Tumor segmentation via enhanced area growth algorithm for lung CT images

阈值 计算机科学 分割 边界(拓扑) 区域增长 算法 点(几何) 人工智能 肺肿瘤 计算机视觉 图像分割 肺癌 数学 图像(数学) 几何学 医学 尺度空间分割 内科学 数学分析
作者
Abdollah Khorshidi
出处
期刊:BMC Medical Imaging [BioMed Central]
卷期号:23 (1) 被引量:3
标识
DOI:10.1186/s12880-023-01126-y
摘要

Abstract Background Since lung tumors are in dynamic conditions, the study of tumor growth and its changes is of great importance in primary diagnosis. Methods Enhanced area growth (EAG) algorithm is introduced to segment the lung tumor in 2D and 3D modes on 60 patients CT images from four different databases by MATLAB software. The contrast augmentation, color intensity and maximum primary tumor radius determination, thresholding, start and neighbor points’ designation in an array, and then modifying the points in the braid on average are the early steps of the proposed algorithm. To determine the new tumor boundaries, the maximum distance from the color-intensity center point of the primary tumor to the modified points is appointed via considering a larger target region and new threshold. The tumor center is divided into different subsections and then all previous stages are repeated from new designated points to define diverse boundaries for the tumor. An interpolation between these boundaries creates a new tumor boundary. The intersections with the tumor boundaries are firmed for edge correction phase, after drawing diverse lines from the tumor center at relevant angles. Each of the new regions is annexed to the core region to achieve a segmented tumor surface by meeting certain conditions. Results The multipoint-growth-starting-point grouping fashioned a desired consequence in the precise delineation of the tumor. The proposed algorithm enhanced tumor identification by more than 16% with a reasonable accuracy acceptance rate. At the same time, it largely assurances the independence of the last outcome from the starting point. By significance difference of p < 0.05, the dice coefficients were 0.80 ± 0.02 and 0.92 ± 0.03, respectively, for primary and enhanced algorithms. Lung area determination alongside automatic thresholding and also starting from several points along with edge improvement may reduce human errors in radiologists’ interpretation of tumor areas and selection of the algorithm’s starting point. Conclusions The proposed algorithm enhanced tumor detection by more than 18% with a sufficient acceptance ratio of accuracy. Since the enhanced algorithm is independent of matrix size and image thickness, it is very likely that it can be easily applied to other contiguous tumor images. Trial registration PAZHOUHAN, PAZHOUHAN98000032. Registered 4 January 2021, http://pazhouhan.gerums.ac.ir/webreclist/view.action?webreclist_code=19300

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
hey754完成签到,获得积分10
5秒前
震动的念波完成签到 ,获得积分10
7秒前
超越俗尘完成签到,获得积分10
13秒前
不安分的心完成签到,获得积分20
13秒前
15秒前
16秒前
21秒前
老实的黑米完成签到 ,获得积分10
22秒前
晶aaaaa完成签到 ,获得积分10
22秒前
163完成签到 ,获得积分10
25秒前
Jaxon完成签到,获得积分10
26秒前
WUYISONG完成签到,获得积分10
26秒前
竹舍翁暮雨君完成签到 ,获得积分10
32秒前
马伯乐完成签到 ,获得积分10
35秒前
Luu完成签到 ,获得积分10
35秒前
轻松香菇完成签到 ,获得积分10
35秒前
读行千万完成签到,获得积分10
38秒前
琯柠完成签到 ,获得积分10
39秒前
夏曦浣完成签到 ,获得积分10
42秒前
桃花扇完成签到,获得积分10
43秒前
Chief完成签到,获得积分0
43秒前
ZaZa完成签到,获得积分10
43秒前
话说dota完成签到 ,获得积分10
45秒前
她的城完成签到,获得积分0
49秒前
sun完成签到 ,获得积分10
53秒前
鲁卓林完成签到,获得积分10
57秒前
CBX完成签到 ,获得积分10
1分钟前
顾矜的应助被Vincent采纳,获得10
1分钟前
清新的乌冬面完成签到 ,获得积分10
1分钟前
liao_duoduo完成签到 ,获得积分10
1分钟前
xue112完成签到 ,获得积分0
1分钟前
在水一方的应助被Vincent采纳,获得10
1分钟前
今天开心吗完成签到 ,获得积分10
1分钟前
木偶完成签到 ,获得积分10
1分钟前
睡不醒的Sean完成签到 ,获得积分10
1分钟前
英姑的应助被Vincent采纳,获得10
1分钟前
鹿小新完成签到 ,获得积分0
1分钟前
勤奋的白桃完成签到 ,获得积分10
1分钟前
qieshuidao完成签到,获得积分10
1分钟前
H梦完成签到 ,获得积分10
1分钟前
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 2000
Sex, Aging, and Death in a Medieval Medical Compendium: Trinity College Cambridge MS R.14.52, Its Texts, Language, and Scribe 500
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
基于结构调控的功能化水诱导发电材料与器件研究 500
基于界面调控的高效湿气发电材料与器件研究 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 8190366
求助须知:如何正确求助?哪些是违规求助? 9577455
关于积分的说明 21852543
捐赠科研通 7789004
什么是DOI,文献DOI怎么找? 3436331
关于科研通互助平台的介绍 2560154
邀请新用户注册赠送积分活动 2482995