Robust Tumor Segmentation with Hyperspectral Imaging and Graph Neural Networks

no code implementations • 20 Nov 2023 • Mayar Lotfy, Anna Alperovich, Tommaso Giannantonio, Bjorn Barz, Xiaohan Zhang, Felix Holm, Nassir Navab, Felix Boehm, Carolin Schwamborn, Thomas K. Hoffmann, Patrick J. Schuler

Despite the limited dataset, the GNN-based model significantly outperforms context-agnostic approaches, accurately distinguishing between healthy and tumor tissues, even in images from previously unseen patients.

Tumor Segmentation

Intra-operative Brain Tumor Detection with Deep Learning-Optimized Hyperspectral Imaging

no code implementations • 6 Feb 2023 • Tommaso Giannantonio, Anna Alperovich, Piercosimo Semeraro, Manfredo Atzori, Xiaohan Zhang, Christoph Hauger, Alexander Freytag, Siri Luthman, Roeland Vandebriel, Murali Jayapala, Lien Solie, Steven de Vleeschouwer

Surgery for gliomas (intrinsic brain tumors), especially when low-grade, is challenging due to the infiltrative nature of the lesion.

Light Field Intrinsics With a Deep Encoder-Decoder Network

no code implementations • CVPR 2018 • Anna Alperovich, Ole Johannsen, Michael Strecke, Bastian Goldluecke

We present a fully convolutional autoencoder for light fields, which jointly encodes stacks of horizontal and vertical epipolar plane images through a deep network of residual layers.

Disparity Estimation Lightfield

Accurate Depth and Normal Maps From Occlusion-Aware Focal Stack Symmetry

no code implementations • CVPR 2017 • Michael Strecke, Anna Alperovich, Bastian Goldluecke

We introduce a novel approach to jointly estimate consistent depth and normal maps from 4D light fields, with two main contributions.