Hybrid transformer UNet for thyroid segmentation from ultrasound scans

计算机科学 分割 人工智能 模式识别(心理学) 特征提取 变压器 图像分割 计算机视觉 量子力学 物理 电压
作者
Jianning Chi,Zelan Li,Zhiyi Sun,Xiaosheng Yu,Huan Wang
出处
期刊:Computers in Biology and Medicine [Elsevier BV]
卷期号:153: 106453-106453 被引量:19
标识
DOI:10.1016/j.compbiomed.2022.106453
摘要

Deep learning based medical image segmentation methods have been widely used for thyroid gland segmentation from ultrasound images, which is of great importance for the diagnosis of thyroid disease since it can provide various valuable sonography features. However, existing thyroid gland segmentation models suffer from: (1) low-level features that are significant in depicting thyroid boundaries are gradually lost during the feature encoding process, (2) contextual features reflecting the changes of difference between thyroid and other anatomies in the ultrasound diagnosis process are either omitted by 2D convolutions or weakly represented by 3D convolutions due to high redundancy. In this work, we propose a novel hybrid transformer UNet (H-TUNet) to segment thyroid glands in ultrasound sequences, which consists of two parts: (1) a 2D Transformer UNet is proposed by utilizing a designed multi-scale cross-attention transformer (MSCAT) module on every skipped connection of the UNet, so that the low-level features from different encoding layers are integrated and refined according to the high-level features in the decoding scheme, leading to better representation of differences between anatomies in one ultrasound frame; (2) a 3D Transformer UNet is proposed by applying a 3D self-attention transformer (SAT) module to the very bottom layer of 3D UNet, so that the contextual features representing visual differences between regions and consistencies within regions could be strengthened from successive frames in the video. The learning process of the H-TUNet is formulated as a unified end-to-end network, so the intra-frame feature extraction and inter-frame feature aggregation can be learned and optimized jointly. The proposed method was evaluated on Thyroid Segmentation in Ultrasonography Dataset (TSUD) and TG3k Dataset. Experimental results have demonstrated that our method outperformed other state-of-the-art methods with respect to the certain benchmarks for thyroid gland segmentation.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
量子星尘发布了新的文献求助10
11秒前
CyberHamster完成签到,获得积分10
21秒前
xiaohong完成签到,获得积分10
24秒前
朱比特完成签到,获得积分10
25秒前
26秒前
zmuzhang2019发布了新的文献求助10
32秒前
onestepcloser完成签到 ,获得积分0
32秒前
zoe完成签到 ,获得积分10
33秒前
发嗲的慕蕊完成签到 ,获得积分10
34秒前
Linson完成签到,获得积分10
35秒前
顾矜应助赵三岁采纳,获得10
49秒前
yyy2025完成签到,获得积分10
53秒前
木雨亦潇潇完成签到,获得积分10
1分钟前
香蕉觅云应助nine2652采纳,获得10
1分钟前
量子星尘发布了新的文献求助10
1分钟前
芳华如梦完成签到 ,获得积分10
1分钟前
1分钟前
1分钟前
1分钟前
土豆丝完成签到 ,获得积分10
1分钟前
琦琦完成签到,获得积分10
1分钟前
zzzz完成签到,获得积分20
1分钟前
GEZIKU完成签到 ,获得积分10
1分钟前
1分钟前
1分钟前
赵三岁发布了新的文献求助10
1分钟前
wwb完成签到,获得积分10
1分钟前
1分钟前
1分钟前
肯德基没有黄焖鸡完成签到 ,获得积分10
1分钟前
能干冰露完成签到,获得积分10
1分钟前
牛奶拌可乐完成签到 ,获得积分10
1分钟前
量子星尘发布了新的文献求助30
1分钟前
周小鱼完成签到 ,获得积分10
2分钟前
2分钟前
2分钟前
老张完成签到,获得积分10
2分钟前
2分钟前
zhugao完成签到,获得积分10
2分钟前
2分钟前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Handbook of Industrial Diamonds.Vol2 1100
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038039
求助须知:如何正确求助?哪些是违规求助? 3575756
关于积分的说明 11373782
捐赠科研通 3305574
什么是DOI,文献DOI怎么找? 1819239
邀请新用户注册赠送积分活动 892655
科研通“疑难数据库(出版商)”最低求助积分说明 815022