Weakly-Interactive-Mixed Learning: Less Labelling Cost for Better Medical Image Segmentation

计算机科学 过度拟合 分割 注释 人工智能 任务(项目管理) 机器学习 图像分割 监督学习 图像自动标注 尺度空间分割 模式识别(心理学) 图像检索 图像(数学) 人工神经网络 管理 经济
作者
Xiuping Nie,Lilu Liu,Lifeng He,Liang Zhao,Haojian Lu,Songmei Lou,Rong Xiong,Yue Wang
出处
期刊:IEEE Journal of Biomedical and Health Informatics [Institute of Electrical and Electronics Engineers]
卷期号:27 (7): 3270-3281 被引量:6
标识
DOI:10.1109/jbhi.2023.3268157
摘要

Common medical image segmentation tasks require large training datasets with pixel-level annotations which are very expensive and time-consuming to prepare. To overcome such limitation and achieve the desired segmentation accuracy, a novel Weakly-Interactive-Mixed Learning (WIML) framework is proposed by efficiently using weak labels. On one hand, utilize weak labels to reduce annotation time for high-quality strong labels by designing a Weakly-Interactive Annotation (WIA) part of the WIML which prudently introduces interactive learning into the weakly-supervised segmentation strategy. On the other hand, utilize weak labels and very few strong labels to achieve desired segmentation accuracy by designing a Mixed-Supervised Learning (MSL) part of the WIML which can boost the segmentation accuracy by providing strong prior knowledge during training. Besides, a multi-task Full-Parameter-Sharing Network (FPSNet) is proposed to better implement this framework. Specifically, to further reduce annotation time, attention modules (scSE) are integrated into FPSNet to improve the class activation map (CAM) performance for the first time. To further improve segmentation accuracy, a Full-Parameter-Sharing (FPS) strategy is designed in FPSNet to alleviate the overfitting of the segmentation task supervised by very few strong labels. The proposed method is validated on the BraTS 2019 and LiTS 2017 datasets, and experiments demonstrate that the proposed method WIML-FPSNet outperforms several state-of-the-art segmentation methods with minimal annotation efforts.
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
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
自律完成签到 ,获得积分10
刚刚
刚刚
orixero的应助被GXL采纳,获得10
1秒前
1秒前
Owen的应助被王小乙采纳,获得10
1秒前
王ww完成签到,获得积分10
1秒前
2秒前
3秒前
ding的应助被Tiko采纳,获得10
3秒前
失眠的新之完成签到,获得积分10
3秒前
abc1122完成签到,获得积分10
3秒前
4秒前
4秒前
6秒前
好运buff发布了新的文献求助30
6秒前
freshfire发布了新的文献求助30
6秒前
Gates发布了新的文献求助10
7秒前
锄訫完成签到 ,获得积分10
7秒前
7秒前
深情安青的应助被dongxu采纳,获得10
7秒前
8秒前
linhongwei完成签到,获得积分10
8秒前
REALLY完成签到 ,获得积分10
8秒前
jinrui关注了科研通微信公众号
8秒前
Ava的应助被12233采纳,获得10
9秒前
9秒前
夏果完成签到,获得积分20
9秒前
LEETHEO发布了新的文献求助10
10秒前
研友_VZG7GZ的应助被小茗同学采纳,获得30
10秒前
12秒前
12秒前
肖赵峰完成签到,获得积分20
14秒前
biancaliu发布了新的文献求助10
14秒前
ding的应助被cen采纳,获得10
14秒前
14秒前
chenheng完成签到,获得积分10
16秒前
16秒前
17秒前
WangDongdong发布了新的文献求助10
17秒前
18秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183423
求助须知:如何正确求助?哪些是违规求助? 9572834
关于积分的说明 21827410
捐赠科研通 7780522
什么是DOI,文献DOI怎么找? 3434016
关于科研通互助平台的介绍 2558189
邀请新用户注册赠送积分活动 2480357