Horvat, Natally

The increase in the number of injectable filler procedures has led to a rise in associated complications, with vascular compromise being the most feared. As a result, blood flow can be interrupted, leading to ischemia, necrosis or ulcerations, pulmonary embolism, blindness, and cerebral vascular injuries. In this context, Doppler high‐frequency ultrasound (DHFUS) is a radiological tool that can be used to avoid, to diagnose, and to treat vascular complications. This study aims to review facial vessels anatomy and major variations, describe the examination technique, probe positions and teach how to recognize vascular occlusions, in order to avoid negative outcomes.

ABSTRACT Background: Anal fistulas remain challenging in colorectal surgery, with recurrence and postoperative incontinence common despite advances in treatment. Multiple classification systems exist, but their predictive value for surgical and functional outcomes is unclear. Aims: The aim of this study was to compare Parks, American Society of Colon and Rectal Surgeons (ASCRS), and St. James’s University Hospital (SJUH) MRI-based classifications in predicting surgical outcomes, including continence preservation. Methods: Retrospective analysis of 89 patients undergoing definitive surgical treatment for anorectal fistulas at a single referral center (2012–2019). Exclusions included rectovaginal fistulas, Crohn’s disease, or prior pelvic radiotherapy. Fistulas were classified using Parks, ASCRS, and, when available, SJUH (n=49). Outcomes included the number of procedures, type of initial procedure, fistula closure, and closure without continence deterioration. Continence was assessed using the Cleveland Clinic Jorge-Wexner score. Results: Most fistulas were transsphincteric (Parks Type 2, 62%) and complex (ASCRS, 65%). Overall, 86.5% achieved fistula closure, and 73% achieved closure without continence deterioration. Parks and ASCRS were significantly associated with fistula closure with continence preservation (p=0.008 and 0.007, respectively) and type of initial procedure. Parks remained significant when considering closure alone (p=0.005), while ASCRS showed a borderline association (p=0.051). SJUH classification was associated only with procedure selection. Conclusions: Parks and ASCRS classifications were associated with fistula closure with continence preservation and type of initial procedure. Considering closure alone, only Parks remained significant. SJUH was limited to procedure selection. Overall, Parks and ASCRS guide surgical planning and prediction of functional outcomes, with Parks slightly more sensitive.

A structured approach for interpreting postoperative imaging of the anterolateral abdominal wall integrates anatomic knowledge with surgical techniques and their associated complication patterns.

Imaging is important for evaluation and diagnosis of nail pathologic disorders, and knowledge of imaging protocols and characteristics supports informed treatment planning and effective monitoring of therapeutic outcomes in cutaneous and systemic disease contexts.

The SAR Colorectal and Anal Cancer Disease-focused Panel rectal cancer MRI restaging report template can be used to clarify common areas of confusion and deliver essential insights to ensure that clinically relevant information is effectively communicated to the treatment team.

AbstractObjectiveTo evaluate the diagnostic performance of multiparametric MRI (mpMRI), mpMRI combined with PSA density (PSAd) and combined biopsy (CBx) in detecting clinically significant prostate cancer (csPCa) in men undergoing active surveillance, using radical prostatectomy (RP) specimens as the reference standard.Patients and MethodsIn this prospective single‐centre study, 91 patients with low‐risk prostate cancer under active surveillance underwent mpMRI, PSAd measurement, CBx and ultimately RP. mpMRI was reported using PI‐RADS v2.0, and PSAd was dichotomised at 0.12 ng/ml/cm3. Diagnostic accuracy was compared using ISUP grade ≥2 and ≥3 thresholds. Radical prostatectomy pathology served as the reference standard.ResultsFor detecting ISUP ≥3 cancer, mpMRI combined with PSAd achieved the highest sensitivity (93.3%) and negative predictive value (94.4%). CBx demonstrated the highest specificity (88.2%) and overall diagnostic balance (Youden index = 0.348). mpMRI alone showed intermediate performance. Differences in classification between strategies were statistically significant (McNemar p < 0.001).ConclusionsmpMRI combined with PSAd provides high sensitivity and negative predictive value for ruling out aggressive prostate cancer, supporting its use as a non‐invasive triage tool in active surveillance. CBx remains the most specific method for histological confirmation. These strategies should be used complementarily to optimise decision‐making in active surveillance protocols.

This review explores how multimodal foundation models (MFMs) are transforming biliary tract cancer (BTC) research. BTCs are aggressive malignancies with poor prognosis, presenting unique challenges due to difficult diagnostic methods, molecular complexity, and rarity. Importantly, intrahepatic cholangiocarcinoma (iCCA), perihilar cholangiocarcinoma (pCCA), and distal bile duct cholangiocarcinoma (dCCA) represent fundamentally distinct clinical entities, with iCCA presenting as mass-forming lesions amenable to biopsy and targeted therapies, while pCCA manifests as infiltrative bile duct lesions with challenging diagnosis and primarily palliative management approaches. MFMs offer potential to advance research by integrating radiological images, histopathology, multi-omics profiles, and clinical data into unified computational frameworks, with applications tailored to these distinct BTC subtypes. Key applications include enhanced biomarker discovery that identifies previously unrecognizable cross-modal patterns, potential for improving currently limited diagnostic accuracy—though validation in BTC-specific cohorts remains essential—accelerated drug repurposing, and advanced patient stratification for personalized treatment. Despite promising results, challenges such as data scarcity, high computational demands, and clinical workflow integration remain to be addressed. Future research should focus on standardized data protocols, architectural innovations, and prospective validation studies. The integration of artificial intelligence (AI)-based methodologies offers new solutions for these historically challenging malignancies. However, current evidence for BTC-specific applications remains largely theoretical, with most studies limited to proof-of-concept designs or related cancer types. Comprehensive clinical validation studies and prospective trials demonstrating patient benefit are essential prerequisites for clinical implementation. The timeline for evidence-based clinical adoption likely extends 7–10 years, contingent on successful completion of validation studies addressing current evidence gaps.

The integration of artificial intelligence (AI) in medical imaging has revolutionized diagnostic capabilities, yet the black-box nature of deep learning models poses significant challenges for clinical adoption. Current explainable AI (XAI) approaches, including SHAP, LIME, and Grad-CAM, predominantly focus on post hoc explanations that may inadvertently undermine clinical decision-making by providing misleading confidence in AI outputs. This paper presents a systematic review and meta-analysis of 67 studies (covering 23 radiology, 19 pathology, and 25 ophthalmology applications) evaluating XAI fidelity, stability, and performance trade-offs across medical imaging modalities. Our meta-analysis of 847 initially identified studies reveals that LIME achieves superior fidelity (0.81, 95% CI: 0.78–0.84) compared to SHAP (0.38, 95% CI: 0.35–0.41) and Grad-CAM (0.54, 95% CI: 0.51–0.57) across all modalities. Post hoc explanations demonstrated poor stability under noise perturbation, with SHAP showing 53% degradation in ophthalmology applications (ρ = 0.42 at 10% noise) compared to 11% in radiology (ρ = 0.89). We demonstrate a consistent 5–7% AUC performance penalty for interpretable models but identify modality-specific stability patterns suggesting that tailored XAI approaches are necessary. Based on these empirical findings, we propose a comprehensive three-pillar accountability framework that prioritizes transparency in model development, interpretability in architecture design, and a cautious deployment of post hoc explanations with explicit uncertainty quantification. This approach offers a pathway toward genuinely accountable AI systems that enhance rather than compromise clinical decision-making quality and patient safety.