fig2

Censor-aware semi-supervised survival time prediction in lung cancer using clinical and radiomics features

Figure 2. Box plot for PET and clinical data demonstrating comparison between SSL and SL; SSL significantly outperformed SL for PET_HRF and CF features, while improvements for PET_DRF were modest. PET_DRF: Deep radiomics features extracted from PET; PET_HRF: handcrafted radiomics features extracted from PET; CF: clinical features; SL: supervised learning; SSL: semi-supervised learning; MAE: mean absolute error; P: P-value; PET: positron emission tomography; HRF: handcrafted radiomics features.

Journal of Cancer Metastasis and Treatment
ISSN 2454-2857 (Online) 2394-4722 (Print)

Portico

All published articles are preserved here permanently:

https://www.portico.org/publishers/oae/

Portico

All published articles are preserved here permanently:

https://www.portico.org/publishers/oae/