Self-immunological disease aid diagnosis with ConvSANet and Eu-clidean distance

化学
作者
Mengge Yang,Jiajia Wang,Xiaoyi Lv,Qiqi Xu,Siyu Quan
出处
期刊:Talanta [Elsevier BV]
卷期号:278: 126426-126426
标识
DOI:10.1016/j.talanta.2024.126426
摘要

Ankylosing spondylitis (AS), Osteoarthritis (OA), and Sjögren's syndrome (SS) are three prevalent autoimmune diseases. If left untreated, which can lead to severe joint damage and greatly limit mobility. Once the disease worsens, patients may face the risk of long-term disability, and in severe cases, even life-threatening consequences. In this study, the Raman spectral data of AS, OA, and SS are analyzed to auxiliary disease diagnosis. For the first time, the Euclidean distance(ED) upscaling technique was used for the conversation from one-dimensional(1D) disease spectral data to two-dimensional(2D) spectral images. A dual-attention mechanism network was then constructed to analyze these two-dimensional spectral maps for disease diagnosis. The results demonstrate that the dual-attention mechanism network achieves a diagnostic accuracy of 100 % when analyzing 2D ED spectrograms. Furthermore, a comparison and analysis with s-transforms(ST), short-time fourier transforms(STFT), recurrence maps(RP), markov transform field(MTF), and Gramian angle fields(GAF) highlight the significant advantage of the proposed method, as it significantly shortens the conversion time while supporting disease-assisted diagnosis. Mutual information(MI) was utilized for the first time to validate the 2D Raman spectrograms generated, including ED, ST, STFT, RP, MTF, and GAF spectrograms. This allowed for evaluation of the similarity between the original 1D spectral data and the generated 2D spectrograms. The results indicate that utilizing ED to transform 1D spectral data into 2D images, coupled with the application of convolutional neural network(CNN) for analyzing 2D ED Raman spectrograms, holds great promise as a valuable tool in assisting disease diagnosis. The research demonstrated that the 2D spectrogram created with ED closely resembles the original 1D spectral data. This indicates that ED effectively captures key features and important information from the original data, providing a strong descript.
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
CodeCraft应助Dr Monkey采纳,获得10
刚刚
smottom应助奋斗的珍采纳,获得20
1秒前
Chong123_关注了科研通微信公众号
1秒前
六六发布了新的文献求助10
3秒前
张勇振完成签到,获得积分10
3秒前
GQL完成签到,获得积分10
3秒前
搜集达人应助俊逸的代曼采纳,获得10
3秒前
海东来应助南瓜气气采纳,获得30
6秒前
西西完成签到 ,获得积分10
6秒前
酷波er应助GQL采纳,获得10
7秒前
tramp应助liu采纳,获得20
7秒前
8秒前
8秒前
9秒前
9秒前
12秒前
英姑应助开心的曼岚采纳,获得10
12秒前
13秒前
缥缈丹云发布了新的文献求助10
13秒前
14秒前
东方清婳发布了新的文献求助10
15秒前
15秒前
15秒前
opalc发布了新的文献求助10
15秒前
科研通AI2S应助dejiangcj采纳,获得10
16秒前
SciGPT应助平安顺遂采纳,获得10
16秒前
orixero应助嬛嬛采纳,获得10
18秒前
坚果发布了新的文献求助10
18秒前
天天快乐应助1027采纳,获得10
19秒前
benbenx发布了新的文献求助10
19秒前
chenting发布了新的文献求助10
19秒前
东方清婳完成签到,获得积分10
21秒前
21秒前
明明完成签到,获得积分10
22秒前
丘比特应助liyiliyi117采纳,获得10
24秒前
syh完成签到,获得积分10
24秒前
ZWK发布了新的文献求助10
24秒前
24秒前
25秒前
26秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 360
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 3971424
求助须知:如何正确求助?哪些是违规求助? 3516157
关于积分的说明 11181063
捐赠科研通 3251297
什么是DOI,文献DOI怎么找? 1795776
邀请新用户注册赠送积分活动 876012
科研通“疑难数据库(出版商)”最低求助积分说明 805228