Deep learning pathological microscopic features in endemic nasopharyngeal cancer: Prognostic value and protentional role for individual induction chemotherapy

Autor: Xi Chen, Xiang Guo, Xing Lv, Mengyun Qiang, Kuiyuan Liu, Wei-Xiong Xia, Jia Liu
Jazyk: angličtina
Rok vydání: 2020
Předmět:
0301 basic medicine
Oncology
Male
Cancer Research
Endemic Diseases
Kaplan-Meier Estimate
0302 clinical medicine
Nasopharynx
Antineoplastic Combined Chemotherapy Protocols
Clinical endpoint
Image Processing
Computer-Assisted
DeepSurv
Nasopharyngeal cancer
Original Research
Chemoradiotherapy
Middle Aged
Prognosis
lcsh:Neoplasms. Tumors. Oncology. Including cancer and carcinogens
Progression-Free Survival
030220 oncology & carcinogenesis
Female
Fluorouracil
pathological microfeatures
Adult
medicine.medical_specialty
China
Risk Assessment
lcsh:RC254-282
03 medical and health sciences
Deep Learning
Internal medicine
medicine
Humans
Radiology
Nuclear Medicine and imaging
Pathological
induction chemotherapy
Neoplasm Staging
Retrospective Studies
Receiver operating characteristic
business.industry
nasopharyngeal carcinoma
Induction chemotherapy
Clinical Cancer Research
Nasopharyngeal Neoplasms
medicine.disease
Training cohort
030104 developmental biology
Nasopharyngeal carcinoma
Radiotherapy
Intensity-Modulated
Cisplatin
Concomitant Chemoradiotherapy
business
Zdroj: Cancer Medicine, Vol 9, Iss 4, Pp 1298-1306 (2020)
Cancer Medicine
ISSN: 2045-7634
Popis: Background To explore the prognostic value and the role for treatment decision of pathological microscopic features in patients with nasopharyngeal carcinoma (NPC) using the method of deep learning. Methods The pathological microscopic features were extracted using the software QuPath (version 0.1.3. Queen's University) in the training cohort (Guangzhou training cohort, n = 843). We used the neural network DeepSurv to analyze the pathological microscopic features (DSPMF) and then classified patients into high‐risk and low‐risk groups through the time‐dependent receiver operating characteristic (ROC). The prognosis accuracy of the pathological feature was validated in a validation cohort (n = 212). The primary endpoint was progression‐free survival (PFS). Results We found 429 pathological microscopic features in the H&E image. Patients with high‐risk scores in the training cohort had shorter 5‐year PFS (HR 10.03, 6.06‐16.61; P
The research of this paper is time‐effective, innovative, and practical. It may help clinician to judge the prognosis of the patients with NPC and guide the treatment decision.
Databáze: OpenAIRE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje