GT U-Net: A U-Net Like Group Transformer Network for Tooth Root Segmentation

Li, Yunxiang; Wang, Shuai; Wang, Jun; Zeng, Guodong; Liu, Wenjun; Zhang, Qianni; Jin, Qun; Wang, Yaqi

doi:10.1007/978-3-030-87589-3_40

Cited by 40 publications

(22 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Inspired by this, Radford et al proposed CLIP [17], which uses contrast learning to learn image representations on a dataset of 400 million pairs (image, text) from scratch. And in the natural image semantic segmentation, there are studies [18][19][20] that have begun to use text information to improve the segmentation capabilities of models. In the field of medical image analysis, there are some related works too [21,22].…”

Section: Related Workmentioning

confidence: 99%

LViT: Language meets Vision Transformer in Medical Image Segmentation

Li¹,

Li²,

Zhang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Deep learning has been widely used in medical image segmentation and other aspects. However, the performance of existing medical image segmentation models has been limited by the challenge of obtaining sufficient number of high-quality data with the high cost of data annotation. To overcome the limitation, we propose a new vision-language medical image segmentation model LViT (Language meets Vision Transformer). In our model, medical text annotation is introduced to compensate for the quality deficiency in image data. In addition, the text information can guide the generation of pseudo labels to a certain extent and further guarantee the quality of pseudo labels in semi-supervised learning. We also propose the Exponential Pseudo label Iteration mechanism (EPI) to help extend the semisupervised version of LViT and the Pixel-Level Attention Module (PLAM) to preserve local features of images. In our model, LV (Language-Vision) loss is designed to supervise the training of unlabeled images using text information directly. To validate the performance of LViT, we construct multimodal medical segmentation datasets (image + text) containing pathological images, X-rays, etc. Experimental results show that our proposed LViT has better segmentation performance in both fully and semi-supervised conditions. Code and datasets are available at https://github.com/HUANGLIZI/LViT. * Part of the work was done when Zihan Li is an intern at DAMO Academy.Preprint. Under review.

show abstract

Section: Related Workmentioning

confidence: 99%

LViT: Language meets Vision Transformer in Medical Image Segmentation

Li¹,

Li²,

Zhang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…They used an improved region growing algorithm and parameter adaptive method to expand the resemble regions and remove unnecessary parameters to enhance their segmentation performance. To cost-effectively improve the results of tooth segmentation, Li et al (2021) proposed a group transformer to achieve advanced performance on tooth root segmentation. Koch et al (2019) input the original image into the network in blocks and achieved pretty performance through U-Net.…”

Section: Related Workmentioning

confidence: 99%

Clinical tooth segmentation based on local enhancement

Zhang

Yang

et al. 2022

Front. Mol. Biosci.

View full text Add to dashboard Cite

The tooth arrangements of human beings are challenging to accurately observe when relying on dentists’ naked eyes, especially for dental caries in children, which is difficult to detect. Cone-beam computer tomography (CBCT) is used as an auxiliary method to measure patients’ teeth, including children. However, subjective and irreproducible manual measurements are required during this process, which wastes much time and energy for the dentists. Therefore, a fast and accurate tooth segmentation algorithm that can replace repeated calculations and annotations in manual segmentation has tremendous clinical significance. This study proposes a local contextual enhancement model for clinical dental CBCT images. The local enhancement model, which is more suitable for dental CBCT images, is proposed based on the analysis of the existing contextual models. Then, the local enhancement model is fused into an encoder–decoder framework for dental CBCT images. At last, extensive experiments are conducted to validate our method.

show abstract

“…The first one, which is represented by ViT [11], is to take a patch with a certain size as an element, but it is in the image level and more suitable for classification tasks. The second one is Swin Transformer [12,13,14], which performs pixel-level operations in a small local window, and gradually obtains global information via deepening the network, but it does not fully utilize Transformer's global modeling capability. Therefore, we design a novel model so-called Shuffle Transformer to capture global capability with low computational complexity.…”

Section: Shape Autoencoder (Sae)mentioning

confidence: 99%

Plug-and-play Shape Refinement Framework for Multi-site and Lifespan Brain Skull Stripping

Li¹,

Dan²,

Wang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Skull stripping is a crucial prerequisite step in the analysis of brain magnetic resonance (MR) images. Although many excellent works or tools have been proposed, they suffer from low generalization capability. For instance, the model trained on a dataset with specific imaging parameters (source domain) cannot be well applied to other datasets with different imaging parameters (target domain). Especially, for the lifespan datasets, the model trained on an adult dataset is not applicable to an infant dataset due to the large domain difference. To address this issue, numerous domain adaptation (DA) methods have been proposed to align the extracted features between the source and target domains, requiring concurrent access to the input images of both domains. Unfortunately, it is problematic to share the images due to privacy. In this paper, we design a source-free domain adaptation framework (SDAF) for multi-site and lifespan skull stripping that can accomplish domain adaptation without access to source domain images. Our method only needs to share the source labels as shape dictionaries and the weights trained on the source data, without disclosing private information from source domain subjects. To deal with the domain shift between multi-site lifespan datasets, we take advantage of the brain shape prior which is invariant to imaging parameters and ages. Experiments demonstrate that our framework can significantly outperform the state-of-the-art methods on multi-site lifespan datasets.

show abstract

GT U-Net: A U-Net Like Group Transformer Network for Tooth Root Segmentation

Cited by 40 publications

References 21 publications

LViT: Language meets Vision Transformer in Medical Image Segmentation

LViT: Language meets Vision Transformer in Medical Image Segmentation

Clinical tooth segmentation based on local enhancement

Plug-and-play Shape Refinement Framework for Multi-site and Lifespan Brain Skull Stripping

Contact Info

Product

Resources

About