We developed a machine learning model based on radiomics to predict the BI-RADS category of ultrasound-detected suspicious breast lesions and support medical decision-making towards short-interval follow-up versus tissue sampling. From a retrospective 2015-2019 series of ultrasound-guided core needle biopsies performed by four board-certified breast radiologists using six ultrasound systems from three vendors, we collected 821 images of 834 suspicious breast masses from 819 patients, 404 malignant and 430 benign according to histopathology. A balanced image set of biopsy-proven benign (n = 299) and malignant (n = 299) lesions was used for training and cross-validation of ensembles of machine learning algorithms supervised during learning by histopathological diagnosis as a reference standard. Based on a majority vote (over 80% of the votes to have a valid prediction of benign lesion), an ensemble of support vector machines showed an ability to reduce the biopsy rate of benign lesions by 15% to 18%, always keee model performed better than the radiologist did, since it assigned a BI-RADS 3 classification to histopathology-confirmed benign masses that were classified as BI-RADS 4 by the radiologist.The objective was to assess the instrumental validity and the test-retest reliability of a low-cost hand-held push dynamometer adapted from a load-cell based hanging scale (tHHD) to collect compressive forces in different ranges of compressive forces. Three independent raters applied 50 pre-established compressions each on the tHHD centered on a force platform in three distinct ranges ~70 N, ~160 N, ~250 N. Knee isometric strength was also assessed on 19 subjects in two sessions (48 h apart) using the tHHD anchored by an inelastic adjustable strap. Knee extension and flexion were assessed with the participant seated on a chair with the feet resting on the floor, knees, and hips flexed at 90°. The isometric force peaks were recorded and compared. The ICC and the Cronbach’s α showed excellent consistency and agreement for both instrumental validity and test-retest reliability (range 0.89-0.99), as the correlation and determination coefficients (range 0.80-0.99). The SEM and the MDC analysis returned adequate low values with a coefficient of variation less than 5%. The Bland-Altman results showed consistency and high levels of agreement. The tHHD is a valid method to assess the knee isometric strength, showing portability, cost-effectiveness, and user-friendly interface to provide an effective form to assess the knee isometric strength.Mastectomy skin flap necrosis (MSFN) and partial DIEP (deep inferior epigastric artery perforator) flap loss represent two frequently reported complications in immediate autologous breast reconstruction. These complications could be prevented when areas of insufficient tissue perfusion are detected intraoperatively. Hyperspectral imaging (HSI) is a relatively novel, non-invasive imaging technique, which could be used to objectively assess tissue perfusion through analysis of tissue oxygenation patterns (StO2%), near-infrared (NIR%), tissue hemoglobin (THI%), and tissue water (TWI%) perfusion indices. This prospective clinical pilot study aimed to evaluate the efficacy of HSI for tissue perfusion assessment and to identify a cut-off value for flap necrosis. Ten patients with a mean age of 55.4 years underwent immediate unilateral autologous breast reconstruction. Prior, during and up to 72 h after surgery, a total of 19 hyperspectral images per patient were acquired. MSFN was observed in 3 out of 10 patients. No DIEP flap necrosis was observed. In all MSFN cases, an increased THI% and decreased StO2%, NIR%, and TWI% were observed when compared to the vital group. StO2% was found to be the most sensitive parameter to detect MSFN with a statistically significant lower mean StO2% (51% in the vital group versus 32% in the necrosis group, p less then 0.0001) and a cut-off value of 36.29% for flap necrosis. HSI has the potential to accurately assess mastectomy skin flap perfusion and discriminate between vital and necrotic skin flap during the early postoperative period prior to clinical observation. Although the results should be confirmed in future studies, including DIEP flap necrosis specifically, these findings suggest that HSI can aid clinicians in postoperative mastectomy skin flap and DIEP flap monitoring.Wet-mount microscopy aerobic vaginitis (AV) diagnostic criteria need phase-contrast microscopy and keen microscopists, and the preservation of saline smears is less common in clinical practice. This research work developed new AV diagnostic criteria that combine Gram stain with clinical features. We enrolled 325 AV patients and 325 controls as a study population to develop new AV diagnostic criteria. Then, an independent group, which included 500 women, was used as a validation population. AV-related microscopic findings on Gram-stained and wet-mount smears from the same participants were compared. The accuracy of bacterial indicators from the two methods was verified by bacterial 16S rRNA V4 sequencing (n = 240). Logistic regression was used to analyse AV-related clinical features. The screened clinical features were combined with Gram-stain microscopic indicators to establish new AV diagnostic criteria. There were no significant differences in the leukocyte counts or the parabasal epitheliocytes (PBC) proportion between the Gram-stain and wet-mount methods (400×). Gram stain (1000×) satisfied the ability to identify bacteria as verified by 16S rRNA sequencing but failed to identify toxic leukocytes. The new criteria included Lactobacillary grades (LBG) and background flora (Gram stain, 1000×), leukocytes count and PBC proportion (Gram stain, 400×), and clinical features (vaginal pH > 4.5, vagina hyperemia, and yellow discharge). These criteria satisfied the accuracy and reliability for AV diagnosis (Se = 86.79%, Sp = 95.97%, and Kendall’s W value = 0.899) in perspective validation. In summary, we proposed an alternative and valuable AV diagnostic criteria based on the Gram stain, which can make it possible to diagnose common vaginitis like AV, BV, VVC, and mixed infections on the same smear and can be available for artificial intelligence diagnosis in the future.Circulating biomarkers have been recently investigated among patients undergoing endovascular aortic aneurysm repair (EVAR) for abdominal aortic aneurysm (AAA). Considering the plethora of small descriptive studies reporting potential associations between biomarkers and clinical outcomes, this review aims to summarize the current literature considering both the treated disease (post EVAR) and the untreated disease (AAA before EVAR). All studies describing outcomes of tissue biomarkers in patients undergoing EVAR and in patients with AAA were included, and references were checked for additional sources. In the EVAR scenario, circulating interleukin-6 (IL-6) is a marker of inflammatory reaction which might predict postoperative morbidity; cystatin C is a promising early marker of post-procedural acute kidney injury; plasma matrix metalloproteinase-9 (MMP-9) concentration after 3 months from EVAR might help in detecting post-procedural endoleak. This review also summarizes the current gaps in knowledge and future direction of this field of research. Among markers used in patients with AAA, galectin and granzyme appear to be promising and should be carefully investigated even in the EVAR setting. Larger prospective trials are required to establish and evaluate prognostic models with highest values with these markers.

We examined whether high-sensitivity CRP (hsCRP) reflected the inflammatory disease status evaluated by clinical and ultrasound (US) parameters in RA patients receiving IL-6 receptor antibodies (anti-IL-6R) or JAK inhibitors (JAKi).

We conducted a cross-sectional study of patients with established RA receiving anti-IL-6R (tocilizumab, sarilumab) or JAKi (tofacitinib, baricitinib). Serum hsCRP and US synovitis in both hands were measured. Associations between hsCRP and clinical inflammatory activity were evaluated using composite activity indices. The association between hsCRP and US synovitis was analyzed.

63 (92% female) patients (42 anti- IL-6R and 21 JAKi) were included, and the median disease duration was 14.4 (0.2-37.5) years. Most patients were in remission or had low levels of disease. Overall hsCRP values were very low, and significantly lower in anti-IL-6R patients (median 0.04 mg/dL vs. 0.16 mg/dL). Anti-IL-6R (82.4%) patients and 48% of JAKi patients had very low hsCRP levels (≤0.1 mg/dL) (

= 0.002). In the anti-IL-6R group, hsCRP did not correlate with the composite activity index or US synovitis. In the JAKi group, hsCRP moderately correlated with US parameters (r = 0.5) but not clinical disease activity, and hsCRP levels were higher in patients with US synovitis (0.02 vs. 0.42 mg/dL) (

= 0.001).

In anti-IL-6R RA-treated patients, hsCRP does not reflect the inflammatory disease state, but in those treated with JAKi, hsCRP was associated with US synovitis.

In anti-IL-6R RA-treated patients, hsCRP does not reflect the inflammatory disease state, but in those treated with JAKi, hsCRP was associated with US synovitis.The aim of this study was to investigate the potential of a machine learning algorithm to accurately classify parenchymal density in spiral breast-CT (BCT), using a deep convolutional neural network (dCNN). In this retrospectively designed study, 634 examinations of 317 patients were included. After image selection and preparation, 5589 images from 634 different BCT examinations were sorted by a four-level density scale, ranging from A to D, using ACR BI-RADS-like criteria. Subsequently four different dCNN models (differences in optimizer and spatial resolution) were trained (70% of data), validated (20%) and tested on a „real-world” dataset (10%). Moreover, dCNN accuracy was compared to a human readout. The overall performance of the model with lowest resolution of input data was highest, reaching an accuracy on the „real-world” dataset of 85.8%. The intra-class correlation of the dCNN and the two readers was almost perfect (0.92) and kappa values between both readers and the dCNN were substantial (0.71-0.76). Moreover, the diagnostic performance between the readers and the dCNN showed very good correspondence with an AUC of 0.89. Artificial Intelligence in the form of a dCNN can be used for standardized, observer-independent and reliable classification of parenchymal density in a BCT examination.Contrast-induced nephropathy (CIN) is an impairment of renal function that occurs after the administration of an iodinated contrast medium (CM). Kidney dysfunction in CIN is considered transient and reversible in most cases. However, it is the third most common cause of hospital-acquired acute kidney injury and is associated with increased morbidity and mortality, especially in high-risk patients. Diagnostic and interventional procedures that require intravascular CM are being used with increasing frequency, especially among the elderly, who can be particularly susceptible to CIN due to multiple comorbidities. Therefore, identifying the exact mechanisms of CIN and its associated risk factors is crucial not only to provide optimal preventive management for at-risk patients, but also to increase the feasibility of diagnostic and interventional procedure that use CM. CM induces kidney injury by impairing renal hemodynamics and increasing the generation of reactive oxygen species, in addition to direct cytotoxicity.