@inproceedings{PB-VRVis-2018-047,
author = {Novikow, Alexey A. and Major, David and Wimmer, Maria and Lenis, Dimitrios and B{\"u}hler, Katja},
title = {Deep Sequential Segmentation of Organs in Volumetric Medical Scans},
year = {2018},
booktitle = {IEEE Transactions on Medical Imaging},
editor = {N.N.},
url = {https://www.vrvis.at/publications/PB-VRVis-2018-047},
abstract = {Segmentation in 3D scans is playing an  increasingly important role in current clinical practice  supporting diagnosis, tissue quantification, or treatment  planning. The current 3D approaches based on Convolutional  Neural Networks (CNN) usually suffer from at least three main  issues caused predominantly by implementation constraints -  first, they require resizing the volume to the  lower-resolutional reference dimensions, second, the capacity of  such approaches is very limited due to memory restrictions, and  third, all slices of volumes have to be available at any given  training or testing time. We address these problems by a  U-Net-like architecture consisting of bidirectional  Convolutional LSTM (C-LSTM) and convolutional, pooling,  upsampling and concatenation layers enclosed into  time-distributed wrappers. Our network can either process the  full volumes in a sequential manner, or segment slabs of slices  on demand. We demonstrate performance of our architecture on  vertebrae and liver segmentation tasks in 3D CT scans.},
}