Group Shift Pointwise Convolution for Volumetric Medical Image Segmentation

by   Junjun He, et al.

Recent studies have witnessed the effectiveness of 3D convolutions on segmenting volumetric medical images. Compared with the 2D counterparts, 3D convolutions can capture the spatial context in three dimensions. Nevertheless, models employing 3D convolutions introduce more trainable parameters and are more computationally complex, which may lead easily to model overfitting especially for medical applications with limited available training data. This paper aims to improve the effectiveness and efficiency of 3D convolutions by introducing a novel Group Shift Pointwise Convolution (GSP-Conv). GSP-Conv simplifies 3D convolutions into pointwise ones with 1x1x1 kernels, which dramatically reduces the number of model parameters and FLOPs (e.g. 27x fewer than 3D convolutions with 3x3x3 kernels). Naïve pointwise convolutions with limited receptive fields cannot make full use of the spatial image context. To address this problem, we propose a parameter-free operation, Group Shift (GS), which shifts the feature maps along with different spatial directions in an elegant way. With GS, pointwise convolutions can access features from different spatial locations, and the limited receptive fields of pointwise convolutions can be compensated. We evaluate the proposed methods on two datasets, PROMISE12 and BraTS18. Results show that our method, with substantially decreased model complexity, achieves comparable or even better performance than models employing 3D convolutions.


Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions

Neural networks rely on convolutions to aggregate spatial information. H...

Segmentation with Super Images: A New 2D Perspective on 3D Medical Image Analysis

Deep learning is showing an increasing number of audience in medical ima...

Convolution with even-sized kernels and symmetric padding

Compact convolutional neural networks gain efficiency mainly through dep...

3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation

Vision transformers (ViTs) have quickly superseded convolutional network...

Multi-scale Octave Convolutions for Robust Speech Recognition

We propose a multi-scale octave convolution layer to learn robust speech...

MelGlow: Efficient Waveform Generative Network Based on Location-Variable Convolution

Recent neural vocoders usually use a WaveNet-like network to capture the...

Emerging Convolutions for Generative Normalizing Flows

Generative flows are attractive because they admit exact likelihood opti...

Please sign up or login with your details

Forgot password? Click here to reset