Details

Autor(en) / Beteiligte

• Koch, Thorbjorn Louring
• Perslev, Mathias
• Igel, Christian
• Brandt, Sami Sebastian

Titel

Accurate Segmentation of Dental Panoramic Radiographs with U-NETS

Ist Teil von

• 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), 2019, p.15-19

Ort / Verlag

IEEE

Erscheinungsjahr

2019

Quelle

IEEE Electronic Library (IEL)

Beschreibungen/Notizen

• Fully convolutional neural networks (FCNs) have proven to be powerful tools for medical image segmentation. We apply an FCN based on the U-Net architecture for the challenging task of semantic segmentation of dental panoramic radiographs and discuss general tricks for improving segmentation performance. Among those are network ensembling, test-time augmentation, data symmetry exploitation and bootstrapping of low quality annotations. The performance of our approach was tested on a highly variable dataset of 1500 dental panoramic radiographs. A single network reached the Dice score of 0.934 where 1201 images were used for training, forming an ensemble increased the score to 0.936.