Related references
Note: Only part of the references are listed.
Article
Multidisciplinary Sciences
Zhiming Cui et al.
Summary: This paper presents a deep learning system for efficient, precise, and fully automatic segmentation of dental cone-beam CT images. The system achieves comparable segmentation accuracy to experienced radiologists, while being 500 times faster. It consistently obtains accurate results on challenging cases with variable dental abnormalities, demonstrating its potential to boost clinical workflows of digital dentistry.
NATURE COMMUNICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Tae Jun Jang et al.
Summary: This paper proposes a fully automated method for identifying and segmenting 3D individual teeth from CBCT images. The method utilizes deep learning-based hierarchical multi-step model to overcome the difficulty of separating an individual tooth from adjacent teeth and its surrounding alveolar bone. Experimental results show that the proposed method achieves high accuracy in tooth identification and segmentation.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Dentistry, Oral Surgery & Medicine
Wei Duan et al.
Summary: This study proposed a two-phase deep learning solution for accurately extracting and segmenting single teeth and pulp cavities, achieving high accuracy in experimental results.
DENTOMAXILLOFACIAL RADIOLOGY
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Jeya Maria Jose Valanarasu et al.
Summary: Deep convolutional neural networks have been widely adopted in medical image segmentation, but lack understanding of long-range dependencies due to inherent biases in convolutional architectures. Transformer-based architectures leverage self-attention mechanism to encode long-range dependencies, motivating the exploration of transformer solutions for medical image segmentation tasks.
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2021, PT I
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Yuanfeng Ji et al.
Summary: This paper presents a unified Transformer network called Multi-Compound Transformer (MCTrans) to address cross-scale dependencies, semantic correspondence, and feature representation consistency in biomedical segmentation. MCTrans integrates rich feature learning and semantic structure mining into a unified framework, leading to significant improvements in biomedical image segmentation.
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2021, PT I
(2021)
Article
Computer Science, Information Systems
Yunbo Rao et al.
Article
Computer Science, Information Systems
S. Lee et al.
Proceedings Paper
Engineering, Biomedical
Jun Ma et al.
MEDICAL IMAGING 2019: IMAGE PROCESSING
(2019)
Article
Radiology, Nuclear Medicine & Medical Imaging
Yangzhou Gan et al.
