Kidney cancers are one of the most common malignancies worldwide. Accurate diagnosis is a critical step in the management of kidney cancer patients and is influenced by multiple factors including tumor size or volume, cancer types and stages, etc. For malignant tumors, partial or radical surgery of the kidney might be required, but for clinicians, the basis for making this decision is often unclear. Partial nephrectomy could result in patient death due to cancer if kidney removal was necessary, whereas radical nephrectomy in less severe cases could resign patients to lifelong dialysis or need for future transplantation without sufficient cause. Using machine learning to consider clinical data alongside computed tomography images could potentially help resolve some of these surgical ambiguities, by enabling a more robust classification of kidney cancers and selection of optimal surgical approaches. In this study, we used the publicly available KiTS dataset of contrast-enhanced CT images and corresponding patient metadata to differentiate four major classes of kidney cancer: clear cell (ccRCC), chromophobe (chRCC), papillary (pRCC) renal cell carcinoma, and oncocytoma (ONC). We rationalized these data to overcome the high field of view (FoV), extract tumor regions of interest (ROIs), classify patients using deep machine-learning models, and extract/post-process CT image features for combination with clinical data. Regardless of marked data imbalance, our combined approach achieved a high level of performance (85.66% accuracy, 84.18% precision, 85.66% recall, and 84.92% F1-score). When selecting surgical procedures for malignant tumors (RCC), our method proved even more reliable (90.63% accuracy, 90.83% precision, 90.61% recall, and 90.50% F1-score). Using feature ranking, we confirmed that tumor volume and cancer stage are the most relevant clinical features for predicting surgical procedures. Once fully mature, the approach we propose could be used to assist surgeons in performing nephrectomies by guiding the choices of optimal procedures in individual patients with kidney cancer.

Current approaches to classifying hypospadias severity are based on meatus position. These classification tools lack precise reflection on the degree of urethral hypoplasia and extent of urethral underdevelopment hence are not good representative of hypospadias severity. Here, an alternative classification system is introduced that objectively reflects the developmental pathology underlying this condition. The study goal was to appraise location of bifurcation in the corpus spongiosum (BCS) relative to the penile shaft as an indicator of hypospadias severity. Patients aged <18 years with primary hypospadias were included in the study. Urethral defect ratio (UDR) was calculated by dividing the extent of urethral defect (distance between the glandular knobs and BCS) relative to stretched penile length (SPL). Hypospadias severity was then categorized into three distinct grades (UDR <0.5, 0.5-0.99, ≥1.0). The Inter-Class Correlation (ICC) was evaluated to assess the intra- and inter-rater agreement between the reviewers of UDC ratio. Linear regression analysis was performed to estimate the correlation between UDC ratios and either plate objective scoring tool (POST) and Curvature degrees. A total of 67 patients aged 12.3 ± 3.7 months with primary hypospadias were enrolled. UDR ranged between 0.2 and 1.3. A significant difference in hypospadias level was observed between UDR grades, which further correlated degree of curvature (P < 0.0001), urethral plate quality (P < 0.0001), and associated anomalies (P < 0.05). The Inter-Class Correlation (ICC) value to examine the intra- and inter-rater agreement between the two reviewers in UDC ratio was 0.998 (95% CI 0.998, 0.999). Regression analysis revealed that UDR and both POST and Curvature degree were significantly associated (P < 0.001). A hypospadias severity scoring system based on embryological etiology and urethral hypoplasia and assessed relative to the penile shaft represents an objective, feasible, and consistent tool. These results clearly indicate that the reviewers have had excellent consistency/reliability across their consecutive readings. This new system can facilitate objective description of hypospadias-spectrum anomalies and thus support precise communication between individual surgeons and centers.

Diabetes mellitus (DM) can lead to plantar ulcers, amputation and death. Plantar foot thermogram images acquired using an infrared camera have been shown to detect changes in temperature distribution associated with a higher risk of foot ulceration. Machine learning approaches applied to such infrared images may have utility in the early diagnosis of diabetic foot complications. In this work, a publicly available dataset was categorized into different classes, which were corroborated by domain experts, based on a temperature distribution parameter—the thermal change index (TCI). We then explored different machine-learning approaches for classifying thermograms of the TCI-labeled dataset. Classical machine learning algorithms with feature engineering and the convolutional neural network (CNN) with image enhancement techniques were extensively investigated to identify the best performing network for classifying thermograms. The multilayer perceptron (MLP) classifier along with the features extracted from thermogram images showed an accuracy of 90.1% in multi-class classification, which outperformed the literature-reported performance metrics on this dataset.

Several congenital and acquired conditions may result in severe narrowing of the urethra in men, which represent an ongoing surgical challenge and a significant burden on both health and quality of life. In the field of urethral reconstruction, tissue engineering has emerged as a promising alternative to overcome some of the limitations associated with autologous tissue grafts. In this direction, preclinical as well as clinical studies, have shown that degradable scaffolds are able to restore the normal urethral architecture, supporting neo-vascularization and stratification of the tissue. While a wide variety of degradable biomaterials are under scrutiny, such as decellularized matrices, natural, and synthetic polymers, the search for scaffold materials that could fulfill the clinical performance requirements continues. In this article, we discuss the design requirements of the scaffold that appear to be crucial to better resemble the structural, physical, and biological properties of the native urethra and are expected to support an adequate recovery of the urethral function. In this context, we review the biological performance of the degradable polymers currently applied for urethral reconstruction and outline the perspectives on novel functional polymers, which could find application in the design of customized urethral constructs.