Objectives: To evaluate the correlation between radiomic features extracted from contrast-enhanced mammography (CEM) tumor lesions and peritumoral background with prognostic factors in breast cancer (BC). Methods: In this retrospective, single-center study, 134 women with histologically confirmed breast cancer underwent CEM examination. Radiomic features were extracted from manually segmented lesions and lesion contours were automatically delineated using PyRadiomics. The extracted features were categorized into seven classes: First-order Features, Shape Features (2D), Gray Level Co-occurrence Matrix (GLCM), Gray Level Run Length Matrix (GLRLM), Gray Level Size Zone Matrix (GLSZM), and Neighboring Gray Tone Difference Matrix (NGTDM). Histological examination assessed tumor type, grade, receptor structure (ER, PgR, HER2), Ki67 index, and lymph node involvement. Pearson correlation and multivariate regression were applied to evaluate associations between radiomic features and prognostic factors. Results: Significant correlations were found between First-order Features and prognostic factors such as ER, PgR, and Ki67 (p < 0.05). GLCM-based texture features showed strong associations with Ki67 and HER2 (p < 0.01). Radiomic features from peritumoral regions, especially shape and GLSZM metrics, were significantly correlated with Ki67 and lymph node involvement. Conclusions: Radiomic analysis of both tumor and peritumoral regions offers significant insights into BC prognosis. These findings support the integration of radiomics into personalized diagnostic and therapeutic strategies, potentially improving clinical decision making in BC management.

Background: Low back pain (LBP) is the most frequent indication to magnetic resonance imaging (MRI) examinations of the lumbosacral spine. The individual role of soft tissues, including muscles, on LBP is not fully understood and the contribution of each MRI-derived parameter of soft tissues status on the intensity of LBP has not been investigated in detail. Methods: The study design was observational retrospective, single center carried out at a University Hospital. Images were acquired using a using a 1.5 Tesla scanner. Patients completed a symptom questionnaire and rated their pain intensity using the Visual Analogue Scale (VAS). The VAS scores were categorized as mild, moderate, and severe using cutoff values of 3.8 and 5.7, based on the literature. Biometric data, including weight and height, were also recorded to calculate the body mass index (BMI). The ratios between intramuscular fat infiltration and net muscle area were also calculated. Patient sample included 94 patients with LBP underwent MRI of the lumbosacral spine. Results: The stepwise analysis revealed that increasing psoas net area was associated with lower VAS levels (odds ratio [OR]: 0.94: 95% confidence interval [CI]: 0.90-0.98; p = .005), and an increase of one square centimeter of total psoas area resulted in a greater probability of reporting a mild ( + 1.21%; 95% CI: 0.37, 2.05%) or a moderate VAS ( + 0.40%; 95% CI: -0.02, 0.82%), Furthermore, a more severe VAS was associated with a higher BMI (OR: 1.13; 95% CI: 1.00-1.27). Conclusion: Our study demonstrates a relationship between LBP and MRI parameters of paravertebral and psoas muscles status. The psoas muscle is extremely important for spine stabilization and is linked to clinical symptoms of patients affected by LBP. These findings could contribute to future studies and improve treatment options in patients with LBP, possibly reducing the impact on disability, quality of life and socioeconomical burden.

The aim of this study is to report the authors’ experience of percutaneous transarterial embolization (TAE) in patients with spontaneous soft tissue hematomas (SSTH) and active bleeding with anticoagulation impairment. The study retrospectively identified 78 patients who received a diagnosis of SSTH by CT scan and underwent TAE between 2010 and 2019 in a single trauma center. The patients were stratified using Popov classification into categories: 2A, 2B, 2C, and 3. The patient’s 30-day survival after TAE was considered the primary outcome; immediate technical success, the need for additional TAE, and TAE-related complications were considered secondary outcomes. Immediate technical success, complication rate, and risk factors for death were analyzed. Follow-up stopped on day 30 from TAE. 27 patients (35%) fell into category 2A, 8 (10%) into category 2B, 4 (5%) into category 2C, and 39 (50%) into category 3. Immediate technical success was achieved in 77 patients (98.7%). Complications included damage at the arterial puncture site (2 patients, 2.5%) and acute kidney injury (24 patients, 31%). Only 2 patients (2.5%) had been discharged with a new diagnosis of chronic kidney disease. The 30-day overall mortality rate was 19% (15 patients). The mortality rate was higher in hemodynamically unstable patients, in Popov categories 2B, 2C, and 3, and in patients with an initial eGFR < 30 mL/min × 1.73 m². The study demonstrated a higher mortality risk for categories 2B, 2C, and 3 compared to category 2A. Nonetheless, TAE has proven effective and safe in type 2A patients. Even though it is unclear whether type 2A patients could benefit from conservative treatment rather than TAE, in the authors’ opinion, a TAE endovascular approach should be promptly considered for all patients in ACT with active bleeding demonstrated on CT scans.

Objective: This study evaluates the accuracy of a Machine Learning model of Random Forest (RF) type, using MRI data and radiomic features to predict lymph node involvement in prostate cancer (PCa). Methods: Ninety-five patients who underwent mp-MRI, prostatectomy, and lymphadenectomy at the Fondazione Policlinico Campus Bio-medico Radiological Department from 2016 to 2022 were analyzed. Radiomic features were extracted from T2-weighted, DWI, and ADC sequences and processed using a Random Forest (RF) model. Clinical data such as PSA levels and Gleason scores were also considered. Results: The RF model demonstrated significant accuracy in predicting lymph node involvement, achieving 84% accuracy for nodules in the peripheral zone (80% for predicting positive lymph node involvement and 85% for negative lymph node involvement) and 87% for those in the transitional zone (86% for predicting positive lymph node involvement and 88% for negative lymph node involvement). In the peripheral zone, key features included ADC shape maximum 2D diameter row and T2 noduloglcm difference variance, while in the transitional zone, DWI glcm difference average and DWI glcm Idm were important. DWI and ADC sequences were particularly crucial for accurate lymph node assessment. First-order features emerged as the most significant in whole-gland analysis, indicating fundamental differences in tumor composition and density critical for identifying malignancies with higher metastatic potential. Conclusions: AI-driven radiomic analysis, especially using DWI- and ADC-derived features, effectively predicts lymph node involvement in PCa patients, in particular in negative linfonode status patients, offering a promising tool for preoperative linfonode sparing patient selection. Further validation with larger cohorts is needed. Some limitations of this study are a relatively small sample size and it being a retrospective study.