Machine learning-based radiomics for multiple primary prostate cancer biological characteristics prediction with 18F-PSMA-1007 PET: comparison among different volume segmentation thresholds.

BACKGROUND: PET-based radiomics features could predict the biological characteristics of primary prostate cancer (PCa). However, the optimal thresholds to predict the biological characteristics of PCa are unknown. This study aimed to compare the predictive power of 18F-PSMA-1007 PET radiomics features at different thresholds for predicting multiple biological characteristics. METHODS: One hundred and seventy-three PCa patients with complete preoperative 18F-PSMA-1007 PET examination and clinical data before surgery were collected. The prostate lesions' volumes of interest were semi-automatically sketched with thresholds of 30%, 40%, 50%, and 60% maximum standardized uptake value (SUVmax). The radiomics features were respectively extracted. The prediction models of Gleason score (GS), extracapsular extension (ECE), and vascular invasion (VI) were established using the support vector machine. The performance of models from different thresholding regions was assessed using receiver operating characteristic curve and confusion matrix-derived indexes. RESULTS: For predicting GS, the 50% SUVmax model showed the best predictive performance in training (AUC, 0.82 [95%CI 0.74-0.88]) and testing cohorts (AUC, 0.80 [95%CI 0.66-0.90]). For predicting ECE, the 40% SUVmax model exhibit the best predictive performance (AUC, 0.77 [95%CI 0.68-0.84] and 0.77 [95%CI 0.63-0.88]). As for VI, the 50% SUVmax model had the best predictive performance (AUC, 0.74 [95%CI 0.65-0.82] and 0.74 [95%CI 0.56-0.82]). CONCLUSION: The 18F-1007-PSMA PET-based radiomics features at 40-50% SUVmax showed the best predictive performance for multiple PCa biological characteristics evaluation. Compared to the single PSA model, radiomics features may provide additional benefits in predicting the biological characteristics of PCa.

Multimodal radiomics based on 18F-Prostate-specific membrane antigen-1007 PET/CT and multiparametric MRI for prostate cancer extracapsular extension prediction.

OBJECTIVES: To compare the performance of the multiparametric magnetic resonance imaging (mpMRI) radiomics and 18F-Prostate-specific membrane antigen (PSMA)-1007 PET/CT radiomics model in diagnosing extracapsular extension (EPE) in prostate cancer (PCa), and to evaluate the performance of a multimodal radiomics model combining mpMRI and PET/CT in predicting EPE. METHODS: We included 197 patients with PCa who underwent preoperative mpMRI and PET/CT before surgery. mpMRI and PET/CT images were segmented to delineate the regions of interest and extract radiomics features. PET/CT, mpMRI, and multimodal radiomics models were constructed based on maximum correlation, minimum redundancy, and logistic regression analyses. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC) and indices derived from the confusion matrix. RESULTS: AUC values for the mpMRI, PET/CT, and multimodal radiomics models were 0.85 (95% CI, 0.78-0.90), 0.73 (0.64-0.80), and 0.83 (0.75-0.89), respectively, in the training cohort and 0.74 (0.61-0.85), 0.62 (0.48-0.74), and 0.77 (0.64-0.87), respectively, in the testing cohort. The net reclassification improvement demonstrated that the mpMRI radiomics model outperformed the PET/CT one in predicting EPE, with better clinical benefits. The multimodal radiomics model performed better than the single PET/CT radiomics model (P < .05). CONCLUSION: The mpMRI and 18F-PSMA-PET/CT combination enhanced the predictive power of EPE in patients with PCa. The multimodal radiomics model will become a reliable and robust tool to assist urologists and radiologists in making preoperative decisions. ADVANCES IN KNOWLEDGE: This study presents the first application of multimodal radiomics based on PET/CT and MRI for predicting EPE.

A dynamic online nomogram predicting prostate cancer short-term prognosis based on 18F-PSMA-1007 PET/CT of periprostatic adipose tissue: a multicenter study.

BACKGROUND: Rising prostate-specific antigen (PSA) levels following radical prostatectomy are indicative of a poor prognosis, which may associate with periprostatic adipose tissue (PPAT). Accordingly, we aimed to construct a dynamic online nomogram to predict tumor short-term prognosis based on 18F-PSMA-1007 PET/CT of PPAT. METHODS: Data from 268 prostate cancer (PCa) patients who underwent 18F-PSMA-1007 PET/CT before prostatectomy were analyzed retrospectively for model construction and validation (training cohort: n = 156; internal validation cohort: n = 65; external validation cohort: n = 47). Radiomics features (RFs) from PET and CT were extracted. Then, the Rad-score was constructed using logistic regression analysis based on the 25 optimal RFs selected through maximal relevance and minimal redundancy, as well as the least absolute shrinkage and selection operator. A nomogram was constructed to predict short-term prognosis which determined by persistent PSA. RESULTS: The Rad-score consisting of 25 RFs showed good discrimination for classifying persistent PSA in all cohorts (all P < 0.05). Based on the logistic analysis, the radiomics-clinical combined model, which contained the optimal RFs and the predictive clinical variables, demonstrated optimal performance at an AUC of 0.85 (95% CI: 0.78-0.91), 0.77 (95% CI: 0.62-0.91) and 0.84 (95% CI: 0.70-0.93) in the training, internal validation and external validation cohorts. In all cohorts, the calibration curve was well-calibrated. Analysis of decision curves revealed greater clinical utility for the radiomics-clinical combined nomogram. CONCLUSION: The radiomics-clinical combined nomogram serves as a novel tool for preoperative individualized prediction of short-term prognosis among PCa patients.

A radiomics nomogram based on 18 F-FDG PET/CT and clinical risk factors for the prediction of peritoneal metastasis in gastric cancer.

PURPOSE: Peritoneal metastasis (PM) is usually considered an incurable factor of gastric cancer (GC) and not fit for surgery. The aim of this study is to develop and validate an 18 F-FDG PET/CT-derived radiomics model combining with clinical risk factors for predicting PM of GC. METHOD: In this retrospective study, 410 GC patients (PM - = 281, PM + = 129) who underwent preoperative 18 F-FDG PET/CT images from January 2015 to October 2021 were analyzed. The patients were randomly divided into a training cohort (n = 288) and a validation cohort (n = 122). The maximum relevance and minimum redundancy (mRMR) and the least shrinkage and selection operator method were applied to select feature. Multivariable logistic regression analysis was preformed to develop the predicting model. Discrimination, calibration, and clinical usefulness were used to evaluate the performance of the nomogram. RESULT: Fourteen radiomics feature parameters were selected to construct radiomics model. The area under the curve (AUC) of the radiomics model were 0.86 [95% confidence interval (CI), 0.81-0.90] in the training cohort and 0.85 (95% CI, 0.78-0.92) in the validation cohort. After multivariable logistic regression, peritoneal effusion, mean standardized uptake value (SUVmean), carbohydrate antigen 125 (CA125) and radiomics signature showed statistically significant differences between different PM status patients( P  < 0.05). They were chosen to construct the comprehensive predicting model which showed a performance with an AUC of 0.92 (95% CI, 0.89-0.95) in the training cohort and 0.92 (95% CI, 0.86-0.98) in the validation cohort, respectively. CONCLUSION: The nomogram based on 18 F-FDG PET/CT radiomics features and clinical risk factors can be potentially applied in individualized treatment strategy-making for GC patients before the surgery.

Acute Phase Blood Glucose Levels and Functional Outcomes in Patients with Spontaneous Intracerebral Hemorrhage.

Objective: Post-stroke hyperglycemia as a common phenomenon is associated with unfavorable outcomes. Focusing on admission hyperglycemia, other markers of dysglycemia were overlooked. This study aimed to explore the contribution of acute phase blood glucose levels in combination with other radiological signs to the prognostication of functional outcomes in patients with spontaneous intracerebral hemorrhage (sICH). Methods: Consecutive patients with sICH with at least five random plasma glucose measurements and complete radiological data during hospitalization were included. We calculated the average, maximum, minimum, standard deviation, and coefficient of variation of blood glucose levels for each patient. Radiological data, including island, black hole, blend, and satellite signs were collected. Functional outcomes were evaluated using the Barthel index. Unfavorable outcomes were defined as a Barthel index score ≤ 60. Univariate and multivariate analyses were performed to identify independent predictors of unfavorable outcomes. Results: Two hundred and thirty-eight patients (mean age 58.5, 163 men and 75 women) were included, and 71 had a history of diabetes. Unfavorable outcomes occurred in 107 patients (45.0%) at 3 months. Multivariate logistic regression analysis demonstrated that maximum blood glucose levels (odds ratio, 1.256; 95% confidence interval, 1.124‒1.404; p < 0.001) and island sign (odds ratio, 2.701; 95% confidence interval, 1.322‒5.521; p = 0.006) were independent predictors of unfavorable outcomes in the nondiabetic group. Meanwhile, patients without diabetes who experienced hematoma expansion had higher average (p = 0.036) and maximum blood glucose levels (p = 0.014). Interpretation: Maximum blood glucose levels and island sign were independently associated with unfavorable outcomes in patients without diabetes, whereas no glycemic variability indices were associated with unfavorable outcomes. Glucose levels influenced hematoma expansion and functional outcomes, particularly in patients without diabetes with sICH. Thus, clinical management of blood glucose levels should be strengthened for patients with sICH with or without a history of diabetes.