This study aims to predict the 1-year survival time of patients with metastatic melanoma using a binary classification approach. The dataset consists of CT scans from 71 patients diagnosed with metastatic melanoma, all studied at Université Clermont Auvergne Hospital, France. The number of lesions per patient ranges from 1 to 11. The survival time is predicted by feeding the CT scan data into a 3D Convolutional Neural Network (CNN), which serves as the model to anticipate the survival outcome based on the available imaging data.