Shape-margin knowledge augmented network for thyroid nodule segmentation and diagnosis

边距(机器学习) 结核(地质) 分割 计算机科学 可解释性 特征(语言学) 人工智能 判别式 计算机辅助诊断 甲状腺 特征提取 甲状腺结节 图像分割 模式识别(心理学) 医学 机器学习 内科学 古生物学 生物 哲学 语言学
作者
Weihua Liu,Chaochao Lin,Duanduan Chen,Lijuan Niu,Rui Zhang,Z.P. Pi
出处
期刊:Computer Methods and Programs in Biomedicine [Elsevier BV]
卷期号:244: 107999-107999 被引量:4
标识
DOI:10.1016/j.cmpb.2023.107999
摘要

Thyroid nodule segmentation is a crucial step in the diagnostic procedure of physicians and computer-aided diagnosis systems. However, prevailing studies often treat segmentation and diagnosis as independent tasks, overlooking the intrinsic relationship between these processes. The sequencial steps of these independent tasks in computer-aided diagnosis systems may lead to the accumulation of errors. Therefore, it is worth combining them as a whole by exploring the relationship between thyroid nodule segmentation and diagnosis. According to the diagnostic procedure of thyroid imaging reporting and data system (TI-RADS), the assessment of shape and margin characteristics is the prerequisite for radiologists to discriminate benign and malignant thyroid nodules. Inspired by TI-RADS, this study aims to integrate these tasks into a cohesive process, leveraging the insights from TI-RADS, thereby enhancing the accuracy and interpretability of thyroid nodule analysis. Specifically, this paper proposes a shape-margin knowledge augmented network (SkaNet) for simultaneous thyroid nodule segmentation and diagnosis. Due to the visual feature similarities between segmentation and diagnosis, SkaNet shares visual features in the feature extraction stage and then utilizes a dual-branch architecture to perform thyroid nodule segmentation and diagnosis tasks respectively. In the shared feature extraction, the combination of convolutional feature maps and self-attention maps allows to exploitation of both local information and global patterns in thyroid nodule images. To enhance effective discriminative features, an exponential mixture module is introduced, combining convolutional feature maps and self-attention maps through exponential weighting. Then, SkaNet is jointly optimized by a knowledge augmented multi-task loss function with a constraint penalty term. The constraint penalty term embeds shape and margin characteristics through numerical computations, establishing a vital relationship between thyroid nodule diagnosis results and segmentation masks. We evaluate the proposed approach on a public thyroid ultrasound dataset (DDTI) and a locally collected thyroid ultrasound dataset. The experimental results reveal the value of our contributions and demonstrate that our approach can yield significant improvements compared with state-of-the-art counterparts. SkaNet highlights the potential of combining thyroid nodule segmentation and diagnosis with knowledge augmented learning into a unified framework, which captures the key shape and margin characteristics for discriminating benign and malignant thyroid nodules. Our findings suggest promising insights for advancing computer-aided diagnosis joint with 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
1秒前
种花兔完成签到,获得积分10
1秒前
可爱的函函应助陌路孤星采纳,获得10
1秒前
李健的小迷弟应助sunly采纳,获得10
2秒前
R_完成签到 ,获得积分10
2秒前
虚幻惜筠完成签到,获得积分10
2秒前
3秒前
李健的小迷弟应助阳光BOY采纳,获得10
3秒前
run完成签到,获得积分10
4秒前
4秒前
manman发布了新的文献求助10
4秒前
4秒前
易琚发布了新的文献求助10
5秒前
6秒前
6秒前
Si完成签到,获得积分10
7秒前
辻辰发布了新的文献求助20
8秒前
8秒前
9秒前
10秒前
简墨完成签到,获得积分10
10秒前
思源应助小池采纳,获得10
11秒前
迟迟发布了新的文献求助10
12秒前
12秒前
武大西门发布了新的文献求助10
13秒前
丫丫完成签到,获得积分10
13秒前
lzx完成签到,获得积分10
14秒前
浅月影梦发布了新的文献求助10
15秒前
英姑应助十点睡六点起采纳,获得10
15秒前
15秒前
16秒前
仙魔洞完成签到,获得积分10
17秒前
17秒前
都可以完成签到,获得积分10
17秒前
yier发布了新的文献求助10
18秒前
英姑应助陌路孤星采纳,获得10
18秒前
和国彪完成签到,获得积分20
18秒前
18秒前
naomi发布了新的文献求助30
19秒前
caiia发布了新的文献求助10
20秒前
高分求助中
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
Effective Learning and Mental Wellbeing 300
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 3974358
求助须知:如何正确求助?哪些是违规求助? 3518706
关于积分的说明 11195521
捐赠科研通 3254897
什么是DOI,文献DOI怎么找? 1797614
邀请新用户注册赠送积分活动 877011
科研通“疑难数据库(出版商)”最低求助积分说明 806128