Pancreatic ductal adenocarcinoma (PDAC) stands out as the predominant malignant neoplasm affecting the pancreas, characterized by a poor prognosis, in most cases patients being diagnosed in a nonresectable stage. Image-based artificial intelligence (AI) models implemented in tumor detection, segmentation, and classification could improve diagnosis with better treatment options and increased survival. This review included papers published in the last five years and describes the current trends in AI algorithms used in PDAC. We analyzed the applications of AI in the detection of PDAC, segmentation of the lesion, and classification algorithms used in differential diagnosis, prognosis, and histopathological and genomic prediction. The results show a lack of multi-institutional collaboration and stresses the need for bigger datasets in order for AI models to be implemented in a clinically relevant manner.

Pancreatic ductal adenocarcinoma (PDAC) is the most common malignant tumor of the pancreas, carrying a poor prognosis, in most cases patients being diagnosed in a nonresectable stage. Image-based artificial intelligence (AI) models implemented in tumor detection, segmentation and classification could improve diagnosis with better treatment options and increased survival. This review included papers published in the last 5 years and describes the current trends in AI algorithms used in PDAC. We analyzed the applications of AI in detection of PDAC, segmentation of the lesion and classification algorithms used in differential diagnosis, prognosis, and histopathological and genomic prediction. The results show lack of multi-institutional collaboration and stresses the need for bigger datasets in order for AI models to be implemented in a clinically relevant manner.

Idiopathic superior mesenteric vein (SMV) stenosis, where no clear causative factor is identifiable, remains a clinical rarity. We present a detailed case report of a patient with idiopathic stenosis of the SMV who underwent successful endovascular stenting. This report outlines the patient’s clinical presentation, diagnostic imaging findings, procedural approach by the interventional radiology team, and subsequent management. Endovascular stenting is a viable therapeutic option for patients with idiopathic SMV stenosis. This case demonstrates that with appropriate interventional and post-procedural management, long-term stent patency and thrombosis prevention can be achieved. The success of this case encourages further investigation into endovascular treatments for venous stenoses.

Background: The Liver Imaging Reporting and Data System (LI-RADS) combines standardized terminology with a classification system for imaging findings in patients with HCC, therefore rendering diagnostic biopsy unnecessary in many cases. This retrospective study included 23 patients with a biopsy diagnosis of HCC, performed either before or after local interventional procedures, in order to evaluate the histopathologic changes induced by previous procedures and their potential influence on the response to immune therapy. Material and Methods: The study encompassed a cohort of patients diagnosed with Hepatocellular Carcinoma (HCC). Diagnosis was established via contrast-enhanced computer tomography or magnetic resonance imaging that identified LI-RADS-5 nodules in conjunction with historical liver disease and elevated alpha-fetoprotein (AFP) levels or via histological examination confirming positivity for glypican3, heat shock protein 70, and glutamine synthetase. The study detailed the liver disease etiology, LI-RADS scores, characteristics and dimensions of HCC nodules, serum AFP concentrations, Edmondson–Steiner grading, and the expression of programmed cell death ligand 1 (PD-L1) in the tumor cells. Results: Among the study’s cohort of Hepatocellular Carcinoma (HCC) patients, a portion had not received any prior treatments, while the remainder experienced local HCC recurrence following trans-arterial chemoembolization or radiofrequency ablation. Observations indicated elevated alpha-fetoprotein (AFP) levels in those who had not undergone any previous interventions, showing statistical significance. The Edmondson–Steiner classification predominantly identified grade III differentiation across patients, irrespective of their treatment history. Furthermore, an increase in intra-tumoral programmed cell death ligand 1 (PD-L1) expression was noted in patients who had not been subjected to previous therapies. Conclusion: Liver biopsy offers valuable insights for patients with Hepatocellular Carcinoma (HCC), assisting in the tailoring of immune therapy strategies, particularly in cases of recurrence following prior local interventions.

Background: Systemic sclerosis (SSc) is an autoimmune disease with interstitial lung disease (ILD) representing the leading cause of mortality. Diaphragmatic muscle impairment, which may contribute to respiratory dysfunction, is underexplored in SSc. Objective: This study aimed to assess diaphragmatic thickness using HRCT in patients with SSc-ILD and to investigate whether this parameter correlates with disease severity and clinical outcomes. Methods: We conducted a multicentric retrospective observational study that included 161 participants: 69 with SSc-ILD and 92 matched controls without pulmonary disease. Preliminary findings from this cohort were previously communicated as a conference abstract at EULAR 2024. Diaphragmatic thickness was measured on axial and coronal CT images at the celiac axis level by two independent radiologists. Clinical and functional parameters were collected, including forced vital capacity (FVC), diffusing capacity for carbon monoxide (DLCO), echocardiographic findings, and 6 min walking test performance. Results: The left hemidiaphragm was significantly thinner in patients with SSc-ILD compared with controls (2.98 ± 1.04 mm vs. 3.44 ± 0.97 mm; p = 0.004), while the right hemidiaphragm showed a non-significant trend toward reduction (3.21 ± 1.09 mm vs. 3.52 ± 1.05 mm; p = 0.072). Thinning of the right hemidiaphragm correlated significantly with lower FVC (p < 0.05). ROC analysis identified an optimal left diaphragm cut-off of ≤3.115 mm (AUC = 0.635, 95% CI: 0.556–0.709, sensitivity = 66.7%, specificity = 60.9%). No associations were found with the autoantibody profile, disease duration, or treatment. Interobserver reliability was excellent (Bland–Altman mean difference −0.002 mm, p = 0.95). Conclusions: HRCT-measured left hemidiaphragm thickness is significantly reduced in patients with SSc-ILD compared with controls, and right hemidiaphragm thickness correlates with impaired lung function. Although its discriminative performance is modest (AUC 0.635), this parameter may serve as a supplementary zero-burden addition to routine HRCT evaluation alongside pulmonary function tests. The retrospective cross-sectional design precludes conclusions about causality or prognosis; prospective studies incorporating concurrent functional diaphragm assessment are warranted.