SSL-Unet: A Self-Supervised Learning Strategy Base on U-Net for Retinal Vessel Segmentation

We propose a SSL-Unet model for retinal vascular segmentation as well as two self-supervised training strategies. The strategy can help the self-supervised module to learn pseudo labels for improving the segmentation performance. Moreover, the fusion of both self-supervised and supervised paradigms is applied to retinal segmentation for the first time. Meanwhile, it can also be extended to any segmentation network.

SSL-Unet: A Self-Supervised Learning Strategy Base on U-Net for Retinal Vessel Segmentation

We propose a SSL-Unet model for retinal vascular segmentation as well as two self-supervised training strategies. The strategy can help the self-supervised module to learn pseudo labels for improving the segmentation performance. Moreover, the fusion of both self-supervised and supervised paradigms is applied to retinal segmentation for the first time. Meanwhile, it can also be extended to any segmentation network.

Automated vessel segmentation in lung CT and CTA images via deep neural networks

BACKGROUND: The distribution of pulmonary vessels in computed tomography (CT) and computed tomography angiography (CTA) images of lung is important for diagnosing disease, formulating surgical plans and pulmonary research. PURPOSE: Based on the pulmonary vascular segmentation task of International Symposium on Image Computing and Digital Medicine 2020 challenge, this paper reviews 12 different pulmonary vascular segmentation algorithms of lung CT and CTA images and then objectively evaluates and compares their performances. METHODS: First, we present the annotated reference dataset of lung CT and CTA images. A subset of the dataset consisting 7,307 slices for training and 3,888 slices for testing was made available for participants. Second, by analyzing the performance comparison of different convolutional neural networks from 12 different institutions for pulmonary vascular segmentation, the reasons for some defects and improvements are summarized. The models are mainly based on U-Net, Attention, GAN, and multi-scale fusion network. The performance is measured in terms of Dice coefficient, over segmentation ratio and under segmentation rate. Finally, we discuss several proposed methods to improve the pulmonary vessel segmentation results using deep neural networks. RESULTS: By comparing with the annotated ground truth from both lung CT and CTA images, most of 12 deep neural network algorithms do an admirable job in pulmonary vascular extraction and segmentation with the dice coefficients ranging from 0.70 to 0.85. The dice coefficients for the top three algorithms are about 0.80. CONCLUSIONS: Study results show that integrating methods that consider spatial information, fuse multi-scale feature map, or have an excellent post-processing to deep neural network training and optimization process are significant for further improving the accuracy of pulmonary vascular segmentation.

Automated Vessel Segmentation in CT and CTA scans of the Lung Via Deep Neural Networks

Background: The distribution of pulmonary vessels in computed tomography images is important for diagnosing disease, formulating surgical plans and pulmonary research. However, there are many challenges of pulmonary vascular segmentation due to its characteristics of narrow and long pipes, discrete distribution and tree-like structure. With the development of deep learning and medical image processing, an automatic, accurate and fast segmentation algorithm of pulmonary blood vessels becomes possible. Methods: Based on the International Symposium on Image Computing and Digital Medicine 2020 challenge pulmonary vascular segmentation task, this paper objectively evaluates the performance of 12 different algorithms in chest computed tomography and computed tomography angiography. First, we present the annotated reference dataset including computed tomography and computed tomography angiography. Second, by analyzing the advantages and disadvantages of each team’s algorithm from 12 different institution, the reasons for some defects and improvements are summarized. Finally, we discuss the ways and methods to improve the results. Results: These methods were compared with the ground truth by the numerical results and the intuitive results from computed tomography and computed tomography angiography images. Most methods do an admirable job in pulmonary vascular extraction, with dice coefficients ranging from 0.70 to 0.85, and the dice coefficient for the top three methods are about 0.80. Conclusions: These results show that the methods which consider spatial information, fuse multi-scale feature map, or have an excellent post-processing are significant for further improving the accuracy of pulmonary vascular segmentation. Keywords: segmentation; pulmonary; vessel; U-Net; network; CT images; CTA

Anatomical Modeling of Brain Vasculature in Two-Photon Microscopy by Generalizable Deep Learning

Objective and Impact Statement. Segmentation of blood vessels from two-photon microscopy (2PM) angiograms of brains has important applications in hemodynamic analysis and disease diagnosis. Here, we develop a generalizable deep learning technique for accurate 2PM vascular segmentation of sizable regions in mouse brains acquired from multiple 2PM setups. The technique is computationally efficient, thus ideal for large-scale neurovascular analysis. Introduction. Vascular segmentation from 2PM angiograms is an important first step in hemodynamic modeling of brain vasculature. Existing segmentation methods based on deep learning either lack the ability to generalize to data from different imaging systems or are computationally infeasible for large-scale angiograms. In this work, we overcome both these limitations by a method that is generalizable to various imaging systems and is able to segment large-scale angiograms. Methods. We employ a computationally efficient deep learning framework with a loss function that incorporates a balanced binary-cross-entropy loss and total variation regularization on the network’s output. Its effectiveness is demonstrated on experimentally acquired in vivo angiograms from mouse brains of dimensions up to 808×808×702 μm. Results. To demonstrate the superior generalizability of our framework, we train on data from only one 2PM microscope and demonstrate high-quality segmentation on data from a different microscope without any network tuning. Overall, our method demonstrates 10× faster computation in terms of voxels-segmented-per-second and 3× larger depth compared to the state-of-the-art. Conclusion. Our work provides a generalizable and computationally efficient anatomical modeling framework for brain vasculature, which consists of deep learning-based vascular segmentation followed by graphing. It paves the way for future modeling and analysis of hemodynamic response at much greater scales that were inaccessible before.