Comparison of hypospadias phenotype pixel segmentation to GMS score.

BACKGROUND: Hypospadias phenotype assessment determines if the anatomy is favorable for reconstruction. Glans-Urethral Meatus-Shaft (GMS) has been adopted in an effort to standardize hypospadias classification. While extremely subjective, GMS has been widely used to classify the severity of the phenotype to predict surgical outcomes. The use of digital image analysis has proven to be feasible and prior efforts by our team have demonstrated that machine learning algorithms can emulate an expert's assessment of the phenotype. Nonetheless, the creation of these image recognition algorithms is highly subjective. In order to reduce a subjective input in the evaluation of the phenotype, we propose a novel approach to analyze the anatomy using digital image pixel analysis and to compare the results using the GMS score. Our hypothesis is that pixel cluster segmentation can discriminate between favorable and unfavorable anatomy. OBJECTIVE: To evaluate whether image segmentation and digital pixel analysis are able to analyze favorable vs unfavorable hypospadias anatomy in a less subjective manner than GMS score. METHODS: A total of 148 patients with different types of hypospadias were classified by 1 of 5 independent experts following the GMS score into "favorable" (GG), "moderately favorable" (GM) and "unfavorable" (GP) glans. From there, 592 images were generated using digital image segmentation. 584 were included for final analysis due to certain images being excluded for poor image quality or inadequate capture of target anatomy. For each image, the region of interest was segmented separately by two evaluators into "glans," "urethral plate," "foreskin" and "periurethral plate". The values obtained for each segmented region using machine-learning statistical pixel k-means cluster analysis were analyzed and compared to the GMS score given to that image using an ANOVA analysis. RESULTS: Analysis of image segmentation demonstrated that k-means pixel cluster analysis discriminated "favorable" vs "unfavorable" urethral plates. There was a significant difference between scores when comparing the GG and GM groups (p = 0.03) and GG and GP groups (p = 0.05). Pixel cluster analysis could not discriminate between "moderately favorable" and "unfavorable" urethral plates. CONCLUSIONS: Through our analysis, we found significant pairwise difference for different tissue qualities. Digital image segmentation and statistical k-means cluster analysis can discriminate anatomical features in a similar way to the GMS score. Future research can target discerning between different tissue qualities in an effort to predict surgical outcomes for hypospadias repair.

Comprehensive multidisciplinary phenotyping of patients with hypospadias. A pilot study.

INTRODUCTION: Hypospadias is an abnormal formation of the urethra, ventral skin, and corporal bodies. Location of the urethral meatus has historically been the phenotypic landmark that defines hypospadias. Nonetheless, classifications following location of the urethral meatus fail to consistently predict outcomes and have no correlation with the genotype. Description of the urethral plate is very subjective and difficult to reproduce. We hypothesize that the use of digital pixel cluster analysis and correlation to histological analysis can provide a novel method to describe the phenotype of patients with hypospadias. METHODS: A standardized hypospadias phenotyping protocol was developed. 1. Digital images of the anomaly, 2. Anthropometric assessment of penile dimensions (penile length, urethral plate length and width, glans width, ventral curvature), 3. Classification using the GMS score, 4. Tissue sampling (foreskin, glans, urethral plate, periurethral ventral skin) and H&E analysis by a blinded pathologist. A k-means colorimetric pixel cluster analysis was performed following the same anatomical landmark distribution as the histology samples. Analysis was performed using MATLAB v R2021b 9.11.0.1769968. RESULTS: A total of 24 patients prospectively enrolled with a standard protocol. Mean age at surgery was 16.25 months Urethral meatus was distal shaft in 7 patients, 8 coronal, 4 glanular, 3 midshaft, 2 penoscrotal. Average GMS score was 7.14 (±1.58). Average glans size was 15.71 mm (±2.33) and urethral plate width 5.57 mm (±2.06). Eleven patients underwent Thiersch-Duplay repair, 7 TIP, 5 MAGPI, and 1 a first stage preputial flap. Mean follow-up was 14.25 months ( ± 3.7 months). Two (8.3%) postoperative complications (1 urethrocutaneous fistula and 1 ventral skin wound dehiscence) were reported in the study period. Eleven (52.3%) patients with histological analysis had an abnormal pathology report. Of those, 6 (54%) had reported abnormal lymphocyte infiltration interpreted as chronic inflammation at the urethral plate. The second most common finding was hyperkeratosis visualized in the urethral plate in 4 (36.3%) and one with reported fibrosis in the urethral plate. K-means pixel analysis demonstrated a k1 mean of 64.2 for reported urethral plate inflammation vs 53.1 for non-reported urethral plate inflammation (p = 0.002) CONCLUSIONS: Current phenotyping of hypospadias using only anthropometric variables can be expanded including histological and pixel analysis correlation. Pixel clustering has a potential for a priori prediction of urethral plate quality beyond the current subjective assessment. A larger cohort will allow identification of possible predictive associations that might impact intraoperative decision-making and surgical outcomes.

Evaluation of Cardiovascular Autonomic Function during Inpatient Rehabilitation following Traumatic Spinal Cord Injury.

Assessment of the degree of impaired autonomic nervous system (ANS) function is not part of routine clinical practice during inpatient rehabilitation following traumatic spinal cord injury (SCI). The goal of this investigation was to determine the utility of the International Standards for Neurologic Classification of SCI (ISNCSCI) and the recently revised International Standards to document remaining Autonomic Function after SCI (ISAFSCI) in documenting cardiovascular ANS impairment during inpatient rehabilitation following traumatic SCI. Beat-to-beat recording of supine heart rate (HR) and blood pressure (BP) were collected at the bedside for estimation of total cardiovascular ISAFSCI score, cardio-vagal modulation (i.e., high frequency HR variability [HFHRV]) and sympathetic vasomotor regulation (i.e., Mayer wave component of systolic BP [SBPmayer]). A total of 41 participants completed baseline testing, which was conducted 11 ± 5 days from the admission ISNCSCI examination. There were no differences in supine HR or BP based on the ISNCSCI or ISAFSCI assessments. The HFHRV was generally lower with more distal lesions (r2 = 0.15; p = 0.01), and SBPmayer was significantly lower in those with American Spinal Injury Association Impairment Scale (AIS) A compared with AIS B, C, D (Cohen's d = -1.4; p < 0.001). There were no significant differences in HFHRV or SBPmayer in patients with or without ISAFSCI evidence of cardiovascular ANS impairment. These preliminary data suggest that neither the ISNCSCI nor the ISAFSCI are sensitive to changes in ANS cardiovascular function following traumatic SCI. Bedside assessment of HR and BP variabilities may provide insight, but are not readily available in the clinical setting. Further research is required to evaluate methods that accurately assess the degree of ANS impairment following traumatic SCI.

Orthostatic systemic and cerebral hemodynamics in newly injured patients with spinal cord injury.

BACKGROUND: Low blood pressure (BP) may lead to reduced cerebral blood flow velocity (CBFv) during an orthostatic challenge in newly injured patients with traumatic spinal cord injury (SCI), which, may relate to the neurological level of injury (NLI) as documented on the International Standards for the Neurologic Classification of SCI (ISNCSCI), or to evidence of cardiovascular autonomic impairment as determined by the International Standards to document remaining Autonomic Function after SCI (ISAFSCI). OBJECTIVE: To examine the influence of patient demographics, ISNCSCI and ISAFSCI scores on hemodynamic responses to a bedside sit-up test in newly injured patients with SCI. DESIGN: Cross-sectional, prospective analysis. METHODS: A modified sit-up test was conducted at the bedside with the hips at an angle between 45° and 90° and the legs horizontal, level with the hips. Heart rate, BP, and CBFv were recorded for 10 min in the supine and seated positions. RESULTS: Fifty-three newly injured patients (median 39.5 days post-injury) with traumatic SCI were enrolled. Overall, 28 (53%) patients met ISAFSCI criteria, and the number of criteria met (total score) was significantly related to orthostatic changes in CBFv. Change in SBP and change in CBFv were not significantly related, but NLI and total sensory score from the ISNCSCI were significant predictors of the change in CBFv. CONCLUSIONS: Total ISAFSCI score, NLI and sensory scores were positively associated with orthostatic changes in CBFv. Long term follow-up should be considered to determine the consequences of diminished CBFv on cognitive function and quality of life following SCI.