With the advancement of medicine, more and more researchers have turned their attention to the study of fetal genetic diseases in recent years. However, it is still a challenge to detect genetic diseases in the fetus, especially in an area lacking access to healthcare. The existing research primarily focuses on using teenagers’ or adults’ face information to screen for genetic diseases, but there are no relevant directions on disease detection using fetal facial information. To fill the vacancy, we designed a two-stage ensemble learning model based on sonography, Fgds-EL, to identify genetic diseases with 932 images. Concretely speaking, we use aggregated information of facial regions to detect anomalies, such as the jaw, frontal bone, and nasal bone areas. Our experiments show that our model yields a sensitivity of 0.92 and a specificity of 0.97 in the test set, on par with the senior sonographer, and outperforming other popular deep learning algorithms. Moreover, our model has the potential to be an effective noninvasive screening tool for the early screening of genetic diseases in the fetus.

(1) Objective: To investigate the prenatal diagnosis and genetic counseling for 16p11.2 microdeletion syndrome and to evaluate its pregnancy outcome. (2) Methods: This study included 4968 pregnant women who selected invasive prenatal diagnoses from 1 January 2017 to 1 August 2022. These 4698 pregnancies underwent chromosomal microarray analysis (CMA), data on 81 fetuses diagnosed with 16p11.2 microdeletion syndrome based on prenatal ultrasound features and genetic test results were recorded, and their pregnancy outcome was evaluated. (3) Results: 1.63% of fetuses (81/4968) were diagnosed with 16p11.2 microdeletion syndrome. Among these, there were skeletal malformations in 48.15% of the 81 fetuses, cardiovascular malformations in 30.86%, central nervous system malformations (CNS) in 11.11%, digestive system structural abnormalities in 6.17%, and isolated ultrasonography markers in 3.70%. (4) Conclusions: 16p11.2 microdeletion syndrome can display various systemic ultrasound abnormalities in the perinatal period but vertebral malformations are the most common. Our study is the first to report that TBX1 and CJA5 are associated with 16p11.2 microdeletion syndrome, expanding the disease spectrum of 16p11.2 microdeletion syndrome. In our study, the ventricular septal defect is the main feature of cardiac structural abnormalities caused by 16p11.2 microdeletion syndrome. In addition, our study highlights the use of CMA in 16p11.2 microdeletion syndrome, analyzed their genetic results, and evaluated the follow-up prognosis, which can be useful for prenatal diagnosis and genetic counseling.

A global survey has revealed that genetic syndromes affect approximately 8% of the population, but most genetic diagnoses are typically made after birth. Facial deformities are commonly associated with chromosomal disorders. Prenatal diagnosis through ultrasound imaging is vital for identifying abnormal fetal facial features. However, this approach faces challenges such as inconsistent diagnostic criteria and limited coverage. To address this gap, we have developed FGDS, a three-stage model that utilizes fetal ultrasound images to detect genetic disorders. Our model was trained on a dataset of 2554 images. Specifically, FGDS employs object detection technology to extract key regions and integrates disease information from each region through ensemble learning. Experimental results demonstrate that FGDS accurately recognizes the anatomical structure of the fetal face, achieving an average precision of 0.988 across all classes. In the internal test set, FGDS achieves a sensitivity of 0.753 and a specificity of 0.889. Moreover, in the external test set, FGDS outperforms mainstream deep learning models with a sensitivity of 0.768 and a specificity of 0.837. This study highlights the potential of our proposed three-stage ensemble learning model for screening fetal genetic disorders. It showcases the model’s ability to enhance detection rates in clinical practice and alleviate the burden on medical professionals.

Background: There are few studies on the detection rate by chromosomal microarray analysis (CMA) of the prenatal diagnosis of talipes equinovarus (TE) compared to conventional karyotyping. We aimed to explore the molecular etiology of fetal TE and examine the detection rate by CMA, which provides more information for the clinical screening and genetic counseling of TE. Methods: In this retrospective study, pregnancies diagnosed with fetal TE were enrolled and clinical data for all cases were retrieved from our medical record database, including demographic data for pregnancies, ultrasound findings, karyotype/CMA results, and pregnant and perinatal outcomes. Results: Among the 164 patients, 17 (10.4%) clinically significant variants were detected by CMA. In 148 singleton pregnancies, the diagnostic rate of clinically significant variants was significantly higher in the non-isolated TE group than in the isolated TE group (10/37, 27.0% vs. 6/111, 5.4%, P < 0.001). In twin pregnancies, 1 (6.3%) pathogenic copy number variant was present in the other 16 twin pregnancies. Conclusions: This study demonstrates that CMA is useful for the prenatal genetic diagnosis of fetal TE. Fetal TE with the associated structural malformation correlates with a higher probability of clinically significant variants. This data may aid prenatal diagnosis and genetic counseling for fetal TE.