Low-set ears and associated anomalies in human foetuses

Anthropometric Study of Auricular Development in Human Fetal Cadavers

The aim of the study is to comprehensively examine the composition and localization of the auricle in formalin-fixed human fetuses during the second and third trimesters of the antenatal period. Ninety-seven auricles were evaluated (33 females and 31 males in the second, and 22 females and 11 males in the third trimester). Nine morphometric dimensions were directly measured from auricles. The position of the auricula relative to lateral cantus and oral commissure levels, and the ear inclination angle were determined. The frequency of lobule attachment types was also noted. All fetuses exhibited normal development within the 50% to 97% percentile range. Morphometric data (ear length, ear width, distance from tragus to helix, auricular base length, concha length, conchal width, lobule length, and lobule width) for the second and third trimesters were presented, along with comparisons of ear dimensions by side and sex. Attachment types of lobules in fetuses were with pendulous lobules being the most common at 62.5%, nonpendulous lobules at 21.88%, and partial pendulous lobules the least common at 15.62%. None of the fetuses exhibited low-set ears. Dimensional measurements revealed no statistically significant differences between fetuses, except for the left auricular base length in females, left concha length in males, and left lobule width in males, which were higher. Scatter plots of parameters with age and regression analysis were provided. These results contribute to a deeper understanding of fetal auricle development and serve as a reference during the second and third trimesters. Quantitative values of normal fetal ear growth can aid specialists in distinguishing congenital or developmental anomalies from normal ears.

Artificial intelligence-based diagnosis in fetal pathology using external ear shapes

OBJECTIVE

Here we trained an automatic phenotype assessment tool to recognize syndromic ears in two syndromes in fetuses-=CHARGE and Mandibulo-Facial Dysostosis Guion Almeida type (MFDGA)-versus controls.

METHOD

We trained an automatic model on all profile pictures of children diagnosed with genetically confirmed MFDGA and CHARGE syndromes, and a cohort of control patients, collected from 1981 to 2023 in Necker Hospital (Paris) with a visible external ear. The model consisted in extracting landmarks from photographs of external ears, in applying geometric morphometry methods, and in a classification step using machine learning. The approach was then tested on photographs of two groups of fetuses: controls and fetuses with CHARGE and MFDGA syndromes.

RESULTS

The training set contained a total of 1489 ear photographs from 526 children. The validation set contained a total of 51 ear photographs from 51 fetuses. The overall accuracy was 72.6% (58.3%-84.1%, p < 0.001), and 76.4%, 74.9%, and 86.2% respectively for CHARGE, control and MFDGA fetuses. The area under the curves were 86.8%, 87.5%, and 90.3% respectively for CHARGE, controls, and MFDGA fetuses.

CONCLUSION

We report the first automatic fetal ear phenotyping model, with satisfactory classification performances. Further validations are required before using this approach as a diagnostic tool.