Aileen Green, Peter Temsah, Leonard Goldfarb, Kristen Sanfolippo, Eric Knoche, Razi Muzaffar, Medhat M Osman
{"title":"Evaluating appropriateness of 18F-fluciclovine PET/CT relative to standard of care imaging guidelines and the impact of ADT on positivity: a prospective study in 62 Veterans Administration patients at a single institution.","authors":"Aileen Green, Peter Temsah, Leonard Goldfarb, Kristen Sanfolippo, Eric Knoche, Razi Muzaffar, Medhat M Osman","doi":"10.1097/MNM.0000000000001836","DOIUrl":"10.1097/MNM.0000000000001836","url":null,"abstract":"<p><strong>Background: </strong>According to the National Comprehensive Cancer Network Guidelines, 18F-fluciclovine PET/CT is considered appropriate after negative standard of care (SOC) imaging.</p><p><strong>Objective: </strong>To prospectively compare 18F-fluciclovine to SOC imaging, investigate whether it should be done when SOC imaging is (+), and evaluate its detection rate in patients receiving androgen deprivation therapy.</p><p><strong>Methods: </strong>We recruited 57 prostate cancer patients with biochemical recurrence with 18F-fluciclovine PET/CT and SOC imaging within 30 days. Prostate-specific antigen (PSA) level, Gleason score (GS), history of radical prostatectomy (RP), radiation therapy (RT) or hormone therapy (HT) were reviewed.</p><p><strong>Results: </strong>The 57 patients had a median PSA of 2.6 and average GS of 7.4; 27 (47.4%) had RP, 28 (49.1%) had RT, 1 (1.75%) had HT and 1 (1.75%) observation only. 18F-fluciclovine identified disease recurrence in 45/57 patients (78.9%), including oligometastasis in 18/45 (40%). SOC imaging identified recurrent disease in 12/57 patients (21.1%) while 18F-fluciclvoine identified additional sites of disease in 11/12 (91.7%). The (+) 18F-fluciclovine studies had a median PSA 2.6 ng/ml compared to 6.0 ng/ml in the (+) SOC studies.</p><p><strong>Conclusion: </strong>18F-fluciclovine was superior to SOC imaging for lesion detection, identification of oligometastasis and identification of additional sites of disease.</p>","PeriodicalId":19708,"journal":{"name":"Nuclear Medicine Communications","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140185151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
R. Mititelu, Alexandru Mitoi, C. Mazilu, Mariana Jinga, F. Radu, Ana Bucurica, Teodora Mititelu, S. Bucurică
{"title":"Advancements in hepatocellular carcinoma management: the role of 18F-FDG PET-CT in diagnosing portal vein tumor thrombosis.","authors":"R. Mititelu, Alexandru Mitoi, C. Mazilu, Mariana Jinga, F. Radu, Ana Bucurica, Teodora Mititelu, S. Bucurică","doi":"10.1097/MNM.0000000000001863","DOIUrl":"https://doi.org/10.1097/MNM.0000000000001863","url":null,"abstract":"Portal vein thrombosis, a relatively frequent complication associated with hepatocellular carcinoma (HCC) and liver cirrhosis, is recognized as a significant global health concern. This is mainly due to these conditions' high prevalence and potentially severe outcomes. The aim of our study was to conduct a comprehensive literature review to evaluate the efficacy, accuracy, and clinical implications of 18F-FDG PET-CT in diagnosing and managing portal vein tumor thrombosis (PVTT) in patients with HCC. HCC, which accounts for 80% of liver malignancies, ranks as the fourth most prevalent cancer globally and is a significant contributor to cancer-related mortality. The majority of HCC patients are diagnosed at an advanced stage, leading to a deterioration in patient outcomes. Involvement of the portal vein is also a significant negative factor. This review analyzes the application of 18F-FDG PET-CT in the detection and management of PVTT in patients with HCC, with an emphasis on the importance of the maximum standardized uptake value as an essential diagnostic and prognostic marker. 18F-FDG PET-CT is invaluable for detecting recurrence and guiding management strategies, particularly in patients with high-grade HCC, and plays a pivotal role in differentiating malignant portal vein thrombi from their benign counterparts.","PeriodicalId":19708,"journal":{"name":"Nuclear Medicine Communications","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2024-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140964767","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Alp Notghi, Gregory James, Joseph O'Brien, Ramesh Arasaradnam, Adrien Michael Peters, Fergus McKiddie, Tim Watts
{"title":"British Nuclear Medicine Society SeHCAT guidelines.","authors":"Alp Notghi, Gregory James, Joseph O'Brien, Ramesh Arasaradnam, Adrien Michael Peters, Fergus McKiddie, Tim Watts","doi":"10.1097/MNM.0000000000001854","DOIUrl":"https://doi.org/10.1097/MNM.0000000000001854","url":null,"abstract":"","PeriodicalId":19708,"journal":{"name":"Nuclear Medicine Communications","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2024-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141247737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Prospective evaluation of 68 Ga-NODAGA-RGD PET-CT in patients of carcinoma thyroid with thyroglobulin elevated negative radioiodine scintigraphy (TENIS) with a head-to-head comparison with FDG-PET/CT.","authors":"Abhay Gondhane, Priyanka Verma, Ashok Chandak, Sandip Basu","doi":"10.1097/MNM.0000000000001828","DOIUrl":"10.1097/MNM.0000000000001828","url":null,"abstract":"<p><strong>Background and aim: </strong>This study aimed to examine the expression of RGD binding integrins in patients of elevated serum thyroglobulin (Tg) level with negative radioiodine scintigraphy (TENIS) employing 68 Ga-NODAGA-RGD PET-CT.</p><p><strong>Material and methods: </strong>This was a prospective study involving 30 proven cases of TENIS with histopathological diagnosis of differentiated thyroid carcinoma post-surgery. In addition to observing the lesional concentration on 68 Ga-NODAGA-RGD PET-CT, a 4-point visual grading system (grade I-IV), was undertaken to estimate the degree of radiotracer avidity, for potential of theranostics.</p><p><strong>Results: </strong>On 18 F-FDG-PET/CT, the uptake was seen in 182 lesions out of a total of 200 (91%). 68 Ga-NODAGA-RGD PET-CT showed expression in a total of 110/200 (55%) lesions. On patient-specific analysis, 68 Ga-NODAGA-RGD PET-CT was positive for the disease in 21/30 patients (70%) and negative in 9/30 (30%) patients. The overall patient-specific sensitivity and specificity of 68 Ga-NODAGA-RGDPET-CT were 75% and 100%, respectively. 18 F-FDG PET-CT was positive for the disease in 26/30 patients (86.66%) and negative in 4/30 (13.33%) patients. The overall patient-specific sensitivity and specificity of 18 F-FDG-PET/CT were 92.86% and 100%, respectively. The 4-point visual grading system revealed 14/200 (7%) lesions demonstrating Grade I uptake, 49/200 (24.5%) lesions grade II uptake, 17/200 (8.5%) lesions grade III uptake and 40/200 (20%) lesions grade IV uptake.</p><p><strong>Conclusion: </strong>The results suggested that RGD-binding integrin is expressed in a sizeable fraction of metastatic lesions of TENIS cases, albeit demonstrating a varying degree of uptake. Out of the soft tissue, lung, and bone lesions, metastatic bone lesions showed more RGD affinity than other sites. The patients with substantial RGD uptake on a 4-point visual grading system may be potential targets for RGD-based therapy.</p>","PeriodicalId":19708,"journal":{"name":"Nuclear Medicine Communications","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140040094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Preoperative prediction of microsatellite instability status: development and validation of a pan-cancer PET/CT-based radiomics model.","authors":"Menglu Wang, Mengye Peng, Xinyue Yang, Ying Zhang, Tingting Wu, Zeyu Wang, Kezheng Wang","doi":"10.1097/MNM.0000000000001816","DOIUrl":"10.1097/MNM.0000000000001816","url":null,"abstract":"<p><strong>Objective: </strong>The purpose of this study is to verify the feasibility of preoperative prediction of patients' microsatellite instability status by applying a PET/CT-based radiation model.</p><p><strong>Methods: </strong>This retrospective study ultimately included 142 patients. Three prediction models have been developed. The predictive performance of all models was evaluated by the receiver operating characteristic curve and area under the curve values. The PET/CT radiological histology score (Radscore) was calculated to evaluate the microsatellite instability status, and the corresponding nomogram was established. The correlation between clinical factors and radiological characteristics was analyzed to verify the value of radiological characteristics in predicting microsatellite instability status.</p><p><strong>Results: </strong>Twelve features were retained to establish a comprehensive prediction model of radiological and clinical features. M phase of the tumor has been proven to be an independent predictor of microsatellite instability status. The receiver operating characteristic results showed that the area under the curve values of the training set and the validation set of the radiomics model were 0.82 and 0.75, respectively. The sensitivity, specificity, positive predictive value and negative predictive value of the training set were 0.72, 0.78, 0.83 and 0.66, respectively. The sensitivity, specificity, positive predictive value and negative predictive value of the validation set were 1.00, 0.50, 0.76 and 1.00, respectively. The risk of patients with microsatellite instability was calculated by Radscore and nomograph, and the cutoff value was -0.4385. The validity of the results was confirmed by the decision and calibration curves.</p><p><strong>Conclusion: </strong>Radiological models based on PET/CT can provide clinical and practical noninvasive prediction of microsatellite instability status of several different cancer types, reducing or avoiding unnecessary biopsy to a certain extent.</p>","PeriodicalId":19708,"journal":{"name":"Nuclear Medicine Communications","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139681341","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Analyzing the value of delayed 18 F-FDG PET/CT images in diagnosing small colorectal cancer liver metastases in patients with hypothyroidism based on diagnostic accuracy and image standardized uptake value.","authors":"Yusong Pei, Zhiguo Wang, Shanhu Hao, Yanan Tong, Ruixian Wu, Xinxin Qiao, Yanqing Liu, Guoxu Zhang","doi":"10.1097/MNM.0000000000001825","DOIUrl":"10.1097/MNM.0000000000001825","url":null,"abstract":"<p><strong>Purpose: </strong>The objective of this study was to investigate the value of delayed 18F fluorodeoxyglucose PET/computed tomography (18F-FDG PET/CT) images in patients with small colorectal cancer liver metastases (CRLMs) with hypothyroidism.</p><p><strong>Method: </strong>We performed a retrospective analysis of 66 small-CRLM patients with hypothyroidism and 66 small-CRLM patients with euthyroidism, all of whom underwent dual-time-point 18 F-FDG PET/CT imaging. First, the diagnostic accuracy of PET/CT early imaging and PET/CT delayed imaging on lesions was analyzed. Next, the correlation of metabolic parameters between PET/CT early imaging and PET/CT delayed imaging was analyzed according to the grouping of all lesions. Finally, PET/CT parameters were analyzed for correlation with thyroid hormones.</p><p><strong>Results: </strong>The diagnostic accuracy of delayed imaging in small-CRLM patients with hypothyroidism is not as good as that in small-CRLM patients with euthyroidism; PET/CT metabolic parameters are also unfavorable for the diagnosis of small-CRLM. For small-CRLM patients with hypothyroidism, the greater the thyroid-stimulating hormone level, the greater the uptake of 18 F-FDG in normal liver tissue, and the smaller the ratio of tumor lesion uptake to normal liver tissue uptake.</p><p><strong>Conclusion: </strong>PET/CT-delayed imaging has better performance than early imaging in small-CRLM patients with euthyroidism. However, the more severe the hypothyroidism, the worse the diagnostic delayed imaging performance. The scan time can be extended appropriately to optimize the imaging efficacy.</p>","PeriodicalId":19708,"journal":{"name":"Nuclear Medicine Communications","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139900256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Olof Jonmarker, Ted Nilsson, Rimma Axelsson, Lovisa Hult Ericson, Thuy A Tran, Antonios Tzortzakakis, Irina Savitcheva, Maria Holstensson
{"title":"[ 18 F]-PSMA-1007 PET imaging optimization and inter-rater reliability - a comparison of three different reconstructions read by four radiologists.","authors":"Olof Jonmarker, Ted Nilsson, Rimma Axelsson, Lovisa Hult Ericson, Thuy A Tran, Antonios Tzortzakakis, Irina Savitcheva, Maria Holstensson","doi":"10.1097/MNM.0000000000001823","DOIUrl":"10.1097/MNM.0000000000001823","url":null,"abstract":"<p><strong>Objectives: </strong>To increase understanding of optimal imaging parameters [ 18 F]PSMA-1007 when imaging patients with prostate cancer and to determine interrater agreement using [ 18 F]PSMA-1007.</p><p><strong>Methods: </strong>In this observational study, four independent physicians read reconstruction sets using bedtimes of 1, 2 and 3 minutes of patients undergoing [ 18 F]PSMA-1007. positron emission topography. Clear and equivocal lesions and their locations were recorded. Image noise was rated on a four-point scale. Lesion counts were compared using inter-class correlation whereas noise ratings were compared using generalized estimating equations. Repeated cases were used to assess intra-rater agreement.</p><p><strong>Results: </strong>Sixty reconstruction sets of 16 consecutively examined participants were included. Participants had a mean age of 71.5 years, six of them were examined prior to any treatment, three had a history of radiotherapy and seven of prostatectomy. Median Gleason score of primary tumors was 7. Imaging was performed after a mean of 132 min using a mean 3.95 MBq/Kg body weight of [ 18 F] PSMA-1007. Neither the total number of lesions per location nor the proportion of equivocal lesions varied consistently between bedtimes. Inter-rater reliability scores varied depending on location from 0.40 to 1.0 and were similar for all bedtimes. Intra-rater reliability varied between 0.70 and 0.76 for the three different bedtimes. Noise ratings were significantly lower for 1 minute than 3 minutes per bed.</p><p><strong>Conclusion: </strong>In the setting of [ 18 F]PSMA-1007 PET CT, 1, 2 and 3 minutes per bed produce similar results unlikely to affect clinical interpretation. Image noise ratings favor 2 and 3 minutes per bed.</p>","PeriodicalId":19708,"journal":{"name":"Nuclear Medicine Communications","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139681377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Predictive value of local control by 4'-[methyl-11C]-thiotymidine PET volume parameters in p16-negative oropharyngeal, hypopharyngeal, and supraglottic squamous cell carcinoma.","authors":"Yohei Ouchi, Takehito Kishino, Takenori Miyashita, Terushige Mori, Katsuya Mitamura, Takashi Norikane, Yuka Yamamoto, Hiroshi Hoshikawa","doi":"10.1097/MNM.0000000000001821","DOIUrl":"10.1097/MNM.0000000000001821","url":null,"abstract":"<p><strong>Purpose: </strong>We investigated the potential of baseline 4'-[methyl- 11 C]-thiothymidine ([ 11 C]4DST) PET for predicting loco-regional control of head and neck squamous cell carcinoma (HNSCC).</p><p><strong>Methods: </strong>A retrospective analysis was performed using volumetric parameters, such as SUVmax, proliferative tumor volume (PTV), and total lesion proliferation (TLP), of pretreatment [ 11 C]4DST PET for 91 patients with HNSCC with primary lesions in the oral cavity, hypopharynx, supraglottis, and oropharynx, which included p16-negative patients. PTV and TLP were calculated for primary lesions and metastatic lymph nodes combined. We examined the association among the parameters and relapse-free survival and whether case selection focused on biological characteristics improved the accuracy of prognosis prediction.</p><p><strong>Results: </strong>The area under the curves (AUCs) using PTV and TLP were high for the oropharyngeal/hypopharyngeal/supraglottis groups (0.91 and 0.87, respectively), whereas that of SUVmax was 0.66 ( P < 0.01). On the other hand, the oral group had lower AUCs for PTV and TLP (0.72 and 0.77, respectively). When all cases were examined, the AUCs using PTV and TLP were 0.84 and 0.83, respectively.</p><p><strong>Conclusion: </strong>Baseline [ 11 C]4DST PET/CT volume-based parameters can provide important prognostic information with p16-negative oropharyngeal, hypopharyngeal, and supraglottic cancer patients.</p>","PeriodicalId":19708,"journal":{"name":"Nuclear Medicine Communications","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139513199","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yasuhiro Fukushima, Keisuke Suzuki, Mai Kim, Wenchao Gu, Satoshi Yokoo, Yoshito Tsushima
{"title":"Evaluation of bone marrow invasion on the machine learning of 18 F-FDG PET texture analysis in lower gingival squamous cell carcinoma.","authors":"Yasuhiro Fukushima, Keisuke Suzuki, Mai Kim, Wenchao Gu, Satoshi Yokoo, Yoshito Tsushima","doi":"10.1097/MNM.0000000000001826","DOIUrl":"10.1097/MNM.0000000000001826","url":null,"abstract":"<p><strong>Objectives: </strong>Lower gingival squamous cell carcinoma (LGSCC) has the potential to invade the alveolar bone. Traditionally, the diagnosis of LGSCC relied on morphological imaging, but inconsistencies between these assessments and surgical findings have been observed. This study aimed to assess the correlation between LGSCC bone marrow invasion and PET texture features and to enhance diagnostic accuracy by using machine learning.</p><p><strong>Methods: </strong>A retrospective analysis of 159 LGSCC patients with pretreatment 18 F-fluorodeoxyglucose (FDG) PET/computed tomography (CT) examination from 2009 to 2017 was performed. We extracted radiomic features from the PET images, focusing on pathologic bone marrow invasion detection. Extracted features underwent the least absolute shrinkage and selection operator algorithm-based selection and were then used for machine learning via the XGBoost package to distinguish bone marrow invasion presence. Receiver operating characteristic curve analysis was performed.</p><p><strong>Results: </strong>From the 159 patients, 88 qualified for further analysis (59 men; average age, 69.2 years), and pathologic bone marrow invasion was identified in 69 (78%) of these patients. Three significant radiological features were identified: Gray level co-occurrence matrix_Correlation, INTENSITY-BASED_IntensityInterquartileRange, and MORPHOLOGICAL_SurfaceToVolumeRatio. An XGBoost machine-learning model, using PET radiomic features to detect bone marrow invasion, yielded an area under the curve value of 0.83.</p><p><strong>Conclusion: </strong>Our findings highlighted the potential of 18 F-FDG PET radiomic features, combined with machine learning, as a promising avenue for improving LGSCC diagnosis and treatment. Using 18 F-FDG PET texture features may provide a robust and accurate method for determining the presence or absence of bone marrow invasion in LGSCC patients.</p>","PeriodicalId":19708,"journal":{"name":"Nuclear Medicine Communications","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139900257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Machine learning diagnosis of active Juvenile Idiopathic Arthritis on blood pool [ 99M Tc] Tc-MDP scintigraphy images.","authors":"Hossein Kian Ara, Nafiseh Alemohammad, Zeinab Paymani, Marzieh Ebrahimi","doi":"10.1097/MNM.0000000000001822","DOIUrl":"10.1097/MNM.0000000000001822","url":null,"abstract":"<p><strong>Purpose: </strong>Neural network has widely been applied for medical classifications and disease diagnosis. This study employs deep learning to best discriminate Juvenile Idiopathic Arthritis (JIA), a pediatric chronic joint inflammatory disease, from healthy joints by exploring blood pool images of 2phase [ 99m Tc] Tc-MDP bone scintigraphy.</p><p><strong>Methods: </strong>Self-deigned multi-input Convolutional Neural Network (CNN) in addition to three available pre-trained models including VGG16, ResNet50 and Xception are applied on 1304 blood pool images of 326 healthy and known JIA children and adolescents (aged 1-16).</p><p><strong>Results: </strong>The self-designed model ROC analysis shows diagnostic efficiency with Area Under the Curve (AUC) 0.82 and 0.86 for knee and ankle joints, respectively. Among the three pertained models, VGG16 ROC analysis reveals AUC 0.76 and 0.81 for knee and ankle images, respectively.</p><p><strong>Conclusion: </strong>The self-designed model shows best performance on blood pool scintigraph diagnosis of patients with JIA. VGG16 was the most efficient model rather to other pre-trained networks. This study can pave the way of artificial intelligence (AI) application in nuclear medicine for the diagnosis of pediatric inflammatory disease.</p>","PeriodicalId":19708,"journal":{"name":"Nuclear Medicine Communications","volume":null,"pages":null},"PeriodicalIF":1.5,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139681340","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}