RESUMO
RATIONALE AND OBJECTIVES: This study aims to predict intermediate to high-risk prostate cancer (PCa) prognosis based on 18-fluoro-2-deoxyglucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT) radiomics. Additionally, subgroup analysis will be performed on the androgen deprivation therapy (ADT) group and the metastatic PCa group. MATERIALS AND METHODS: In the retrospective analysis of 104 intermediate to high-risk PCa patients who underwent 18F-FDG PET/CT prior to treatment. The data set was divided into a training set (n = 72) and a testing set (n = 32). Two different PET/CT models were constructed using multivariate logistic regression with cross-validation: radiomics model A and an alternative ensemble learning-based model B. The superior model was then selected to develop a radiomics nomogram. Separate models were also developed for the ADT and metastatic PCa subgroups. RESULTS: Model A, which integrates eight radiomics features showed excellent performance with an area under curve (AUC) of 0.844 in the training set and 0.804 in the testing set. The radiomics nomogram incorporating the radiomics score (radscore) from model A and the tumor-to-liver ratio (TLR) showed good prognostic accuracy in the testing set with an AUC of 0.827. In the subgroup analyses for endocrine therapy and metastatic cancer, the PET/CT radiomics model showed AUCs of 0.845 and 0.807 respectively, suggesting its potential effectiveness. CONCLUSION: The study establishes the utility of the 18F-FDG PET/CT radiomics nomogram in predicting the prognosis of intermediate to high-risk PCa patients, indicating its potential for clinical application.
RESUMO
Purpose: To investigate the ability of a PET/CT-based radiomics nomogram to predict occult lymph node metastasis in patients with clinical stage N0 non-small cell lung cancer (NSCLC). Materials and methods: This retrospective study included 228 patients with surgically confirmed NSCLC (training set, 159 patients; testing set, 69 patients). ITKsnap3.8.0 was used for image(CT and PET images) segmentation, AK version 3.2.0 was used for radiomics feature extraction, and Python3.7.0 was used for radiomics feature screening. A radiomics model for predicting occult lymph node metastasis was established using a logistic regression algorithm. A nomogram was constructed by combining radiomics scores with selected clinical predictors. Receiver operating characteristic (ROC) curves were used to verify the performance of the radiomics model and nomogram in the training and testing sets. Results: The radiomics nomogram comprising six selected features achieved good prediction efficiency, including radiomics characteristics and tumor location information (central or peripheral), which demonstrated good calibration and discrimination ability in the training (area under the ROC curve [AUC] = 0.884, 95% confidence interval [CI]: 0.826-0.941) and testing (AUC = 0.881, 95% CI: 0.8031-0.959) sets. Clinical decision curves demonstrated that the nomogram was clinically useful. Conclusion: The PET/CT-based radiomics nomogram is a noninvasive tool for predicting occult lymph node metastasis in NSCLC.