Despite rapid proliferation of AI applications in prostate MRI showing impressive technical performance, clinical adoption remains limited. We conducted a comprehensive narrative review of literature from January 2018 to December 2024, examining AI applications in prostate MRI with emphasis on real-world performance and implementation challenges. Among 200+ studies reviewed, AI systems achieve 87% sensitivity and 72% specificity for cancer detection in research settings. However, external validation reveals average performance drops of 12%, with some implementations showing degradation up to 31%. Only 31% of studies follow reporting guidelines, 11% share code, and 4% provide model weights. Seven real-world implementation studies demonstrate integration times of 3–14 months, with one major center terminating deployment due to unacceptable false positive rates. The translation gap between artificial and clinical intelligence remains substantial. Success requires shifting focus from accuracy metrics to patient outcomes, establishing transparent reporting standards, developing realistic economic models, and creating appropriate regulatory frameworks. The field must combine methodological rigor, clinical relevance, and implementation science to realize AI’s transformative potential in prostate cancer care.

Theranostics utilizes the nuclear properties of radioactive isotopes, especially for molecular imaging and targeted therapy. Radiopharmaceuticals (RPs), which combine a pharmaceutical ligand with a radionuclide, enable accurate diagnosis and treatment of various diseases through modalities such as PET and SPECT imaging. The aim of this papare is to review adverse reactions associated with diagnostic and therapeutic radiopharmaceuticals, with an emphasis on their severity and clinical management. This review evaluates documented adverse effects (AEs) related to RPs used in nuclear medicine imaging (PET and SPECT) and radionuclide therapy, focusing on their severity and clinical management strategies. It also considers the mechanisms of RPs toxicity, distinguishes between general and specific AEs, and highlights the limitations in current adverse drug reaction (ADR) assessment tools. The methodology used was the research and synthesis of most relevant published literature data; most relevant papers were synthesized regarding the reporting system of ARs and categorized by the specific and systemic adverse effects of RPs. Side effects from diagnostic RPs are relatively rare and typically minimal. Therapeutic RPs, selected for their high-energy radiation properties, can cause DNA damage to malignant cells while minimizing harm to healthy tissues. Although adverse effects do occur, they are generally fewer and less severe compared to conventional therapies. Severe toxicity is rare and often preventable. Both patient- and provider-reported ADRs offer important safety insights, though validated assessment instruments remain limited. Radionuclide therapy offers a targeted approach that is a less invasive alternative to conventional treatments with a favorable safety profile. Continued evaluation of adverse reactions and the development of standardized ADR assessment tools are essential for improving patient outcomes and RP safety monitoring.

Background/Objectives: [18F]FDG PET/CT radiomics could improve risk stratification in untreated breast carcinoma. Methods: PubMed Central was accessed for full-text English articles (2015–2025) evaluating radiomic features from pretreatment [18F]FDG PET/CT. The Newcastle-Ottawa Scale (NOS) was used to evaluate the risk of bias. Results: Seven studies (1394 patients with a median cohort of about 150 patients) met the inclusion criteria. Radiomics outperformed conventional metabolic measures at predicting pCR to NAC (with the best AUC 0.83 when combining intra- and peritumoral features); differentiating molecular subtypes (AUC 0.856 luminal vs. non-luminal; 0.818 HER2+ vs. HER2−, and 0.888 triple negative vs. others); and assessing androgen receptor (AR) expression. No additional value was found for ER/PR status. Age influenced SUV and texture metrics, especially in triple-negative lesions. Methodological variation was notable: all studies were retrospective, the majority were single-center, only two provided external validation with different protocols of acquisition and segmentation, and at least four distinct software platforms were used for feature extraction and statistical analysis. Conclusions: [18F]FDG PET/CT radiomics shows good potential for predicting neoadjuvant response and molecular profile in breast cancer. However, small, diverse cohorts and non-standardized methodologies limit the evidence. Prospective multicenter studies with standardized acquisition, segmentation and feature extraction are required before clinical use.

Adrenal glands are vital endocrine organs whose accurate segmentation on CT imaging presents significant challenges due to their small size and variable morphology. This study evaluates the efficacy of deep learning approaches for automatic adrenal gland segmentation from multiphase CT scans. We implemented three convolutional neural network architectures (U-Net, SegNet, and NablaNet) and assessed their performance on a dataset comprising 868 adrenal glands from contrast-enhanced abdominal CT scans. Performance was evaluated using the Dice similarity coefficient (DSC), alongside practical implementation metrics including training and deployment time. U-Net demonstrated superior segmentation performance (DSC: 0.630 ± 0.05 for right, 0.660 ± 0.06 for left adrenal glands) compared to NablaNet (DSC: 0.552 ± 0.08 for right, 0.550 ± 0.07 for left) and SegNet (DSC: 0.320 ± 0.10 for right, 0.335 ± 0.09 for left). While all models achieved high specificity, boundary delineation accuracy remained challenging. Our findings demonstrate the feasibility of deep learning-based adrenal gland segmentation while highlighting the persistent challenges in achieving the segmentation quality observed with larger abdominal organs. U-Net provides the optimal balance between accuracy and computational requirements, establishing a foundation for further refinement of AI-assisted adrenal imaging tools.

Radiomic feature stability is a necessary condition for clinical translation, yet the impact of inter-observer segmentation variability remains insufficiently characterized for [18F]FDG PET/CT in breast carcinoma. We evaluated the inter-observer reproducibility of 107 original radiomic features extracted from [18F]FDG PET/CT images of 42 patients with biopsy-proven, treatment-naive primary breast carcinoma, using an IBSI-aligned PyRadiomics workflow. Two nuclear medicine physicians independently segmented each tumor using semi-automatic Otsu thresholding to generate an initial tumor mask, followed by manual correction. Reproducibility was quantified using ICC(A,1) with bootstrap-derived 95% confidence intervals. A two-stage reproducibility and redundancy-based feature reduction strategy, combining an ICC threshold with Spearman correlation-based redundancy removal, was applied across nine threshold combinations, and features were classified into three pre-specified stability categories. The segmentation agreement was good, with a mean Dice coefficient of 0.847. Most features showed excellent reproducibility (81/107, 75.7% with ICC ≥ 0.90; median ICC 0.972), whereas shape features based on maximum lesion extension showed poor reproducibility (ICC 0.10–0.25). The reduction strategy resulted in 19 stable non-redundant features, with eight retained across all threshold combinations; 79 features (73.8%) met high-stability criteria. These results and the proposed stability classification framework provide a methodological basis for future predictive PET radiomics studies in breast carcinoma.