no code implementations • 8 Mar 2024 • Zikang Xu, Fenghe Tang, Quan Quan, Qingsong Yao, S. Kevin Zhou
Ensuring fairness in deep-learning-based segmentors is crucial for health equity.
no code implementations • 5 Dec 2023 • Zikang Xu, Fenghe Tang, Quan Quan, Jianrui Ding, Chunping Ning, S. Kevin Zhou
With the rapid expansion of machine learning and deep learning (DL), researchers are increasingly employing learning-based algorithms to alleviate diagnostic challenges across diverse medical tasks and applications.
1 code implementation • 4 Dec 2023 • Bingkun Nian, Fenghe Tang, Jianrui Ding, Pingping Zhang, Jie Yang, S. Kevin Zhou, Wei Liu
In this paper, we present a high-performance deep neural network for weak target image segmentation, including medical image segmentation and infrared image segmentation.
1 code implementation • 4 Dec 2023 • Fenghe Tang, Bingkun Nian, Jianrui Ding, Quan Quan, Jie Yang, Wei Liu, S. Kevin Zhou
This work revisits the relationship between CNNs and Transformers in lightweight universal networks for medical image segmentation, aiming to integrate the advantages of both worlds at the infrastructure design level.
1 code implementation • 16 Nov 2023 • Quan Quan, Fenghe Tang, Zikang Xu, Heqin Zhu, S. Kevin Zhou
To address these problems, we propose Slide-SAM, which treats a stack of three adjacent slices as a prediction window.
2 code implementations • 2 Aug 2023 • Fenghe Tang, Jianrui Ding, Lingtao Wang, Chunping Ning, S. Kevin Zhou
In order to extract global context information while taking advantage of the inductive bias, we propose CMUNeXt, an efficient fully convolutional lightweight medical image segmentation network, which enables fast and accurate auxiliary diagnosis in real scene scenarios.
1 code implementation • 24 May 2023 • Lingtao Wang, Jianrui Ding, Fenghe Tang, Chunping Ning
Accurate detection of thyroid lesions is a critical aspect of computer-aided diagnosis.
1 code implementation • 16 May 2023 • Fenghe Tang, Jianrui Ding, Lingtao Wang, Min Xian, Chunping Ning
Our approach enables the effective transfer of probability distribution knowledge to the segmentation network, resulting in improved segmentation accuracy.
2 code implementations • 24 Oct 2022 • Fenghe Tang, Lingtao Wang, Chunping Ning, Min Xian, Jianrui Ding
However, due to the inherent local characteristics of ordinary convolution operations, U-Net encoder cannot effectively extract global context information.