ABSTRACT
Ischemic heart condition is one of the most prevalent causes of death that can be treated more effectively and lead to fewer fatalities if identified early. Heart muscle fibrosis affects the diastolic and systolic function of the heart and is linked to unfavorable cardiovascular outcomes. Cardiac magnetic resonance (CMR) scarring, a risk factor for ischemic heart disease, may be accurately identified by magnetic resonance imaging (MRI) to recognize fibrosis. In the past few decades, numerous methods based on MRI have been employed to identify and categorize cardiac fibrosis. Because they increase the therapeutic advantages and the likelihood that patients will survive, developing these approaches is essential and has significant medical benefits. A brand-new method that uses MRI has been suggested to help with diagnosing. Advances in deep learning (DL) networks contribute to the early and accurate diagnosis of heart muscle fibrosis. This study introduces a new deep network known as FibrosisNet, which detects and classifies fibrosis if it is present. It includes some of 17 various series layers to achieve the fibrosis detection target. The introduced classification system is trained and evaluated for the best performance results. In addition, deep transfer-learning models are applied to the different famous convolution neural networks to find fibrosis detection architectures. The FibrosisNet architecture achieves an accuracy of 96.05%, a sensitivity of 97.56%, and an F1-Score of 96.54%. The experimental results show that FibrosisNet has numerous benefits and produces higher results than current state-of-the-art methods and other advanced CNN approaches.
ABSTRACT
INTRODUCTION: Fragile-X syndrome(FXS) is a neurological disease caused by abnormal repeats in the 5'untranslated region of the FMR1 gene leading to a defective fragile-X-messenger-ribonucleoprotein-1 (FMRP). Although relatively common in children, it is usually under-diagnosed especially in developing countries where genetic screening is not routinely practiced. So far, FXS lacks a laboratory biomarker that can be used for screening, severity scoring or therapeutic monitoring of potential new treatments. METHODS: 110 subjects were recruited; 80 male children with suspected FXS and 30 matched healthy children. We evaluated the clinical utility of serum matrix metalloproteinase-9(MMP9) and amyloid-beta protein precursor(APP) as potential biomarkers for FXS. RESULTS: Out of 80 suspected children, 14 had full mutation, 8 had the premutation and 58 children had normal genotypes. No statistically-significant difference was detected between children with different genotypes concerning age of onset(P = 0.658), main clinical presentation(P = 0.388), clinical severity-score(P = 0.799), patient's disease-course(P = 0.719) and intellectual disability(P = 0.351). Both MMP9 and APP showed a statistically significant difference when comparing different genotype subgroups(P = 0.019 and < 0.001, respectively). Clinically, MMP9 levels were highest in children presenting with language defects, while APP was highest in children with neurodevelopmental delay. In receiver operating curve analysis, comparing full and premutation with the normal genotype group, MMP9 has an area-under-the-curve of 0.701(95 % CI 0.557-0.845), while APP was marginally better at 0.763(95 % CI 0.620-0.906). When combined together, elevated MMP9 or APP had excellent sensitivity > 95 % for picking-up FXS cases in the clinical setting. CONCLUSIONS: Screening for circulating biomarkers in the absence of FXS genetic diagnosis is justified. Our study is the first to evaluate both MMP9 and APP in FXS suspected children in a clinical setting and to assess their correlation with disease presentation and severity.
