A Deep-Learning-Based Method Can Detect Both Common and Rare Genetic Disorders in Fetal Ultrasound

Abstract

A global survey indicates that genetic syndromes affect approximately 8% of the population, but most genetic diagnoses can only be performed after babies are born. Abnormal facial characteristics have been identified in various genetic diseases; however, current facial identification technologies cannot be applied to prenatal diagnosis. We developed Pgds-ResNet, a fully automated prenatal screening algorithm based on deep neural networks, to detect high-risk fetuses affected by a variety of genetic diseases. In screening for Trisomy 21, Trisomy 18, Trisomy 13, and rare genetic diseases, Pgds-ResNet achieved sensitivities of 0.83, 0.92, 0.75, and 0.96, and specificities of 0.94, 0.93, 0.95, and 0.92, respectively. As shown in heatmaps, the abnormalities detected by Pgds-ResNet are consistent with clinical reports. In a comparative experiment, the performance of Pgds-ResNet is comparable to that of experienced sonographers. This fetal genetic screening technology offers an opportunity for early risk assessment and presents a non-invasive, affordable, and complementary method to identify high-risk fetuses affected by genetic diseases. Additionally, it has the capability to screen for certain rare genetic conditions, thereby enhancing the clinic’s detection rate.

3D ultrasound evaluation of fetal ears in prenatal syndrome diagnosis – a comparative study

“…The fetal face portrayed in 3 D images looks very similar to the postnatal appearance [3] and may be easier for parents to visua-lize [23] and also facilitates demonstration by clinicians to both parents and colleagues [3,9,11,22,23]. Besides 3 D ultrasound, in the recent past, the usage of artificial intelligence for detecting syndrome-specific fetal anomalies has become more popular [24,25], and fetal facial abnormalities could thus be linked to Trisomy 21, 18, 13 and rare genetic diseases [25].…”

Enhancing Fetal Anomaly Detection in Ultrasonography Images: A Review of Machine Learning-Based Approaches

“…These challenges can be mitigated through the incorporation of techniques such as regularization parameter tuning and the strategic use of skip connections, as exemplified by ResNets. The inclusion of skip connections not only alleviates the vanishing gradient problem but also [58,[95][96][97][98][99][100][101][102][103]107,109,[115][116][117]120,[124][125][126][127][128][129][130][135][136][137]141,142,145,150,153,157,160,161,169]. Each study's color code reflects its relevance to a certain organ, including the heart, brain, lung, or analyzing for chromosomal abnormalities.…”

“…Each entry provides information about the employed methods, total number of images, key performance metrics, and application domain. [58,[95][96][97][98][99][100][101][102][103]107,109,[115][116][117]120,[124][125][126][127][128][129][130][135][136][137]141,142,145,150,153,157,160,161,169]. Each study's color code reflects its relevance to a certain organ, including the heart, brain, lung, or analyzing for chromosomal abnormalities.…”

“…Their dataset consisted of 845 normal images and 275 rare genetic disease images. Their feature extraction process indicated that the fetal nose, jaw, and forehead contained valuable diagnostic information [160]. However, their model was trained on a relatively small dataset from a single data center.…”