Probability Map-Guided Network for 3D Volumetric Medical Image Segmentation

人工智能 计算机科学 计算机视觉 模式识别(心理学) 图像分割 分割 特征(语言学) 阈值 光学(聚焦) 编码(内存) 概率分布 医学影像学 失真(音乐) 尺度空间分割 迭代重建 图像处理 图像(数学) 特征提取 职位(财务) 噪音(视频) 范围分割 人工神经网络 可靠性(半导体) 图像复原 基于分割的对象分类 概率密度函数 图像纹理 先验概率
作者
Zhiqin Zhu,Zimeng Zhang,Guanqiu Qi,Yuanyuan Li,Pan Yang,Yu Liu
出处
期刊:IEEE transactions on image processing [Institute of Electrical and Electronics Engineers]
卷期号:34: 7222-7234 被引量:8
标识
DOI:10.1109/tip.2025.3623259
摘要

3D medical images are volumetric data that provide spatial continuity and multi-dimensional information. These features provide rich anatomical context. However, their anisotropy may result in reduced image detail along certain directions. This can cause blurring or distortion between slices. In addition, global or local intensity inhomogeneities are often observed. This may be due to limitations of the imaging equipment, inappropriate scanning parameters, or variations in the patient's anatomy. This inhomogeneity may blur lesion boundaries and may also mask true features, causing the model to focus on irrelevant regions. Therefore, a probability map-guided network for 3D volumetric medical image segmentation (3D-PMGNet) is proposed. The probability maps generated from the intermediate features are used as supervisory signals to guide the segmentation process. A new probability map reconstruction method is designed, combining dynamic thresholding with local adaptive smoothing. This enhances the reliability of high-response regions while suppressing low-response noise. A learnable channel-wise temperature coefficient is introduced to adjust the probability distribution to make it closer to the true distribution; in addition, a feature fusion method based on dynamic prompt encoding is developed. The response strength of the main feature maps is dynamically adjusted, and this adjustment is achieved through the spatial position encoding derived from the probability maps. The proposed method has been evaluated on four datasets. Experimental results show that the proposed method outperforms state-of-the-art 3D medical image segmentation methods. The source codes have been publicly released at https://github.com/ZHANGZIMENG01/3D-PMGNet.
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
山楂完成签到,获得积分10
刚刚
1秒前
小李发布了新的文献求助10
1秒前
桃桃子完成签到,获得积分10
1秒前
1秒前
2秒前
伶俐一曲发布了新的文献求助10
2秒前
情怀应助心灵美盼烟采纳,获得10
2秒前
直率的花生完成签到,获得积分10
2秒前
2秒前
狂野的梦之完成签到,获得积分10
2秒前
快乐爱斯米完成签到,获得积分10
2秒前
123木头人完成签到,获得积分10
3秒前
领导范儿应助LM采纳,获得10
3秒前
4秒前
4秒前
Caterinaaa完成签到,获得积分10
4秒前
6秒前
丞丞汁儿发布了新的文献求助10
6秒前
6秒前
alex发布了新的文献求助10
7秒前
Alicia完成签到,获得积分10
7秒前
Beta发布了新的文献求助10
7秒前
Rong完成签到,获得积分20
9秒前
xuyun完成签到,获得积分10
10秒前
11发布了新的文献求助10
10秒前
酷波er应助aunsty采纳,获得10
11秒前
shiyongkang1完成签到,获得积分10
11秒前
eghiefefe完成签到,获得积分10
11秒前
伶俐一曲完成签到,获得积分10
11秒前
12秒前
liuliu完成签到,获得积分10
12秒前
12秒前
啊管今天吃什么完成签到,获得积分10
12秒前
14秒前
熊熊阁发布了新的文献求助30
14秒前
FashionBoy应助ZYL采纳,获得10
14秒前
英格兰胖头鱼完成签到,获得积分10
14秒前
ac完成签到,获得积分10
14秒前
沉静灵枫完成签到,获得积分10
15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
Les Mantodea de Guyane Insecta, Polyneoptera 2000
Quality by Design - An Indispensable Approach to Accelerate Biopharmaceutical Product Development 800
Pulse width control of a 3-phase inverter with non sinusoidal phase voltages 777
Signals, Systems, and Signal Processing 610
Research Methods for Applied Linguistics: A Practical Guide 600
Research Methods for Applied Linguistics 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 工程类 有机化学 化学工程 生物化学 计算机科学 物理 内科学 复合材料 催化作用 物理化学 光电子学 电极 细胞生物学 基因 无机化学
热门帖子
关注 科研通微信公众号,转发送积分 6405937
求助须知:如何正确求助?哪些是违规求助? 8225159
关于积分的说明 17439640
捐赠科研通 5458395
什么是DOI,文献DOI怎么找? 2884282
邀请新用户注册赠送积分活动 1860639
关于科研通互助平台的介绍 1701663