An image dataset of newborn ears for detecting auricle deformities
Early and accurate diagnosis of ear deformity in newborns is crucial for an effective corrective treatment, since this commonly seen ear anomalies would affect aesthetics and cause mental problems if untreated. The identification of auricle deformity, and the classification of its sub-types are not easy tasks even for experienced doctors, partly because of the rich bio-metric features embedded in the ear shape. Machine learning has already been introduced to analyze the auricle shape. However, there is little publicly available datasets of ear images from newborns.
We released a dataset that contains quality-controlled photos of 3,852 ears from 1,926 newborns. The dataset also contains medical diagnosis of the ear shape, and the health data of each newborn and its mother. Our aim is to provide a freely accessible dataset, which would facilitate researches related with ear anatomies, such as the AI-aided detection and classification of auricle deformities and medical risk analysis.
A techniqual paper of the dataset, entitled "A publicly available newborn ear shape dataset for medical diagnosis of auricular deformities", has already been accepted by Scientific Data (https://www.nature.com/sdata/).
Here we provided the code used for data analysis in the publication. Please refer to 'Brief instruction.docx' for introduction of the code.
Any questions, please contact
Liu-Jie Ren, Email: renliujie@fudan.edu.cn
Yao-Yao Fu, Email: fuyaoyao2007@126.com
Eye & ENT Hospital, Fudan University, Shanghai, China