The Prostate Imaging and Reporting Data System (PI-RADS) has a key role in the management of prostate cancer (PCa). However, the clinical interpretation of PI-RADS 3 score lesions may be challenging and misleading, thus postponing PCa diagnosis to biopsy outcome. Multiparametric magnetic resonance imaging (mpMRI) radiomic analysis may represent a stand-alone noninvasive tool for PCa diagnosis. Hence, this study aims at developing a mpMRI-based radiomic PCa diagnostic model in a cohort of PI-RADS 3 lesions. We enrolled 133 patients with 155 PI-RADS 3 lesions, 84 of which had PCa confirmation by fusion biopsy. Local radiomic features were generated from apparent diffusion coefficient maps, and the four most informative were selected using LASSO, the Wilcoxon rank-sum test (p < 0.001), and support vector machines (SVMs). The selected features where augmented and used to train an SVM classifier, externally validated on a holdout subset. Linear and second-order polynomial kernels were exploited, and their predictive performance compared through receiver operating characteristics (ROC)-related metrics. On the test set, the highest performance, equally for both kernels, was specificity = 76%, sensitivity = 78%, positive predictive value = 80%, and negative predictive value = 74%. Our findings substantially improve radiologist interpretation of PI-RADS 3 lesions and let us advance towards an image-driven PCa diagnosis.

Background: Rectal cancer is a malignant neoplasm of the large intestine resulting from the uncontrolled proliferation of the rectal tract. Predicting the pathologic response of neoadjuvant chemoradiotherapy at an MRI primary staging scan in patients affected by locally advanced rectal cancer (LARC) could lead to significant improvement in the survival and quality of life of the patients. In this study, the possibility of automatizing this estimation from a primary staging MRI scan, using a fully automated artificial intelligence-based model for the segmentation and consequent characterization of the tumor areas using radiomic features was evaluated. The TRG score was used to evaluate the clinical outcome. Methods: Forty-three patients under treatment in the IRCCS Sant’Orsola-Malpighi Polyclinic were retrospectively selected for the study; a U-Net model was trained for the automated segmentation of the tumor areas; the radiomic features were collected and used to predict the tumor regression grade (TRG) score. Results: The segmentation of tumor areas outperformed the state-of-the-art results in terms of the Dice score coefficient or was comparable to them but with the advantage of considering mucinous cases. Analysis of the radiomic features extracted from the lesion areas allowed us to predict the TRG score, with the results agreeing with the state-of-the-art results. Conclusions: The results obtained regarding TRG prediction using the proposed fully automated pipeline prove its possible usage as a viable decision support system for radiologists in clinical practice.

Purpose: To report response rates (using mRECIST), overall survival (OS), progression-free survival and local tumour recurrence-free survival (LRFS) of balloon-occluded transarterial chemoembolisation (bTACE) for hepatocellular carcinoma (HCC). Materials and Methods: Patients from five European centres treated with conventional or drug-eluting microsphere bTACE for HCC were included, and patients already lost to follow-up before 12 months were excluded. Possible factors contributing to LRFS and OS were evaluated with Cox proportional hazards models. Results: Seventy-three patients were enrolled. The mean number of nodules per patient was 2.07(± 1.68), and the average maximum diameter of the nodules was 37 ± 19.9 mm. The response of the target lesion at 6 months was complete response (CR) in 58.9%, partial response (PR) in 28.8%, stable disease (SD) in 6.8% and progressive disease (PD) in 5.5%. The median follow-up time was 31 months; at the last follow-up, target tumour response was CR in 49.3%, PR in 12.3%, SD in 5.5% and PD 32.9%. Overall response at the last follow-up was CR in 17.8%, PR in 9.6%, SD 2.7% and PD in 69.9% (for new lesions in 37% of patients). Median OS was not reached; mean overall survival was 50.0 months, while median LRFS was 31.0 months. At uni- and multivariable analysis, only tumour maximum diameter was related to LRFS (hazard ratio [HR] = 1.021; 95% CI 1.004–1.038, P = 0.015). Conclusions: bTACE demonstrated high efficacy for HCC, with a complete response in 58.9% of patients, a median local recurrence-free survival of 31.0 months and a mean overall survival of 50.0 months. Graphical

Lumbar back pain is one of the main causes of disability around the world. Most patients will complain of back pain at least once in their lifetime. The degenerative spine is considered the main cause and is extremely common in the elderly population. Consequently, treatment-related costs are a major burden to the healthcare system in developed and undeveloped countries. After the failure of conservative treatments or to avoid daily chronic drug intake, invasive treatments should be suggested. In a world where many patients reject surgery and prefer minimally invasive procedures, interventional radiology is pivotal in pain management and could represent a bridge between medical therapy and surgical treatment. We herein report the different image-guided procedures that can be used to manage degenerative spine-related low back pain. Particularly, we will focus on indications, different techniques, and treatment outcomes reported in the literature. This literature review focuses on the different minimally invasive percutaneous treatments currently available, underlining the central role of radiologists having the capability to use high-end imaging technology for diagnosis and subsequent treatment, allowing a global approach, reducing unnecessary surgeries and prolonged pain-reliever drug intake with their consequent related complications, improving patients’ quality of life, and reducing the economic burden.

Regenerative medicine is taking a step forward in treating multiple diseases. The possibility of renewing damaged tissues with stem cells has become a topic of interest in recent decades. Still a relatively new research topic, many issues in this discipline are being addressed, from cell culturing to the study of different graft materials, and, moreover, cell delivery. For instance, direct intravenous injection has a big downfall regarding its lack of precision and poorly targeted treatment. Trans-arterial and direct percutaneous infusion to the aimed tissue/organ are both considered ideal for reaching the desired region but require image guidance to be performed safely and precisely. In this context, interventional radiology becomes pivotal for providing different cell delivery possibilities in every case. In this review, we analyze different basic stem cell therapy concepts and the current and future role of interventional radiology with a focus on trans-arterial delivery.