• Corpus ID: 239050547

OSS-Net: Memory Efficient High Resolution Semantic Segmentation of 3D Medical Data

  title={OSS-Net: Memory Efficient High Resolution Semantic Segmentation of 3D Medical Data},
  author={Christoph Reich and Tim Prangemeier and Ozdemir Cetin and Heinz Koeppl},
Convolutional neural networks (CNNs) are the current state-of-the-art meta-algorithm for volumetric segmentation of medical data, for example, to localize COVID-19 infected tissue on computer tomography scans or the detection of tumour volumes in magnetic resonance imaging. A key limitation of 3D CNNs on voxelised data is that the memory consumption grows cubically with the training data resolution. Occupancy networks (O-Nets) are an alternative for which the data is represented continuously in… 

Figures and Tables from this paper

Scalable 3D Semantic Segmentation for Gun Detection in CT Scans
A novel deep 3D semantic segmentation method for gun detection in baggage CT scans that enables fast training and low video memory consumption for high-resolution voxelized volumes and a moving pyramid approach that utilizes multiple forward passes at inference time for segmenting an instance.


V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
This work proposes an approach to 3D image segmentation based on a volumetric, fully convolutional, neural network, trained end-to-end on MRI volumes depicting prostate, and learns to predict segmentation for the whole volume at once.
An application of cascaded 3D fully convolutional networks for medical image segmentation
This work shows that a multi-class 3D FCN trained on manually labeled CT scans of several anatomical structures can achieve competitive segmentation results, while avoiding the need for handcrafting features or training class-specific models.
A Fixed-Point Model for Pancreas Segmentation in Abdominal CT Scans
This paper forms a fixed-point model which uses a predicted segmentation mask to shrink the input region and outperform the state-of-the-art by more than \(4\%\), measured by the average Dice-Sorensen Coefficient (DSC).
A Partially Reversible U-Net for Memory-Efficient Volumetric Image Segmentation
A partially reversible U-Net architecture that reduces memory consumption substantially and alleviates the biggest memory bottleneck and enables very deep (theoretically infinitely deep) 3D architectures is proposed.
3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
The proposed network extends the previous u-net architecture from Ronneberger et al. by replacing all 2D operations with their 3D counterparts and performs on-the-fly elastic deformations for efficient data augmentation during training.
Three-Dimensional CT Image Segmentation by Combining 2D Fully Convolutional Network with 3D Majority Voting
We propose a novel approach for automatic segmentation of anatomical structures on 3D CT images by voting from a fully convolutional network (FCN), which accomplishes an end-to-end, voxel-wise
An Effective Deep Neural Network for Lung Lesions Segmentation From COVID-19 CT Images
A new segmentation method to meet the needs of CT images processing under COVID-19 epidemic by implementing patch mechanism strategy to satisfy the applicability of 3-D network and remove irrelevant background.
Automatic Multi-Organ Segmentation on Abdominal CT With Dense V-Networks
It is concluded that the deep-learning-based segmentation represents a registration-free method for multi-organ abdominal CT segmentation whose accuracy can surpass current methods, potentially supporting image-guided navigation in gastrointestinal endoscopy procedures.
Occupancy Networks: Learning 3D Reconstruction in Function Space
This paper proposes Occupancy Networks, a new representation for learning-based 3D reconstruction methods that encodes a description of the 3D output at infinite resolution without excessive memory footprint, and validate that the representation can efficiently encode 3D structure and can be inferred from various kinds of input.
3D Semantic Segmentation with Submanifold Sparse Convolutional Networks
This work introduces new sparse convolutional operations that are designed to process spatially-sparse data more efficiently, and uses them to develop Spatially-Sparse Convolutional networks, which outperform all prior state-of-the-art models on two tasks involving semantic segmentation of 3D point clouds.