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