Self-co-attention neural network for anatomy segmentation in whole breast ultrasound

•We devise a self-attention mechanism with spatial and channel attention modules.•The non-local block is employed to learn high-order semantic context cues.•The weighted up-sampling block is developed in the decoder path.•The co-attention module is introduced to consider segmentation coherence. The...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Medical image analysis Ročník 64; s. 101753
Hlavní autori:	Lei, Baiying, Huang, Shan, Li, Hang, Li, Ran, Bian, Cheng, Chou, Yi-Hong, Qin, Jing, Zhou, Peng, Gong, Xuehao, Cheng, Jie-Zhi
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Elsevier B.V 01.08.2020
Predmet:	Breast anatomy segmentation Encoder-decoder architecture Non-local cue Self-co-attention mechanism Self-co-attention mechanism Encoder-decoder architecture Non-local cue Breast anatomy segmentation
ISSN:	1361-8415, 1361-8423, 1361-8423
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	•We devise a self-attention mechanism with spatial and channel attention modules.•The non-local block is employed to learn high-order semantic context cues.•The weighted up-sampling block is developed in the decoder path.•The co-attention module is introduced to consider segmentation coherence. The automated whole breast ultrasound (AWBUS) is a new breast imaging technique that can depict the whole breast anatomy. To facilitate the reading of AWBUS images and support the breast density estimation, an automatic breast anatomy segmentation method for AWBUS images is proposed in this study. The problem at hand is quite challenging as it needs to address issues of low image quality, ill-defined boundary, large anatomical variation, etc. To address these issues, a new deep learning encoder-decoder segmentation method based on a self-co-attention mechanism is developed. The self-attention mechanism is comprised of spatial and channel attention module (SC) and embedded in the ResNeXt (i.e., Res-SC) block in the encoder path. A non-local context block (NCB) is further incorporated to augment the learning of high-level contextual cues. The decoder path of the proposed method is equipped with the weighted up-sampling block (WUB) to attain class-specific better up-sampling effect. Meanwhile, the co-attention mechanism is also developed to improve the segmentation coherence among two consecutive slices. Extensive experiments are conducted with comparison to several the state-of-the-art deep learning segmentation methods. The experimental results corroborate the effectiveness of the proposed method on the difficult breast anatomy segmentation problem on AWBUS images. [Display omitted]
Bibliografia:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	1361-8415 1361-8423 1361-8423
DOI:	10.1016/j.media.2020.101753