Background: This study investigated the performance of ensemble learning holomic models for the detection of breast cancer, receptor status, proliferation rate, and molecular subtypes from [¹⁸F]FDG-PET/CT images with and without incorporating data pre-processing algorithms. Additionally, machine learning (ML) models were compared with conventional data analysis using standard uptake value lesion classification. Methods: A cohort of 170 patients with 173 breast cancer tumors (132 malignant, 38 benign) was examined with [¹⁸F]FDG-PET/CT. Breast tumors were segmented and radiomic features were extracted following the imaging biomarker standardization initiative (IBSI) guidelines combined with optimized feature extraction. Ensemble learning including five supervised ML algorithms was utilized in a 100-fold Monte Carlo (MC) cross-validation scheme. Data pre-processing methods were incorporated prior to machine learning, including outlier and borderline noisy sample detection, feature selection, and class imbalance correction. Feature importance in each model was assessed by calculating feature occurrence by the R-squared method across MC folds. Results: Cross validation demonstrated high performance of the cancer detection model (80% sensitivity, 78% specificity, 80% accuracy, 0.81 area under the curve (AUC)), and of the triple negative tumor identification model (85% sensitivity, 78% specificity, 82% accuracy, 0.82 AUC). The individual receptor status and luminal A/B subtype models yielded low performance (0.46–0.68 AUC). SUV_max model yielded 0.76 AUC in cancer detection and 0.70 AUC in predicting triple negative subtype. Conclusions: Predictive models based on [¹⁸F]FDG-PET/CT images in combination with advanced data pre-processing steps aid in breast cancer diagnosis and in ML-based prediction of the aggressive triple negative breast cancer subtype.

Pituitary adenomas count among the most common intracranial tumors. During pituitary oncogenesis structural, textural, metabolic and molecular changes occur which can be revealed with our integrated ultrahigh-resolution multimodal imaging approach including optical coherence tomography (OCT), multiphoton microscopy (MPM) and line scan Raman microspectroscopy (LSRM) on an unprecedented cellular level in a label-free manner. We investigated 5 pituitary gland and 25 adenoma biopsies, including lactotroph, null cell, gonadotroph, somatotroph and mammosomatotroph as well as corticotroph. First-level binary classification for discrimination of pituitary gland and adenomas was performed by feature extraction via radiomic analysis on OCT and MPM images and achieved an accuracy of 88%. Second-level multi-class classification was performed based on molecular analysis of the specimen via LSRM to discriminate pituitary adenomas subtypes with accuracies of up to 99%. Chemical compounds such as lipids, proteins, collagen, DNA and carotenoids and their relation could be identified as relevant biomarkers, and their spatial distribution visualized to provide deeper insight into the chemical properties of pituitary adenomas. Thereby, the aim of the current work was to assess a unique label-free and non-invasive multimodal optical imaging platform for pituitary tissue imaging and to perform a multiparametric morpho-molecular metabolic analysis and classification.

Background/Objectives: Cancer-associated cachexia in head and neck squamous cell carcinoma (HNSCC) is challenging to diagnose due to its complex pathophysiology. This study aimed to identify metabolic biomarkers linked to cachexia and survival in HNSCC patients using [¹⁸F]FDG-PET/CT imaging and machine learning (ML) techniques. Methods: We retrospectively analyzed 253 HNSCC patients from Vienna General Hospital and the MD Anderson Cancer Center. Automated organ segmentation was employed to quantify metabolic and volumetric data from [¹⁸F]FDG-PET/CT scans across 29 tissues and organs. Patients were categorized into low weight loss (LoWL; grades 0–2) and high weight loss (HiWL; grades 3–4) groups, according to the weight loss grading system (WLGS). Machine learning models, combined with Cox regression, were used to identify survival predictors. Shapley additive explanation (SHAP) analysis was conducted to determine the significance of individual features. Results: The HiWL group exhibited increased glucose metabolism in skeletal muscle and adipose tissue (p = 0.01), while the LoWL group showed higher lung metabolism. The one-year survival rate was 84.1% in the LoWL group compared to 69.2% in the HiWL group (p < 0.01). Pancreatic volume emerged as a key biomarker associated with cachexia, with the ML model achieving an AUC of 0.79 (95% CI: 0.77–0.80) and an accuracy of 0.82 (95% CI: 0.81–0.83). Multivariate Cox regression confirmed pancreatic volume as an independent prognostic factor (HR: 0.66, 95% CI: 0.46–0.95; p < 0.05). Conclusions: The integration of metabolic and volumetric data provided a strong predictive model, highlighting pancreatic volume as a key imaging biomarker in the metabolic assessment of cachexia in HNSCC. This finding enhances our understanding and may improve prognostic evaluations and therapeutic strategies.

Purpose: Advancements of deep learning in medical imaging are often constrained by the limited availability of large, annotated datasets, resulting in underperforming models when deployed under real-world conditions. This study investigated a generative artificial intelligence (AI) approach to create synthetic medical images taking the example of bone scintigraphy scans, to increase the data diversity of small-scale datasets for more effective model training and improved generalization. Methods: We trained a generative model on ^99mTc-bone scintigraphy scans from 9,170 patients in one center to generate high-quality and fully anonymized annotated scans of patients representing two distinct disease patterns: abnormal uptake indicative of (i) bone metastases and (ii) cardiac uptake indicative of cardiac amyloidosis. A blinded reader study was performed to assess the clinical validity and quality of the generated data. We investigated the added value of the generated data by augmenting an independent small single-center dataset with synthetic data and by training a deep learning model to detect abnormal uptake in a downstream classification task. We tested this model on 7,472 scans from 6,448 patients across four external sites in a cross-tracer and cross-scanner setting and associated the resulting model predictions with clinical outcomes. Results: The clinical value and high quality of the synthetic imaging data were confirmed by four readers, who were unable to distinguish synthetic scans from real scans (average accuracy: 0.48% [95% CI 0.46–0.51]), disagreeing in 239 (60%) of 400 cases (Fleiss’ kappa: 0.18). Adding synthetic data to the training set improved model performance by a mean (± SD) of 33(± 10)% AUC (p < 0.0001) for detecting abnormal uptake indicative of bone metastases and by 5(± 4)% AUC (p < 0.0001) for detecting uptake indicative of cardiac amyloidosis across both internal and external testing cohorts, compared to models without synthetic training data. Patients with predicted abnormal uptake had adverse clinical outcomes (log-rank: p < 0.0001). Conclusions: Generative AI enables the targeted generation of bone scintigraphy images representing different clinical conditions. Our findings point to the potential of synthetic data to overcome challenges in data sharing and in developing reliable and prognostic deep learning models in data-limited environments. Graphical

Purpose: Transthyretin cardiac amyloidosis (ATTR-CM) is a progressive, underdiagnosed disease with high morbidity and mortality. While disease-modifying therapies (DMTs) slow progression, early treatment response markers remain scarce. This study assessed AI-quantified thoracic [ ^99m Tc]Tc-DPD SPECT/CT markers as potential non-invasive biomarkers for monitoring therapeutic efficacy. Methods: This longitudinal study included ATTR-CM patients receiving DMTs (transthyretin stabilizers, RNA interference, or antisense oligonucleotides). [ ^99m Tc]Tc-DPD SPECT/CT scans were acquired at baseline and after treatment (median interval 9 months, IQR 7–10). AI-driven segmentation and quantification extracted 26 markers (SUV metrics, retention index, amyloid-affected volume, and amyloid activity). Functional, clinical, and blood parameters, as well as clinical outcomes, were evaluated for their association with changes in imaging markers. Results: In 45 patients (37 ATTRwt-CM, 8 ATTRv-CM), 65% (17/26) of AI-extracted SPECT/CT markers significantly decreased after treatment (all p < 0.001), including SUV _max reductions in the left ventricle (18.6 to 14.1) and myocardium (19.5 to 15.5). None of the markers significantly increased ( p > 0.05). Six of the imaging markers, most notably SUV _peak ( p = 0.007) of the myocardium and amyloid activity of the left ventricle ( p = 0.009), were associated with reductions in NT-proBNP. Lower values for three markers, including amyloid activity of the myocardium, retention index, and SUV _mean of the left atrium (all p = 0.016), were associated with improved NYHA class. An increase in amyloid-affected volume of the right ventricle (HR 3.19, 95% CI [1.29; 7.86], p = 0.005) and a decrease in right ventricular SUVmean (adjHR 0.15 95% CI [0.02;1.10], logrank p = 0.030) were associated with death or heart failure-associated hospitalization before and after multivariate adjustment. AI-driven analysis extracted imaging markers substantially faster and eliminated inter-rater variability. Conclusion: AI-driven [ ^99m Tc]Tc-DPD SPECT/CT analysis effectively detects treatment-induced reductions in cardiac amyloid burden, offering a non-invasive biomarker for early response assessment in ATTR-CM. AI-enabled imaging markers enhance reproducibility and efficiency, providing valuable support for personalized treatment strategies as new therapeutic options for ATTR-CM become available.

The efficacy of radioligand therapy (RLT) targeting prostate-specific membrane antigen (PSMA) is currently being investigated for its application in patients with early-stage prostate cancer (PCa). However, little is known about PSMA expression in healthy organs in this cohort. Collectively, 202 [⁶⁸Ga]Ga-PSMA-11 positron emission tomography (PET) scans from 152 patients were studied. Of these, 102 PET scans were from patients with primary PCa and hormone-sensitive biochemically recurrent PCa and 50 PET scans were from patients with metastatic castration-resistant PCa (mCRPC) before and after three cycles of [¹⁷⁷Lu]Lu-PSMA-RLT. PSMA-standardized uptake values (SUV) were measured in multiple organs and PSMA-total tumor volume (PSMA-TTV) was determined in all cohorts. The measured PET parameters of the different cohorts were normalized to the bloodpool and compared using t- or Mann–Whitney U tests. Patients with early-stage PCa had lower PSMA-TTVs (10.39 mL vs. 462.42 mL, p < 0.001) and showed different SUVs in the thyroid, submandibular glands, heart, liver, kidneys, intestine, testes and bone marrow compared to patients with advanced CRPC, with all tests showing p < 0.05. Despite the differences in the PSMA-TTV of patients with mCRPC before and after [¹⁷⁷Lu]Lu-PSMA-RLT (462.42 mL vs. 276.29 mL, p = 0.023), no significant organ differences in PET parameters were detected. These suggest different degrees of PSMA-ligand binding among patients with different stages of PCa that could influence radiotoxicity during earlier stages of disease in different organs when PSMA-RLT is administered.