Correction Learning for Medical Image Segmentation

Medical image segmentation using deep learning typically requires a large quantity of well-annotated data. However, the acquisition of pixel-level annotations is arduous and expensive, often requiring the expertise of experienced medical professionals. Recent advancements in few-shot learning can help address label scarcity in medical image segmentation by leveraging a small amount of labeled data. Most research on prototypical learning for medical image segmentation involves prototypes averaged across the entire class, ignoring fine details. In this work, we propose a novel dual prototype network and introduce part prototypes to supplement local prototypes for extracting fine-grained features and enhancing model performance in one-shot medical image segmentation. Extensive experiments on the CHAOS dataset demonstrate the effectiveness of the proposed method on one-shot segmentation, outperforming other methods by a significant margin.Clinical relevance- The proposed method can address the problem of prototypical self-supervised learning in the one-shot medical image segmentation scenario, saving annotation costs in clinical practice.

Many challenges and open issues related to the tremendous growth in digitizing collections of cultural heritage documents have been raised, such as information retrieval in digital libraries or analyzing page content of historical books. Recently, graphic/text segmentation in historical documents has posed specific challenges due to many particularities of historical document images (e.g. noise and degradation, presence of handwriting, overlapping layouts, great variability of page layout). To cope with those challenges, a method based on learning texture features for historical document image enhancement and segmentation is proposed in this article. The proposed method is based on using the simple linear iterative clustering (SLIC) superpixels, Gabor descriptors and support vector machines (SVM). It has been evaluated on 100 document images which have been selected from the databases of the competitions (i.e. historical document layout analysis and historical book recognition) in the context of ICDAR conference and HIP workshop (2011 and 2013). To demonstrate the enhancement and segmentation quality, the evaluation is based on manually labeled ground truth and shows the effectiveness of the proposed method through qualitative and numerical experiments. The proposed method provides interesting results on historical document images having various page layouts and different typographical and graphical properties.

Active contours driven by local likelihood image fitting energy for image segmentation

Biological Image Segmentation Using Region-Scalable Fitting Energy with B-Spline Level Set Implementation and Watershed

Intensity inhomogeneity or weak texture region image segmentation plays an important role in computer vision and image processing. RSF (Region-Scalable Fitting) active contour model has been proved to be an effective method to segment intensity inhomogeneity. However RSF model is sensitive to the initial location of evolution curve , it tends to fall into local optimal. Aiming at the problem, this paper proposed a new method for image segmentation based on fractional differentiation and RSF model. The proposed method adds the global Grünwald-Letnikov fractional gradient into the RSF model. Thus the gradient of the intensity inhomogeneity and weak texture regions is strengthened. As a result, both the robustness of initial location of evolution curve and efficiency of image segmentation are improved. Theoretical analysis and experimental results demonstrate that the proposed algorithm is capable of segmenting the intensity inhomogeneities and weak texture images. It is robust to curve initial location, furthermore the efficiency of segmentation is improved.

Image segmentation actually could be regarded as a computer vision pre-processing step of cloud computing and big data analysis. Active contour model is a new research direction for images segmentation in synthetic aperture radar(SAR) images. However, due to the SAR images have speckle noise and low signal-to-clutter ratio, active contour models cannot produce satisfied segmentation results. To solve these issues, active contours driven by visual saliency fitting energy is proposed in this paper. First, a saliency map is calculated by improved local contrast measure. Then, a visual saliency fitting energy is proposed based on saliency map and local binary fitting energy. The saliency map has a higher signal-to-clutter ratio and the local binary fitting energy is an active contour model that can effectively segment images with intensity inhomogeneity. In this way, the proposed method has a better segmentation result. The experiments on ship chips in SAR images demonstrate that the proposed method is robust to speckle noise and the segmentation result has good connectivity and integrity for entire ship targets.

Superpixel algorithm aims to semantically group neighboring pixels into a coherent region. It could significantly boost the performance of the subsequent vision processing task such as image segmentation. Recently, the work simple linear iterative clustering (SLIC) [1] has drawn huge attention for its state-of-the-art segmentation performance and high computational efficiency. However, the performance of SLIC is dramatically degraded for noisy images. In this work, we propose three measures to improve the robustness of SLIC against noise: 1) a new pixel intensity distance measurement is designed by explicitly considering the within-cluster noise variance; 2) the spatial distance measurement is refined by exploiting the variation of pixel locations in a cluster; and 3) a noise-robust estimator is proposed to update the cluster centers by excluding the possible outliers caused by noise. Extensive experimental results on synthetic noisy images validate the effectiveness of those improvements. In addition, we apply the proposed noise-robust SLIC to superpixel-based noise level estimation task to demonstrate its practical usage.

Active contour models are always designed on the assumption that images are approximated by regions with piecewise-constant intensities. This assumption, however, cannot be satisfied when describing intensity inhomogeneous images which frequently occur in real world images and induced considerable difficulties in image segmentation. A milder assumption that the image is statistically homogeneous within different local regions may better suit real world images. By taking local image information into consideration, an enhanced active contour model is proposed to overcome difficulties caused by intensity inhomogeneity. In addition, according to curve evolution theory, only the region near contour boundaries is supposed to be evolved in each iteration. We try to detect the regions near contour boundaries adaptively for satisfying the requirement of curve evolution theory. In the proposed method, pixels within a selected region near contour boundaries have the opportunity to be updated in each iteration, which enables the contour to be evolved gradually. Experimental results on synthetic and real world images demonstrate the advantages of the proposed model when dealing with intensity inhomogeneity images.

The local intensity fitting active contour models can handle inhomogeneous images, but they suffer from the shortcomings of poor performance in segmenting images with severe intensity inhomogeneity and being sensitive to initializations. To overcome these problems, we put forward a robust active contour model by introducing two adjustment coefficient functions. The energy functional of the proposed model is presented by integrating the local fitting term and two adjustment coefficient functions. The local fitting term is defined by introducing two local fitting functions that approximate the image intensities inside and outside of the contour. These two adjustment coefficient functions, which improve the segmentation performance and enhance the robustness to initialization, are constructed by utilizing the Sigmoid function as well as the difference between local intensity averages and image actual intensities. The results of the experiments on synthetic and real images demonstrate that the presented model not only is capable of handling intensity inhomogeneity better under more flexible initializations but also takes less time in comparison with other region-based models. Furthermore, these two adjustment coefficients can be employed to other local intensity fitting models to enhance the robustness to initialization and to decrease the segmentation time.

This paper investigates the application of the Simple Linear Iterative Clustering (SLIC) algorithm for complex object image segmentation, on the example of images of human body injuries. The study solves the problem of the lack of quantitative evidence regarding SLIC's algorithm performance in high-precision area and boundary assessment of the lesion on a digital image of a human body with a wound injury on it. A comprehensive methodology is developed to evaluate SLIC's algorithm efficacy across various complex images and image resolutions. The research utilizes a combined dataset of 3696 wound images from the Foot Ulcer Segmentation Challenge (FUSeg) and WoundSeg datasets. Bayesian optimization is utilized to fine-tune SLIC algorithm hyperparameters, focusing on the number of segments and compactness. Results indicate that SLIC algorithm demonstrates consistent performance across different implementations, achieving Dice scores around 0.84 and Soft Boundary F1 scores around 0.55. The study reveals that the optimal number of segments for SLIC algorithm can be defined relative to the spatial dimensions of the input image, with maximal image dimension *2 being the most effective value. A thorough analysis of various segmentation metrics is conducted, including IoU, Dice Score, and Boundary F1 Score. The research introduces and employs the Soft Boundary F1 Score – modification of Boundary F1 Score, a novel metric designed to provide a more nuanced evaluation of boundary detection accuracy while offering a smoother optimization landscape. This metric proves particularly valuable in assessing the performance of SLIC algorithm in image with complex objects on them segmentation tasks. Importantly, this research presents an idealized SLIC-based segmentation approach, where superpixels are optimally combined using ground-truth masks to establish an upper bound of performance. This idealized SLIC algorithm segmentation is compared with a pre-trained on the FUSeg dataset UNet model, showcasing superior generalization capability across diverse wound types. On the WoundSeg dataset, the idealized SLIC algorithm approach achieved a Dice score of 0.84, significantly outperforming the UNet model (0.12 Dice score). As a result, this study provides valuable insights for improving complex objects segmentation methods and highlights the need for further research on developing effective methods for superpixel classification in real-world scenarios. The findings also highlight the potential of SLIC-based approaches in addressing the challenges of diverse data types and limited training data.

For better analyzing and adopting superpixel methods in image segmentation, an improved Simple Linear Iterative Clustering (SLIC) algorithm is put forward, which sustains that homogeneous regions show high consistence during clustering. Firstly, a primary iteration of SLIC approach is employed to generate uniform superpixels. Then an update strategy is introduced to determine whether to recluster the candidate region. In homogeneous regions, a cluster center often shows relatively small deviation of last position in spatial-color feature space when local iteration occurs, which can be regarded as redundant computation and be reduced. Experimental results show that the strategy brings a remarkable increased efficiency for traditional SLIC without significant affection on segmentation results.

Due to the low contrast, blurry boundaries, and large amount of shadows in breast ultrasound (BUS) images, automatic tumor segmentation remains a challenging task. Deep learning provides a solution to this problem, since it can effectively extract representative features from lesions and the background in BUS images. A novel automatic tumor segmentation method is proposed by combining a dilated fully convolutional network (DFCN) with a phase-based active contour (PBAC) model. The DFCN is an improved fully convolutional neural network with dilated convolution in deeper layers, fewer parameters, and batch normalization techniques; and has a large receptive field that can separate tumors from background. The predictions made by the DFCN are relatively rough due to blurry boundaries and variations in tumor sizes; thus, the PBAC model, which adds both region-based and phase-based energy functions, is applied to further improve segmentation results. The DFCN model is trained and tested in dataset 1 which contains 570BUS images from 89 patients. In dataset 2, a 10-fold support vector machine (SVM) classifier is employed to verify the diagnostic ability using 460 features extracted from the segmentation results of the proposed method. Advantages of the present method were compared with three state-of-the-art networks; the FCN-8s, U-net, and dilated residual network (DRN). Experimental results from 170BUS images show that the proposed method had a Dice Similarity coefficient of 88.97±10.01%, a Hausdorff distance (HD) of 35.54±29.70 pixels, and a mean absolute deviation (MAD) of 7.67±6.67 pixels, which showed the best segmentation performance. In dataset 2, the area under curve (AUC) of the 10-fold SVM classifier was 0.795 which is similar to the classification using the manual segmentation results. The proposed automatic method may be sufficiently accurate, robust, and efficient for medical ultrasound applications.

A smoke detection method is proposed in single-frame video sequence images for forest fire detection in large space and complex scenes. A new superpixel merging algorithm is further studied to improve the existing horizon detection algorithm. This method performs Simple Linear Iterative Clustering (SLIC) superpixel segmentation on the image, and the over-segmentation problem is solved with a new superpixel merging algorithm. The improved sky horizon line segmentation algorithm is used to eliminate the interference of clouds in the sky for smoke detection. According to the spectral features, the superpixel blocks are classified by support vector machine (SVM). The experimental results show that the superpixel merging algorithm is efficient and simple, and easy to program. The smoke detection technology based on image segmentation can eliminate the interference of noise such as clouds and fog on smoke detection. The accuracy of smoke detection is 77% in a forest scene, it can be used as an auxiliary means of monitoring forest fires. A new attempt is given for forest fire warning and automatic detection.

Active contour model driven by Self Organizing Maps for image segmentation

Pixel accurate 2-D, 3-D medical image segmentation to identify abnormalities for further analysis is on high demand for computer-aided medical imaging applications. Various segmentation algorithms have been studied and applied in medical imaging for many years, but the problem remains challenging due to growing a large number of variety of applications starting from lung disease diagnosis based on x-ray images, nucleus detection, and segmentation based on microscopic pictures to kidney tumour segmentation. The recent innovation in deep learning brought revolutionary advances in computer vision. Image segmentation is one such area where deep learning shows its capacity and improves the performance by a larger margin than its successor. This chapter overviews the most popular deep learning-based image segmentation techniques and discusses their capabilities and basic advantages and limitations in the domain of medical imaging.