LZTR1-Related Hypertrophic Cardiomyopathy Without Typical Noonan Syndrome Features

Prenatal diagnosis of autosomal recessive Noonan syndrome associated with biallelic LZTR1 variants presented with thick nuchal translucency and cardiac abnormalities

Noonan syndrome (NS) is a common clinical variable disease characterized by a number of features, mainly including congenital heart defects, short stature, and a variable degree of developmental delay. This disorder is transmitted mostly in an autosomal dominant manner and is genetically heterogeneous. We report three prenatal cases of LZTR1-related recessive NS. One case had a recurrent cystic hygroma at 13 weeks gestation and the pregnancy was terminated. Two cases had an increased nuchal translucency at 12 weeks' gestation, but a normal second trimester ultrasound; both presented with hypertrophic cardiomyopathy in the third trimester. The two infants were diagnosed with NS after birth. All of the three cases had invasive genetic investigations during pregnancy, and trio exome sequencing revealed biallelic likely pathogenic or pathogenic LZTR1 variants in the fetuses. All parents were LZTR1 variant carriers. Our report further strengthens the association of LZTR1 with an autosomal recessive form of NS. The affected fetuses are more likely to have cardiac anomalies. Clarification of molecular diagnosis has important implications in these families because they carry a 25% recurrence risk.

Abnormalities of pubertal development and gonadal function in Noonan syndrome

Background

Noonan syndrome (NS) is a genetic multisystem disorder characterised by variable clinical manifestations including dysmorphic facial features, short stature, congenital heart disease, renal anomalies, lymphatic malformations, chest deformities, cryptorchidism in males.

Methods

In this narrative review, we summarized the available data on puberty and gonadal function in NS subjects and the role of the RAS/mitogen-activated protein kinase (MAPK) signalling pathway in fertility. In addition, we have reported our personal experience on pubertal development and vertical transmission in NS.

Conclusions

According to the literature and to our experience, NS patients seem to have a delay in puberty onset compared to the physiological timing reported in healthy children. Males with NS seem to be at risk of gonadal dysfunction secondary not only to cryptorchidism but also to other underlying developmental factors including the MAP/MAPK pathway and genetics. Long-term data on a large cohort of males and females with NS are needed to better understand the impact of delayed puberty on adult height, metabolic profile and well-being. The role of genetic counselling and fertility related-issues is crucial.

Automated Facial Recognition for Noonan Syndrome Using Novel Deep Convolutional Neural Network With Additive Angular Margin Loss

BACKGROUND

Noonan syndrome (NS), a genetically heterogeneous disorder, presents with hypertelorism, ptosis, dysplastic pulmonary valve stenosis, hypertrophic cardiomyopathy, and small stature. Early detection and assessment of NS are crucial to formulating an individualized treatment protocol. However, the diagnostic rate of pediatricians and pediatric cardiologists is limited. To overcome this challenge, we propose an automated facial recognition model to identify NS using a novel deep convolutional neural network (DCNN) with a loss function called additive angular margin loss (ArcFace).

METHODS

The proposed automated facial recognition models were trained on dataset that included 127 NS patients, 163 healthy children, and 130 children with several other dysmorphic syndromes. The photo dataset contained only one frontal face image from each participant. A novel DCNN framework with ArcFace loss function (DCNN-Arcface model) was constructed. Two traditional machine learning models and a DCNN model with cross-entropy loss function (DCNN-CE model) were also constructed. Transfer learning and data augmentation were applied in the training process. The identification performance of facial recognition models was assessed by five-fold cross-validation. Comparison of the DCNN-Arcface model to two traditional machine learning models, the DCNN-CE model, and six physicians were performed.

RESULTS

At distinguishing NS patients from healthy children, the DCNN-Arcface model achieved an accuracy of 0.9201 ± 0.0138 and an area under the receiver operator characteristic curve (AUC) of 0.9797 ± 0.0055. At distinguishing NS patients from children with several other genetic syndromes, it achieved an accuracy of 0.8171 ± 0.0074 and an AUC of 0.9274 ± 0.0062. In both cases, the DCNN-Arcface model outperformed the two traditional machine learning models, the DCNN-CE model, and six physicians.

CONCLUSION

This study shows that the proposed DCNN-Arcface model is a promising way to screen NS patients and can improve the NS diagnosis rate.