Prediction of Recurrence using a Stacked Denoising Autoencoder and Multifaceted Feature Analysis of Pretreatment MRI in Patients with Nasopharyngeal Carcinoma.

IF 1.2 4区 医学 Q3 PHARMACOLOGY & PHARMACY
Yibin Liu, Xianwen Wang, Jiongyi Li, Junxiao Gao, Bin He, Xianlong Wang, Lianfang Tian, Bin Li, Qianhui Qiu
{"title":"Prediction of Recurrence using a Stacked Denoising Autoencoder and Multifaceted Feature Analysis of Pretreatment MRI in Patients with Nasopharyngeal Carcinoma.","authors":"Yibin Liu, Xianwen Wang, Jiongyi Li, Junxiao Gao, Bin He, Xianlong Wang, Lianfang Tian, Bin Li, Qianhui Qiu","doi":"10.2174/0118744710384129250327060846","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>Nasopharyngeal Carcinoma (NPC) exhibits high incidence in southern China. Despite improved survival with intensity-modulated radiotherapy (IMRT), 10%-20% of patients experience local recurrence. Traditional TNM staging fails to reflect tumor heterogeneity, necessitating robust recurrence prediction models. This study aimed to develop an MRIbased NPC recurrence prediction model by integrating radiomics, deep learning, and clinical features.</p><p><strong>Methods: </strong>A total of 184 pathologically confirmed NPC patients receiving radical radiotherapy were included. After propensity score matching (1:1), 136 cases were analyzed. Stacked denoising autoencoder (SDAE) extracted deep features from contrast-enhanced T1-weighted MRI. Radiomic features (morphology, texture, first-order statistics), clinical parameters (gender, age, TNM stage), and SDAE features were combined to construct 12 models using SVM, MLP, logistic regression (LR), and random forest (RF). Performance was evaluated via AUC, accuracy, sensitivity, and specificity, with external validation (91 cases).</p><p><strong>Results: </strong>Model 1 (radiomics + SDAE + clinical features + SVM) achieved the highest AUC (0.89, 95% CI: 0.84-0.93), accuracy (81.5%), sensitivity (67.3%), and specificity (97.9%). External validation showed AUC 0.83, sensitivity 88.9%, and specificity 78%. The DeLong test confirmed no significant AUC difference between internal and external cohorts (P >0.05).</p><p><strong>Discussion: </strong>The fusion of SDAE-enhanced features outperformed traditional radiomics. SVM demonstrated optimal performance in small samples, likely due to its high-dimensional feature handling and anti-overfitting capability. Limitations include single-center retrospective design and lack of functional imaging (DWI/PET) or molecular markers (EBV-DNA). Future multicenter prospective studies and multimodal data integration are warranted to enhance biological interpretability and clinical utility.</p><p><strong>Conclusion: </strong>This model provides a tool for early recurrence risk stratification and personalized therapy optimization, advancing precision medicine in NPC management.</p>","PeriodicalId":10991,"journal":{"name":"Current radiopharmaceuticals","volume":" ","pages":"224-243"},"PeriodicalIF":1.2000,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Current radiopharmaceuticals","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.2174/0118744710384129250327060846","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"PHARMACOLOGY & PHARMACY","Score":null,"Total":0}
引用次数: 0

Abstract

Introduction: Nasopharyngeal Carcinoma (NPC) exhibits high incidence in southern China. Despite improved survival with intensity-modulated radiotherapy (IMRT), 10%-20% of patients experience local recurrence. Traditional TNM staging fails to reflect tumor heterogeneity, necessitating robust recurrence prediction models. This study aimed to develop an MRIbased NPC recurrence prediction model by integrating radiomics, deep learning, and clinical features.

Methods: A total of 184 pathologically confirmed NPC patients receiving radical radiotherapy were included. After propensity score matching (1:1), 136 cases were analyzed. Stacked denoising autoencoder (SDAE) extracted deep features from contrast-enhanced T1-weighted MRI. Radiomic features (morphology, texture, first-order statistics), clinical parameters (gender, age, TNM stage), and SDAE features were combined to construct 12 models using SVM, MLP, logistic regression (LR), and random forest (RF). Performance was evaluated via AUC, accuracy, sensitivity, and specificity, with external validation (91 cases).

Results: Model 1 (radiomics + SDAE + clinical features + SVM) achieved the highest AUC (0.89, 95% CI: 0.84-0.93), accuracy (81.5%), sensitivity (67.3%), and specificity (97.9%). External validation showed AUC 0.83, sensitivity 88.9%, and specificity 78%. The DeLong test confirmed no significant AUC difference between internal and external cohorts (P >0.05).

Discussion: The fusion of SDAE-enhanced features outperformed traditional radiomics. SVM demonstrated optimal performance in small samples, likely due to its high-dimensional feature handling and anti-overfitting capability. Limitations include single-center retrospective design and lack of functional imaging (DWI/PET) or molecular markers (EBV-DNA). Future multicenter prospective studies and multimodal data integration are warranted to enhance biological interpretability and clinical utility.

Conclusion: This model provides a tool for early recurrence risk stratification and personalized therapy optimization, advancing precision medicine in NPC management.

应用叠置去噪自编码器预测鼻咽癌患者复发及预处理MRI多面特征分析。
背景:预测鼻咽癌复发的策略有待进一步发展和验证。我们基于鼻咽癌(NPC)患者治疗前常规磁共振序列(CE-T1W)的多组学特征融合建立了复发预测模型,用于预测治疗后复发。方法:采用深度无监督堆叠去噪自编码器(stacked denoising autoencoder, SDAE)和多组学特征融合方法建立鼻咽癌复发预测模型。本文收集184例经病理证实并接受根治性综合治疗的新诊断鼻咽癌(NPC)患者的资料和磁共振图像。采用倾向评分匹配(复发:无复发= 1:1)来平衡可能影响复发的临床因素,匹配病例136例。利用SDAE提取深度特征,结合放射组学(radiomics)特征与临床特征的融合特征,采用支持向量机(SVM)、多层感知器(MLP)、逻辑回归(LR)和随机森林(RF)机器学习方法构建模型。比较各模型的平均曲线下面积(AUC)、准确性、敏感性和特异性,评价其预测复发的效果。结果:经过参数调整,建立了12个基于不同融合特征的机器学习模型。模型1 (Radiomics+AutoEncoder+Clinical+SVM)的预测效果更好,平均AUC、准确率、灵敏度和特异性分别为0.89 (95% CI: 0.84- 0.93)、81.5%、67.3%和97.9%。模型2 (Radiomics + AutoEncoder +支持向量机),3 (Radiomics + SVM)模型,模型4 (Radiomics + AutoEncoder +临床+ MLP),模型5 (Radiomics +汽车编码器+ MLP), 6 (Radiomics + MLP)模型,模型7 (Radiomics + AutoEncoder +临床+ LR)模型8 (Radiomics + AutoEncoder + LR), 9 (Radiomics + LR)模型,模型10 (Radiomics +汽车编码器+临床+ RF), 11 (Radiomics + AutoEncoder + RF)模型,模型12 (Radiomics + RF)实现了auc的0.87,0.87,0.82,0.80,0.82,0.82,0.78,0.80,0.81,0.80,和0.82,分别。结论:基于鼻咽癌患者治疗前CE-T1WI建立的放射组学+autoEncoder+临床融合特征预测鼻咽癌复发的SVM模型具有较好的预测效果,且较为可靠,可为临床诊疗决策和干预提供更多信息和帮助。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Current radiopharmaceuticals
Current radiopharmaceuticals PHARMACOLOGY & PHARMACY-
CiteScore
3.20
自引率
4.30%
发文量
43
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信