Trained Models for Spinal Tumor Segmentation in Multiple Myeloma Patients

This repository contains trained deep learning model weights for automatic segmentation of spinal tumors in patients with multiple myeloma using CT data. Four architectures were trained and evaluated: MedNeXt, nnU-Net, ResNet, and ResAttNet. The models were developed as part of a bachelor's thesis focused on optimization of deep learning models for spinal tumor segmentation in multiple myeloma patients