A Location-Sensitive Local Prototype Network for Few-Shot Medical Image Segmentation

03/18/2021
by   Qinji Yu, et al.
11

Despite the tremendous success of deep neural networks in medical image segmentation, they typically require a large amount of costly, expert-level annotated data. Few-shot segmentation approaches address this issue by learning to transfer knowledge from limited quantities of labeled examples. Incorporating appropriate prior knowledge is critical in designing high-performance few-shot segmentation algorithms. Since strong spatial priors exist in many medical imaging modalities, we propose a prototype-based method – namely, the location-sensitive local prototype network – that leverages spatial priors to perform few-shot medical image segmentation. Our approach divides the difficult problem of segmenting the entire image with global prototypes into easily solvable subproblems of local region segmentation with local prototypes. For organ segmentation experiments on the VISCERAL CT image dataset, our method outperforms the state-of-the-art approaches by 10 mean Dice coefficient. Extensive ablation studies demonstrate the substantial benefits of incorporating spatial information and confirm the effectiveness of our approach.

READ FULL TEXT

page 2

page 4

page 6

research
12/07/2022

Few-shot Medical Image Segmentation with Cycle-resemblance Attention

Recently, due to the increasing requirements of medical imaging applicat...
research
08/02/2021

Recurrent Mask Refinement for Few-Shot Medical Image Segmentation

Although having achieved great success in medical image segmentation, de...
research
03/03/2022

Anomaly Detection-Inspired Few-Shot Medical Image Segmentation Through Self-Supervision With Supervoxels

Recent work has shown that label-efficient few-shot learning through sel...
research
12/10/2020

Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding

Despite deep convolutional neural networks achieved impressive progress ...
research
11/16/2020

High-level Prior-based Loss Functions for Medical Image Segmentation: A Survey

Today, deep convolutional neural networks (CNNs) have demonstrated state...
research
01/07/2022

Effect of Prior-based Losses on Segmentation Performance: A Benchmark

Today, deep convolutional neural networks (CNNs) have demonstrated state...
research
09/14/2019

3D Deep Affine-Invariant Shape Learning for Brain MR Image Segmentation

Recent advancements in medical image segmentation techniques have achiev...

Please sign up or login with your details

Forgot password? Click here to reset