- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) - Honolulu, HI (2018.7.18-2018.7.21)] 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) - Clumped Nuclei Segmentation with Adjacent Point Match and Local Shape-Based Intensity Analysis in Fluorescence Microscopy Images
摘要： Highly clumped nuclei captured in fluorescence microscopy images are commonly observed in a wide spectrum of tissue-related biomedical investigations. To ensure the quality of downstream biomedical analyses, it is essential to accurately segment clustered nuclei. However, this presents a technical challenge as fluorescence intensity alone is often insufficient for recovering the true nuclei boundaries. In this paper, we propose an segmentation algorithm that identifies point pair connection candidates and evaluates adjacent point connections with a formulated ellipse fitting quality indicator. After connection relationships are determined, we recover the resulting dividing paths by following points with specific eigenvalues from the image Hessian in a constrained searching space. We validate our algorithm with 560 image patches from two classes of tumor regions of seven brain tumor patients. Both qualitative and quantitative experimental results suggest that our algorithm is promising for dividing overlapped nuclei in fluorescence microscopy images widely used in various biomedical research.
关键词： clumped nuclei segmentation,fluorescence microscopy images,adjacent point match,local shape-based intensity analysis
更新于2025-09-04 15:30:14
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - Automatic Segmentation of Lumen Intima Layer in Transverse Mode Ultrasound Images
摘要： We propose an elliptical active disc technique for the segmentation of common carotid artery lumen intimal layer from transverse mode ultrasound images. The segmentation and subsequent outlining problem is posed as one of optimization of a local energy function with respect to the five degrees-of-freedom that characterize the elliptical active disc. Gradient descent technique is used to find the minimum of the energy function with respect to the five parameters that describe the disc. In addition, we use Green's theorem to optimize the computation of the partial derivatives. For automatic initialization of the active disc, we use the normalized cross-correlation technique. We report results of experimental validation on SPLab, Brno university database, which contains 971 transverse mode ultrasound images of the carotid artery. We achieve accurate carotid artery lumen intima detection in 97.63% of cases. In addition, for lumen intima layer segmentation we achieve an average Dice index of 94.83%.
关键词： ultrasound images,stroke,segmentation,active disc,Common carotid artery,lumen intima layer
更新于2025-09-04 15:30:14
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - Neural Cell Segmentation in Large-Scale 3D Color Fluorescence Microscopy Images for Developemental Neuroscience
摘要： The cells composing brain tissue, neurons, and glia, form extraordinarily complex networks that support cognitive functions. Understanding the organization and development of these networks requires quantitative data resolved at the single cell level. To this aim, we apply novel large-scale 3D multicolor microscopy methodologies in combination with ”Brainbow”, a transgenic approach enabling to label neural cells with diverse combinations of spectrally distinct fluorescent proteins. In this paper, we present a pipeline based on Convolutional Neural Network (CNN) to detect and segment individual astrocytes, the main type of glial cells of the brain, and map the domains occupied by their fine processes. This bioimage analysis approach successfully handles the challenging variety of astrocyte shape, color, size and their overlap with background elements. Our method shows significant improvement compared with classical techniques, opening the way to varied biological inquiries.
关键词： deep learning,segmentation
更新于2025-09-04 15:30:14
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Multi-Source Remote Sensing Data Classification via Fully Convolutional Networks and Post-Classification Processing
摘要： This paper presents a new data fusion methodology named Fusion-FCN for the classification of multi-source remote sensing data using fully convolutional networks (FCNs). Three different types of data including LiDAR data, hyperspectral images and very high resolution images are utilized in the proposed framework. Considering the confusions between similar categories (e.g., road and highway), we further implement post-classification processing with the topological relationship among different objects based on the result yielded by the proposed Fusion-FCN. The proposed method achieved an overall accuracy of 80.78% and a kappa coefficient of 0.80, which ranked first in the 2018 IEEE GRSS Data Fusion Contest.
关键词： Data fusion,deep learning,image segmentation,fully convolutional network
更新于2025-09-04 15:30:14
-
[Lecture Notes in Computer Science] Algorithms and Architectures for Parallel Processing Volume 11335 (18th International Conference, ICA3PP 2018, Guangzhou, China, November 15-17, 2018, Proceedings, Part II) || SMIM: Superpixel Mutual Information Measurement for Image Quality Assessment
摘要： The image quality assessment (IQA) is a fundamental problem in signal processing that aims to measure the objective quality of an image by designing a mathematical model. Most full-reference (FR) IQA methods use ?xed sliding windows to obtain structure information but ignore the variable spatial con?guration information. In this paper, we propose a novel full-reference IQA method, named “superpixel normalized mutual information (SMIM)” based on the perspective of variable receptive ?eld and information entropy. First, we ?nd that consistence relationship exists between the information ?delity and human visual of individuals. Thus, we reproduce the human visual system (HVS) to semantically divide the image into multiple patches via superpixel segmentation. Then the weights of each image patches are adaptively calculated via its information volume. We veri?ed the e?ectiveness of SMIM by applying it to data from the TID2008 database and data generated using some real application scenarios. Experiments show that SMIM outperforms some state-of-the-art FR IQA algorithms, including visual information ?delity (VIF).
关键词： Superpixel segmentation,Mutual information,Image quality assessment
更新于2025-09-04 15:30:14
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - Peekaboo-Where are the Objects? Structure Adjusting Superpixels
摘要： This paper addresses the search for a fast and meaningful image segmentation in the context of k-means clustering. The proposed method builds on a widely-used local version of Lloyd’s algorithm, called Simple Linear Iterative Clustering (SLIC). We propose an algorithm which extends SLIC to dynamically adjust the local search, adopting superpixel resolution dynamically to structure existent in the image, and thus provides for more meaningful superpixels in the same linear runtime as standard SLIC. The proposed method is evaluated against state-of-the-art techniques and improved boundary adherence and undersegmentation error are observed, whilst still remaining among the fastest algorithms which are tested.
关键词： Image texture analysis,Image segmentation,Clustering algorithms
更新于2025-09-04 15:30:14
-
[IEEE 2018 International Joint Conference on Neural Networks (IJCNN) - Rio de Janeiro (2018.7.8-2018.7.13)] 2018 International Joint Conference on Neural Networks (IJCNN) - Automatic Guidewire Tip Segmentation in 2D X-ray Fluoroscopy Using Convolution Neural Networks
摘要： Guidewire tip detection in the percutaneous coronary intervention is important. It assists physicians in navigating and is a prerequisite for clinic applications such as surgical skill assessment and robot assisted surgery. Nevertheless, accurate detection is not a trivial task due to the noisy background of the 2D X-ray image and the thin, deformable structure of the tip. In this paper, an automatic method based on cascaded convolution neural networks is proposed to segment the tip in the 2D X-ray image. The main contribution of the method is to use a cascade detection-segmentation structure to overcome the noisy background and the large deformation of the tip, achieve robust, high-precision segmentation. On the other hand, sufficient annotated training samples are necessary for convolution neural network models, while pixel-level annotating is tedious and time-consuming. Accordingly, a novel data augmentation algorithm is introduced to improve the model generalization and performance, reduce the cost of data annotation. Evaluations were conducted on a dataset consisting of 22 different sequences of 2D X-ray images, 15 sequences for training and 7 sequences for evaluation. The proposed approach obtained tip precision of 0.532 pixels, F1 score of 0.939, false tracking rate of 0.800%, and missing tracking rate of 9.900% on the test set. And the running speed is 4-5 frames per second.
关键词： Guidewire tip detection,2D X-ray fluoroscopy,Convolution Neural Networks,Data augmentation,Segmentation
更新于2025-09-04 15:30:14
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - Detection and Tracking of Astral Microtubules in Fluorescence Microscopy Images
摘要： In this paper we explore detection and tracking of astral micro-tubules, a sub-population of microtubules which only exists during and immediately before mitosis and aids in the spindle orientation by connecting it to the cell cortex. Its analysis can be useful to deter-mine the presence of certain diseases, such as brain pathologies and cancer. The proposed algorithm focuses on overcoming the prob-lems regarding fluorescence microscopy images and microtubule behaviour by using various image processing techniques and is then compared with three existing algorithms, tested on consistent sets of images.
关键词： image segmentation,Medical diagnostic imaging,kalman filter,fluorescence microscopy,microtubules
更新于2025-09-04 15:30:14
-
Haze Removal of Single Remote Sensing Image by Combining Dark Channel Prior with Superpixel
摘要： Dehazing is important in remote sensing image restorations to enhance the acquired low quality image for interpretation. However, traditional methods have some limitations for dehazing of remote sensing images due to its color distortion and noise. In this paper, we propose an improved method combining superpixel segmentation with luminance information of a haze image to estimate the atmospheric light instead of dark channel prior. Using this method with the haze imaging model, we can directly estimate the thickness of the haze and restore a high quality haze-free image. Experimental results on a variety of remote sensing haze images demonstrate our approach can achieve better image quality when compared with well-known He's [1] method for remote sensing images.
关键词： atmospheric scattering model,Haze removal,superpixel segmentation
更新于2025-09-04 15:30:14