Purpose 68 Ga-PSMA PET/CT has high speci city and sensitivity for the detection of both intraprostatic tumor focal lesions and metastasis. However, approximately 10% of primary prostate cancer are invisible on PSMA-PET (exhibit no or minimal uptake). In this work, we investigated whether machine learningbased radiomics models derived from PSMA-PET images could predict invisible intraprostatic lesions on 68 Ga-PSMA-11 PET in patients with primary prostate cancer.Methods In this retrospective study, patients with or without prostate cancer who underwent 68 Ga-PSMA PET/CT and presented negative on PSMA-PET image at either of two different institutions were included: institution 1 (between 2017 to 2020) for the training set and institution 2 (between 2019 to 2020) for the external test set. Three random forest (RF) models were built using selected features extract from standard PET images, delayed PET images, and both standard and delayed PET images. Then, subsequent 10-fold cross-validation was performed. In the test phase, the three RF models and PSA density (PSAD, cut-off value: 0.15ng/ml/ml) were tested with the external test set. The area under the receiver operating characteristic curve (AUC) was calculated for the models and PSAD. The AUCs of the radiomics model and PSAD were compared.Results A total of 64 patients (39 with prostate cancer and 25 with benign prostate disease) were in the training set, and 36 (21 with prostate cancer and 15 with benign prostate disease) were in the test set.The average AUCs of the three RF models from 10-fold cross-validation were 0.87 (95% CI: 0.72, 1.00), 0.86 (95% CI: 0.63, 1.00) and 0.91 (95% CI: 0.69, 1.00), respectively. In the test set, the AUCs of the three trained RF models and PSAD were 0.903 (95% CI: 0.830, 0.975), 0.856 (95% CI: 0.748, 0.964), 0.925 (95% CI:0.838, 1.00), and 0.662 (95% CI: 0.510, 0.813). The AUCs of the three radiomics models were higher than that of PSAD (0.903, 0.856 and 0.925 vs 0.662, respectively; P = .007, P = .045 and P = .005, respectively).Conclusion Random forest models developed by 68 Ga-PSMA-11 PET-based radiomics features were proven useful for accurate prediction of invisible intraprostatic lesion on 68 Ga-PSMA-11 PET in patients with primary prostate cancer and showed better diagnostic performance compared with PSAD.
Purpose 68Ga-PSMA PET/CT has high specificity and sensitivity for the detection of both intraprostatic tumor focal lesions and metastasis. However, approximately 10% of primary prostate cancer are invisible on PSMA-PET (exhibit no or minimal uptake). In this work, we investigated whether machine learning-based radiomics models derived from PSMA-PET images could predict invisible intraprostatic lesions on 68Ga-PSMA-11 PET in patients with primary prostate cancer.Methods In this retrospective study, patients with or without prostate cancer who underwent 68Ga-PSMA PET/CT and presented negative on PSMA-PET image at either of two different institutions were included: institution 1 (between 2017 to 2020) for the training set and institution 2 (between 2019 to 2020) for the external test set. Three random forest (RF) models were built using selected features extract from standard PET images, delayed PET images, and both standard and delayed PET images. Then, subsequent 10-fold cross-validation was performed. In the test phase, the three RF models and PSA density (PSAD, cut-off value: 0.15ng/ml/ml) were tested with the external test set. The area under the receiver operating characteristic curve (AUC) was calculated for the models and PSAD. The AUCs of the radiomics model and PSAD were compared.Results A total of 64 patients (39 with prostate cancer and 25 with benign prostate disease) were in the training set, and 36 (21 with prostate cancer and 15 with benign prostate disease) were in the test set. The average AUCs of the three RF models from 10-fold cross-validation were 0.87 (95% CI: 0.72, 1.00), 0.86 (95% CI: 0.63, 1.00) and 0.91 (95% CI: 0.69, 1.00), respectively. In the test set, the AUCs of the three trained RF models and PSAD were 0.903 (95% CI: 0.830, 0.975), 0.856 (95% CI: 0.748, 0.964), 0.925 (95% CI:0.838, 1.00), and 0.662 (95% CI: 0.510, 0.813). The AUCs of the three radiomics models were higher than that of PSAD (0.903, 0.856 and 0.925 vs 0.662, respectively; P = .007, P = .045 and P = .005, respectively).Conclusion Random forest models developed by 68Ga-PSMA-11 PET-based radiomics features were proven useful for accurate prediction of invisible intraprostatic lesion on 68Ga-PSMA-11 PET in patients with primary prostate cancer and showed better diagnostic performance compared with PSAD.
Background:The recently described pathological subtype of hepatocellular carcinoma (HCC), named macrotrabecular massive (MTM), is associated with an unfavorable prognosis. This study aimed to evaluate the potential for tumor metabolism obtained by β-2-[18F] fluoro-2-deoxy-D-glucose positron emission tomography/computed tomography ( 18 F-FDG PET/CT) to be used as a preoperative imaging indicator for predicting MTM-HCCs.Methods: This study was designed to be cross-sectional. Patients who underwent preoperative 18 F-FDG PET/CT and who had surgically-diagnosed HCC between June 2015 and June 2021 were retrospectively included. Tumor metabolism was determined by the tumor-to-normal liver standardized uptake value ratio (TLR) of the primary tumor as shown on 18 F-FDG PET/CT. Clinical, pathological, and PET/CT characteristics were compared between non-MTM-HCCs and MTM-HCCs. Univariate analyses were used to screen the predictive factors of MTM-HCCs, then multivariate binary logistic regression analyses were performed. A regression-based diagnostic model was then established. Substantial necrosis was assessed to compare the predictive performance between traditional imaging and TLR measured on 18 F-FDG PET/ CT. The receiver operating characteristic (ROC) curve analyses and the DeLong test were used to assess the predictive performance.Results: A total of 93 patients (mean age, 52.6±11.3 years; 81 male) with 36 MTM-HCCs were included.Multivariate binary logistic regression analyses identified higher platelet count [PLT; ≥118.5×10 3 /μL; odds ratio (OR), 3.63; 95% confidence interval (CI), 1.13-12.87; P=0.035], higher aspartate transaminase (AST; ≥52 IU/L; OR, 4.15; 95% CI: 1.34-14.33; P=0.017), and larger TLR (≥2.2; OR, 5.55; 95% CI: 1.90-17.56; P=0.002) as independent predictors of MTM-HCCs. A TLR ≥2.2 helped to identify 72.2% of the MTM-HCCs with a specificity of 75.4%. The AUC of the regression-based diagnostic model for predicting MTM-HCCs was 0.835 (95% CI: 0.746-0.923), with a sensitivity of 80.6% and a specificity of 78.9%. Substantial necrosis enabled the identification of MTM-HCCs with 52.8% sensitivity and 87.7% specificity, with an AUC of 0.702 (95% CI: 0.588-0.817). There was no statistical difference between TLR and substantial necrosis in predicting MTM-HCCs using the DeLong test (P>0.05). Conclusions: Tumor metabolism determined by TLR on 18 F-FDG PET/CT is a valuable imaging indicator for MTM-HCCs. Noninvasive prediction of this subtype can achieve good sensitivity and excellent predictive performance based on the regression model of AST, PLT, and TLR.
Background: To explore the prognostic role of ovarian endometriosis in symptomatic adenomyosis patients underwent uterine artery embolization (UAE).Methods: This was a retrospective, single-center study. A total of 76 patients with adenomyosis who underwent UAE in The First Affiliated Hospital of Sun Yat-sen University between May 2009 and July 2016 were enrolled in this study. These patients were divided into two groups based on whether complicated with ovarian endometriosis. After UAE, the patients were followed up for 12 months. The improvements of dysmenorrhea and menorrhagia were evaluated according to the symptom relief criteria. The improvement rates in both groups were analyzed and compared.Results: Among the 76 patients with adenomyosis, 17 (22.3%) were diagnosed with OE and 59 (77.6%) were non-OE. In the OE group, all patients (17/17, 100%) had dysmenorrhea and 11 (11/17, 64.7%) had menorrhagia. In non-OE group, 57 patients (57/59, 96.6%) had dysmenorrhea and 50 (50/59, 84.7%) had menorrhagia. The improvement rates of dysmenorrhea in the two groups were 47.1% (OE group) and 86.0% (non-OE group), respectively (P<0.05). The improvement rates of menorrhagia in the two groups were 63.6% (OE group) and 84.0% (non-OE group), respectively (P=0.263).Conclusions: Patients without OE showed a lower incidence of dysmenorrhea and may have an advantage in the improvement of dysmenorrhea compared with those with OE when they underwent UAE. However, no significant difference was observed in the improvement of menorrhagia.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.