亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

SSM-Net: Semi-supervised multi-task network for joint lesion segmentation and classification from pancreatic EUS images

计算机科学 人工智能 模式识别(心理学) 分割
作者
Jiajia Li,Pingping Zhang,Xia Yang,Lei Zhu,Teng Wang,Ping Zhang,Ruhan Liu,Bin Sheng,Kaixuan Wang
出处
期刊:Artificial Intelligence in Medicine [Elsevier BV]
卷期号:154: 102919-102919 被引量:5
标识
DOI:10.1016/j.artmed.2024.102919
摘要

Pancreatic cancer does not show specific symptoms, which makes the diagnosis of early stages difficult with established image-based screening methods and therefore has the worst prognosis among all cancers. Although endoscopic ultrasonography (EUS) has a key role in diagnostic algorithms for pancreatic diseases, B-mode imaging of the pancreas can be affected by confounders such as chronic pancreatitis, which can make both pancreatic lesion segmentation and classification laborious and highly specialized. To address these challenges, this work proposes a semi-supervised multi-task network (SSM-Net) to leverage unlabeled and labeled EUS images for joint pancreatic lesion classification and segmentation. Specifically, we first devise a saliency-aware representation learning module (SRLM) on a large number of unlabeled images to train a feature extraction encoder network for labeled images by computing a contrastive loss with a semantic saliency map, which is obtained by our spectral residual module (SRM). Moreover, for labeled EUS images, we devise channel attention blocks (CABs) to refine the features extracted from the pre-trained encoder on unlabeled images for segmenting lesions, and then devise a merged global attention module (MGAM) and a feature similarity loss (FSL) for obtaining a lesion classification result. We collect a large-scale EUS-based pancreas image dataset (LS-EUSPI) consisting of 9,555 pathologically proven labeled EUS images (499 patients from four categories) and 15,500 unlabeled EUS images. Experimental results on the LS-EUSPI dataset and a public thyroid gland lesion dataset show that our SSM-Net clearly outperforms state-of-the-art methods.
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
在水一方应助scholar丨崔采纳,获得10
6秒前
不能随便完成签到,获得积分10
11秒前
25秒前
碧蓝香芦完成签到 ,获得积分10
29秒前
scholar丨崔发布了新的文献求助10
31秒前
33秒前
33秒前
可爱的函函应助陈苗采纳,获得10
39秒前
北北完成签到 ,获得积分10
44秒前
55秒前
58秒前
Nowind发布了新的文献求助10
1分钟前
三叔发布了新的文献求助10
1分钟前
三叔完成签到,获得积分0
1分钟前
怕孤单的绿柏完成签到,获得积分10
1分钟前
Augustines完成签到,获得积分10
1分钟前
1分钟前
lijunliang完成签到 ,获得积分10
1分钟前
Lucas应助欣喜的以丹采纳,获得10
1分钟前
爱吃煎饼果子的芋圆完成签到 ,获得积分10
1分钟前
1分钟前
小神仙完成签到 ,获得积分10
2分钟前
尊敬夜南发布了新的文献求助10
2分钟前
sss发布了新的文献求助10
2分钟前
123发布了新的文献求助10
2分钟前
科研通AI5应助sss采纳,获得10
2分钟前
2分钟前
章水云发布了新的文献求助10
2分钟前
psyche完成签到,获得积分10
2分钟前
fighting完成签到,获得积分10
2分钟前
小马甲应助sljzhangbiao11采纳,获得10
3分钟前
大模型应助最溜皮大爷采纳,获得10
3分钟前
所所应助喂喂采纳,获得10
3分钟前
5High_0完成签到 ,获得积分10
3分钟前
3分钟前
陈苗发布了新的文献求助10
4分钟前
uuuuu完成签到,获得积分10
4分钟前
优美的谷完成签到,获得积分10
4分钟前
Panini完成签到 ,获得积分10
4分钟前
4分钟前
高分求助中
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
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 3990022
求助须知:如何正确求助?哪些是违规求助? 3532092
关于积分的说明 11256327
捐赠科研通 3270943
什么是DOI,文献DOI怎么找? 1805140
邀请新用户注册赠送积分活动 882270
科研通“疑难数据库(出版商)”最低求助积分说明 809228