计算机科学
推论
变压器
分割
人工智能
计算机工程
图像分割
计算资源
可扩展性
卷积神经网络
机器学习
数据挖掘
分布式计算
计算复杂性理论
算法
数据库
物理
量子力学
电压
作者
Yan Pang,Jiun Lung Liang,Teng Huang,Hao Chen,Yunhao Li,Dan Li,Hung‐Mo Lin,Qiong Wang
出处
期刊:IEEE Transactions on Medical Imaging
[Institute of Electrical and Electronics Engineers]
日期:2024-03-01
卷期号:43 (3): 994-1005
标识
DOI:10.1109/tmi.2023.3326188
摘要
Hybrid transformer-based segmentation approaches have shown great promise in medical image analysis. However, they typically require considerable computational power and resources during both training and inference stages, posing a challenge for resource-limited medical applications common in the field. To address this issue, we present an innovative framework called Slim UNETR, designed to achieve a balance between accuracy and efficiency by leveraging the advantages of both convolutional neural networks and transformers. Our method features the Slim UNETR Block as a core component, which effectively enables information exchange through self-attention mechanism decomposition and cost-effective representation aggregation. Additionally, we utilize the throughput metric as an efficiency indicator to provide feedback on model resource consumption. Our experiments demonstrate that Slim UNETR outperforms state-of-the-art models in terms of accuracy, model size, and efficiency when deployed on resource-constrained devices. Remarkably, Slim UNETR achieves 92.44% dice accuracy on BraTS2021 while being 34.6x smaller and 13.4x faster during inference compared to Swin UNETR. Code: https://github.com/aigzhusmart/Slim-UNETR.
科研通智能强力驱动
Strongly Powered by AbleSci AI