AutoEncoder.

An autoencoder is a special type of neural network that is trained to copy its input to its output. Learns to compress the data while minimizing the reconstruction error.

About dataset:

his dataset consists of anonymized and deidentified panoramic dental X-rays of 116 patients, taken at Noor Medical Imaging Center, Qom, Iran. The subjects cover a wide range of dental conditions from healthy, to partial and complete edentulous cases. The mandibles of all cases are manually segmented by two dentists. This dataset is used as the basis for the article by Abdi et al

Data source:

Abdi, Amir; Kasaei, Shohreh (2020), “Panoramic Dental X-rays With Segmented Mandibles”, Mendeley Data, V2, doi: 10.17632/hxt48yk462.2

If you find this code useful in your research, please consider citing the blog:

@misc{antoniogonzaautoencoder, Author = {Antonio Gonzalez}, Title = {X-Ray Dental Recontruction Using AutoEncoder}, Year = {2021}, Source = {https://github.com/antoniogonzalezai}, }