T. Neubauer (2020)

Volumetric Tumor Segmentation on Multimodal Medical Images using Deep Learning

Wo ist die Publikation erschienen?

Master's Thesis


The automatic segmentation of tumors on different imaging modalities supports medical experts in patient diagnosis and treatment. Magnetic resonance imaging (MRI), Computed Tomography (CT), or Positron Emission Tomography (PET) show the tumor in a different anatomical, functional, or molecular context. The fusion of this multimodal information leads to more profound knowledge and enables more precise diagnoses. So far, the potential of multimodal data is only used by a few established segmentation methods. Moreover, much less is known about multimodal methods that provide several modality-specific tumor segmentations instead of a single segmentation for a specific modality. This thesis aims to develop a segmentation method that uses the multimodal context to improve the modality-specific segmentation results. For the implementation, an artificial neural network is used, which is based on a fully convolutional neural network. The network architecture has been designed to learn complex multimodal features to predict multiple tumor segmentations on different modalities efficiently. The evaluation is based on a dataset consisting of MRI and PET/CT scans of soft tissue tumors. The experiment investigated how different network architectures, multimodal fusion strategies, and input modalities affect the segmentation result. The investigation showed that multimodal models lead to significantly better results than models for single modalities. Promising results have also been achieved with multimodal models that segment several modality-specific tumor contours simultaneously.