51. Efficient high cone-angle artifact reduction in circular cone-beam CT using deep learning with geometry-aware dimension reduction
- Author
-
Felix Lucka, Kees Joost Batenburg, Maureen van Eijnatten, Juha Koivisto, Henri Der Sarkissian, Jan Wolff, Tymour Forouzanfar, Shannon Doyle, Jordi Minnema, Centrum Wiskunde & Informatica, Amsterdam (CWI), The Netherlands, Oral and Maxillofacial Surgery / Oral Pathology, AMS - Tissue Function & Regeneration, Publica, Maxillofacial Surgery (VUmc), Oral Implantology, Maxillofacial Surgery (AMC + VUmc), Medical Image Analysis, and EAISI Health more...
- Subjects
Cone beam computed tomography ,cone-beam computed tomography ,Computer science ,Geometry ,Iterative reconstruction ,01 natural sciences ,Convolutional neural network ,030218 nuclear medicine & medical imaging ,010309 optics ,Reduction (complexity) ,03 medical and health sciences ,0302 clinical medicine ,0103 physical sciences ,convolutional neural networks ,Image Processing, Computer-Assisted ,Artifact reduction ,Radiology, Nuclear Medicine and imaging ,Segmentation ,Radiological and Ultrasound Technology ,Artificial neural network ,business.industry ,Deep learning ,Dimensionality reduction ,Cone-beam computed tomography ,deep learning ,Convolutional neural networks ,Artificial intelligence ,Neural Networks, Computer ,business ,Artifacts ,artifact reduction - Abstract
© 2021 Institute of Physics and Engineering in Medicine.High cone-angle artifacts (HCAAs) appear frequently in circular cone-beam computed tomography (CBCT) images and can heavily affect diagnosis and treatment planning. To reduce HCAAs in CBCT scans, we propose a novel deep learning approach that reduces the three-dimensional (3D) nature of HCAAs to two-dimensional (2D) problems in an efficient way. Specifically, we exploit the relationship between HCAAs and the rotational scanning geometry by training a convolutional neural network (CNN) using image slices that were radially sampled from CBCT scans. We evaluated this novel approach using a dataset of input CBCT scans affected by HCAAs and high-quality artifact-free target CBCT scans. Two different CNN architectures were employed, namely U-Net and a mixed-scale dense CNN (MS-D Net). The artifact reduction performance of the proposed approach was compared to that of a Cartesian slice-based artifact reduction deep learning approach in which a CNN was trained to remove the HCAAs from Cartesian slices. In addition, all processed CBCT scans were segmented to investigate the impact of HCAAs reduction on the quality of CBCT image segmentation. We demonstrate that the proposed deep learning approach with geometry-aware dimension reduction greatly reduces HCAAs in CBCT scans and outperforms the Cartesian slice-based deep learning approach. Moreover, the proposed artifact reduction approach markedly improves the accuracy of the subsequent segmentation task compared to the Cartesian slice-based workflow. more...
- Published
- 2021
- Full Text
- View/download PDF