Co-optimization Learning Network for MRI Segmentation of Ischemic Penumbra Tissues

Abstract

Convolutional neural networks (CNNs) have brought hope for the medical image auxiliary diagnosis. However, the shortfall of labeled medical image data is the bottleneck that limits the performance improvement of supervised CNN methods. In addition, annotating a large number of labeled medical image data is often expensive and time-consuming. In this study, we propose a co-optimization learning network (COL-Net) for Magnetic Resonance Imaging (MRI) segmentation of ischemic penumbra tissues. COL-Net base on the limited labeled samples and consists of an unsupervised reconstruction network (R), a supervised segmentation network (S), and a transfer block (T). The reconstruction network extracts the robust features from reconstructing pseudo unlabeled samples, which is the auxiliary branch of the segmentation network. The segmentation network is used to segment the target lesions under the limited labeled samples and the auxiliary of the reconstruction network. The transfer block is used to co-optimization the feature maps between the bottlenecks of the reconstruction network and segmentation network. We propose a mix loss function to optimize COL-Net. COL-Net is verified on the public ischemic penumbra segmentation challenge (SPES) with two dozen labeled samples. Results demonstrate that COL-Net has high predictive accuracy and generalization with the Dice coefficient of 0.79. The extended experiment also shows COL-Net outperforms most supervised segmentation methods. COL-Net is a meaningful attempt to alleviate the limited labeled sample problem in medical image segmentation.

Nonconvex Nonlocal Tucker Decomposition for 3D Medical Image Super-Resolution

“…Thus, the performance of these methods highly depends on the learned HR image patches. Deep learning-based methods (Ledig et al, 2017 ; Zhao et al, 2019 ; Fan et al, 2020 ; Liu et al, 2021 ) have obtained outstanding performances in high-level image processing tasks, such as alignment, segmentation, and object detection. Recently, they also began to show their advantage in low-level image processing tasks.…”