Combined hepatocellular-cholangiocarcinoma (cHCC-CCA) is a rare primary liver cancer which displays clinicopathologic features of both hepatocellular (HCC) and cholangiocellular carcinoma (CCA). The similarity to HCC and CCA makes the diagnostic workup particularly challenging. Alpha-fetoprotein (AFP) and carbohydrate antigen 19-9 (CA 19-9) are blood tumour markers related with HCC and CCA, respectively. They can be used as diagnostic markers in cHCC-CCA as well, albeit with low sensitivity. The imaging features of cHCC-CCA overlap with those of HCC and CCA, dependent on the predominant histopathological component. Using the Liver Imaging and Reporting Data System (LI-RADS), as many as half of cHCC-CCAs may be falsely categorised as HCC. This is especially relevant since the diagnosis of HCC may be made without histopathological confirmation in certain cases. Thus, in instances of diagnostic uncertainty (e.g., simultaneous radiological HCC and CCA features, elevation of CA 19-9 and AFP, HCC imaging features and elevated CA 19-9, and vice versa) multiple image-guided core needle biopsies should be performed and analysed by an experienced pathologist. Recent advances in the molecular characterisation of cHCC-CCA, innovative diagnostic approaches (e.g., liquid biopsies) and methods to analyse multiple data points (e.g., clinical, radiological, laboratory, molecular, histopathological features) in an all-encompassing way (e.g., by using artificial intelligence) might help to address some of the existing diagnostic challenges.

Background/Objectives: Peptide receptor radionuclide therapy (PRRT) is an established treatment for metastatic neuroendocrine tumors (NETs), yet long-term disease control occurs only in a subset of patients. Predicting progression-free survival (PFS) could support individualized treatment planning. This study evaluates laboratory, imaging, and multimodal deep learning models for PFS prediction in PRRT-treated patients. Methods: In this retrospective, single-center study 116 patients with metastatic NETs undergoing [177Lu]Lu-DOTATOC were included. Clinical characteristics, laboratory values, and pretherapeutic somatostatin receptor positron emission tomography/computed tomographies (SR-PET/CTs) were collected. Seven models were trained to classify low- vs. high-PFS groups, including unimodal (laboratory, SR-PET, or CT) and multimodal fusion approaches. Performance was assessed via repeated 3-fold cross-validation with area under the receiver operating characteristic curve (AUROC) and area under the precision–recall curve (AUPRC). Explainability was evaluated by feature importance analysis and gradient based saliency maps. Results: Forty-two patients (36%) displayed short PFS (≤1 year) and 74 patients displayed long PFS (>1 year). Groups were similar in most characteristics, except for higher baseline chromogranin A (p = 0.003), elevated $\gamma$-GT (p = 0.002), and fewer PRRT cycles (p < 0.001) in short-PFS patients. The Random Forest model trained only on laboratory biomarkers reached an AUROC of 0.59 ± 0.02. Unimodal three-dimensional convolutional neural networks using SR-PET or CT performed worse (AUROC 0.42 ± 0.03 and 0.54 ± 0.01, respectively). A multimodal fusion model integrating laboratory values, SR-PET, and CT—augmented with a pretrained CT branch—achieved the best results (AUROC 0.72 ± 0.01, AUPRC 0.80 ± 0.01). Explainability analyses provided insights into model predictions, with explainability patterns in the fusion model appearing physiologically plausible and predominantly tumor-focused. Conclusions: Multimodal deep learning combining SR-PET, CT, and laboratory biomarkers outperformed unimodal approaches for PFS prediction after PRRT. Upon external validation, such models may support risk-adapted follow-up strategies.

Purpose: This study examines the association between tumor volume doubling time (TVDT) and clinical outcomes for patients with hepatocellular carcinoma (HCC) treated with transarterial embolization (TAE) and evaluates the impact of tumor genotype on TVDT. Methods: This was a retrospective cohort study at a single tertiary care cancer center, including treatment-naïve patients with biopsy-proven HCC treated with TAE from 1/2014 to 6/2022. The patients underwent initial baseline contrast-enhanced cross-sectional imaging more than 30 days prior to embolization. Index tumors were defined as the largest HCC present on baseline imaging treated with TAE, and TVDT was calculated using Schwartz’s equation with perpendicular trans-axial measurements. Genetic mutation analysis was performed on HCC tissue specimens using next-generation sequencing. Survival analysis was performed using the Kaplan–Meier method, and Cox regression was used to assess prognostic factors for survival. Results: Patients with a TVDT ≤ 2.5 months had a worse overall survival (OS) after TAE (p = 0.011). On multivariate regression analysis, predictors of worse OS following TAE included TVDT ≤ 2.5 months (p = 0.036), Eastern Cooperative Oncology Group (ECOG) performance score of 1 or 2 (p = 0.006), and alpha fetoprotein > 200 ng/mL (p = 0.013). The presence of ≥5 HCC tumors on initial imaging was associated with a worse local tumor progression-free survival (LTPFS) on multivariate analysis (p = 0.002). No single genetic mutation was associated with shorter TVDT. Conclusion: Patients with HCC exhibiting rapid growth, defined as shorter TVDT, may be associated with worse overall survival following TAE. Rapid tumor growth does not seem to be correlated with a single genetic mutation.

Background/Objectives: The aim of this study was to develop and validate a robust, radiomics-based classification model that uses pre-treatment MRI to non-invasively differentiate among major soft tissue sarcoma (STS) subtypes and a benign mimic. Methods: In this retrospective study, a cohort of 332 patients with biopsy-proven leiomyosarcoma, myxofibrosarcoma, myxoid liposarcoma, dedifferentiated liposarcoma, and undifferentiated pleomorphic sarcoma, along with the benign mimic intramuscular myxoma, was analyzed. Pre-treatment T1-weighted fat-saturated contrast-enhanced and T2-weighted fat-saturated MRI sequences were used for analysis. Following manual tumor segmentation, 1240 three-dimensional radiomic features were extracted. An XGBoost classifier was trained and validated using a robust 250-iteration bootstrap framework with nested cross-validation to ensure rigorous feature selection and unbiased performance evaluation. The model’s performance was assessed independently on T1-only, T2-only, and combined T1+T2 feature sets. Results: The combined T1 and T2 model achieved superior performance with an accuracy of 0.68 ± 0.04 and an AUC of 0.92 ± 0.02. At the subtype level, balanced accuracy was highest for intramuscular myxoma (0.91 ± 0.05), dedifferentiated liposarcoma (0.84 ± 0.06), and leiomyosarcoma (0.83 ± 0.05). SHAP analysis identified key features driving predictions, such as low T2 GLSZM Zone Size Entropy for myxoma and high T2 GLSZM Gray-Level Variance for leiomyosarcoma, which aligns with known pathological characteristics. Misclassifications predominantly occurred between subtypes with overlapping radiomic profiles. Conclusions: Radiomics applied to pre-treatment MRI enables robust, non-invasive classification of STS subtypes, demonstrating strong clinical potential for improving diagnostic confidence and informing triage strategies.