Background Since 1992, the incidence of lung cancer has shown an overall downward trend, with survival rates significantly improving in recent years due to the application of immune checkpoint inhibitors (ICIs). Assessing programmed death ligand 1 (PD-L1) expression status in lung cancer patients is crucial for predicting the efficacy of ICIs and formulating treatment plans. Therefore, there is an urgent need to assess PD-L1 expression status in lung cancer patients, particularly those with nonsmall cell lung cancer (NSCLC). While numerous studies have demonstrated promising results using artificial intelligence (AI) models based on radiomics, current understanding in this area remains incomplete. Method We conducted a search of medical databases and screened studies that meet the criteria. We performed feature extraction and data extraction from these studies, analysed them using R software, and generated forest plots. We conducted subgroup analyses based on imaging modality and algorithm model. Results A total of 35 studies were included in the analysis. For the Tumor Proportion Score (TPS)1 group, the pooled area under the curve (AUC) for the validation set was 0.782. For the TPS50 group, the pooled AUC for the validation set was 0.798. Subgroup analysis revealed that machine learning performed better when predicting TPS50, while deep learning was superior for predicting TPS1. When predicting TPS, prediction models constructed using 2 - fluoro-2-deoxy- d -glucose ( 18 F) positron emission tomography/computed tomography (CT) and contrast-enhanced CT outperformed those based on noncontrast CT. Conversely, when predicting a TPS, the noncontrast-CT-based prediction model significantly outperformed the other two groups. Conclusions Imaging modality and algorithm model are key factors influencing AI prediction models for PD-L1 expression in NSCLC patients.

BACKGROUND:The incidence of lung diseases has been increasing in recent years, especially lung cancer and interstitial lung disease. However, the diagnosis of lung diseases such as lung cancer and ILD still has some limitations. Therefore, finding an appropriate imaging agent and technique is of great clinical value for the diagnostic evaluation of lung diseases. METHOD:A thorough search of all relevant literature up to 20 June 2024 was undertaken. Studies evaluating lung lesions with FAPI PET were screened and patient diagnostic data were extracted. Risk of bias was checked by the QUADAS-2. Meta-analysis was performed in STATA17.0. Subgroups were analysed for the effectiveness of FAPI PET/CT in the diagnostic assessment of various lung diseases. RESULT:19 studies were finally sieved. Meta-analysis showed that the sensitivity of FAPI PET/CT for the detection of lung tumours was 0.99 (95% CI: 0.90-1.00), with a specificity of 0.82 (95% CI: 0.72-0.89). The sensitivity of FAPI PET/CT for the assessment of non-neoplastic lesions was 0.93 (95% CI: 0.72-0.99) and the specificity was 0.96 (95% CI: 0.79-0.99). Subgroup analysis showed that FAPI PET/CT had a sensitivity of 0.93 (95% CI: 0.83-0.97) in lung tumour staging (n = 397). In addition, the sensitivity and specificity of FAPI PET/CT were 0.80 (95% CI: 0.70-0.89) and 0.90 (95% CI: 0.84-0.96) for pneumonia, and 1.00 for assessing idiopathic pulmonary fibrosis. CONCLUSION:Our results show that FAPI PET/CT has an excellent diagnostic performance for lung tumours and non-tumour lesions.Points for clinical research: Currently CT is unable to accurately determine the activity of lung diseases such as IPF and hence may lead to delays in the diagnosis and treatment of some lung diseases. We aimed to find evidence-based medical evidence suitable for FAPI PET in lung diseases, especially non-oncological diseases, by performing a meta-analysis of FAPI PET in assessing lung diseases.

Alzheimer’s disease (AD) is the most common neurodegenerative disease and the most likely to lead to dementia. With the availability of the latest therapies, the need for Alzheimer’s disease diagnosis is now gradually increasing. Whereas blood phosphorylated-tau (p-tau) has demonstrated excellent performance in the prediction and diagnosis of disease progression and Aβ positivity in AD, there are differences between different p-tau subtypes. Therefore, a pooled analysis of different blood p-tau subtypes is of more important clinical value. Relevant literature was screened by complete search in four databases, Pubmed, Embase, Cochrane Library and Scopus. Relevant data and AUC and their confidence intervals of the included literature were extracted and analyzed by classification according to p-tau subtypes. Quality assessment was performed using the QUADAS-2 tool. Our results reveal that p-tau217 performs better in the diagnostic performance in most stages of AD, which is consistent with the guidelines. However, our results concluded that p-tau217 has poorer diagnostic performance in the stages of cognitive unimpaired or less cognitively impaired, especially in the Aβ positivity diagnosis of SCD and CU. Head-to-head meta-analyses formally confirmed that p-tau217 significantly outperforms p-tau181 across AD dementia, Aβ positivity, tau positivity, and biological staging (all P < 0.05), whereas no significant difference was observed between p-tau231 and p-tau181. By integrating single-arm pooled AUC estimates with formal head-to-head statistical comparisons, our study provides evidence-based support for plasma p-tau217 as the subtype with the most robust diagnostic performance across AD pathology and biological staging. Head-to-head analyses formally confirmed that p-tau217 significantly outperforms p-tau181 in Aβ positivity, Tau positivity, and biological staging.

A 43-year-old man presented with left hip pain. Contrast-enhanced CT demonstrated lytic destruction of the left ilium and sacrum with associated soft-tissue extension, suggestive of a bone tumor. Subsequent & sup1;F-8-FDG PET/CT revealed only mild or no FDG avidity in lesions involving the ilium, sacrum, and right fibula. In contrast, these lesions demonstrated intense or elevated uptake on PSMA/FAPI bispecific tracer & sup1;F-8-ALF-NOTA-PSFA-1 PET/CT. These observations indicate that & sup1;F-8-ALF-NOTA-PSFA-1 PET/CT holds considerable potential for sarcoma detection and may support the development of PSMA/FAPI bispecific targeted receptor radionuclide therapy.

A 43-year-old man presented with left hip pain. Contrast-enhanced CT demonstrated lytic destruction of the left ilium and sacrum with associated soft-tissue extension, suggestive of a bone tumor. Subsequent ¹⁸F-FDG PET/CT revealed only mild or no FDG avidity in lesions involving the ilium, sacrum, and right fibula. In contrast, these lesions demonstrated intense or elevated uptake on PSMA/FAPI bispecific tracer ¹⁸F-ALF-NOTA-PSFA-1 PET/CT. These observations indicate that ¹⁸F-ALF-NOTA-PSFA-1 PET/CT holds considerable potential for sarcoma detection and may support the development of PSMA/FAPI bispecific targeted receptor radionuclide therapy.

Amyloid and tau proteins are important proteins in the pathological changes of Alzheimer's disease (AD), while Aβ pathology and tau pathology are the most critical factors contributing to the development of AD. Some studies have shown that there is a causal relationship between AD and diabetes mellitus, but there are no studies showing a causal relationship between diabetic traits and AD biomarkers, so further exploration is needed. We first summarized and analyzed the currently published literature on the link between diabetes and AD through a systematic review. Forest plots were used to observe whether there is an association between diabetes and AD. Then a two-sample Mendelian randomization (MR) analysis based on GWAS summary statistics was performed to verify the causal relationship between diabetic traits and AD biomarkers. Based on summary statistics from the GWAS, potential causal relationships between diabetic traits and AD biomarkers were explored separately. The results of the meta-analysis part showed that diabetes can increase the risk of AD. Meanwhile, our two-sample MR results showed a significant causal relationship between diabetes and plasma Aβ40. In addition, our two-sample MR results also showed a causal relationship between increased HbA1c and plasma APLP2. Other diabetic traits may have potential effects on different AD plasma markers.

Introduction:The progression of Alzheimer's disease (AD) has been shown to significantly correlate with changes in brain tissue structure and leads to cognitive decline and dementia. Using radiomic features derived from brain magnetic resonance imaging (MRI) scan, we can get the help of deep learning (DL) model for diagnosing AD. Methods:This study proposes the use of the DL model under the framework of MR radiomics for AD diagnosis. Two cross-racial independent cohorts from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database (141 AD, 166 Mild Cognitive Impairment (MCI), and 231 normal control (NC) subjects) and Huashan hospital (45 AD, 35 MCI, and 31 NC subjects) were enrolled. We first performed preprocessing of MRI using methods such as spatial normalization and denoizing filtering. Next, we conducted Statistical Parametric Mapping analysis based on a two-sample t-test to identify regions of interest and extracted radiomic features using Radiomics tools. Subsequently, feature selection was carried out using the Least Absolute Shrinkage and Selection Operator model. Finally, the selected radiomic features were used to implement the AD diagnosis task with the TabNet model. Results:The model was quantitatively evaluated using the average values obtained from five-fold cross-validation. In the three-way classification task, the model achieved classification average area under the curve (AUC) of 0.8728 and average accuracy (ACC) of 0.7111 for AD versus MCI versus NC. For the binary classification task, the average AUC values were 0.8778, 0.8864, and 0.9506 for AD versus MCI, MCI versus NC, and AD versus NC, respectively, with average ACC of 0.8667, 0.8556, and 0.9222 for these comparisons. Conclusions:The proposed model exhibited excellent performance in the AD diagnosis task, accurately distinguishing different stages of AD. This confirms the value of MR DL radiomic model for AD diagnosis.

Background:Deep learning (DL) technologies are playing increasingly important roles in computer-aided diagnosis in medicine. In this study, we sought to address issues related to the diagnosis of Alzheimer's disease (AD) based on multi-modal features, and introduced a multi-modal three-dimensional Inception-v4 model that employs transfer learning for AD diagnosis based on magnetic resonance imaging (MRI) and clinical score data. Methods:The multi-modal three-dimensional (3D) Inception-v4 model was first pre-trained using data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Subsequently, independent validation data were used to fine-tune the model with pre-trained weight parameters. The model was quantitatively evaluated using the mean values obtained from five-fold cross-validation. Further, control experiments were conducted to verify the performance of the model patients with AD, and in the study of disease progression. Results:In the AD diagnosis task, when a single image marker was used, the average accuracy (ACC) and area under the curve (AUC) were 62.21% and 71.87%, respectively. When transfer learning was not employed, the average ACC and AUC were 75.74% and 83.13%, respectively. Conversely, the combined approach proposed in this study achieved an average ACC of 87.84%, and an average AUC of 90.80% [with an average precision (PRE) of 87.21%, an average recall (REC) of 82.52%, and an average F1 of 83.58%]. Conclusions:In comparison with existing methods, the performance of the proposed method was superior in terms of diagnostic accuracy. Specifically, the method showed an enhanced ability to accurately distinguish among various stages of AD. Our findings show that multi-modal feature fusion and transfer learning can be valuable resources in the treatment of patients with AD, and in the study of disease progression.

To investigate the correlation between glymphatic impairment and synaptic loss and to explore whether this relationship is affected by amyloid-β (Aβ) pathology or reactive astrocytes in individuals spanning the Alzheimer’s disease–related pathological spectrum. We investigated the diffusion tensor imaging analysis along the perivascular space (DTI-ALPS) index as a biomarker of the glymphatic system. A total of 182 participants underwent synaptic vesicle glycoprotein 2 A (SV2A) PET/MRI and amyloid-β (Aβ) PET/CT imaging, with SV2A serving as a biomarker of synaptic density. Additionally, plasma Aβ42/40 ratios were measured in 139 participants, and glial fibrillary acidic protein (GFAP) levels were assessed in 143 participants. Controlling for age, sex, years of education, and cognitive status, we investigated the relationships between glymphatic system impairment and synaptic density, along with other biomarkers. Mediation analyses were conducted using the SPSS PROCESS macro (version 3.3) to examine whether synaptic density mediates the relationship between the ALPS index and cognitive performance. A lower ALPS index, indicating greater glymphatic impairment, was significantly associated with reduced synaptic density. The ALPS index was also significantly positively associated with the residual SV2A PET standardized uptake value ratio (SUVr) in the hippocampus of participants with Aβ deposition or greater plasma GFAP concentrations. The correlation between hippocampal synaptic loss and cerebral Aβ was stronger in participants with a lower ALPS index. In addition, the hippocampal synaptic density fully mediated the association between ALPS index and global cognition. Glymphatic system impairment is significantly correlated with synaptic density loss. GFAP levels and cerebral Aβ plaques may strengthened this association. These findings suggest a potential link between glymphatic dysfunction and synaptic degeneration in AD, which may have implications for understanding disease mechanisms and therapeutic monitoring.

ObjectiveTo compare the diagnostic performance of radiomics-based analysis and the conventional standardized uptake value ratio (SUVr) method in classifying Alzheimer’s disease (AD) and non-Alzheimer’s disease (NAD) using AV45 PET imaging.MethodsThis retrospective study included 79 patients diagnosed with AD and 34 patients diagnosed with NAD between July 2023 and August 2024. All patients underwent AV45 PET imaging, and the images were registered to a standard template for the extraction of SUVr metrics, including SUVmaxr, SUVmeanr, and SUVmoder, as well as radiomic features (a total of 660 features) from regions of interest (ROIs) in the brain lobes. Feature importance was ranked using a random forest algorithm, and three models were constructed: an SUVr model, a radiomics model, and a combined model. The classification performance was assessed using receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA). Model accuracy, sensitivity, specificity, and precision were evaluated using the Mann–Whitney test, DeLong test, and confusion matrices.ResultsThere were no significant differences in gender and age between AD and NAD groups (p > 0.05). SUVr analysis showed no statistically significant differences in SUVmaxr values in the frontal and occipital lobes between AD and NAD patients, while SUVmeanr and SUVmoder in other lobes exhibited significant differences (p < 0.05). The 15 most important radiomic features were primarily concentrated in the temporal, frontal, and parietal lobes, with the highest-ranked features being original_firstorder_Skewness and original_glcm_ClusterShade. The area under the curve (AUC) of the Radiomics model was 0.89 (95% CI: 0.75–0.98), significantly higher than that of the SUVr model (AUC = 0.67, 95% CI: 0.45–0.86, p = 0.026). The combined model achieved an AUC of 0.88, showing no significant improvement over the Radiomics model alone. The Radiomics model outperformed the SUVr model in terms of accuracy (88% vs. 68%), sensitivity (96% vs. 78%), specificity (73% vs. 45%), and precision (88% vs. 75%). DCA analysis further confirmed the superior diagnostic performance of the Radiomics model.ConclusionThe radiomics-based approach significantly outperformed the conventional SUVr method, particularly in terms of sensitivity and specificity. This study highlights the potential of radiomics for quantitative PET imaging analysis and its promising clinical applications.

Background Most stroke patients suffer from an imbalance in blood supply, which causes severe brain damage leading to functional deficits in motor, sensory, swallowing, cognitive, emotional, and speech functions. Repetitive transcranial magnetic stimulation (rTMS) is thought to restore functions impaired during the stroke process and improve the quality of life of stroke patients. However, the efficacy of rTMS in treating post-stroke function impairment varies significantly. Therefore, we conducted a meta-analysis of the number of patients with effective rTMS in treating post-stroke dysfunction. Methods The PubMed, Embase, and Cochrane Library databases were searched. Screening and full-text review were performed by three investigators. Single-group rate meta-analysis was performed on the extracted data using a random variable model. Then subgroup analyses were performed at the levels of stroke acuity (acute, chronic, or subacute); post-stroke symptoms (including upper and lower limb motor function, dysphagia, depression, aphasia); rTMS stimulation site (affected side, unaffected side); and whether or not it was a combination therapy. Results We obtained 8955 search records, and finally 33 studies (2682 patients) were included in the meta-analysis. The overall analysis found that effective strength (ES) of rTMS was 0.53. In addition, we found that the ES of rTMS from acute/subacute/chronic post-stroke was 0.69, 0.45, and 0.52. We also found that the ES of rTMS using high-frequency stimulation was 0.56, while the ES of rTMS using low-frequency stimulation was 0.53. From post-stroke symptoms, we found that the ES of rTMS in sensory aspects, upper limb functional aspects, swallowing function, and aphasia was 0.50, 0.52, 0.51, and 0.54. And from the site of rTMS stimulation, we found that the ES of rTMS applied to the affected side was 0.51, while the ES applied to the unaffected side was 0.54. What’s more, we found that the ES of rTMS applied alone was 0.53, while the ES of rTMS applied in conjunction with other therapeutic modalities was 0.53. Conclusions By comparing the results of the data, we recommend rTMS as a treatment option for rehabilitation of functional impairment in patients after stroke. We also recommend that rehabilitation physicians or clinicians use combination therapy as one of the options for patients.

Background Synaptic loss is an important factor in Alzheimer disease (AD); however, blood assays that conveniently and rapidly reflect changes in synaptic density are lacking. Purpose To correlate multiple potential synaptic blood markers with synaptic density measured using 18F-SynVesT-1, a fluorine 18 (18F)-labeled radiotracer, brain PET and to explore the independent associations between these markers and synaptic density. Materials and Methods This prospective study included 50 cognitively unimpaired (mean age, 65.0 years ± 8.3 [SD]; 37 female) participants and 70 participants with cognitive impairment (mean age, 69.5 years ± 7.9; 43 female) from the Memory Clinic of Shanghai Jiao Tong University Affiliated Ruijin Hospital and communities in Shanghai. Amyloid-β (Aβ) and tau were assessed using 18F-florbetapir and 18F-MK6240 PET/CT. Synaptic density was evaluated with 18F-SynVesT-1 PET/MRI. Pearson correlation analysis was used to investigate relationships of plasma (Aβ42/40 ratio, phosphorylated tau 181 [p-tau-181], glial fibrillary acid protein [GFAP], neurofilament light) and serum (C-reactive protein, tumor necrosis factor-α, α-synuclein, neurogranin, active plasminogen activator inhibitor-1, tissue plasminogen activator) biomarkers with synaptic density. Linear regression models and mediation analysis were used to explore effects of other AD-related pathologies on these relationships. Results Correlations were observed between increased p-tau-181 and GFAP and decreased synaptic density in global cortex (rp-tau-181 = -0.352, rGFAP = -0.386; both P < .001) and hippocampus (rp-tau-181 = -0.361, rGFAP = -0.369; both P < .001) at 18F-SynVesT-1 PET/MRI. The relationships between p-tau-181 and GFAP with 18F-SynVesT-1 PET/MRI persisted after controlling for plasma Aβ42/40 ratio, Aβ PET, or cortical thickness (P value range, <.001-.01). This association disappeared after controlling for tau PET (P value range, .08-.83). Conclusion Plasma p-tau-181 and GFAP are closely associated with synaptic density measured using 18F-SynVesT-1 PET/MRI, with the relationship primarily influenced by tau accumulation rather than Aβ deposition or cortical thickness. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Giannakopoulos in this issue.

This article aims to compare the diagnostic performance of 18-fluorodeoxyglucose ([18F]FDG) PET/CT and fibroblast activating protein inhibitor (FAPI) PET/CT in the assessment of primary tumors, lymph nodes, and distant metastases in lung cancer patients. A systematic search was conducted on the Cochrane Library, Embase, and PubMed/MEDLINE databases from inception until November 1, 2022. Included studies assessed the use of FAPI PET/CT and [18F]FDG PET/CT in patients with lung cancer. The Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool was used to evaluate the risk of bias. A random variable model was used to analyze the diagnostic tests of the two imaging modalities. The sensitivity of FAPI PET/CT in detecting primary lung cancer lesions was 0.98 (95 • This article is to compare the performance of [ 18 F]FDG PET/CT with FAPI PET/CT in the assessment of primary tumors, lymph nodes, and distant metastases in lung cancer. • However, FAPI PET/CT has a higher sensitivity for the diagnostic assessment of metastatic lung cancer lesions.

Toludesvenlafaxine is a recently developed antidepressant that belongs to the triple reuptake inhibitor class. Despite the in vitro evidence that toludesvenlafaxine inhibits the reuptake of serotonin (5-HT), norepinephrine (NE) and dopamine (DA), there is no in vivo evidence that toludesvenlafaxine binds to DAT and increases DA level, a mechanism thought to contribute to its favorable clinical performance. Positron emission tomography/computed tomography (PET/CT) was used to examine the DAT binding capacity in healthy rats and human subjects and microdialysis was used to examine the striatal DA level in rats. [18F]FECNT and [11C]CFT were used as PET/CT radioactive tracer for rat and human studies, respectively. In rats, 9 mg/kg of toludesvenlafaxine hydrochloride (i.v.) followed by an infusion of 3 mg/kg via minipump led to the binding rate to striatum DAT at 3.7 – 32.41

Purpose Multiple myeloma (MM), the second most hematological malignancy, have been studied extensively in the prognosis of the clinical parameters, however there are only a few studies have discussed the role of dual modalities and multiple algorithms of 18 F-FDG ( 18 F-fluorodeoxyglucose) PET/CT based radiomics signatures for prognosis in MM patients. We hope to deeply mine the utility of raiomics data in the prognosis of MM. Methods We extensively explored the predictive ability and clinical decision-making ability of different combination image data of PET, CT, clinical parameters and six machine learning algorithms, Cox proportional hazards model (Cox), linear gradient boosting models based on Cox’s partial likelihood (GB-Cox), Cox model by likelihood based boosting (CoxBoost), generalized boosted regression modelling (GBM), random forests for survival model (RFS) and support vector regression for censored data model (SVCR). And the model evaluation methods include Harrell concordance index, time dependent receiver operating characteristic (ROC) curve, and decision curve analysis (DCA). Results We finally confirmed 5 PET based features, and 4 CT based features, as well as 6 clinical derived features significantly related to progression free survival (PFS) and we included them in the model construction. In various modalities combinations, RSF and GBM algorithms significantly improved the accuracy and clinical net benefit of predicting prognosis compared with other algorithms. For all combinations of various modalities based models, single-modality PET based prognostic models’ performance was outperformed baseline clinical parameters based models, while the performance of models of PET and CT combined with clinical parameters was significantly improved in various algorithms. Conclusion 18 F‑FDG PET/CT based radiomics models implemented with machine learning algorithms can significantly improve the clinical prediction of progress and increased clinical benefits providing prospects for clinical prognostic stratification for precision treatment as well as new research areas.

Neuroendocrine neoplasm (NEN) is a type of heterogeneous tumor that originates from peptidergic neurons and neuroendocrine cells. The presence of over-expressed somatostatin receptors (SSTR) on the surface of NEN tumor cells has led to the administration of radiolabeled somatostatin analogs (SSA) in combination with over-expressed SSTR, which is called peptide receptor radionuclide therapy (PRRT). The 1, 4, 7, 10-tetraazacyclododecane-1, 4, 7, 10-tetraacceticacid- D-Phe1-Tyr3-Thr8-octreotide (DOTATATE)-based α/β radionuclide therapy is one of the representative therapeutic methods of PRRT. This article reviews the progress of research on α/β radionuclide therapy based on DOTATATE and its related combination therapy, drug toxicity and safety, as well as expectation for modalities with clinical value for NEN treatment.

We report a case of hidradenocarcinoma, which showed only slight 18 F-FDG uptake. However, the rare sweat gland tumor demonstrated intense tracer uptake on 68 Ga-FAPI PET/CT. This case demonstrates the potential value of 68 Ga-FAPI PET/CT for the evaluation of hidradenocarcinoma.

ABSTRACT We report a case of hidradenocarcinoma, which showed only slight 18F-FDG uptake. However, the rare sweat gland tumor demonstrated intense tracer uptake on 68Ga-FAPI PET/CT. This case demonstrates the potential value of 68Ga-FAPI PET/CT for the evaluation of hidradenocarcinoma.

Abstract Objective: Standard imaging techniques may not be suitable for evaluating thoracic tumor metastases, despite the high prevalence of thoracic cancers worldwide. Recent developments in PET/CT techniques using fibrogenic activating protein inhibitors (FAPI) show promise in assessing thoracic tumor metastasis. We reviewed the latest data on FAPI PET/CT for analyzing original malignancies, lymph node metastases, and remote metastases in thoracic cancers. Additionally, a meta-analysis was conducted to determine the sensitivity of FAPI PET/CT in diagnosing thoracic malignancies, including primary and non-primary foci (lymph node metastases and remote metastases) Methods: We searched the Cochrane Library, Embase, and PubMed databases from their establishment until June 23, 2023. Our screening and review included all studies that used FAPI PET/CT to examine thoracic malignancies. Three investigators conducted the filtration and full-text analysis, while two investigators collected the data. We used the QUADAS-2 tool to assess the risk of bias. A diagnostic test study was performed using a random-effects model. Results: Our systematic review and meta-analysis comprised 13 studies out of the 796 total publications we identified. These 13 articles included data from 475 patients with thoracic tumors, 475 primary thoracic tumor lesions, and 3296 metastatic thoracic tumor lesions. In order to identify primary thoracic cancers , patient-based FAPI PET/CT had a sensitivity of 0.98 (95% CI: 0.90-1.00). For the diagnosis of original thoracic tumor lesions and the diagnosis of metastatic thoracic tumor lesions, the sensitivity of lesion-based FAPI PET/CT was 0.98 (95% CI: 0.91-1.00) and 0.99 (95% CI: 0.95-1.00), respectively. Conclusion: FAPI PET/CT demonstrates superior sensitivity and specificity in diagnosing thoracic cancers. Radiologists, nuclear medicine experts, and clinicians could think about employing FAPI PET/CT to assess primary and non-primary foci (lymph node metastases and remote metastases)in thoracic cancers.

Abstract Dermatomyositis is an idiopathic inflammatory myopathy often associated with malignancies. 68Ga-FAPI PET/CT was performed on a 58-year-old man with newly diagnosed dermatomyositis. 68Ga-FAPI PET/CT showed multiple increased FAPI activity in whole-body muscles and nasopharyngeal lesion. A biopsy of the nasopharyngeal lesion confirmed nasopharyngeal carcinoma. 68Ga-FAPI PET/CT can provide a “1-stop” imaging method for patients with dermatomyositis.