Search

With profound effects on patient care, the role of artificial intelligence (AI) in radiomics has become a disruptive force in contemporary medicine. Radiomics, the quantitative feature extraction and analysis from medical images, offers useful imaging biomarkers that can reveal important information about the nature of diseases, how well patients respond to treatment and patient outcomes. The use of AI techniques in radiomics, such as machine learning and deep learning, has made it possible to create sophisticated computer-aided diagnostic systems, predictive models, and decision support tools. The many uses of AI in radiomics are examined in this review, encompassing its involvement of quantitative feature extraction from medical images, the machine learning, deep learning and computer-aided diagnostic (CAD) systems approaches in radiomics, and the effect of radiomics and AI on improving workflow automation and efficiency, optimize clinical trials and patient stratification. This review also covers the predictive modeling improvement by machine learning in radiomics, the multimodal integration and enhanced deep learning architectures, and the regulatory and clinical adoption considerations for radiomics-based CAD. Particular emphasis is given to the enormous potential for enhancing diagnosis precision, treatment personalization, and overall patient outcomes.

Objectives: The main objective of this study was to report and investigate the characteristics and longitudinal changes in dark-without-pressure (DWP) fundus lesions in patients with autoimmune diseases using multimodal imaging techniques. Methods: In this retrospective observational case series, five patients affected by ocular and systemic autoimmune disorders and DWP were examined. DWP was assessed by multimodal imaging, including color fundus photography (CFP), near-infrared reflectance (NIR), blue reflectance (BR), blue autofluorescence (BAF), optical coherence tomography (OCT), OCT-angiography (OCT-A), fluorescein angiography (FA) and indocyanine green angiography (ICGA), and functional testing, including standard automated perimetry (SAP) and electroretinography (ERG). Follow-up examinations were performed for four out of five patients (range: 6 months–7 years). Results: DWP fundus lesions were found in the retinal mid-periphery and were characterized by the hypo-reflectivity of the ellipsoid zone on OCT. DWP appeared hypo-reflective in NIR, BR and BAF, and exhibited hypo-fluorescence in FA in two patients while showing no signs in one patient. ICGA showed hypo-fluorescent margins in one patient. SAP and ERG testing did not show alterations attributable to the DWP lesion. Follow-up examinations documented rapid dimensional changes in DWP even in the short term (1 month). Conclusions: This study suggests a possible association between autoimmune diseases and DWP. New FA and ICGA features were described. The proposed pathogenesis hypotheses may operate as a basis for further investigation of a lesion that is still largely unknown. Large population studies would be necessary to confirm whether there is a higher incidence of DWP in this patient category.

This study investigates the biochemical composition and biological properties of different parts (leaves, roots, and twigs) of two Cistus species (Cistus monspeliasis and Cistus parviflorus). The extracts were analysed using UHPLC-MS/MS to determine their chemical profiling. A range of antioxidant assays were performed to evaluate the extract’s antioxidant capabilities. The enzyme inhibition studies focused on acetylcholinesterase (AChE), butyrylcholinesterase (BChE), α-amylase, and α-glucosidase and tyrosinase. In addition, the study examined the antimicrobial effects on different bacteria and yeasts and evaluated the toxicity using the MTT assay. Quinic acid, citric acid, gallic acid, catechin, quercetin derivatives, kaempferol, myricetin, ellagic acid, prodelphinidins, procyanidins, scopoletin, and flavogallonic acid dilactone are the main bioactive compounds found in both species. In enzyme inhibition assays, C. monspeliasis roots exhibited significant activity against acetylcholinesterase (AChE) and butyrylcholinesterase (BChE), with the values of 2.58 ± 0.02 mg GALAE/g and 11.37 ± 1.93 mg GALAE/g, respectively. Cytotoxicity studies showed mostly weak toxicity, with some samples moderately reducing viability in RAW and HepG2 cells. These findings underscore the diverse biochemical profiles and bioactive potential of Cistus species, suggesting their utility as natural sources of antioxidants and enzyme inhibitors for pharmaceutical and nutraceutical development.

PurposeMagnetic resonance imaging (MRI)-guided radiotherapy enables adaptive treatment plans based on daily anatomical changes and accurate organ visualization. However, the bias field artifact can compromise image quality, affecting diagnostic accuracy and quantitative analyses. This study aims to assess the impact of bias field correction on 0.35 T pelvis MRIs by evaluating clinical anatomy visualization and generative adversarial network (GAN) auto-segmentation performance.Materials and methods3D simulation MRIs from 60 prostate cancer patients treated on MR-Linac (0.35 T) were collected and preprocessed with the N4ITK algorithm for bias field correction. A 3D GAN architecture was trained, validated, and tested on 40, 10, and 10 patients, respectively, to auto-segment the organs at risk (OARs) rectum and bladder. The GAN was trained and evaluated either with the original or the bias-corrected MRIs. The Dice similarity coefficient (DSC) and 95th percentile Hausdorff distance (HD95th) were computed for the segmented volumes of each patient. The Wilcoxon signed-rank test assessed the statistical difference of the metrics within OARs, both with and without bias field correction. Five radiation oncologists blindly scored 22 randomly chosen patients in terms of overall image quality and visibility of boundaries (prostate, rectum, bladder, seminal vesicles) of the original and bias-corrected MRIs. Bennett’s S score and Fleiss’ kappa were used to assess the pairwise interrater agreement and the interrater agreement among all the observers, respectively.ResultsIn the test set, the GAN trained and evaluated on original and bias-corrected MRIs showed DSC/HD95th of 0.92/5.63 mm and 0.92/5.91 mm for the bladder and 0.84/10.61 mm and 0.83/9.71 mm for the rectum. No statistical differences in the distribution of the evaluation metrics were found neither for the bladder (DSC: p = 0.07; HD95th: p = 0.35) nor for the rectum (DSC: p = 0.32; HD95th: p = 0.63). From the clinical visual grading assessment, the bias-corrected MRI resulted mostly in either no change or an improvement of the image quality and visualization of the organs’ boundaries compared with the original MRI.ConclusionThe bias field correction did not improve the anatomy visualization from a clinical point of view and the OARs’ auto-segmentation outputs generated by the GAN.

Abstract Background Renal ischemia/reperfusion injury is an unavoidable event in transplantation in which free radical-mediated injury determines release of pro-inflammatory cytokines and activation of innate immunity. In addition to their cholesterol-lowering action, statins have shown dose-dependent pleiotropic effects on inflammatory pathways and oxidative stress. We investigated the effects of high-dose atorvastatin (atorvastatin 40 mg/kg) in preventing ischemia/reperfusion injury in an animal model of kidney transplant. Methods Forty female rats underwent left nephrectomy and orthotopic autotransplantation. Animals were divided in four groups: A = Transplant only; B = high-dose atorvastatin + Transplant; C = right nephrectomy + Transplant; D = high-dose atorvastatin + right nephrectomy + Transplant. Bilateral nephrectomy was performed 24 h post-transplant. Oxidative stress was assessed measuring malondialdehyde (MDA), superoxide dismutase (SOD), glutathione peroxidase (GPx) and myeloperoxidase (MPO) activity on renal tissue; ischemia/reperfusion injury was also evaluated by histology. Donor pre-treatment with high-dose atorvastatin improved oxidative stress. Results MDA levels were lower in group B versus A (p = 0.002) and D (p = 0.004). High-dose atorvastatin pre-treated rats displayed higher GPx activity in group B versus A (p = 0.009) and D (p = 0.005). SOD scavenger activity was also higher in group B versus A (p

Introduction: Doyne honeycomb retinal dystrophy (DHRD), or autosomal dominant radial drusen, is a genetic disease caused by pathogenic variants of the epidermal growth factor (EGF)-containing fibulin-like extracellular matrix protein 1 EFEMP1 gene and is characterized by the formation of subretinal drusenoid deposits. In a previous study, we reported the short-term beneficial effects of nanosecond laser treatment (2RT) on retinal function in DHRD. The aim of the present report was to describe the findings of a long-term follow-up of retinal structure/function in a small case series of patients with DHRD who underwent 2RT treatment. Case Presentation: Three DHRD patients (case 1, male and cases 2 and 3, two sister females, age range 41–46) with EFEMP1 pathogenic variant (c.1033C>T; p.R345W) and drusenoid deposits at the posterior pole were examined at baseline and after 2RT treatment, at regular intervals (every 2–4 months) up to 30 months. All 3 patients underwent one or two treatment sessions in one or both eyes during the follow-up period. Case 3 was treated with only the left eye (LE). Each patient underwent a full ophthalmologic examination, spectral domain optical coherence tomography (OCT), central perimetry with frequency doubling technology, and mesopic and photopic Ganzfeld electroretinograms. Compared to baseline findings, during follow-up, visual acuity improved in both eyes in case 1 and LE in case 2, while it decreased in the right eye in case 2 and LE in case 3; perimetric sensitivity was stable in case 1 and improved in both eyes in cases 2 and 3; and electroretinogram amplitude improved in cases 1 and 2 and was stable in case 3 (both eyes). OCT central macular thickness and retinal structure were stable in all cases. None of the patients had treatment-related side effects. Conclusion: This is the first report showing that in a long-term follow-up, 2RT treatment in DHRD may improve or stabilize some retinal function parameters without significant structural changes.

Abstract Background The THUNDER-2 phase II single institutional trial investigates the benefits of MRI-guided radiotherapy (MRIgRT) in treating locally advanced rectal cancer (LARC). This study focuses on evaluating the impact of escalating radiation therapy dose in non-responder patients using the Early Tumour Regression Index (ERI) for predicting complete response (CR). The trial’s primary endpoint is to increase the CR rate in non-responders by 10% and assess the feasibility of the delta radiomics-based MRIgRT predictive model. This interim analysis assesses the feasibility and safety of the proposed MRIgRT dose escalation strategy in terms of acute toxicity (gastrointestinal, genitourinary and haematological) and treatment adherence. Methods Stage cT2-3, N0-2, or cT4 patients with anal sphincter involvement, N0-2a, M0, but without high-risk features were enrolled. MRIgRT treatment consisted of a standard dose of 55 Gy to the Gross Tumor Volume (GTV) and mesorectum, and 45 Gy to the mesorectum and drainage nodes in 25 fractions with concomitant chemotherapy. 0.35 T MRI was used for simulation imaging and daily alignment. ERI was calculated at the 10th fraction. Non-responders with an ERI above 13.1 received intensified dose escalation from the 11th fraction, resulting in a total dose of 60.1 Gy. Acute toxicity was assessed using the CTCAE v.5 scale. Results From March 2021 to November 2022, 33 out of the total number of 63 patients to be enrolled (52.4%) were included, with one withdrawal unrelated to treatment. Sixteen patients (50%) underwent dose escalation. Treatment was well tolerated, with only one patient (3.1%) in the standard treatment group experiencing acute Grade 3 diarrhea, proctitis, and cystitis. No significant differences in toxicity were observed between the two groups (p = 0.5463). Conclusions MRIgRT treatment with dose escalation up to 60.1 Gy is well tolerated in LARC patients predicted as non-responders by ERI, confirming the feasibility and safety of this approach. The THUNDER-2 trial’s primary and secondary endpoints will be fully analyzed when all planned patients will be enrolled.

Background: Prostatic artery embolization (PAE) is an emerging treatment for benign prostatic hyperplasia (BPH). However, changes in public interest in PAE over time, especially relative to interest in alternative BPH treatments, are difficult to assess. The online tool for analysis of the popularity of top search queries (Google Trends; Alphabet Inc) provides a relative search volume (RSV) of specified keywords and insight about patterns of user searches.Purpose: The purpose of this study is to assess changes in public interest in PAE over time and compare them with changes in public interest in alternative BPH treatments as indicated by search queries.Material and Methods: Using Google Trends, we identified the RSV of specified keywords within search queries submitted between 2010 and 2019 in the United States. The RSVs of keywords with high search volume were identified and normalized on a scale of values from 0 to 100. Interest in PAE was assessed by comparing RSVs and trends of the keyword PAE as well as of other prostate-treatment-related keywords. Prostate embolization was a PAE-related, BPH-treatment-specific keyword with the highest average RSV. A linear regression analysis was performed to characterize annual search trends of the use of these keywords. Subsequently, the annual search trend of prostate embolization was compared with that of keywords related to transurethral resection of the prostate (TURP) and minimally invasive surgical treatments (MISTs).Results: The mean annual RSV of prostate embolization increased by 8.6 fold between 2010 and 2019. However, during this period, the mean RSV of the keywords transurethral resection of the prostate and TURP were 3.6 and 49.3 times higher, respectively (P

BackgroundHepatic arteriovenous malformations (AVMs) in hereditary hemorrhagic telangiectasia (HHT) patients are most commonly hepatic artery to hepatic venous shunts which can result in high-output heart failure. This condition can be debilitating and is a leading cause of liver transplantation in HHT patients. However, it is not known what characteristics can discriminate between asymptomatic patients and those who will develop heart failure symptoms.Results176 patients with HHT were evaluated with computed tomography angiography (CTA) between April 2004 and February 2019 at our HHT Center of Excellence. 63/176 (35.8%) patients were found to have hepatic AVMs on CTA. 18 of these patients were excluded because of the presence of another condition which could confound evaluation of heart failure symptoms. In the remaining 45 patients included in our cohort, 25/45 (55.6%) patients were classified as asymptomatic and 20/45 (44.4%) were classified as symptomatic, and these groups were compared. In symptomatic patients, mean common hepatic artery (CHA) diameter was significantly higher (11.1 versus 8.4 mm) and mean hemoglobin levels were significantly lower (10.7 vs 12.6 g/dL). A stepwise multiple logistic regression analysis demonstrated that both CHA diameter and hemoglobin level were independent predictors of heart failure symptoms with ORs of 2.554 (95% CI 1.372-4.754) and 0.489 (95% CI 0.299-0.799), respectively. The receiver operator characteristic (ROC) curve of our analysis demonstrated an AUC of 0.906 (95% CI 0.816-0.996), sensitivity 80.0% (95% CI 55.7-93.4%), and specificity 75.0% (95% CI 52.9-89.4%).ConclusionsCTA is an effective and easily reproducible method to evaluate hepatic involvement of HHT. Utilizing CTA, clinical, and laboratory data we determined CHA diameter and hemoglobin level were independent predictors of heart failure symptoms.