WITS: Weakly-supervised individual tooth segmentation model trained on box-level labels

作者：

Highlights：

• We propose an ellipses detection method which can better fit the shape of tooth.

• We propose a level-set-based curvature model with restriction term which can force the active contour to fit the non-convex tooth and preserve the signed distance property of level function.

• The proposed model is a weakly-supervised model which is trained on box-level labels but can obtain pixel-level results.

摘要

•We propose an ellipses detection method which can better fit the shape of tooth.•We propose a level-set-based curvature model with restriction term which can force the active contour to fit the non-convex tooth and preserve the signed distance property of level function.•The proposed model is a weakly-supervised model which is trained on box-level labels but can obtain pixel-level results.

论文关键词：Tooth detection,Deep learning,Active contour,Oral CBCT images,Level set

论文评审过程：Received 12 June 2021, Revised 5 July 2022, Accepted 13 August 2022, Available online 15 August 2022, Version of Record 26 August 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108974