.png){kind=icon}
返回
MSKD: Structured knowledge distillation for efficient medical image segmentation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.compbiomed.2023.107284.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In recent years, deep learning has revolutionized the field of medical image segmentation by enabling the development of powerful deep neural networks. However, these models tend to be complex and computationally demanding, posing challenges for practical implementation in clinical settings. To address this issue, we propose an efficient structured knowledge distillation framework that leverages a powerful teacher network to assist in training a lightweight student network. Specifically, we propose the Feature Filtering Distillation method, which focuses on transferring region-level semantic information while minimizing redundant information transmission from the teacher to the student network. This approach effectively mitigates the problem of inaccurate segmentation caused by similar internal organ characteristics. Additionally, we propose the Region Graph Distillation method, which exploits the higher-order representational capabilities of graphs to enable the student network to better imitate structured semantic information from the teacher. To validate the effectiveness of our proposed methods, we conducted experiments on the Synapse multi-organ segmentation and KiTS kidney tumor segmentation datasets using various network models. The results demonstrate that our method significantly improves the segmentation performance of lightweight neural networks, with improvements of up to 18.56% in Dice coefficient. Importantly, our approach achieves these improvements without introducing additional model parameters. Overall, our proposed knowledge distillation methods offer a promising solution for efficient medical image segmentation, empowering medical experts to make more accurate diagnoses and improve patient treatment.
Keyword:
Knowledge distillation
Medical image segmentation
Lightweight neural networks
Deep learning
Teacher-student model
Feature filtering distillation
Region graph distillation
期刊
IF:
6.3
论文数:
8.3K
被引数:
3.3W
机构
引用论文
分享收藏Analysis of the formation of monodisperse populations by homogeneous nucleation通过均相成核分析单分散种群的形成
PREAI
分享收藏When Predators Don't Eat Their Prey: Nonconsumptive Predator Effects on Prey Dynamics1.png)
Ecology
EcologyIF0
PREAI
分享收藏Distant regulatory elements in a Sox10‐βGEO BAC transgene are required for expression of Sox10 in the enteric nervous system and other neural crest‐derived tissuesSox10-βgeo BAC转基因中的远距离调控元件是肠神经系统和其他神经源性组织中 Sox10 表达所必需的
OAAI
OAAI分享收藏Colorimetric detection of pesticides based on calixarene modified silver nanoparticles in water
PREAI
分享收藏
查看更多内容