Deep learning approach to semantic segmentation in 3D point cloud intra-oral scans of teeth

Farhad Ghazvinian Zanjani, David Anssari Moin, Bas Verheij, Frank Claessen, Teo Cherici, Tao Tan, Peter H. N. de With

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

118 Downloads (Pure)

Abstract

Accurate segmentation of data, derived from intra-oral scans (IOS), is a crucial step in a computer-aided design (CAD) system for many clinical tasks, such as implantology and orthodontics in modern dentistry. In order to reach the highest possible quality, a segmentation model may process a point cloud derived from an IOS in its highest available spatial resolution, especially for performing a valid analysis in finely detailed regions such as the curvatures in border lines between two teeth. In this paper, we propose an end-to-end deep learning framework for semantic segmentation of individual teeth as well as the gingiva from point clouds representing IOS. By introducing a non-uniform resampling technique, our proposed model is trained and deployed on the highest available spatial resolution where it learns the local fine details along with the global coarse structure of IOS. Furthermore, the point-wise cross-entropy loss for semantic segmentation of a point cloud is an ill-posed problem, since the relative geometrical structures between the instances (e.g. the teeth) are not formulated. By training a secondary simple network as a discriminator in an adversarial setting and penalizing unrealistic arrangements of assigned labels to the teeth on the dental arch, we improve the segmentation results considerably. Hence, a heavy post-processing stage for relational and dependency modeling (e.g. iterative energy minimization of a constructed graph) is not required anymore. Our experiments show that the proposed approach improves the performance of our baseline network and outperforms the state-of-the-art networks by achieving 0.94 IOU score.
Original languageEnglish
Title of host publicationInternational Conference on Medical Imaging with Deep Learning (MIDL)
PublisherPMLR
Pages557-571
Publication statusPublished - 2019
EventInternational Conference on Medical Imaging with Deep Learning (MIDL) - ICL South Kensington Campus, London, United Kingdom
Duration: 8 Jul 201910 Jul 2019

Publication series

NameProceedings of Machine Learning Research
Volume102

Conference

ConferenceInternational Conference on Medical Imaging with Deep Learning (MIDL)
CountryUnited Kingdom
CityLondon
Period8/07/1910/07/19

Fingerprint Dive into the research topics of 'Deep learning approach to semantic segmentation in 3D point cloud intra-oral scans of teeth'. Together they form a unique fingerprint.

Cite this