Learning For Image Segmentation Research Articles

Boundary-aware information maximization for self-supervised medical image segmentation

Self-supervised representation learning can boost the performance of a pre-trained network on downstream tasks for which labeled data is limited. A popular method based on this paradigm, known as contrastive learning, works by constructing sets of positive and negative pairs from the data, and then pulling closer the representations of positive pairs while pushing apart those of negative pairs. Although contrastive learning has been shown to improve performance in various classification tasks, its application to image segmentation has been more limited. This stems in part from the difficulty of defining positive and negative pairs for dense feature maps without having access to pixel-wise annotations.In this work, we propose a novel self-supervised pre-training method that overcomes the challenges of contrastive learning in image segmentation. Our method leverages Information Invariant Clustering (IIC) as an unsupervised task to learn a local representation of images in the decoder of a segmentation network, but addresses three important drawbacks of this approach: (i) the difficulty of optimizing the loss based on mutual information maximization; (ii) the lack of clustering consistency for different random transformations of the same image; (iii) the poor correspondence of clusters obtained by IIC with region boundaries in the image. Toward this goal, we first introduce a regularized mutual information maximization objective that encourages the learned clusters to be balanced and consistent across different image transformations. We also propose a boundary-aware loss based on cross-correlation, which helps the learned clusters to be more representative of important regions in the image. Compared to contrastive learning applied in dense features, our method does not require computing positive and negative pairs and also enhances interpretability through the visualization of learned clusters.Comprehensive experiments involving four different medical image segmentation tasks reveal the high effectiveness of our self-supervised representation learning method. Our results show the proposed method to outperform by a large margin several state-of-the-art self-supervised and semi-supervised approaches for segmentation, reaching a performance close to full supervision with only a few labeled examples.

A Convolutional Neural Network for Ultrasound Plane Wave Image Segmentation With a Small Amount of Phase Array Channel Data.

Single-angle plane wave has a huge potential in ultrasound high frame rate imaging, which, however, has a number of difficulties, such as low imaging quality and poor segmentation results. To overcome these difficulties, an end-to-end convolutional neural network (CNN) structure from single-angle channel data was proposed to segment images in this article. The network removed the traditional beamforming process and used raw radio frequency (RF) data as input to directly obtain segmented image. The signal features at each depth were extracted and concatenated to obtain the feature map by a special depth signal extraction module, and the feature map was then put into the residual encoder and decoder to obtain the output. A simulated hypoechoic cysts dataset of 2000 and an actual industrial defect dataset of 900 were used for training separately. Good results have been achieved in both simulated medical cysts segmentation and actual industrial defects segmentation. Experiments were conducted on both datasets with phase array sparse element data as input, and segmentation results were obtained for both. On the whole, this work achieved better quality segmented images with shorter processing time from single-angle plane wave channel data using CNNs; compared with other methods, our network has been greatly improved in intersection over union (IOU), F1 score, and processing time. Also, it indicated that the feasibility of applying deep learning in image segmentation can be improved using phase array sparse element data as input.

A novel multi-discriminator deep network for image segmentation

Several studies have shown the excellent performance of deep learning in image segmentation. Usually, this benefits from a large amount of annotated data. Medical image segmentation is challenging, however, since there is always a scarcity of annotated data. This study constructs a novel deep network for medical image segmentation, referred to as asymmetric U-Net generative adversarial networks with multi-discriminators (AU-MultiGAN). Specifically, the asymmetric U-Net is designed to produce multiple segmentation maps simultaneously and use the dual-dilated blocks in the feature extraction stage only. Further, the multi-discriminator module is embedded into the asymmetric U-Net structure, which can capture the available information of samples sufficiently and thereby promote the information transmission of features. A hybrid loss by the combination of segmentation and discriminator losses is developed, and an adaptive method of selecting the scale factors is devised for this new loss. More importantly, the convergence of the proposed model is proved mathematically. The proposed AU-MultiGAN approach is implemented on some standard medical image benchmarks. Experimental results show that the proposed architecture can be successfully applied to medical image segmentation, and obtain superior performance in comparison with the state-of-the-art baselines.

Detection of Number and Character Area of License Plate Using Deep Learning and Semantic Image Segmentation

Detection of Number and Character Area of License Plate Using Deep Learning and Semantic Image Segmentation

Evaluation and Analysis of Cardiovascular Function in Intensive Care Unit Patients by Ultrasound Image Segmentation Based on Deep Learning

Many studies have shown that cardiovascular disease has become one of the major diseases leading to death in the world. Therefore, it is a very meaningful topic to use image segmentation technology to segment blood vessels for clinical application. In order to automatically extract the features of blood vessel images in the process of segmentation, the deep learning algorithm is combined with image segmentation technology to segment the nerve cell membrane and carotid artery images of ICU patients, and to segment the blood vessel images from a multi-dimensional perspective. The relevant data are collected to observe the effect of this model. The results show that the three-dimensional multi-scale linear filter has a good effect on carotid artery segmentation in the image segmentation of nerve cell membranes and carotid artery. When analyzing the accuracy of vascular image segmentation from network parameters and training parameters, it is found that the accuracy of the threedimensional multi-scale linear filter can reach about 85%. Therefore, it can be found that the combination of deep learning algorithm and image segmentation technology has a good segmentation effect, and the segmentation accuracy is also high. The experiment achieves the desired effect, which provides experimental basis for the clinical application of the vascular image segmentation technology.

Training of head and neck segmentation networks with shape prior on small datasets.

Cancer in the head and neck area is commonly treated with radiotherapy. A key step for low-risk treatment is the accurate delineation of organs at risk in the planning imagery. The success of deep learning in image segmentation led to automated algorithms achieving human expert performance on certain datasets. However, such algorithms require large datasets for training and fail to segment previously unseen pathologies, where human experts still succeed. As pathologies are rare and large datasets costly to generate, we investigate the effect of: reduced training data, batch sizes and incorporation of prior knowledge. The small data problem is studied by training a full-volume segmentation network with the reduced amount of data from the MICCAI 2015 head and neck segmentation challenge. To improve the segmentation, we evaluate the batch size as a hyper-parameter and first study and then incorporate a stacked autoencoder as shape prior into the training process. We found that using half of the training data (12 images of 25) results in an accuracy drop of only 3% for the segmentation of organs at risk. Also, the batch size turns out to be relevant for the quality of the segmentation when trained with less than half of the data. By applying PCA on the autoencoder's latent space we achieve a compact and accurate shape model, which is used as a regularizer and significantly improves the segmentation results. Small training data of up to 12 training images is enough to train accurate head and neck segmentation models. By using a shape prior for regularization, the performance of the segmentation can be improved significantly on the full dataset. When training on fewer than 12 images, the batch size is relevant and models have to be trained much longer until convergence.

Orthogonal design of experiments for parameter learning in image segmentation

This paper employs the methods from the design of experiments for supervised parameter learning in image segmentation. We propose to use orthogonal arrays in order to keep the number of experiments small and several algorithms are formulated. Analysis of means is applied to estimate the optimal parameter settings. In addition, a combination of orthogonal arrays and genetic algorithm is used to further improve the performance. The proposed algorithms are experimentally validated based on two segmentation algorithms and the Berkeley image database. A comparison with exhaustive search, an alternating scheme and a Monte-Carlo approach is also provided.