WET-UNet: Wavelet integrated efficient transformer networks for nasopharyngeal carcinoma tumor segmentation

分割 计算机科学 人工智能 编码器 深度学习 图像分割 小波变换 小波 模式识别(心理学) 操作系统
作者
Yan Zeng,Jun Li,Zhe Zhao,Wei Liang,Penghui Zeng,Shao‐Dong Shen,Kun Zhang,Chong Shen
出处
期刊:Science Progress [SAGE Publishing]
卷期号:107 (2) 被引量:1
标识
DOI:10.1177/00368504241232537
摘要

Nasopharyngeal carcinoma is a malignant tumor that occurs in the epithelium and mucosal glands of the nasopharynx, and its pathological type is mostly poorly differentiated squamous cell carcinoma. Since the nasopharynx is located deep in the head and neck, early diagnosis and timely treatment are critical to patient survival. However, nasopharyngeal carcinoma tumors are small in size and vary widely in shape, and it is also a challenge for experienced doctors to delineate tumor contours. In addition, due to the special location of nasopharyngeal carcinoma, complex treatments such as radiotherapy or surgical resection are often required, so accurate pathological diagnosis is also very important for the selection of treatment options. However, the current deep learning segmentation model faces the problems of inaccurate segmentation and unstable segmentation process, which are mainly limited by the accuracy of data sets, fuzzy boundaries, and complex lines. In order to solve these two challenges, this article proposes a hybrid model WET-UNet based on the UNet network as a powerful alternative for nasopharyngeal cancer image segmentation. On the one hand, wavelet transform is integrated into UNet to enhance the lesion boundary information by using low-frequency components to adjust the encoder at low frequencies and optimize the subsequent computational process of the Transformer to improve the accuracy and robustness of image segmentation. On the other hand, the attention mechanism retains the most valuable pixels in the image for us, captures the remote dependencies, and enables the network to learn more representative features to improve the recognition ability of the model. Comparative experiments show that our network structure outperforms other models for nasopharyngeal cancer image segmentation, and we demonstrate the effectiveness of adding two modules to help tumor segmentation. The total data set of this article is 5000, and the ratio of training and verification is 8:2. In the experiment, accuracy = 85.2% and precision = 84.9% can show that our proposed model has good performance in nasopharyngeal cancer image 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
net80yhm发布了新的文献求助10
1秒前
NCU-Xzzzz完成签到,获得积分10
1秒前
拼搏一曲完成签到 ,获得积分10
2秒前
荒野风发布了新的文献求助10
2秒前
轻松的鸿煊完成签到 ,获得积分10
3秒前
NCU-Xzzzz发布了新的文献求助10
3秒前
5秒前
JJG完成签到,获得积分20
6秒前
Hello应助Tiam采纳,获得10
7秒前
7秒前
ty完成签到,获得积分10
9秒前
zehua309完成签到,获得积分10
10秒前
火星上含芙完成签到 ,获得积分10
11秒前
量子星尘发布了新的文献求助10
13秒前
13秒前
掌门发布了新的文献求助10
13秒前
愉快的花卷完成签到,获得积分10
13秒前
少言完成签到,获得积分10
15秒前
kiko完成签到,获得积分10
16秒前
隐形惜筠完成签到 ,获得积分10
18秒前
黑眼圈完成签到,获得积分10
22秒前
123发布了新的文献求助10
24秒前
25秒前
26秒前
又又妈妈完成签到,获得积分10
26秒前
欢呼的丁真完成签到,获得积分10
27秒前
ty发布了新的文献求助10
27秒前
Faded完成签到 ,获得积分10
28秒前
ding应助Amorfati采纳,获得10
28秒前
好好学习天天向上完成签到,获得积分10
29秒前
所所应助lh采纳,获得10
30秒前
李爱国应助深情丸子采纳,获得10
30秒前
烟花应助阿湫采纳,获得10
30秒前
30秒前
乌梅不乌发布了新的文献求助10
31秒前
31秒前
YY完成签到,获得积分10
32秒前
33秒前
33秒前
Tiam发布了新的文献求助10
33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
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
Research on Disturbance Rejection Control Algorithm for Aerial Operation Robots 500
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 4038524
求助须知:如何正确求助?哪些是违规求助? 3576221
关于积分的说明 11374737
捐赠科研通 3305912
什么是DOI,文献DOI怎么找? 1819354
邀请新用户注册赠送积分活动 892688
科研通“疑难数据库(出版商)”最低求助积分说明 815048