Back to Search
Start Over
Deep learning-based survival prediction for multiple cancer types using histopathology images
- Source :
- PLoS ONE, PLoS ONE, Vol 15, Iss 6, p e0233678 (2020)
- Publication Year :
- 2020
-
Abstract
- Providing prognostic information at the time of cancer diagnosis has important implications for treatment and monitoring. Although cancer staging, histopathological assessment, molecular features, and clinical variables can provide useful prognostic insights, improving risk stratification remains an active research area. We developed a deep learning system (DLS) to predict disease specific survival across 10 cancer types from The Cancer Genome Atlas (TCGA). We used a weakly-supervised approach without pixel-level annotations, and tested three different survival loss functions. The DLS was developed using 9,086 slides from 3,664 cases and evaluated using 3,009 slides from 1,216 cases. In multivariable Cox regression analysis of the combined cohort including all 10 cancers, the DLS was significantly associated with disease specific survival (hazard ratio of 1.58, 95% CI 1.28–1.70, p
- Subjects :
- FOS: Computer and information sciences
0301 basic medicine
Oncology
Male
Computer Science - Machine Learning
Datasets as Topic
Pathology and Laboratory Medicine
Quantitative Biology - Quantitative Methods
Machine Learning (cs.LG)
Machine Learning
0302 clinical medicine
Mathematical and Statistical Techniques
Risk Factors
Neoplasms
Image Processing, Computer-Assisted
Medicine and Health Sciences
Quantitative Methods (q-bio.QM)
Multidisciplinary
Image and Video Processing (eess.IV)
Hazard ratio
Statistics
Age Factors
Squamous Cell Carcinomas
Middle Aged
Prognosis
Head and Neck Tumors
030220 oncology & carcinogenesis
Hepatocellular carcinoma
Cohort
Physical Sciences
Medicine
Female
Anatomy
Research Article
Adult
medicine.medical_specialty
Computer and Information Sciences
Histology
Neural Networks
Imaging Techniques
Science
Histopathology
Research and Analysis Methods
Risk Assessment
Carcinomas
03 medical and health sciences
Deep Learning
Sex Factors
Head and Neck Squamous Cell Carcinoma
Artificial Intelligence
Diagnostic Medicine
Internal medicine
FOS: Electrical engineering, electronic engineering, information engineering
medicine
Humans
Statistical Methods
Cancer staging
Neoplasm Staging
Proportional hazards model
business.industry
Biology and Life Sciences
Cancers and Neoplasms
Electrical Engineering and Systems Science - Image and Video Processing
medicine.disease
Head and neck squamous-cell carcinoma
Survival Analysis
Confidence interval
030104 developmental biology
Head and Neck Cancers
Anatomical Pathology
FOS: Biological sciences
Feasibility Studies
business
Mathematics
Forecasting
Neuroscience
Subjects
Details
- ISSN :
- 19326203
- Volume :
- 15
- Issue :
- 6
- Database :
- OpenAIRE
- Journal :
- PloS one
- Accession number :
- edsair.doi.dedup.....4f83c174071cad446aa4081fd2350b72