Deep learning signatures reveal multiscale intratumor heterogeneity associated with biological functions and survival in recurrent nasopharyngeal carcinoma.
Xun ZhaoYu-Jing LiangXu ZhangDong-Xiang WenWei FanLin-Quan TangDi DongJie TianHai-Qiang MaiPublished in: European journal of nuclear medicine and molecular imaging (2022)
Our study demonstrated that PET/CT-based deep learning signatures showed satisfactory prognostic predictive performance in rNPC patients. The nomogram incorporating deep learning signatures successfully divided patients into different risks and had great potential to guide individual treatment: patients with a low-risk were supposed to be treated with surgery and re-irradiation, while for high-risk patients, the application of palliative chemotherapy may be sufficient.
Keyphrases
- deep learning
- end stage renal disease
- newly diagnosed
- chronic kidney disease
- pet ct
- peritoneal dialysis
- squamous cell carcinoma
- prognostic factors
- machine learning
- genome wide
- computed tomography
- minimally invasive
- risk assessment
- dna methylation
- artificial intelligence
- single cell
- radiation therapy
- percutaneous coronary intervention
- atrial fibrillation
- lymph node metastasis
- patient reported
- positron emission tomography
- coronary artery bypass
- replacement therapy