3D Md-Unet: A novel model of multi-dataset collaboration for medical image segmentation

计算机科学 图像(数学) 人工智能 分割 图像分割 计算机视觉 模式识别(心理学) 数据挖掘
作者
Manying Lin,Qingling Cai,Jun Zhou
出处
期刊:Neurocomputing [Elsevier BV]
卷期号:492: 530-544 被引量:9
标识
DOI:10.1016/j.neucom.2021.12.045
摘要

• The multi-dataset collaborative network can process different organs or lesions for medical image segmentation at the same time. • The proposed adapter (SSA) can extract specific and common features from multiple classes within a dataset and various datasets. • The proposed adaptive weight update strategy can balance multi-dataset better, which is based on classes instead of voxels. • The dual-branched (DB) structure is more effective than the single one for multi-dataset collaboration. Image segmentation is widely used in the medical field. Convolutional neural network has become more diverse and effective in recent years. However, at present, most networks are designed for a single dataset (i.e., a single organ or target). The designed network is only suitable for a single dataset, and its accuracy is very different (especially small-size image datasets). In response to this problem, a collaborative network can be designed to simultaneously extract the specific and common features of a multi-dataset (i.e., multiple organs or targets). The network can be used for multi-dataset segmentation and help to balance the segmentation performance of different datasets, especially to improve the accuracy of small-size image datasets. By exploring the adapters modified by the convolution kernels, the adaptive weight update strategy and the network branched structure, the paper proposes a multi-dataset collaborative image segmentation network, called Md-Unet, which integrates a shared-specific adapter (SSA), an asymmetric similarity loss function with the proposed adaptive weight update strategy, and a dual-branch. Experimental results showed that compared with the baseline 3D U 2 Net, the accuracy of the module using the SSA was improved by 3.7%, using several loss functions with the proposed adaptive weight update strategy was improved by 0.64%–30.63%, and using dual-branch integrated architecture was improved by 17.47%. Moreover, Md-Unet had a significant improvement on small-size image datasets compared with single-dataset models.
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
blue发布了新的文献求助10
刚刚
刘铭晨完成签到,获得积分10
刚刚
XYZ完成签到 ,获得积分10
1秒前
wmszhd完成签到,获得积分10
1秒前
付艳完成签到,获得积分10
1秒前
CAOHOU应助论文顺利采纳,获得10
2秒前
nancy93228完成签到 ,获得积分10
3秒前
搜集达人应助JW采纳,获得10
5秒前
???完成签到,获得积分10
7秒前
优秀的白曼完成签到,获得积分10
9秒前
王小西发布了新的文献求助10
10秒前
碧蓝莫言完成签到 ,获得积分10
12秒前
清璃完成签到 ,获得积分10
13秒前
虚心的寒梦完成签到,获得积分10
13秒前
秋秋发布了新的文献求助10
13秒前
kkk完成签到,获得积分10
15秒前
bnhh完成签到,获得积分10
15秒前
Betty应助lindahuang采纳,获得10
16秒前
ilk666完成签到,获得积分10
17秒前
小王同学发布了新的文献求助10
17秒前
奶油布丁完成签到,获得积分10
20秒前
酶没美镁完成签到,获得积分10
20秒前
天天快乐应助李治海采纳,获得10
21秒前
星辰大海应助lll采纳,获得10
21秒前
龙1完成签到,获得积分10
21秒前
yzhilson完成签到 ,获得积分10
22秒前
量子星尘发布了新的文献求助10
23秒前
RRR完成签到,获得积分10
24秒前
金色天际线完成签到,获得积分10
25秒前
明ming到此一游完成签到 ,获得积分10
28秒前
pophoo完成签到,获得积分10
28秒前
11发布了新的文献求助10
29秒前
酷炫的黄豆完成签到 ,获得积分10
30秒前
hzz完成签到,获得积分10
33秒前
34秒前
深情安青应助科研通管家采纳,获得10
34秒前
fang应助科研通管家采纳,获得10
34秒前
Passskd发布了新的文献求助10
34秒前
fang应助科研通管家采纳,获得10
34秒前
34秒前
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 4038303
求助须知:如何正确求助?哪些是违规求助? 3576013
关于积分的说明 11374210
捐赠科研通 3305780
什么是DOI,文献DOI怎么找? 1819322
邀请新用户注册赠送积分活动 892672
科研通“疑难数据库(出版商)”最低求助积分说明 815029