A Rectal CT Tumor Segmentation Method Based on Improved U-Net

作者
Haowei Dong,Haifei Zhang,Fang Wu,Jianlin Qiu,Jian Zhang,Haoyu Wang
出处
期刊:International Journal of Pattern Recognition and Artificial Intelligence [World Scientific]
卷期号:36 (04) 被引量:3
标识
DOI:10.1142/s0218001422500069
摘要

Automatic and accurate segmentation of tumor area from rectal CT image plays an extremely key role in the treatment and diagnosis of rectal cancer. This paper proposes the MR-U-Net network model. The improvement is that a pair of encoder and decoder is added longitudinally to the U-shaped structure, which is the network structure of the fifth layer, and a residual module is added horizontally to the encoder and decoder of each layer. This model is used to conduct targeted research on the automatic segmentation method of rectal cancer. [H. Gao et al., Rectal tumor segmentation method based on U-Net improved model, J. Comput. Appl.40(8) (2020) 2392–2397] also improved U-Net and used the same dataset as this paper, but the Dice coefficient of all targets was only 83.15%, and the Dice coefficient of small targets was only 87.17%. This paper evaluates the improved MR-U-Net network model with the three indicators of precision, recall and Dice coefficient, and finds that in comparison to Ref. 4 the precision is 95.13%, 2.29% higher than the former work, recall is 94.28%, higher than the former work by 0.34%, Dice coefficient of all targets is 88.45%, increased by 5.3% compared with the former work, and the small targets Dice coefficient is increased by 1.28%, which is the best optimization state of this paper. Experiments show that for datasets with extremely skewed positive and negative samples, the MR-U-Net network structure after improving the hyperparameters in the optimizer can more accurately segment the rectal CT tumor lesion area.

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
MiaCong完成签到,获得积分10
刚刚
歪比巴卜好龙完成签到,获得积分10
刚刚
一天一天发布了新的文献求助10
刚刚
orixero的应助被elmo采纳,获得10
刚刚
dit发布了新的文献求助10
1秒前
难得一佳人完成签到,获得积分10
1秒前
天明完成签到,获得积分10
2秒前
威武苑睐发布了新的文献求助10
2秒前
学术智子发布了新的文献求助10
2秒前
2秒前
2秒前
搜集达人的应助被韭菜盒子采纳,获得10
3秒前
3秒前
双儿完成签到,获得积分10
3秒前
大河同志完成签到,获得积分20
3秒前
汪明晶完成签到,获得积分10
4秒前
4秒前
4秒前
害羞的XM完成签到,获得积分10
4秒前
1101592875的应助被WYL采纳,获得10
4秒前
5秒前
why发布了新的文献求助10
6秒前
双儿发布了新的文献求助10
6秒前
邓少军完成签到,获得积分10
6秒前
yn107发布了新的文献求助30
6秒前
普洛望斯完成签到,获得积分10
7秒前
呆萌的晓槐完成签到,获得积分20
7秒前
JeaZ完成签到,获得积分10
7秒前
8秒前
爱猫的纭发布了新的文献求助10
9秒前
gooooood完成签到 ,获得积分10
10秒前
10秒前
huang发布了新的文献求助10
10秒前
11秒前
ding的应助被饺子采纳,获得10
12秒前
13秒前
HP完成签到 ,获得积分10
13秒前
咕噜咕噜完成签到,获得积分10
14秒前
ccc完成签到,获得积分10
14秒前
14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
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 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 8187652
求助须知:如何正确求助?哪些是违规求助? 9575758
关于积分的说明 21842805
捐赠科研通 7785538
什么是DOI,文献DOI怎么找? 3435073
关于科研通互助平台的介绍 2559480
邀请新用户注册赠送积分活动 2481963