Tympanic Membrane Abnormality Classifier

We created an original tympanic membrane (TM) image database consisting of a total of 400 images by utilizing publicly available online databases and images. The database contained images representing five different pathologies: normal, acute otitis media, otitis externa, chronic suppurative otitis media, and cerumen. The classifier was constructed based on a deep learning algorithm. It is capable of binary classification (Normal vs. Abnormal) and multiclass classification (Normal, AOM, CSOM, Cerumen, OE)

Try some of the images below.

Download the images below and drag them to the dropzone to test our TM classifier.