A wavelet transform-based image segmentation method

Aggregating multi-level feature representation plays a critical role in achieving robust volumetric medical image segmentation, which is important for the auxiliary diagnosis and treatment. Unlike the recent neural architecture search (NAS) methods that typically searched the optimal operators in each network layer, but missed a good strategy to search for feature aggregations, this paper proposes a novel NAS method for 3D medical image segmentation, named UXNet, which searches both the scale-wise feature aggregation strategies as well as the block-wise operators in the encoder-decoder network. UXNet has several appealing benefits. (1) It significantly improves flexibility of the classical UNet architecture, which only aggregates feature representations of encoder and decoder in equivalent resolution. (2) A continuous relaxation of UXNet is carefully designed, enabling its searching scheme performed in an efficient differentiable manner. (3) Extensive experiments demonstrate the effectiveness of UXNet compared with recent NAS methods for medical image segmentation. The architecture discovered by UXNet outperforms existing state-of-the-art models in terms of Dice on several public 3D medical image segmentation benchmarks, especially for the boundary locations and tiny tissues. The searching computational complexity of UXNet is cheap, enabling to search a network with best performance less than 1.5 days on two TitanXP GPUs.

Segmentation of medical images is an important step in many clinical and diagnostic imaging applications. Medical images present many challenges for automated segmentation including poor contrast at tissue boundaries. Traditional segmentation methods based solely on information from the image do not work well in such cases. Statistical shape information for objects in medical images are easy to obtain. In this paper, we propose a graph cuts-based segmentation method for medical images that incorporates statistical shape priors to increase robustness. Our proposed method is able to deal with complex shapes and shape variations while taking advantage of the globally efficient optimization by graph cuts. We demonstrate the effectiveness of our method on kidney images without strong boundaries.

It needs set parameters on image segmentation based on PCNN (Pulse Coupled Neural Network) now. This paper points out the new method for medical image segmentation based on improved PCNN and Tsallis entropy. The new methods can automatically segment the medical images without selecting the PCNN parameters. It gets the best results with combining with the Tsallis entropy. The new method is very useful for PCNN application in the medical images segmentation.

Region segmentation is one of the most common methods of medical image segmentation. However, it still has some disadvantages in practice: (1) Threshold choice will result in a poor performance in the image segmentation if there is little difference in the gray of an image. (2) Region-based segmentation algorithm is usually uncertain in defining the edge between the object and the background. This paper implements an improved algorithm to overcome these problems. In the algorithm, the FCM (fuzzy C-means) clustering method is used to improve the accuracy of image segmentation according to its stability. And Roberts operator is also added to compensate the deficiency in edge detection. This medical image segmentation method is a combination of region segmentation and edge segmentation, which is based on OTSU threshold segmentation, fuzzy C-means clustering and Roberts operator. Experiments show that the improved segmentation algorithm has a better performance than those traditional algorithms in the effect.

The fuzzy C-means (FCM) algorithm has got significant importance compared to other methods in medical image segmentation. In this paper, we propose a conditional spatial fuzzy C-means (csFCM) clustering algorithm to improve the robustness of the conventional FCM algorithm. This is achieved through the incorporation of conditioning effects imposed by some auxiliary variables and spatial information in the membership functions. By combining these two aspects, we are able to solve the problems of sensitivity to noisy data and inhomogeneity. The experimental results on several simulated and real-patient MRI brain images show that the csFCM method has superior performance on image segmentation than the FCM algorithm and some other FCM-based clustering algorithms.

Deep neural networks (DNNs) have achieved great success in medical image segmentation. However, the DNNs are generally deceived by the adversarial examples, making robustness a key factor of DNNs when applied in the field of medical research. In this paper, in order to evaluate the robustness of medical image segmentation networks, we propose a novel Region-based Dense Adversary Generation (RDAG) method to generate adversarial examples. Specifically, our method attacks the DNNs on both pixel-level and region-of-interesting (ROI) level. The pixel-level attack makes DNNs mistakenly segment each individual pixel. Meanwhile, the ROI-level attack will generate perturbation based on region information. We evaluate our proposed method for medical image segmentation on DRIVE and CELL datasets. The experimental results show that our proposed method achieves effective attack results on both datasets for medical image segmentation when compared with several state-of-the-art methods.KeywordsAdversarial examplesMedical image segmentationRegion-based dense adversary generation

Medical image segmentation is a critical application of computer vision in the analysis of medical images. Its primary objective is to isolate regions of interest in medical images from the background, thereby assisting clinicians in accurately identifying lesions, their sizes, locations, and their relationships with surrounding tissues. However, compared to natural images, medical images present unique challenges, such as low resolution, poor contrast, inconsistency, and scattered target regions. Furthermore, the accuracy and stability of segmentation results are subject to more stringent requirements. In recent years, with the widespread application of Convolutional Neural Networks (CNNs) in computer vision, deep learning-based methods for medical image segmentation have become a focal point of research. This paper categorizes, reviews, and summarizes the current representative methods and research status in the field of medical image segmentation. A comparative analysis of relevant experiments is presented, along with an introduction to commonly used public datasets, performance evaluation metrics, and loss functions in medical image segmentation. Finally, potential future research directions and development trends in this field are predicted and analyzed.

FSA-Net: Rethinking the attention mechanisms in medical image segmentation from releasing global suppressed information

Medical image segmentation methods are generally designed as fully-supervised to guarantee model performance, which requires a significant amount of expert annotated samples that are high-cost and laborious. Semi-supervised image segmentation can alleviate the problem by utilizing a large number of unlabeled images along with limited labeled images. However, learning a robust representation from numerous unlabeled images remains challenging due to potential noise in pseudo labels and insufficient class separability in feature space, which undermines the performance of current semi-supervised segmentation approaches. To address the issues above, we propose a novel semi-supervised segmentation method named as Rectified Contrastive Pseudo Supervision (RCPS), which combines a rectified pseudo supervision and voxel-level contrastive learning to improve the effectiveness of semi-supervised segmentation. Particularly, we design a novel rectification strategy for the pseudo supervision method based on uncertainty estimation and consistency regularization to reduce the noise influence in pseudo labels. Furthermore, we introduce a bidirectional voxel contrastive loss in the network to ensure intra-class consistency and inter-class contrast in feature space, which increases class separability in the segmentation. The proposed RCPS segmentation method has been validated on two public datasets and an in-house clinical dataset. Experimental results reveal that the proposed method yields better segmentation performance compared with the state-of-the-art methods in semi-supervised medical image segmentation. The source code is available at https://github.com/hsiangyuzhao/RCPS.

This paper presents a novel method for medical image segmentation that can detect the edges or boundaries of all target objects(defined as high intensity regions) in an image by integrating multi-scale gradient* vector flow(MGVF) into a modified level-set model. The MGVF uses multi-scale images and the gradient of gradient magnitude of a scaled image to generate a vector flow field. This vector flow field is then substituted into a corresponding partial differential equation(PDE) of a modified level-set model that represents the active contour. The proposed method can effectively pull the active contour to attach to the boundary of each target object in an image, especially the boundary of an object that is very close to another object and the boundary of an object with low gradient magnitude. The experiments were tested on 1600 two dimensional CT scan images and the results have shown that the proposed method can accurately detect the boundaries of bones, colons, and residuals inside the colons.

An efficient neural network based method for medical image segmentation

Learning with limited annotations: A survey on deep semi-supervised learning for medical image segmentation

The purpose of medical image segmentation is to divides the lesions image with a special meaning and background regional. The characteristics of medical images are generally more complex. There is often overlap between different regions, the edge of the area is vague. Research based on fuzzy clustering method for medical image segmentation, fuzzy C-means clustering and fuzzy kernel clustering methods were studied and discussed fully considered the spatial information, the single objective problem conversion into multi-objective problem. The experimental results show that the method use in medical image segmentation achieved good results.

Unsupervised domain adaption (UDA), which aims to enhance the segmentation performance of deep models on unlabeled data, has recently drawn much attention. In this paper, we propose a novel UDA method (namely DLaST) for medical image segmentation via disentanglement learning and self-training. Disentanglement learning factorizes an image into domain-invariant anatomy and domain-specific modality components. To make the best of disentanglement learning, we propose a novel shape constraint to boost the adaptation performance. The self-training strategy further adaptively improves the segmentation performance of the model for the target domain through adversarial learning and pseudo label, which implicitly facilitates feature alignment in the anatomy space. Experimental results demonstrate that the proposed method outperforms the state-of-the-art UDA methods for medical image segmentation on three public datasets, i.e., a cardiac dataset, an abdominal dataset and a brain dataset. The code will be released soon.

In the present work, an integrated modified canny detector and an active contour were proposed for automated medical image segmentation. Since the traditional canny detector (TCD) detects only the edge’s pixels, which are insufficient for labelling the image, a shape feature was extracted to select the initial region of interest ‘IROI’ as an initial mask for the active contour without edge (ACWE), using a proposed modified canny detector (MCD). This procedure overcomes the drawback of the manual initialization of the mask location and shape in the traditional ACWE, which is sensitive to the shape of region of region of interest (ROI). The proposed method solves this problem by selecting the initial location and shape of the IROI using the MCD. Also, a post-processing stage was applied for more cleaning and smoothing the ROI. A practical computational time is achieved as the proposed system requires less than 5 minutes, which is significantly less than the required time using the traditional ACWE. The results proved the ability of the proposed method for medical image segmentation with average dice 87.54%.