Background: Thyroid diseases are the second most common hormonal disorders, necessitating accurate diagnostics. Advances in artificial intelligence and radiomics have enhanced diagnostic precision by analyzing quantitative imaging features. However, reproducibility challenges arising from factors such as the field-of-view (FOV) zooming and segmentation variability limit the clinical application of radiomic-based models. Aim: This study focuses on evaluating the impact of segmentation and FOV zooming on the reproducibility of radiomic features and improved performance of machine learning (ML) when using reproducible features for classification of thyroid scintigraphy images into normal, diffuse goiter (DG), multinodular goiter (MNG), and thyroiditis. Patients and Methods: A retrospective analysis was conducted on 872 thyroid scintigraphy cases from 3 centers. Radiomic feature reproducibility was assessed using the intraclass correlation coefficient (ICC), with robust features (ICC≥0.80) identified under segmentation and zooming conditions. Four ML training scenarios were implemented to train models on Center A data, including (1) all, (2) zoom-robust, (3) segmentation-robust, and (4) mutually robust features, with 3 feature selection methods and 7 classifiers. Models were validated on external data sets (centers B and C). Results: FOV zooming significantly reduced feature reproducibility (ICC≥0.80: 49%), while segmentation effects were minimal (ICC≥0.80: 96%). Models trained on mutually robust features outperformed those trained using all features. Boruta-MLP achieved the highest accuracy (0.71, P-value <0.001 vs. all features) in zoomed data sets, and RFE-MLP performed best (0.69, P-value <0.001 vs. all features) in the baseline data set, with Gray-Level Co-occurrence Matrix (GLCM) features frequently selected. Conclusions: Utilizing robust radiomic features significantly improved the performance of ML models in thyroid disease classification, enabling more accurate and generalizable diagnostic outcomes across diverse data sets.

Introduction: Peptide Receptor Radionuclide Therapy (PRRT) with [¹⁷⁷Lu]Lu-DOTA-TATE is effective in treating advanced Neuroendocrine Tumors (NETs), yet predicting individual response in this treatment remains a challenge due to inter-lesion heterogeneity. There is a lack of standardized, effective methods for using multi-lesion radiomics to predict progression and Time to Progression (TTP) in PRRT-treated patients. This study evaluated how aggregating radiomic features from multiple PET-identified lesions can be used to predict disease progression (event [progression and death] vs. event-free) and TTP. Methods: Eighty-one NETs patients with multiple lesions underwent pre-treatment PET/CT imaging. Lesions were segmented and ranked by minimum Standard Uptake Value (SUV_min) (both descending and ascending), SUV_mean, SUV_max, and volume (descending). From each sorting, the top one, three, and five lesions were selected. For the selected lesions, radiomic features were extracted (using the Pyradiomics library) and lesion aggregation was performed using stacked vs. statistical methods. Eight classification models along with three feature selection methods were used to predict progression, and five survival models and three feature selection methods were used to predict TTP under a nested cross-validation framework. Results: The overall appraisal showed that sorting lesions based on SUV_min (descending) yields better classification performance in progression prediction. This is in addition to the fact that aggregating features extracted from all the lesions, as well as the top five lesions sorted by SUV_mean, lead to the highest overall performance in TTP prediction. The individual appraisal in progression prediction models trained on the single top lesion sorted by SUV_min (descending) showed the highest recall and specificity despite data imbalance. The best-performing model was the Logistic Regression (LR) classifier with Recursive Feature Elimination (RFE) (recall: 0.75, specificity: 0.77). In TTP prediction, the highest concordance index was obtained using a Random Survival Forest (RSF) trained on statistically aggregated features from the top five lesions ranked by SUV_mean, selected via Univariate C-Index (UCI) (C-index = 0.68). Across both tasks, features from the Gray Level Size Zone Matrix (GLSZM) family were consistently among the most predictive, highlighting the importance of spatial heterogeneity in treatment response. Conclusions: This study demonstrates that informed lesion selection and tailored aggregation strategies significantly impact the predictive performance of radiomics-based models for progression and TTP prediction in PRRT-treated NET patients. These approaches can potentially enhance model accuracy and better capture tumor heterogeneity, supporting more personalized and practical PRRT implementation.

Purpose: To develop and validate a multilesion hierarchical radiomic phenotyping and aggregation framework for positron emission tomography (PET) imaging that captures intertumor heterogeneity and improves prognostic modeling in metastatic cancers. Methods: This retrospective study included 81 neuroendocrine tumor (NET) patients imaged with 68Ga-DOTATATE or 68Ga-DOTATOC PET/CT and 76 diffuse large B-cell lymphoma (DLBCL) patients imaged with 18F-FDG PET/CT. Lesion-level radiomic features were extracted using PyRadiomics v3.0.1 and harmonized using ComBat. Unsupervised consensus clustering identified radiomic phenotypes, which were aggregated at four levels: body-level (B), phenotype-specific body-level (BP), organ-level (O), and phenotype-specific organ-level (OP). Nested cross-validation models predicted overall survival (OS), time to progression (TTP), and binary progression, comparing phenotype-agnostic and phenotype-informed aggregation, with and without clinical features, against single-lesion approaches and clinical baselines. Results: Phenotype discovery identified 4 NET and 8 DLBCL radiomic phenotypes, driven mainly by gray-level co-occurrence matrix and gray-level size-zone matrix texture features. Hierarchical aggregation yielded numerically favorable performance relative to single-lesion approaches across end points. B+BP was the performance-favorable representation for survival in both cohorts. Clinical+Aggregated models achieved the highest C-indices for NET OS (0.72 vs 0.65), NET TTP (0.67 vs 0.64), DLBCL OS (0.66 vs 0.62), and DLBCL TTP (0.66 vs 0.58) compared with clinical-only models. Clinical-only models were weakest for binary progression. For DLBCL progression, the richest Clinical+Aggregated representation (B+BP+O+OP) performed best (ROC-AUC = 0.77, MCC = 0.43), whereas NET progression was most stable with phenotype-agnostic body-level aggregation (ROC-AUC = 0.72, MCC = 0.34). Conclusion: Phenotype-informed aggregation of PET radiomics provides a structured approach for incorporating interlesion heterogeneity into patient-level prognostic modeling and showed promising performance relative to conventional single-lesion representations.