%, and 56%, respectively, by 18F-FDG PET. 68Ga-SSO-120 PET detected additional contralateral lymph node, liver, and brain metastases in 1, 1, and 2 patients, respectively (no histopathology available), and 18F-FDG PET detected additional contralateral lymph node metastases in 3 patients (1 confirmed, 1 systematic endobronchial ultrasound-guided transbronchial needle aspiration-negative, and 1 without available histopathology). None of these differences altered Veterans Administration Lung Study Group staging. The region-based monotonic correlation between 68Ga-SSO-120 and 18F-FDG uptake was low (Spearman ρ = 0.26-0.33). Conclusion:68Ga-SSO-120 PET offers high diagnostic precision with compara
{"title":"<sup>68</sup>Ga-SSO-120 PET for Initial Staging of Small Cell Lung Cancer Patients: A Single-Center Retrospective Study.","authors":"David Kersting, Patrick Sandach, Miriam Sraieb, Marcel Wiesweg, Martin Metzenmacher, Kaid Darwiche, Filiz Oezkan, Servet Bölükbas, Martin Stuschke, Lale Umutlu, Michael Nader, Rainer Hamacher, Wolfgang P Fendler, Johannes Wienker, Wilfried E E Eberhardt, Martin Schuler, Ken Herrmann, Hubertus Hautzel","doi":"10.2967/jnumed.123.265664","DOIUrl":"10.2967/jnumed.123.265664","url":null,"abstract":"<p><p>PET imaging using the somatostatin receptor 2 (SSTR2) antagonist satoreotide trizoxetan (SSO-120, previously OPS-202) could offer accurate tumor detection and screening for SSTR2-antagonist radionuclide therapy in patients with SSTR2-expressing small cell lung cancer (SCLC). The aim of this single-center study was to investigate tumor uptake and detection rates of <sup>68</sup>Ga-SSO-120 in comparison to <sup>18</sup>F-FDG PET in the initial staging of SCLC patients. <b>Methods:</b> Patients with newly diagnosed SCLC who underwent additional whole-body <sup>68</sup>Ga-SSO-120 PET/CT during the initial diagnostic workup were retrospectively included. The mean administered activity was 139 MBq, and the mean uptake time was 60 min. Gold-standard staging <sup>18</sup>F-FDG PET/CT was evaluated if available within 2 wk before or after <sup>68</sup>Ga-SSO-120 PET if morphologic differences in CT images were absent. <sup>68</sup>Ga-SSO-120- or <sup>18</sup>F-FDG-positive lesions were reported in 7 anatomic regions (primary tumor, thoracic lymph node metastases, and distant metastases including pleural, contralateral pulmonary, liver, bone, and other) according to the TNM classification for lung cancer (eighth edition). Consensus TNM staging (derived from CT, endobronchial ultrasound-guided transbronchial needle aspiration, PET, and brain MRI) by a clinical tumor board served as the reference standard. <b>Results:</b> Thirty-one patients were included, 12 with limited and 19 with extensive disease according to the Veterans Administration Lung Study Group classification. <sup>68</sup>Ga-SSO-120-positive tumor was detected in all patients (100%) and in 90 of the 217 evaluated regions (41.5%). Thirteen patients (42.0%) had intense average <sup>68</sup>Ga-SSO-120 uptake (region-based mean SUV<sub>max</sub> ≥ 10); 28 patients (90.3%) had average <sup>68</sup>Ga-SSO-120 uptake greater than liver uptake (region-based mean peak tumor-to-liver ratio > 1). In 25 patients with evaluable <sup>18</sup>F-FDG PET, primary tumor, thoracic lymph node metastases, and distant metastases were detected in 100%, 92%, and 64%, respectively, of all investigated patients by <sup>68</sup>Ga-SSO-120 and in 100%, 92%, and 56%, respectively, by <sup>18</sup>F-FDG PET. <sup>68</sup>Ga-SSO-120 PET detected additional contralateral lymph node, liver, and brain metastases in 1, 1, and 2 patients, respectively (no histopathology available), and <sup>18</sup>F-FDG PET detected additional contralateral lymph node metastases in 3 patients (1 confirmed, 1 systematic endobronchial ultrasound-guided transbronchial needle aspiration-negative, and 1 without available histopathology). None of these differences altered Veterans Administration Lung Study Group staging. The region-based monotonic correlation between <sup>68</sup>Ga-SSO-120 and <sup>18</sup>F-FDG uptake was low (Spearman ρ = 0.26-0.33). <b>Conclusion:</b> <sup>68</sup>Ga-SSO-120 PET offers high diagnostic precision with compara","PeriodicalId":16758,"journal":{"name":"Journal of Nuclear Medicine","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10203985","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}
Pub Date : 2023-10-01Epub Date: 2023-08-03DOI: 10.2967/jnumed.123.265489
Anouk C de Jong, Marcel Segbers, Sui Wai Ling, Laura H Graven, Niven Mehra, Paul Hamberg, Tessa Brabander, Ronald de Wit, Astrid A M van der Veldt
CT and bone scintigraphy are not useful for response evaluation of bone metastases to 223Ra treatment in metastatic castration-resistant prostate cancer (mCRPC). PET using 68Ga prostate-specific membrane antigen 11 (68Ga-PSMA) is a promising tool for response evaluation of mCRPC. The aim of this study was to determine the utility of 68Ga-PSMA PET/CT for response evaluation of 223Ra treatment in patients with mCRPC. Methods: Within this prospective, multicenter, imaging discovery study, 28 patients with mCRPC, eligible for 223Ra treatment, were included between 2019 and 2022. Patients received 223Ra according to the standard of care. Study procedures included CT, bone scintigraphy, and 68Ga-PSMA PET/CT at baseline, after 3 and 6 cycles of 223Ra treatment, and on treatment failure. Response to 223Ra treatment was visually assessed on all 3 imaging modalities. Total tumor volume within bone (TTVbone) was determined on 68Ga-PSMA PET/CT. Intrapatient heterogeneity in response was studied using a newly developed image-registration tool for sequential images of PET/CT. Results were compared with failure-free survival (good responders vs. poor responders; cutoff, 24 wk) and alkaline phosphatase (ALP) response after 3 cycles. Results: Visual response assessment criteria could not distinguish good responders from poor responders on 68Ga-PSMA PET/CT and bone scintigraphy. For 68Ga-PSMA PET/CT, TTVbone at baseline was lower in good responders than in poor responders, whereas TTVbone increased in both groups during treatment. TTVbone was higher in patients with new extraosseous metastases during 223Ra treatment. Although TTVbone and ALP correlated at baseline, changes in TTVbone and ALP on treatment did not. 68Ga-PSMA response of TTVbone showed intrapatient heterogeneity in most patients. Conclusion: mCRPC patients with lower TTVbone on 68Ga-PSMA PET/CT have the best clinical outcome after 223Ra treatment. Response is highly heterogeneous in most patients. A decrease in ALP, which occurred in most patients, was not correlated with a decrease in TTVbone, which might make one question the value of ALP for disease monitoring during 223Ra treatment in clinical practice.
{"title":"<sup>68</sup>Ga-PSMA PET/CT for Response Evaluation of <sup>223</sup>Ra Treatment in Metastatic Prostate Cancer.","authors":"Anouk C de Jong, Marcel Segbers, Sui Wai Ling, Laura H Graven, Niven Mehra, Paul Hamberg, Tessa Brabander, Ronald de Wit, Astrid A M van der Veldt","doi":"10.2967/jnumed.123.265489","DOIUrl":"10.2967/jnumed.123.265489","url":null,"abstract":"<p><p>CT and bone scintigraphy are not useful for response evaluation of bone metastases to <sup>223</sup>Ra treatment in metastatic castration-resistant prostate cancer (mCRPC). PET using <sup>68</sup>Ga prostate-specific membrane antigen 11 (<sup>68</sup>Ga-PSMA) is a promising tool for response evaluation of mCRPC. The aim of this study was to determine the utility of <sup>68</sup>Ga-PSMA PET/CT for response evaluation of <sup>223</sup>Ra treatment in patients with mCRPC. <b>Methods:</b> Within this prospective, multicenter, imaging discovery study, 28 patients with mCRPC, eligible for <sup>223</sup>Ra treatment, were included between 2019 and 2022. Patients received <sup>223</sup>Ra according to the standard of care. Study procedures included CT, bone scintigraphy, and <sup>68</sup>Ga-PSMA PET/CT at baseline, after 3 and 6 cycles of <sup>223</sup>Ra treatment, and on treatment failure. Response to <sup>223</sup>Ra treatment was visually assessed on all 3 imaging modalities. Total tumor volume within bone (TTV<sub>bone</sub>) was determined on <sup>68</sup>Ga-PSMA PET/CT. Intrapatient heterogeneity in response was studied using a newly developed image-registration tool for sequential images of PET/CT. Results were compared with failure-free survival (good responders vs. poor responders; cutoff, 24 wk) and alkaline phosphatase (ALP) response after 3 cycles. <b>Results:</b> Visual response assessment criteria could not distinguish good responders from poor responders on <sup>68</sup>Ga-PSMA PET/CT and bone scintigraphy. For <sup>68</sup>Ga-PSMA PET/CT, TTV<sub>bone</sub> at baseline was lower in good responders than in poor responders, whereas TTV<sub>bone</sub> increased in both groups during treatment. TTV<sub>bone</sub> was higher in patients with new extraosseous metastases during <sup>223</sup>Ra treatment. Although TTV<sub>bone</sub> and ALP correlated at baseline, changes in TTV<sub>bone</sub> and ALP on treatment did not. <sup>68</sup>Ga-PSMA response of TTV<sub>bone</sub> showed intrapatient heterogeneity in most patients. <b>Conclusion:</b> mCRPC patients with lower TTV<sub>bone</sub> on <sup>68</sup>Ga-PSMA PET/CT have the best clinical outcome after <sup>223</sup>Ra treatment. Response is highly heterogeneous in most patients. A decrease in ALP, which occurred in most patients, was not correlated with a decrease in TTV<sub>bone</sub>, which might make one question the value of ALP for disease monitoring during <sup>223</sup>Ra treatment in clinical practice.</p>","PeriodicalId":16758,"journal":{"name":"Journal of Nuclear Medicine","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9936954","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}
Pub Date : 2023-10-01Epub Date: 2023-06-15DOI: 10.2967/jnumed.123.265640
Lena M Unterrainer, Anthony E Sisk, Johannes Czernin, Brian M Shuch, Jeremie Calais, Masatoshi Hotta
.
{"title":"[<sup>68</sup>Ga]Ga-FAPI-46 PET for Visualization of Postinfarction Renal Fibrosis.","authors":"Lena M Unterrainer, Anthony E Sisk, Johannes Czernin, Brian M Shuch, Jeremie Calais, Masatoshi Hotta","doi":"10.2967/jnumed.123.265640","DOIUrl":"10.2967/jnumed.123.265640","url":null,"abstract":".","PeriodicalId":16758,"journal":{"name":"Journal of Nuclear Medicine","volume":null,"pages":null},"PeriodicalIF":9.3,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9995544","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}