Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: Deep learning model integrating positron emission tomography and clinical data for prognosis prediction in non-small cell lung cancer patients

Fig. 1

The structure of the proposed model and workflow. In step 1, the performances of the CPH and MLP model with DeepSurv were compared for use as a prediction model using clinical features. In step 2, the performance of a 3D CNN model with 3D PET images and a 2D CNN model with 2D MIP PET images were compared. In step 3, integration of the clinical features and image data for the proposed model occurs. The model performance was evaluated based on three metrics: C-index, MAE, and accuracy

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us