{"title":"PSMA PET/CT for early treatment response assessment of RANKL inhibitor therapy in giant cell tumor of bone","authors":"Wenjie Zhang, Guohua Shen","doi":"10.1007/s00259-025-07194-2","DOIUrl":"https://doi.org/10.1007/s00259-025-07194-2","url":null,"abstract":"","PeriodicalId":11909,"journal":{"name":"European Journal of Nuclear Medicine and Molecular Imaging","volume":"15 1","pages":""},"PeriodicalIF":9.1,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143582592","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}
{"title":"Impact of extended [177Lu] Lu-PSMA-617 therapy on absorbed kidney dose and CKD-EPI values: how long can therapy be safely continued?","authors":"Edanur Topal, Bilal Kovan, Ayca İribas, Serkan Kuyumcu, Mert Basaran, Aydan Malçok Demirtaş, Oner Sanli, Yasemin Sanli","doi":"10.1007/s00259-025-07125-1","DOIUrl":"https://doi.org/10.1007/s00259-025-07125-1","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Purpose</h3><p>This study aimed to evaluate the personalized dosimetric approach by calculating the cumulative renal absorbed dose (cRD) and assessing its impact on renal functions in patients diagnosed with metastatic castration-resistant prostate cancer who underwent four or more cycles of [<sup>177</sup>Lu] Lu-PSMA − 617 therapy.</p><h3 data-test=\"abstract-sub-heading\">Methods</h3><p>The study included 110 patients who received ≥ 4 cycles of [<sup>177</sup>Lu] Lu-PSMA − 617 therapy. Whole-body static and abdominal SPECT-CT imaging was performed at 4, 24, and 96 h post-administration. Kidney function was assessed using dynamic renal scintigraphy and biochemical tests conducted prior to treatment. Estimated glomerular filtration rate (eGFR) levels were calculated using the CKD-EPI formula before each treatment cycle and at the 6th week post-treatment.</p><h3 data-test=\"abstract-sub-heading\">Results</h3><p>Pearson correlation analysis reveal no significant relationship between cRD and CKD-EPI values (<i>p</i> >.05). No significant differences were observed between pre-treatment CKD-EPI levels and those measured after the 4th, 5th, 6th, 7th, and 8th cycles (<i>p</i> >.05). Among patients reaching a cRD of 23 Gy, a statistically significant difference was observed between pre- and post-treatment CKD-EPI values (<i>p</i> <.05). Of the 13 patients exceeding cRD of 28 Gy, five maintained CKD-EPI levels above 90 mL/min/1.73 m<sup>2</sup> post-treatment.</p><h3 data-test=\"abstract-sub-heading\">Conclusion</h3><p>Despite treatment-related declines in eGFR levels, our findings indicate that a personalized dosimetric approach may enable extended cycles of [<sup>177</sup>Lu] Lu-PSMA-617 therapy with manageable nephrotoxicity. Considering the significant inter-patient variability, establishing universal absorbed dose-response relationships remains challenging. Prospective multicenter studies are crucial to refining toxicity thresholds and advancing tailored treatment strategies to optimize safety and efficacy.</p>","PeriodicalId":11909,"journal":{"name":"European Journal of Nuclear Medicine and Molecular Imaging","volume":"31 1","pages":""},"PeriodicalIF":9.1,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143582595","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}
{"title":"Head-to-head comparison of [18F]FAPI-42 and [18F]FDG PET/CT in the evaluation of laryngeal squamous cell carcinoma","authors":"Renxiang Xia, Xudong Wang, Jun Cheng, Xin Li, Jinju Sun, Qingli Zeng, Daoxi Hu, Jianping You, Yanli Xiong, Xiao Chen","doi":"10.1007/s00259-025-07180-8","DOIUrl":"https://doi.org/10.1007/s00259-025-07180-8","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Purpose</h3><p>To investigate the clinical utility of [<sup>18</sup>F]FAPI-42 PET/CT relative to [<sup>18</sup>F]FDG PET/CT for tumor detection and staging in laryngeal squamous cell carcinoma (LSCC) patients.</p><h3 data-test=\"abstract-sub-heading\">Methods</h3><p>Patients with pathologically proven LSCC were prospectively enrolled. All patients underwent [<sup>18</sup>F]FDG and [<sup>18</sup>F]FAPI-42 PET/CT within 1 week. Primary tumor and lymph node showed by [<sup>18</sup>F]FDG and [<sup>18</sup>F]FAPI-42 PET/CT were compared by SUVmax and visual assessment. The primary tumor volumes derived from [<sup>18</sup>F]FDG PET, [<sup>18</sup>F]FAPI-42 PET, and contrast-enhanced CT were also compared.</p><h3 data-test=\"abstract-sub-heading\">Results</h3><p>Twenty-one patients were included from January to October 2024. [<sup>18</sup>F]FAPI-42 PET/CT has a higher positive detection rate of primary tumor than [<sup>18</sup>F]FDG (100% vs. 85.7%). For visual assessment of primary tumor invasion, [<sup>18</sup>F]FAPI-42 was superior to [<sup>18</sup>F]FDG in 9 of 21 patients (42.9%) and inferior to [<sup>18</sup>F]FDG in 1 patient (4.8%), which was confirmed by pathology. The diagnostic efficacy of [<sup>18</sup>F]FAPI-42 PET/CT for T staging was higher than that of [<sup>18</sup>F]FDG PET/CT (95.3% vs. 57.1%, <i>P</i> = 0.021). [<sup>18</sup>F]FAPI-42 led to downstaging of N stage in 4 of 21 patients (19.0%) relative to [<sup>18</sup>F]FDG PET/CT, which was consistent with pathology. Compared with [<sup>18</sup>F]FDG, [<sup>18</sup>F]FAPI-42 PET/CT changed overall staging in 10 of 21 patients, with 5 patients being up-staged and 5 down-staged. When 35% SUVmax of [<sup>18</sup>F]FDG or 40% SUVmax of [<sup>18</sup>F]FAPI-42 was used as a threshold for delineating tumor volume, it was highly consistent with contrast-enhanced CT.</p><h3 data-test=\"abstract-sub-heading\">Conclusion</h3><p>[<sup>18</sup>F]FAPI-42 outperforms [<sup>18</sup>F]FDG in the tumor detection, staging, and the delineation of primary tumor, indicating that [<sup>18</sup>F]FAPI-42 PET/CT may serve as a promising imaging modality for detecting and staging patients with LSCC. Its value regarding distant metastases evaluation requires further investigation.</p><h3 data-test=\"abstract-sub-heading\">Trial registration</h3><p>NCT06304155. https://clinicaltrials.gov/study/NCT06304155.</p>","PeriodicalId":11909,"journal":{"name":"European Journal of Nuclear Medicine and Molecular Imaging","volume":"53 1","pages":""},"PeriodicalIF":9.1,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143575253","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}
Yuqing Sun, Yihan Zhao, Di Sun, Xingyu Mu, Jiao Li, Chenghui Lu, Lu Lu, Chunhao Lin, Jinfu Lv, Ruochen Li, Xufu Wang, Yijin Pan, Wuying Cheng, Yan-Song Lin, Wei Fu
{"title":"Reflective analysis on the current 131I adjuvant therapy indications in intermediate- and high-risk differentiated thyroid cancer","authors":"Yuqing Sun, Yihan Zhao, Di Sun, Xingyu Mu, Jiao Li, Chenghui Lu, Lu Lu, Chunhao Lin, Jinfu Lv, Ruochen Li, Xufu Wang, Yijin Pan, Wuying Cheng, Yan-Song Lin, Wei Fu","doi":"10.1007/s00259-025-07153-x","DOIUrl":"https://doi.org/10.1007/s00259-025-07153-x","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Purpose</h3><p>Radioiodine (<sup>131</sup>I) adjuvant therapy (RAT) is given to treat subclinical tumor of differentiated thyroid cancer (DTC) that may or may not actually be present after prior adequate treatment, yet the indications and benefits for RAT remain controversial. This multi-center study retrospectively evaluated the real targets and responses to RAT in intermediate- and high-risk patients, aiming to refine current “one-size-fits-all” guidelines.</p><h3 data-test=\"abstract-sub-heading\">Methods</h3><p>Totally 599 intermediate- and high-risk DTC patients from three centers were enrolled. The post-operative disease status, instant purpose verification and 12-month response to RAT were assessed using thyroglobulin levels, imagings and post-therapy whole-body scan (Rx-WBS) during follow-ups.</p><h3 data-test=\"abstract-sub-heading\">Results</h3><p>Totally 49.75% patients were assessed as post-operative disease status excellent response (ER)/indeterminate response (IDR), 37.56% patients were biochemical incomplete response (BIR) and 12.69% were structural incomplete response (SIR). Through instant purpose verification, 49.92%, 36.73%, and 13.36% patients were targeted at remnant thyroid, biochemical and structural/functional disease, respectively. 59.39%, 13.48%, 16.55%, and 10.58% patients were ER, IDR, BIR and SIR at 12-month final response, respectively. 95.64% patients with post-operative ER/IDR remained 12-month ER/IDR. 45.78% post-operative BIR converted to ER/IDR. Intermediaterisk, T1/T2 staging, non-thyroid capsule invasion, non-multifocal lesion, times of surgery, no abnormal finding on Rx-WBS were predictors for post-operative BIR transferred to 12-month ER/IDR (all <i>P</i> < 0.05).</p><h3 data-test=\"abstract-sub-heading\">Conclusion</h3><p>Intermediate-risk patients with post-operative ER or IDR might be spared from aggressive RAT, and patients with post-operative BIR could be potential candidates for RAT at higher administered activities (>3.7 GBq, median 5.55 GBq, IQR 4.625 GBq-5.55 GBq), especially in those with less aggressive clinicopathological features who may even obtain ER/IDR at 12-month response.</p>","PeriodicalId":11909,"journal":{"name":"European Journal of Nuclear Medicine and Molecular Imaging","volume":"193 1","pages":""},"PeriodicalIF":9.1,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143575257","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}
{"title":"Clinical comprehensive evaluation of [18F]AlF-FAP-NUR PET: multi-time-point imaging, head-to-head comparison with [18F]FDG","authors":"Ziqi Zhang, Shaoyu Liu, Sihao Liang, Xuejing Bai, Yulu He, Jiawei Zhong, Wanmei Liang, Peng Hou, Huizhen Zhong, Tingfan Wu, Yee Ling Ng, Jing Zhang, Miao Ke, Yimin Fu, Xinlu Wang","doi":"10.1007/s00259-025-07171-9","DOIUrl":"https://doi.org/10.1007/s00259-025-07171-9","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Purpose</h3><p>This study was designed to investigate the clinical feasibility of [<sup>18</sup>F]AlF-FAP-NUR, including the pharmacokinetics, radiation dosimetry estimation, and the head-to-head comparison with [<sup>18</sup>F]FDG. The head-to-head comparison study was designed to investigate the radiotracer uptake of [<sup>18</sup>F]AlF-FAP-NUR, to detect the primary and metastatic lesions in patients with various solid cancers, and to compare the results with those of [<sup>18</sup>F]FDG PET/CT. The correlation of FAP-expression (H-scores) and standardized uptake values (SUVs) derived from [<sup>18</sup>F]AlF-FAP-NUR were also included.</p><h3 data-test=\"abstract-sub-heading\">Methods</h3><p>Ten patients participated in a multi-time-point imaging protocol aimed at assessing pharmacokinetics and estimating radiation dosimetry. Radiation dosimetry calculations were performed using the OLINDA/EXM 2.0 software. For the comparative analysis between [<sup>18</sup>F]AlF-FAP-NUR and [<sup>18</sup>F]FDG PET, a cohort of 35 patients was included. SUVs and tumor-to-background ratios (TBRs) for primary and metastatic lesions were systematically collected and analyzed. To evaluate FAP expression in tissue samples, H-scores were obtained from FAP-immunohistochemistry (FAP-IHC) analyses of samples from 28 patients and correlated with the SUVs measured in [<sup>18</sup>F]AlF-FAP-NUR PET scans. Statistical analyses included non-parametric tests and correlation assessments, with a significance threshold set at <i>P</i> < 0.05.</p><h3 data-test=\"abstract-sub-heading\">Results</h3><p>The study of multi-time-point imaging demonstrated that tumor SUV<sub>max</sub> and TBRs increased over time, quickly peaking and remaining in a plateau phase [<sup>18</sup>F]AlF-FAP-NUR was mainly excreted from kidneys. The effective radiation dose of [<sup>18</sup>F]AlF-FAP-NUR was approximately 1.90E-02 mSv/MBq. In the head-to-head comparative study, [<sup>18</sup>F]AlF-FAP-NUR exhibited excellent detection capabilities for both primary and metastatic lesions, particularly in lymph node, bone, and lung metastases. The sensitivity and specificity of [<sup>18</sup>F]AlF-FAP-NUR PET/CT imaging for detecting lesions, as confirmed by pathology, were 86.7% and 98.3%, respectively. The positive predictive value (PPV) reached 89.7%, more than double that of [<sup>18</sup>F]FDG (PPV for FDG: 42.3%). Correlation analysis of the SUVs of [<sup>18</sup>F]AlF-FAP-NUR and FAP expression (based on H-score) showed that SUVs were all strongly correlated with FAP expression, with the SUV<sub>max</sub> correlation value being as high as 0.7729 (<i>P</i> < 0.001).</p><h3 data-test=\"abstract-sub-heading\">Conclusion</h3><p>Our pilot study in patients with various solid tumors has demonstrated acceptable radiation dosimetry, favorable biodistribution, and significant [<sup>18</sup>F]AlF-FAP-NUR uptake in FAP-expressing tumors. The strong correlation with FAP expre","PeriodicalId":11909,"journal":{"name":"European Journal of Nuclear Medicine and Molecular Imaging","volume":"9 1","pages":""},"PeriodicalIF":9.1,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143575252","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}
Riccardo Muglia, Massimo De Giorgio, Paolo Marra, Francesco Saverio Carbone, Ludovico Dulcetta, Carolina Prussia, Alessandro Loglio, Arianna Ghirardi, Laura Antra Grikke, Claudia Bianchi, Gian Luca Poli, Alberto Gerali, Paola Anna Erba, Sandro Sironi, Stefano Fagiuoli, Mauro Viganò
{"title":"Long-term outcomes of Yttrium-90 transarterial radioembolization for patients with hepatocellular carcinoma","authors":"Riccardo Muglia, Massimo De Giorgio, Paolo Marra, Francesco Saverio Carbone, Ludovico Dulcetta, Carolina Prussia, Alessandro Loglio, Arianna Ghirardi, Laura Antra Grikke, Claudia Bianchi, Gian Luca Poli, Alberto Gerali, Paola Anna Erba, Sandro Sironi, Stefano Fagiuoli, Mauro Viganò","doi":"10.1007/s00259-025-07185-3","DOIUrl":"https://doi.org/10.1007/s00259-025-07185-3","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Aims</h3><p>We retrospectively assessed the long-term outcomes of Yttrium-90 (<sup>90</sup>Y) transarterial radioembolization (TARE) for hepatocellular carcinoma (HCC), focusing on overall survival (OS), radiological response, and safety.</p><h3 data-test=\"abstract-sub-heading\">Methods</h3><p>We included patients with HCC treated with <sup>90</sup>Y TARE at a single center between January 2012 and December 2021 with measurable lesions and a minimum of 2 years of follow-up. Only the former was analyzed for patients with multiple TARE. The primary endpoints were long-term OS, radiological response, and safety; the secondary endpoints included predictors of OS and response, with emphasis on dosimetry. The collected data included demographics, laboratory test results, liver function, and tumor staging. Radiological response was evaluated 3–6 months post-TARE using the modified RECIST (mRECIST) criteria. OS was calculated from TARE until death or censoring. Univariate logistic regression was used to identify the predictors of complete radiological response and OS. Dosimetry was analyzed to determine correlations with mRECIST response.</p><h3 data-test=\"abstract-sub-heading\">Results</h3><p>Among 142 patients (median age 66.8, cirrhotic 92.3%; M: F = 121:21), a median OS of 16.68 months was achieved, with a complete radiological response in 31% (44/142). OS was strongly correlated with radiological response (<i>p</i> < 0.001). Absorbed dose ≥ 234.6 Gy was associated with complete response (<i>p</i> = 0.017) but not with survival (<i>p</i> = 0.102). Rising alpha-fetoprotein levels (<i>p</i> = 0.017) and worsening Child-Pugh scores post-TARE (<i>p</i> = 0.044) were independent predictors of mortality.</p><h3 data-test=\"abstract-sub-heading\">Conclusion</h3><p>A complete radiological response is crucial for long-term survival, highlighting the need for dosimetry optimization in TARE for HCC.</p>","PeriodicalId":11909,"journal":{"name":"European Journal of Nuclear Medicine and Molecular Imaging","volume":"3 1","pages":""},"PeriodicalIF":9.1,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143575256","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}
Hao-Jie Chen, Mingkai Zhang, Min Wei, Xianfeng Yu, Yichen Wang, Jie Yang, Ruixian Li, Weina Zhao, Xuanqian Wang, Shuyu Zhang, Kexin Wang, Tianyu Bai, Yanxi Huo, Weijie Huang, Zhengjia Dai, Guolin Ma, Ying Han, Guanqun Chen, Ni Shu
{"title":"Amyloid pathology related to aberrant structure-function coupling of brain networks in Alzheimer’s disease: insights from [18F]-florbetapir PET imaging","authors":"Hao-Jie Chen, Mingkai Zhang, Min Wei, Xianfeng Yu, Yichen Wang, Jie Yang, Ruixian Li, Weina Zhao, Xuanqian Wang, Shuyu Zhang, Kexin Wang, Tianyu Bai, Yanxi Huo, Weijie Huang, Zhengjia Dai, Guolin Ma, Ying Han, Guanqun Chen, Ni Shu","doi":"10.1007/s00259-025-07172-8","DOIUrl":"https://doi.org/10.1007/s00259-025-07172-8","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Purpose</h3><p>Brain structure-function coupling (SFC), which reflects the degree to which anatomical structure supports neural function, is an emerging imaging marker in neurodegenerative diseases. However, its pathological underpinnings in Alzheimer’s disease (AD) remain poorly understood. This study aimed to examine the association among amyloid pathology, SFC disruption and cognitive decline.</p><h3 data-test=\"abstract-sub-heading\">Methods</h3><p>We included 173 participants from the SILCODE cohort, comprising cognitively unimpaired (CU) and cognitively impaired (CI) individuals. Amyloid pathology was quantified using [<sup>18</sup>F]-florbetapir PET standardized uptake value ratios (SUVR). Structural connectivity (SC) was derived from diffusion-weighted MRI with probabilistic tractography, while functional connectivity (FC) was calculated from resting-state functional MRI. SFC was defined as the coefficient of determination from linear models predicting FC based on SC at regional level. Linear regression and mediation analyses were conducted to assess relationships between amyloid pathology, SFC, and multiple cognitive performances.</p><h3 data-test=\"abstract-sub-heading\">Results</h3><p>Compared to CU individuals, CI participants exhibited increased regional SFC primarily within the default mode network regions (<i>p</i> < 0.05). In CI participants, amyloid pathology correlated with SFC across occipital lobe, precuneus and temporoparietal regions, which was specific by APOE ε4 status (<i>p</i> < 0.05). Mediation analyses revealed that SFC partially mediated the relationship between amyloid pathology and cognitive impairment (<i>ab</i><sub><i>MoCA−B</i></sub> = -0.14, 95% CI [-0.27, -0.02]). Similar findings were replicated with plasma markers.</p><h3 data-test=\"abstract-sub-heading\">Conclusion</h3><p>Amyloid pathology may underlie SFC disruptions, contributing to cognitive decline in AD. These findings suggest that SFC may serve as a potential biomarker for amyloid-related neurodegeneration and cognitive impairment.</p><h3 data-test=\"abstract-sub-heading\">Trial registration</h3><p>The SILCODE is listed on the ClinicalTrials.gov registry (SILCODE: NCT03370744).</p>","PeriodicalId":11909,"journal":{"name":"European Journal of Nuclear Medicine and Molecular Imaging","volume":"37 1","pages":""},"PeriodicalIF":9.1,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143570362","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}
Denis Krajnc, Clemens P. Spielvogel, Boglarka Ecsedi, Zsombor Ritter, H. Alizadeh, Marcus Hacker, Laszlo Papp
{"title":"Clinician-driven automated data preprocessing in nuclear medicine AI environments","authors":"Denis Krajnc, Clemens P. Spielvogel, Boglarka Ecsedi, Zsombor Ritter, H. Alizadeh, Marcus Hacker, Laszlo Papp","doi":"10.1007/s00259-025-07183-5","DOIUrl":"https://doi.org/10.1007/s00259-025-07183-5","url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Background</h3><p>Artificial Intelligence (AI) approaches in clinical science require extensive data preprocessing (DP) steps prior to building AI models. Establishing DP pipelines is a non-trivial task, mainly driven by purely mathematical rules and done by data scientists. Nevertheless, clinician presence shall be paramount at this step. The study proposes a data preprocessing approach driven by clinical domain knowledge, where clinician input, in form of explicit and non-explicit rules, directly impacts the algorithms’ decision-making processes, thus, making the DP planning phase more inclusive for clinicians.</p><h3 data-test=\"abstract-sub-heading\">Methods</h3><p>The rule set table (RST) was introduced as interface which accepts clinician’s input as formal rules (including four actions: exp-keep, exp-remove, pref-keep, pref-remove features or samples) in human-readable form and translates it to machine readable input for preprocessing algorithms. A collection of commonly used algorithms was incorporated for data preprocessing of various clinical cohorts in both single and multi-center scenarios. The impact of RST was evaluated by utilizing 100-fold Monte Carlo cross-validation scheme for prostate and glioma cohorts (single center) with 80 − 20% training-testing split. Furthermore, diffuse large B-cell lymphoma (DLBCL) cohort was evaluated by using Center 1 as training and Center 2 as testing cohort for clinical endpoint prediction. Both scenarios were investigated in manual and automated data preprocessing setups across all cohorts. The XGBoost algorithm was employed for classification tasks across all established models. Predictive performance was estimated by confusion matrix analysis in validation samples of all cohorts. The performance of RST across all actions as well as without RST were compared in both manual and automated settings for each respective cohort.</p><h3 data-test=\"abstract-sub-heading\">Results</h3><p>Performance increase of ML models with manual preprocessing combined with RST was up-to 18% balanced accuracy (BACC) compared to models without RST. The ML models with “exp-keep” and “pref-keep” instructions showed highest performance increase of + 18% BACC (glioma), + 6% BACC (prostate) and + 3% BACC (DLBCL) compared to other models across all datasets.</p><h3 data-test=\"abstract-sub-heading\">Conclusion</h3><p>The study demonstrated the added value of RST in predictive performance of oncology-specific ML models, hence, serving as proof of concept of a more inclusive clinician-driven DP process in future studies.</p>","PeriodicalId":11909,"journal":{"name":"European Journal of Nuclear Medicine and Molecular Imaging","volume":"8 1","pages":""},"PeriodicalIF":9.1,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143570359","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}
Ana Devesa, Philip M. Robson, Busra Cangut, Renata Pyzik, Munir Ghesani, Adam Jacobi, Zahi A. Fayad, Maria Giovanna Trivieri
{"title":"Can pulmonary artery 18F-FDG uptake serve as a risk marker in precapillary pulmonary hypertension?","authors":"Ana Devesa, Philip M. Robson, Busra Cangut, Renata Pyzik, Munir Ghesani, Adam Jacobi, Zahi A. Fayad, Maria Giovanna Trivieri","doi":"10.1007/s00259-025-07181-7","DOIUrl":"https://doi.org/10.1007/s00259-025-07181-7","url":null,"abstract":"","PeriodicalId":11909,"journal":{"name":"European Journal of Nuclear Medicine and Molecular Imaging","volume":"18 1","pages":""},"PeriodicalIF":9.1,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143570352","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}