2023年10月25日 · 本文提出一种用于半监督医学图像分割的新框架mcf，使网络能够意识到自己的错误，并通过子网间比较进行偏差纠正。 为了释放双子网结构的潜力，MCF引入了两个不同的子网，它们独立更新参数。

propose a new framework MCF for semi-supervised medical image segmentation. A CDR module is proposed to guide the network to pay attention and correct its own potential bias. Combined with the characteristics of medical image segmentation databases, DCPLG is proposed to obtain more reliable pseudo-labels. We evaluate the proposed MCF framework ...

We propose a novel mutual correction framework (MCF) to explore network bias correction and improve the performance of SSMIS. Inspired by the plain contrast idea, MCF introduces two different subnets to explore and utilize the discrepancies between subnets to correct cognitive bias of the model.

2013年3月6日 · title = {MCF: Mutual Correction Framework for Semi-Supervised Medical Image Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2023}, pages = {15651-15660} . We build the project based on UA-MT,SASSNet,DTC.

MCF: Mutual Correction Framework for Semi-Supervised Medical Image Segmentation. MCF-train运行视频.mp4与MCF-test运行视频.mp4为demo演示视频. 环境配置：

2024年9月12日 · 由一群卓越的研究者开发，MCF专为解决医学图像分割中的标注难题而设计，以其创新的双向校正机制，极大地提升了模型性能，即便是在标注数据稀缺的情况下。 MCF框架基于Python环境，依托PyTorch的灵活性与效率，巧妙融合CUDA的加速计算，确保深度学习任务的高效运行。 它对medpy和tqdm等库的有效利用，体现了其在处理医疗图像时的专业性和便捷性。 通过版本锁定至Python 3.6.13和特定的依赖项配置，MCF确保了项目稳定性和复现性的高标准 …

A new method called Mutual Correction Framework (MCF) improves the accuracy of medical image segmentation by helping the network correct its mistakes. It uses two subnets to compare predictions and correct biases. MCF outperforms other methods on medical image datasets, especially on edge segmentation.

In this paper, we propose an end-to-end deep learning network, Multi-layer Concatenation Fusion Network (MCFNet), for feature extraction, feature fusion and image reconstruction without manually designing complex feature extraction and fusion rules.

2021年9月21日 · In this paper, we propose a novel mutual consistency network (MC-Net+) to effectively exploit the unlabeled data for semi-supervised medical image segmentation. The MC-Net+ model is motivated by...

2022年11月1日 · In order to enhance the diagnosis efficiency and accuracy, we have presented a novel MCF-Net using an encoding-decoding framework for automatic medical image segmentation that was found to improve the result by a large margin compared with …