A prognostic and predictive model based on deep learning to identify optimal candidates for intensity-modulated radiotherapy alone in patients with stage II nasopharyngeal carcinoma: A retrospective multicenter study DOI
Jiong-Lin Liang,

Yue-Feng Wen,

Ying‐Ping Huang

et al.

Radiotherapy and Oncology, Journal Year: 2024, Volume and Issue: 203, P. 110660 - 110660

Published: Dec. 5, 2024

Language: Английский

Retrospective analysis of 1539 nasopharyngeal carcinoma cases: chemotherapy should not be excluded for non-Asian patients with T1-2N1M0 stage DOI Creative Commons
Xinyu Li, Chong Zhong,

Hui-Xian Xu

et al.

Frontiers in Oncology, Journal Year: 2025, Volume and Issue: 14

Published: Jan. 17, 2025

Many results suggested that chemotherapy cannot provide survival benefit for stage II nasopharyngeal carcinoma. It remained unclear whether the efficacy of differed in non-Asian populations. was designed to analyze effect Asian and patients with Patients were collected using SEER program. The variables included age, sex, race, marital status, time, TNM stage, radiation chemotherapy. Utilizing Rstudio (version: 2024.4.1.748) R 4.4.1), backward elimination method employed screen multivariate Cox regression analyses conducted on screened variables. Kaplan-Meier utilized sub-stages different races T1-2N1M0 stage. log-rank test used statistical analysis. 1539 collected. Chemotherapy statistically significant, a hazard ratio (HR) 0.64, P=0.003 patients. HR 0.33, P<0.001. didn't improve cancer-specific T2N0M0 showed no difference 1.85, P=0.13. For improved 0.53, No significant analysis between two (P=0.065). In race indicated P=0.190. found survival, 0.51, exhibited differences (P<0.0001). is correlated T1-2N1M0-stage carcinoma, but not at same rate, regardless ethnicity.

Language: Английский

Citations

0
Deep Learning in Oncology: Transforming Cancer Diagnosis, Prognosis, and Treatment DOI Creative Commons
Thaís Santos Anjo Reis

Emerging Trends in Drugs Addictions and Health, Journal Year: 2025, Volume and Issue: unknown, P. 100171 - 100171

Published: Feb. 1, 2025

Language: Английский

Citations

0
An Unusual Late Parotid Metastasis of Nasopharyngeal Carcinoma 10 Years After Curative Treatment DOI
Majd Werda, Rania Laajailia,

Chadha Ben Amar

et al.

Indian Journal of Otolaryngology and Head & Neck Surgery, Journal Year: 2025, Volume and Issue: unknown

Published: May 20, 2025

Language: Английский

Citations

0
A novel LVPA-UNet network for target volume automatic delineation: An MRI case study of nasopharyngeal carcinoma DOI Creative Commons
Yu Zhang, Haoran Xu, Junhao Wen

et al.

Heliyon, Journal Year: 2024, Volume and Issue: 10(10), P. e30763 - e30763

Published: May 1, 2024

Accurate delineation of Gross Tumor Volume (GTV) is crucial for radiotherapy. Deep learning-driven GTV segmentation technologies excel in rapidly and accurately delineating GTV, providing a basis radiologists formulating radiation plans. The existing 2D 3D models based on deep learning are limited by the loss spatial features anisotropy respectively, both affected variability tumor characteristics, blurred boundaries, background interference. All these factors seriously affect performance. To address above issues, Layer-Volume Parallel Attention (LVPA)-UNet model 2D-3D architecture has been proposed this study, which three strategies introduced. Firstly, workflows introduced LVPA-UNet. They work parallel can guide each other. Both fine slice MRI anatomical structure be extracted them. Secondly, multi-branch depth-wise strip convolutions adapt to tumors varying shapes sizes within slices volumetric spaces, achieve refined processing boundaries. Lastly, Layer-Channel mechanism adaptively adjust weights channels according their different information, then highlight with tumor. experiments LVPA-UNet 1010 nasopharyngeal carcinoma (NPC) datasets from centers show DSC 0.7907, precision 0.7929, recall 0.8025, HD95 1.8702mm, outperforming eight typical models. Compared baseline model, it improves 2.14%, 2.96%, 1.01%, while reducing 0.5434mm. Consequently, ensuring efficiency through learning, able provide superior results radiotherapy offer technical support medicine.

Language: Английский

Citations

2
Deciphering the Prognostic Efficacy of MRI Radiomics in Nasopharyngeal Carcinoma: A Comprehensive Meta-Analysis DOI Creative Commons

Chih-Keng Wang,

Tingwei Wang, Chia‐Feng Lu

et al.

Diagnostics, Journal Year: 2024, Volume and Issue: 14(9), P. 924 - 924

Published: April 29, 2024

This meta-analysis investigates the prognostic value of MRI-based radiomics in nasopharyngeal carcinoma treatment outcomes, specifically focusing on overall survival (OS) variability. The study protocol was registered with INPLASY (INPLASY202420101). Initially, a systematic review identified 15 relevant studies involving 6243 patients through comprehensive search across PubMed, Embase, and Web Science, adhering to PRISMA guidelines. methodological quality assessed using Quality Prognosis Studies (QUIPS) tool Radiomics Score (RQS), highlighting low risk bias most domains. Our analysis revealed significant average concordance index (c-index) 72% studies, indicating potential clinical prognostication. However, moderate heterogeneity observed, particularly OS predictions. Subgroup analyses meta-regression validation methods software as moderators. Notably, number features prognosis model correlated positively its performance. These findings suggest radiomics’ promising role enhancing cancer strategies, though observed biases call for cautious interpretation standardization future research.

Language: Английский

Citations

0
A prognostic and predictive model based on deep learning to identify optimal candidates for intensity-modulated radiotherapy alone in patients with stage II nasopharyngeal carcinoma: A retrospective multicenter study DOI
Jiong-Lin Liang,

Yue-Feng Wen,

Ying‐Ping Huang

et al.

Radiotherapy and Oncology, Journal Year: 2024, Volume and Issue: 203, P. 110660 - 110660

Published: Dec. 5, 2024

Language: Английский

Citations

0