Neha Agrawal, Raza Abbas Mahdi, Harpreet Singh, Bhagwant Rai Mittal, Alka Khadwal
{"title":"Bilateral Infraorbital and Inferior Alveolar Nerve Involvement in Non-Hodgkin Lymphoma Detected on 18F-FDG PET/CT.","authors":"Neha Agrawal, Raza Abbas Mahdi, Harpreet Singh, Bhagwant Rai Mittal, Alka Khadwal","doi":"10.1007/s13139-026-00995-9","DOIUrl":"10.1007/s13139-026-00995-9","url":null,"abstract":"","PeriodicalId":19384,"journal":{"name":"Nuclear Medicine and Molecular Imaging","volume":"60 5","pages":"644-645"},"PeriodicalIF":2.3,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13627613/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149112903","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Maria Obrycka, Saeid Abdelrazek, Łukasz Żukowski, Janusz Myśliwiec, Piotr Szumowski
{"title":"From Patient Selection to Surveillance: Artificial Intelligence Applications in Radioiodine Therapy - A Systematic Review.","authors":"Maria Obrycka, Saeid Abdelrazek, Łukasz Żukowski, Janusz Myśliwiec, Piotr Szumowski","doi":"10.1007/s13139-026-01049-w","DOIUrl":"https://doi.org/10.1007/s13139-026-01049-w","url":null,"abstract":"<p><p>Radioactive iodine therapy requires individualized decisions regarding patient selection, administered activity planning, imaging assessment, and follow-up. This systematic review summarizes current applications of artificial intelligence (AI) in the <sup>131</sup>I treatment pathway and evaluates barriers limiting clinical implementation. Following PRISMA 2020 guidelines, PubMed, Scopus, Web of Science, and Wiley databases were searched for original studies involving human patients treated with <sup>131</sup>I for differentiated thyroid cancer or benign thyroid disease, where AI, deep learning (DL), or machine learning (ML) methods were utilized. Evidence was synthesized, and study quality was assessed using the NIH/NHLBI Study Quality Assessment Tool. Among 775 identified records, 24 studies met inclusion criteria. AI applications included pretreatment decision support, detection and characterization of iodine-avid disease, dosimetry and activity optimization, radiation-safety assessment, treatment response prediction, levothyroxine dose estimation, and recurrence-risk stratification. The available evidence was dominated by retrospective, single-center studies, primarily focused on differentiated thyroid cancer, with limited external validation. AI has the potential to improve standardization and personalization of <sup>131</sup>I therapy, but heterogeneous methodologies and insufficient evidence of clinical utility currently restrict routine adoption. Prospective multicenter studies with harmonized endpoints and robust validation are required to facilitate clinical translation.</p>","PeriodicalId":19384,"journal":{"name":"Nuclear Medicine and Molecular Imaging","volume":"60 5","pages":"490-515"},"PeriodicalIF":2.3,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13627506/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149112906","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Soyoon Yoon, Jin-Sook Ryu, Yong-Il Kim, Hee Beom Jeong, Sun Ho Lee, Sae Rom Chung, Chong Hyun Suh, Dong Eun Song, Dong Yun Lee
{"title":"Inter-Assay Difference of Parathyroid Hormone Radioimmunoassay in Fine-Needle Aspirate from Neck Nodules According to Nodular Component.","authors":"Soyoon Yoon, Jin-Sook Ryu, Yong-Il Kim, Hee Beom Jeong, Sun Ho Lee, Sae Rom Chung, Chong Hyun Suh, Dong Eun Song, Dong Yun Lee","doi":"10.1007/s13139-026-01006-7","DOIUrl":"10.1007/s13139-026-01006-7","url":null,"abstract":"<p><strong>Purpose: </strong>The reliability of parathyroid hormone (PTH) assays in fine-needle aspirate (FNA) samples remains less established than in serum, particularly regarding assay variability and differences by nodule composition. This study evaluated inter-assay variability of measuring parathyroid hormone in fine-needle aspirates (PTH-FNA) washout samples across solid and cystic nodules.</p><p><strong>Methods: </strong>Patients with indeterminate neck nodules who underwent PTH-FNA testing were retrospectively analyzed. Nodules were classified as solid or cystic, and two commercial radioimmunoassay (RIA) kits (RIAKEY and Immunotech) were compared. Results were defined as positive or negative using each assay's serum PTH threshold (RIAKEY: 57 pg/mL; Immunotech: 85.8 pg/mL). Spearman's correlation (<i>ρ</i>) and diagnostic performance were assessed.</p><p><strong>Results: </strong>Fifty-eight cases were reviewed; 24 solid nodules (12 parathyroid adenomas [PAs], 12 non-parathyroid nodules [nPNs]), and 11 parathyroid cysts (PCs) were eligible. Among solid nodules, assays showed a strong correlation (<i>ρ</i> = 0.829), with Immunotech yielding slightly higher values; No inter-assay differences were observed in PAs, but nPNs differed significantly (<i>p</i> = 0.006). One PA was false-negative with RIAKEY, while Immunotech produced two false-positive nPNs; overall diagnostic performance was comparable (area under the curve = 0.986 vs. 0.979). For PCs, values were more variable than in solid nodules, albeit the correlation remained strong (<i>ρ</i> = 0.936). RIAKEY yielded significantly higher PTH-FNA values (<i>p</i> = 0.026), with discordant results in two cases.</p><p><strong>Conclusion: </strong>PTH-FNA results from two RIA kits were strongly correlated across nodule types. However, assay discrepancies in non-parathyroid and cystic nodules highlight the need for cautious interpretation.</p>","PeriodicalId":19384,"journal":{"name":"Nuclear Medicine and Molecular Imaging","volume":"60 5","pages":"524-532"},"PeriodicalIF":2.3,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13627574/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149112867","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Srinivas Ananth Kumar, Harish Goyal, A Shaheer Ahmed, Dhanapathi Halaniak
{"title":"Myocardial FAPI Uptake Post-myocardial Infarction in a Systemic Vasculitis Patient: Insights from <sup>68</sup>Ga-FAPI PET/CT.","authors":"Srinivas Ananth Kumar, Harish Goyal, A Shaheer Ahmed, Dhanapathi Halaniak","doi":"10.1007/s13139-026-00987-9","DOIUrl":"10.1007/s13139-026-00987-9","url":null,"abstract":"","PeriodicalId":19384,"journal":{"name":"Nuclear Medicine and Molecular Imaging","volume":"60 5","pages":"640-641"},"PeriodicalIF":2.3,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13627482/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149112846","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Long-Term Retrospective Evaluation of Radiochemical Yield Reproducibility of ⁶⁸Ga-Radiopharmaceuticals Using an SiO₂-Based ⁶⁸Ge/⁶⁸Ga Generator.","authors":"Raviteja Nanabala, Maroor Raghavan Ambikalmajan Pillai, Buvaneswari Gopal","doi":"10.1007/s13139-026-01018-3","DOIUrl":"10.1007/s13139-026-01018-3","url":null,"abstract":"<p><strong>Background: </strong>The radiosynthesis of gallium-68 radiopharmaceuticals is influenced by the bifunctional chelating agents (BFCAs) used for chelation. The reaction parameters such as reagent concentration, pH, temperature and reaction time need to be carefully optimized for each targeting molecule to get the highest radiochemical yields. The parent radionuclide <sup>68</sup>Ge used for the preparation of the generator has half-life of 271 days and hence the <sup>68</sup>Ge/<sup>68</sup>Ga generator is often used up to a year by which time the <sup>68</sup>Ge activity is ~ 40% of the load. However, the influence of generator aging on radiochemical yields have not been systematically reported, particularly with respect to different chelating agents in acetate buffer system.</p><p><strong>Results: </strong>The clinical doses of [<sup>68</sup>Ga]Ga-HBEDCC-PSMA-11, [<sup>68</sup>Ga]Ga-DOTA-TATE, and [<sup>68</sup>Ga]Ga-DOTA-Exendin-4 were prepared using an SiO<sub>2</sub> organic matrix-based generator supplied by Isotope Technologies Garching (ITG) in a semi-automated module with a fluidic system. Three generators were used during the course of the study and the radiochemical yields were monitored till the end of the generator life. Fluctuations in radiochemical yields were observed as the generator aged in the radiosynthesis of [<sup>68</sup>Ga]Ga-DOTA-TATE and [<sup>68</sup>Ga]Ga-DOTA-Exendin-4 whereas it was unaffected with [<sup>68</sup>Ga]Ga-HBEDCC-PSMA-11.</p><p><strong>Conclusions: </strong>The radiochemical yields are influenced as the generator ages, however, the extent of influence will depend on the chelating agent and buffer systems used for making the targeting molecule.</p>","PeriodicalId":19384,"journal":{"name":"Nuclear Medicine and Molecular Imaging","volume":"60 5","pages":"581-589"},"PeriodicalIF":2.3,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13627561/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149112884","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Setareh Hasanabadi, Seyed Mahmud Reza Aghamiri, Ahmad Ali Abin, Habibeh Vosoughi, Farshad Emami, Mehrdad Bakhshayesh Karam, Marzieh Nejabat, Abtin Dorudinia, Hossein Arabi, Habib Zaidi
{"title":"Enhanced Lymphoma Subtype Classification and Prognosis Using Machine Learning with <sup>18</sup>F-FDG PET/CT Radiomics: Beyond SUV<sub>max</sub>.","authors":"Setareh Hasanabadi, Seyed Mahmud Reza Aghamiri, Ahmad Ali Abin, Habibeh Vosoughi, Farshad Emami, Mehrdad Bakhshayesh Karam, Marzieh Nejabat, Abtin Dorudinia, Hossein Arabi, Habib Zaidi","doi":"10.1007/s13139-026-01017-4","DOIUrl":"https://doi.org/10.1007/s13139-026-01017-4","url":null,"abstract":"<p><strong>Background: </strong>This study explored a machine learning approach using <sup>18</sup>F-FDG PET/CT as a non-invasive alternative to biopsy, incorporating tumor-to-liver ratio (TLR) PET radiomics, and performed survival analysis to improve lymphoma management.</p><p><strong>Methods: </strong>In this cohort study, baseline <sup>18</sup>F-FDG PET/CT scans of newly diagnosed, histologically confirmed lymphoma patients were analyzed. Lesions were segmented using 3D Slicer, and radiomic features were extracted and normalized by tumor-to-liver ratios. Patient-level features were used to train three machine learning models (XGBoost, AdaBoost, Logistic Regression) using nested cross-validation with SMOTE for class balancing. A model based on SUV<sub>max</sub> metrics served as baseline. Radiomic features were also evaluated for correlation with 3- and 5-year survival using the Mann-Whitney U test.</p><p><strong>Results: </strong>A total of 156 lymphoma patients were analyzed, with 2,076 lesions segmented and 200 radiomic features extracted. For subtype classification, AdaBoost achieved the highest AUC for Diffuse Large B-cell (DLBCL) (0.863, accuracy 0.742), while XGBoost performed best for High-Grade Non-Hodgkin lymphoma (NHL) (AUC 0.825, accuracy 0.735) and Nodular Sclerosis Hodgkin Lymphoma (NS-HL) (AUC 0.827, accuracy 0.832). Logistic regression showed the best results for Classical Hodgkin Lymphoma (C-HL) (AUC 0.849, accuracy 0.775). The SUV<sub>max</sub>-based model (LR-SUV_MAX) consistently underperformed (AUCs: C-HL 0.630, High-Grade NHL 0.700, NS-HL 0.638, DLBCL 0.664), with all differences being statistically significant (<i>p</i> < 0.001). Radiomic and clinical features including SUV-GLSZM small area emphasis (<i>p</i> = 0.0019), age (<i>p</i> = 0.0002), and spleen involvement (<i>p</i> = 0.0014) were significantly associated with 3- and 5-year overall survival in 110 and 74 patients, respectively.</p><p><strong>Conclusion: </strong>Radiomic features combined with machine learning significantly improve lymphoma subtype classification over SUV<sub>max</sub> alone and show potential for predicting patient survival.</p><p><strong>Supplementary information: </strong>The online version contains supplementary material available at https://doi.org/10.1007/s13139-026-01017-4.</p>","PeriodicalId":19384,"journal":{"name":"Nuclear Medicine and Molecular Imaging","volume":"60 5","pages":"566-580"},"PeriodicalIF":2.3,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13627636/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149112843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Complementary Roles of <sup>18</sup>F-FDG PET/CT and <sup>68</sup>Ga-FAPI PET/CT in a Case of Cutaneous Angiosarcoma Uncovering Tumor Heterogeneity.","authors":"Srinivas Ananth Kumar, Vishnu Balgi, Harish Goyal, Dhanapathi Halanaik","doi":"10.1007/s13139-026-00997-7","DOIUrl":"10.1007/s13139-026-00997-7","url":null,"abstract":"","PeriodicalId":19384,"journal":{"name":"Nuclear Medicine and Molecular Imaging","volume":"60 5","pages":"650-652"},"PeriodicalIF":2.3,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13627507/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149112848","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}