Doppler Image-Based Weakly-Supervised Vascular Ultrasound Segmentation with Transformer

Vascular segmentation in ultrasound (US) images faces labor-intensive labeling procedures and performance degradation due to unsatisfied image quality. Herein, we propose to use the Doppler image for vascular segmentation with an incremental Transformer structure. First, local features within the im...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings (International Symposium on Biomedical Imaging) s. 1 - 5
Hlavní autori: Ning, Guochen, Liang, Hanying, Chen, Fang, Zhang, Xinran, Liao, Hongen
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 18.04.2023
Predmet:
Conditional random fields
Decoding
Doppler image
Feature extraction
Image segmentation
Shape
Transformer
Transformers
Ultrasonic imaging
Ultrasound Image Segmentation
Weakly-supervised Segmentation
ISSN:1945-8452
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Vascular segmentation in ultrasound (US) images faces labor-intensive labeling procedures and performance degradation due to unsatisfied image quality. Herein, we propose to use the Doppler image for vascular segmentation with an incremental Transformer structure. First, local features within the image patch are extracted by a convolutional neural network (CNN) patch embedding layer and further encoded by a multi-level Transformer to enhance the global dependencies from coarse to fine. A multi-level CNN decoder is introduced to decode corresponding features. Doppler imaging is capable of blood visualization and indicating the positional and structural information used as the pseudo label. A conditional random field (CRF) module and shape similarity loss function are introduced to improve the effectiveness of the Doppler images. The segmentation accuracy of the radial artery and carotid artery datasets can achieve 78.8% and 81.9% in Dice, with 63.5% and 53.7% accuracy in noisy labels. In addition, the framework can be generalized to unseen data without related Doppler images.
ISSN:1945-8452
DOI:10.1109/ISBI53787.2023.10230548