BPAT-UNet: Boundary preserving assembled transformer UNet for ultrasound thyroid nodule segmentation

Bi, Hui; Cai, Chunquan; Sun, Jiawei; Jiang, Yibo; Lu, Gang; Hu, Shu; Ni, Xinye

doi:10.1016/j.cmpb.2023.107614

Cited by 14 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach facilitates efficient and in-depth feature extraction, a crucial aspect of accurate segmentation. In contrast to the dual-decoder structure in D-TrAttUnet (Bougourzi et al 2023) and the boundary-preserving strategy in BPAT-UNet (Bi et al 2023), DAWTran prioritizes precision in feature extraction and alignment, solving spatial information loss during downsampling. Our model introduces the IFA layer, which aligns multi-level feature maps.…”

Section: Discussionmentioning

confidence: 99%

DAWTran: dynamic adaptive windowing transformer network for pneumothorax segmentation with implicit feature alignment

et al. 2023

View full text Add to dashboard Cite

Pneumothorax segmentation in computed tomography (CT) images poses significant challenges due to the resemblance between pneumothorax regions and gas-containing structures such as the trachea and bronchus. In this study, we introduce a novel Dynamic Adaptive Windowing Transformer (DAWTran) network incorporating implicit feature alignment for precise pneumothorax segmentation. The DAWTran network consists of an encoder module, which employs a Dynamic Adaptive Windowing Transformer, and a decoder module. Our proposed Dynamic Adaptive Windowing strategy enables multi-head self-attention to effectively capture multi scale information. The decoder module incorporates an Implicit Feature Alignment function to minimize information deviation. Moreover, we utilize a hybrid loss function to address the imbalance between positive and negative samples. Experimental results demonstrate that the DAWTran network surpasses both Swin-UNet and TransUNet networks in Dice Similarity Coefficient (DSC) and Hausdorff Distance (HD) performance metrics, highlighting its potential for accurate pneumothorax segmentation in clinical applications.

show abstract

Section: Discussionmentioning

confidence: 99%

DAWTran: dynamic adaptive windowing transformer network for pneumothorax segmentation with implicit feature alignment

et al. 2023

View full text Add to dashboard Cite

show abstract

“…As displayed in Table 1 , Chen et al [ 6 ] combined U-net with traditional algorithms to obtain the original data, and super-pixel processed data and Sobel edge processed images were merged as the training data as a complement to enhance the segmentation of thyroid entities. Bi et al [ 7 ] applied the boundary point supervision module and adaptive multi-scale feature fusion module to transformer U-Net to improve the boundary segmentation effect of nodules with small nodule segmentation. Shao et al [ 8 ] proposed FCG-Net by replacing the encoder and decoder with GB module based on the full-scale jump connection of Unet3 + as a way to improve nodule segmentation.…”

Section: Related Workmentioning

confidence: 99%

Three-dimensional visualization of thyroid ultrasound images based on multi-scale features fusion and hierarchical attention

Mi,

Wang,

Feng

et al. 2024

BioMed Eng OnLine

View full text Add to dashboard Cite

Background Ultrasound three-dimensional visualization, a cutting-edge technology in medical imaging, enhances diagnostic accuracy by providing a more comprehensive and readable portrayal of anatomical structures compared to traditional two-dimensional ultrasound. Crucial to this visualization is the segmentation of multiple targets. However, challenges like noise interference, inaccurate boundaries, and difficulties in segmenting small structures exist in the multi-target segmentation of ultrasound images. This study, using neck ultrasound images, concentrates on researching multi-target segmentation methods for the thyroid and surrounding tissues. Method We improved the Unet++ to propose PA-Unet++ to enhance the multi-target segmentation accuracy of the thyroid and its surrounding tissues by addressing ultrasound noise interference. This involves integrating multi-scale feature information using a pyramid pooling module to facilitate segmentation of structures of various sizes. Additionally, an attention gate mechanism is applied to each decoding layer to progressively highlight target tissues and suppress the impact of background pixels. Results Video data obtained from 2D ultrasound thyroid serial scans served as the dataset for this paper.4600 images containing 23,000 annotated regions were divided into training and test sets at a ratio of 9:1, the results showed that: compared with the results of U-net++, the Dice of our model increased from 78.78% to 81.88% (+ 3.10%), the mIOU increased from 73.44% to 80.35% (+ 6.91%), and the PA index increased from 92.95% to 94.79% (+ 1.84%). Conclusions Accurate segmentation is fundamental for various clinical applications, including disease diagnosis, treatment planning, and monitoring. This study will have a positive impact on the improvement of 3D visualization capabilities and clinical decision-making and research in the context of ultrasound image.

show abstract

“…However, the gray value of pixels at the edge of thyroid nodules tends to be very similar to the surrounding pixels, and thus the important low-level features used to represent thyroid boundaries may be lost. Bi et al developed two innovative self-attention pooling techniques to enhance boundary features and generate optimal boundary locations ( 65 ), and Yu et al added an edge-based attention mechanism to strengthen the nodule edge segmentation effect ( 66 ).…”

Section: Overview Of DLmentioning

confidence: 99%

“…A frequency-domain enhancement network, based on the U-net, has been introduced with a cascaded cross-scale attention module that integrates various features of different receptive fields to overcome the insensitivity of the network to changes in target scale ( 67 ). A U-Net was constructed as the backbone, with an adaptive multiscale feature fusion module that fuses features and channel information at different scales ( 65 ).…”

Section: Overview Of DLmentioning

confidence: 99%

A narrative review of deep learning in thyroid imaging: current progress and future prospects

Yang,

Ma,

Chen

2024

Quant Imaging Med Surg

View full text Add to dashboard Cite

Background and Objective Deep learning (DL) has contributed substantially to the evolution of image analysis by unlocking increased data and computational power. These DL algorithms have further facilitated the growing trend of implementing precision medicine, particularly in areas of diagnosis and therapy. Thyroid imaging, as a routine means to screening for thyroid diseases on large-scale populations, is a massive data source for the development of DL models. Thyroid disease is a global health problem and involves structural and functional changes. The objective of this study was to evaluate the general rules and future directions of DL networks in thyroid medical image analysis through a review of original articles published between 2018 and 2023. Methods We searched for English-language articles published between April 2018 and September 2023 in the databases of PubMed, Web of Science, and Google Scholar. The keywords used in the search included artificial intelligence or DL, thyroid diseases, and thyroid nodule or thyroid carcinoma. Key Content and Findings The computer vision tasks of DL in thyroid imaging included classification, segmentation, and detection. The current applications of DL in clinical workflow were found to mainly include management of thyroid nodules/carcinoma, risk evaluation of thyroid cancer metastasis, and discrimination of functional thyroid diseases. Conclusions DL is expected to enhance the quality of thyroid images and provide greater precision in the assessment of thyroid images. Specifically, DL can increase the diagnostic accuracy of thyroid diseases and better inform clinical decision-making.

show abstract

BPAT-UNet: Boundary preserving assembled transformer UNet for ultrasound thyroid nodule segmentation

Cited by 14 publications

References 12 publications

DAWTran: dynamic adaptive windowing transformer network for pneumothorax segmentation with implicit feature alignment

DAWTran: dynamic adaptive windowing transformer network for pneumothorax segmentation with implicit feature alignment

Three-dimensional visualization of thyroid ultrasound images based on multi-scale features fusion and hierarchical attention

A narrative review of deep learning in thyroid imaging: current progress and future prospects

Contact Info

Product

Resources

About