Retroperitoneal ganglioneuroma is a rare neuroectodermal tumor with a benign nature. We performed a literature review among 338 studies. We included 9 studies, whose patients underwent CT and/or MRI to characterize a retroperitoneal mass, which was confirmed to be a ganglioneuroma by histologic exam. The most common features of ganglioneuroma are considered to be a solid nature, oval/lobulated shape, and regular margins. The ganglioneuroma shows a progressive late enhancement on CT. On MRI it appears as a hypointense mass in T1W images and with a heterogeneous high-intensity in T2W. The MRI-“whorled sign” is described in the reviewed studies in about 80% of patients. The MRI characterization of a primitive retroperitoneal cystic mass should not exclude a cystic evolution from solid masses, and in the case of paravertebral location, the differential diagnosis algorithm should include the hypothesis of ganglioneuroma. In our case, the MRI features could have oriented towards a neurogenic nature, however, the predominantly cystic-fluid aspect and the considerable longitudinal non-invasive extension between retroperitoneal structures, misled us to a lymphatic malformation. In the literature, it is reported that the cystic presentation can be due to a degeneration of a well-known solid form while maintaining a benign character: the distinguishing malignity character is the revelation of immature cells on histological examination.

Background: Pancreatic ductal adenocarcinoma (PDAC) is the seventh leading cause of cancer-related deaths worldwide. Surgical resection is the main driver to improving survival in resectable tumors, while neoadjuvant treatment based on chemotherapy (and radiotherapy) is the best option-treatment for a non-primally resectable disease. CT-based imaging has a central role in detecting, staging, and managing PDAC. As several authors have proposed radiomics for risk stratification in patients undergoing surgery for PADC, in this narrative review, we have explored the actual fields of interest of radiomics tools in PDAC built on pre-surgical imaging and clinical variables, to obtain more objective and reliable predictors. Methods: The PubMed database was searched for papers published in the English language no earlier than January 2018. Results: We found 301 studies, and 11 satisfied our research criteria. Of those included, four were on resectability status prediction, three on preoperative pancreatic fistula (POPF) prediction, and four on survival prediction. Most of the studies were retrospective. Conclusions: It is possible to conclude that many performing models have been developed to get predictive information in pre-surgical evaluation. However, all the studies were retrospective, lacking further external validation in prospective and multicentric cohorts. Furthermore, the radiomics models and the expression of results should be standardized and automatized to be applicable in clinical practice.

Background: Post-hepatectomy liver failure (PHLF) is the most worrisome complication after a major hepatectomy and is the leading cause of postoperative mortality. The most important predictor of PHLF is the future liver remnant (FLR), the volume of the liver that will remain after the hepatectomy, representing a major concern for hepatobiliary surgeons, radiologists, and patients. Therefore, an accurate preoperative assessment of the FLR and the prediction of PHLF are crucial to minimize risks and enhance patient outcomes. Recent radiomics and deep learning models show potential in predicting PHLF and the FLR by integrating imaging and clinical data. However, most studies lack external validation and methodological homogeneity and rely on small, single-center cohorts. This review outlines current CT-based approaches for surgical risk stratification and key limitations hindering clinical translation. Methods: A literature analysis was performed on the PubMed Dataset. We reviewed original articles using the subsequent keywords: [(Artificial intelligence OR radiomics OR machine learning OR deep learning OR neural network OR texture analysis) AND liver resection AND CT]. Results: Of 153 pertinent papers found, we underlined papers about the prediction of PHLF and about the FLR. Models were built according to machine learning (ML) and deep learning (DL) automatic algorithms. Conclusions: Radiomics models seem reliable and applicable to clinical practice in the preoperative prediction of PHLF and the FLR in patients undergoing major liver surgery. Further studies are required to achieve larger validation cohorts.

Background/Objectives: Low back pain (LBP) is a clinically relevant symptom in adolescents and adults with scoliosis, but its relationship with curve magnitude is inconsistent, and curve measurement alone therefore cannot explain symptom burden or direct pain management. This narrative review examines imaging findings and clinically plausible mechanisms of scoliosis-related LBP, considered separately for adolescent idiopathic scoliosis, adult idiopathic scoliosis, adult degenerative scoliosis and adult spinal deformity, and their implications for management. Methods: This narrative review was conducted and reported with reference to the SANRA quality domains. PubMed and the Cochrane Library were searched between June and July 2026, with database-specific search strings, search dates and record yields reported in full. Study selection was performed by the first author and reviewed by the co-authors, without independent duplicate screening or formal risk-of-bias assessment. Results: Curve magnitude is not a consistent independent predictor of pain burden, and pain distribution does not reliably follow curve laterality in adult degenerative scoliosis. We propose an author-derived and prospectively unvalidated seven-component framework comprising five candidate pain generators—facet-mediated, vertebrogenic/endplate, foraminal or lateral recess compression, sagittal malalignment with paraspinal overload, and sacroiliac overload—together with biopsychosocial pain modifiers and associated neural-axis abnormalities. Imaging may identify clinically plausible contributors but cannot establish pain causation in isolation; clinical concordance and, for selected interventions, supportive diagnostic procedures remain essential. Standing full-spine radiography, or low-dose biplanar acquisition where serial monitoring is required in adolescents, provides structural and alignment assessment, whereas MRI should be tailored to the clinical scenario and differs in purpose between adolescents and adults. Evidence supporting mechanism-directed interventions derives largely from non-scoliotic chronic LBP cohorts and is identified as such throughout. Conclusions: Imaging in scoliosis-related LBP should identify clinically concordant candidate pain sources rather than merely quantify deformity. Structural abnormalities are not synonymous with pain generators, and treatment selection should integrate imaging with clinical assessment and, when appropriate, supportive diagnostic procedures. The proposed framework and management pathway are author-derived and require prospective validation.