Predicting NSCLC prognosis by automated pathology
Download as PPTX, PDF1 like352 views
The presentation discusses a study on lung cancer, the most prevalent cancer worldwide, focusing on its histopathological classification and the prediction of survival based on fully automated microscopic pathology image features. Utilizing databases like The Cancer Genome Atlas and Stanford Tissue Microarray, the researchers developed an automated workflow to analyze whole slide pathology for various types of lung cancer, including adenocarcinoma and squamous cell carcinoma. Results showed promise in predicting prognosis and survival rates, highlighting the potential of machine learning in pathology.
Related topics:1 of 18
Download to read offline
More Related Content
What's hot (20)
Ad
Viewers also liked (19)
Ad
Similar to Predicting NSCLC prognosis by automated pathology (20)
Predicting NSCLC prognosis by automated pathology
- 1. Presented by: Tsai, Mu-Hung, M.D. Department of Radiation Oncology, National Cheng Kung University Hospital 2016/09/02
- 2. Lung Cancer Most prevalent cancer worldwide Histopathological classification Small cell carcinoma Non-small cell carcinoma Squamous cell carcinoma Adenocarcinoma Grade (Gr.1 – Gr.3) Low level of inter-observer agreement
- 3. Pathology Squamous cell carcinoma Adenocarcinoma
- 4. Aim Fully automated microscopic pathology image features Predict lung cancer survival
- 5. Training Validation Methods & Materials The Cancer Genome Atlas (TCGA) Stanford Tissue Microarray (TMA) Database Cross-validate
- 6. Image: euthman @ Flickr
- 10. Adenocarcinoma vs. Normal Lung
- 11. SCC vs. Normal Lung
- 12. Adenocarcinoma vs. SCC (TCGA)
- 13. Adenocarcinoma vs. SCC (TMA)
- 16. Stage IB Grade 3 adenocarcinoma
- 18. Discussion Automated workflow to analyze whole slide pathology Elastic net-Cox proportional hazards models Computationally efficient Handles right-censored survival data Performance not very sensitive to ML method Obtain large number of features!