Automating Scoliosis Measurements in Radiographic Studies with Machine Learning: Comparing Artificial Intelligence and Clinical Reports

Journal of Digital Imaging - Scoliosis is a condition of abnormal lateral spinal curvature affecting an estimated 2 to 3% of the US population, or seven million people. The Cobb angle is the...     

Fertility Outcome After Renal Transplantation: A Single-Center Experience

BackgroundWomen suffering from kidney disease are more prone to fertility problems, due to uremia. Fortunately, their fertility rate increases dramatically after renal transplantation. This study analyzes the predictors/risk factors of successful pregnancy with live birth outcome while presenting an overview of the 7-year experience of a single center.MethodsThis retrospective cohort study includes 239 women of reproductive age (18–40 years) who underwent renal transplantation in a tertiary Turkish clinic between October 1, 2011, and August 24, 2017. The subjects were invited to take part in a survey questioning their obstetric characteristics and they were assessed in 2 groups: fertile and infertile. Multivariable linear regression analysis was conducted to determine the predictors of a successful pregnancy.ResultsThirty-five 35 patients wished to become pregnant: 12 got pregnant spontaneously, while 21 failed to become pregnant (spontaneously). The mean age of the patients at the survey was 34 ± 7. Regular menstrual cycles after renal transplantation, tacrolimus-mycophenolate mofetil maintenance protocol, and age at transplantation were found to be predictors of spontaneous pregnancy. The duration of peritoneal dialysis was significantly longer in the infertile group (48 vs 12 months).ConclusionEnd-stage renal disease's negative impacts, including menstrual abnormality and fertility problems, can be overcome by successful kidney transplantation with appropriate immunosuppression. Minimizing the duration of peritoneal dialysis, particularly in patients who desire future fertility, may be accepted as a logical management strategy.     

Use of a convolutional neural network and quantitative ultrasound for diagnosis of fatty liver

Quantitative ultrasound (QUS) was used to classify rabbits that were induced to have liver disease by placing them on a fatty diet for a defined duration and/or periodically injecting them with CCl₄. The ground truth of the liver state was based on lipid liver percents estimated via the Folch assay and hydroxyproline concentration to quantify fibrosis. Rabbits were scanned ultrasonically in vivo using a SonixOne scanner and an L9-4/38 linear array. Liver fat percentage was classified based on the ultrasonic backscattered radiofrequency (RF) signals from the livers using either QUS or a 1-D convolutional neural network (CNN). Use of QUS parameters with linear regression and canonical correlation analysis demonstrated that the QUS parameters could differentiate between livers with lipid levels above or below 5%. However, the QUS parameters were not sensitive to fibrosis. The CNN was implemented by analyzing raw RF ultrasound signals without using separate reference data. The CNN outputs the classification of liver as either above or below a threshold of 5% fat level in the liver. The CNN outperformed the classification utilizing the QUS parameters combined with a support vector machine in differentiating between low and high lipid liver levels (i.e., accuracies of 74% versus 59% on the testing data). Therefore, although the CNN did not provide a physical interpretation of the tissue properties (e.g., attenuation of the medium or scatterer properties) the CNN had much higher accuracy in predicting fatty liver state and did not require an external reference scan.     

Microsurgical anatomy of the facial nerve

The facial nerve connections and pathways from the cortex to the brainstem are intricate and complicated. The extra‐axial part of the facial nerve leaves the lateral part of the pontomedullary sulcus and enters the temporal bone through the internal acoustic meatus. In the temporal bone, the facial nerve branches into fibers innervating the glands and tongue. After it emerges from the temporal bone it supplies various facial muscles. It contains a motor, general sensory, special sensory, and autonomic components. The physician needs comprehensive knowledge of the anatomy and courses of the facial nerve to diagnose and treat lesions and diseases of it so that surgical complications due to facial nerve injury can be avoided. This review describes the microsurgical anatomy of the facial nerve and illustrates its anatomy in relation to the surrounding bone, connective, and neurovascular structures.     

Comparative Outcome Analysis of N-Butyl Cyanoacrylate Embolization of the False Lumen Versus Thoracic Endovascular Aortic Repair in Aortic Dissection

PurposeTo evaluate the feasibility, safety, and effectiveness of N-butyl cyanoacrylate (NBCA) embolization for the treatment of aortic dissection.Materials and MethodsIn this single-center retrospective study conducted from February 2003 to June 2019, NBCA embolization of an aortic false lumen was attempted in 12 patients (median age, 59 y; range, 41–68 y) and thoracic endovascular aortic repair (TEVAR) was performed in 53 patients (median age, 59 y; range, 37–70 y) for aortic dissection with one or more indications of persisting pain, malperfusion, rupture or impending rupture, maximal aortic diameter ≥ 55 mm, and/or rapid aortic enlargement. The main exclusion criterion for embolization was the presence of fast blood flow in the aortic false lumen on aortography. The efficacy of NBCA embolization and TEVAR was compared by evaluating technical and clinical outcomes, repeat intervention–free survival (RFS), and overall survival (OS).ResultsTechnical success was achieved in 11 of the 12 patients treated with NBCA embolization (91.7%), and clinical success was achieved in 9 of these 11 (81.8%). No significant difference was found between embolization and TEVAR in clinical success rates (embolization, 81.8%; TEVAR, 84.9%; P = .409) or procedure-related complications (embolization, 1 patient [8.3%]; TEVAR, 4 patients [7.5%]; P = .701). In addition, embolization showed comparable 5-y RFS (embolization, 82.5% ± 9.3; TEVAR, 85.5% ± 4.8; P = .641) and 5-y OS (embolization, 100%; TEVAR, 95.4% ± 3.2; P = .744) rates to TEVAR.ConclusionsNBCA embolization of the false lumen in aortic dissection seems to be a safe and effective treatment modality for the closure of false lumen in selected patients.