The fuzzy c-means clustering with guided image filter (GF) is a useful method for image segmentation. The single-channel GF can be efficiently applied to the gray-scale guidance image, but for the color guidance image, due to the high run-time overhead on the calculation of the inverse of the covariance matrix, it is a hard work to perform the multi-channel GF. To address this issue, we propose a novel weighting multi-channel guided image filter (WMGF) method. In this method, each channel of the color guidance image is utilized to guide the filtering for the input image independently and a novel weight is defined for each channel according to the variance of the image pixels in a local window, which greatly eliminates the mutual influence between different channels and brings about a low run-time overhead. In addition, based on the WMGF method, we present a new fuzzy c-means clustering algorithm (\(\hbox {FCM}_{\scriptscriptstyle {WMGF }}\)) for the color image segmentation, in which the WMGF is performed on the membership matrix in each iteration of the fuzzy c-means clustering. To further enhance the different noise-immunity and edge preservation, the multivariate morphological reconstruction (MMR) method is introduced into the proposed fuzzy clustering method (MMR\(\_\hbox {FCM}_{\scriptscriptstyle {WMGF }}\)) to obtain higher segmentation precision. Experiments on color images with Salt & Pepper and Gaussian noises demonstrate the superiority of the proposed methods.
Purpose: To propose a novel method to improve the mega-voltage CT (MVCT) image quality for helical TomoTherapy while maintaining the stability on dose calculation. Materials and Methods: The Block-Matching 3D-transform (BM3D) and Discriminative Feature Representation (DFR) methods were combined into a novel BM3D+DFR method for their respective advantages. A phantom (Catphan504) and three serials of clinical (head & neck, chest and pelvic) MVCT images from 30 patients were acquired by helical TomoTherapy system. The contrast-to-noise ratio (CNR) and edge detection algorithm (canny) were employed for image quality comparison between the original and BM3D+DFR enhanced MVCT. Simulated rectangular field of 6MV X-ray beams were vertically delivered on original and post-processed MVCT serials of the same CT density phantom, and the dose curves on both serials were compared to test the effects of image enhancement on dose calculation accuracy. Results: Totally 466 transversal MVCT slices were acquired and processed by both BM3D and the proposed BM3D+DFR methods. Compared to the original MVCT image, the BM3D+DFR method presented remarkable improvement in terms of soft tissue contrast and noise reduction. For the phantom image, the CNR of the region of interest (ROI) was improved from 1.70 to 4.03. The average CNR of ROIs for 10 patients from each anatomical group were increased significantly from 1.45±1.51 to 2.09±1.68 for head & neck (p<0.001), from 0.92±0.78 to 1.36±0.85 for chest (p<0.001), and from 1.12±1.22 to 1.76±1.31 for pelvic (p<0.001), respectively. The canny edge detection operator showed that BM3D+DFR provided clearer organ boundaries with less chaos. The root-mean-square of the dosimetry difference on iso-center passed horizontal dose profile curves and vertical percentage depth dose curves were only 0.09% and 0.06%, respectively. Conclusions: The proposed BM3D+DFR method is feasible to improve the soft tissue contrast for the original MVCT images with coincidence in dose calculation and without compromising resolution. After integration in clinical workflow, the post-processed MVCT may be better applied on image-guided and adaptive helical TomoTherapy.
18 March 2020 in IEEE Journal of Biomedical and Health Informatics
Quantitative assessment of retinal layer thickness in spectral domain-optical coherence tomography (SD-OCT) images is vital for clinicians to determine the degree of ophthalmic lesions. However, due to the complex retinal tissues, high-level speckle noises and low intensity constraint, how to accurately recognize the retinal layer structure still remains a challenge. To overcome this problem, this paper proposes an adaptive-guided-coupling-probability level set method for retinal layer segmentation in SD-OCT images. Specifically, based on Bayes's theorem, each voxel probability representation is composed of two probability terms in our method. The first term is constructed as neighborhood Gaussian fitting distribution to characterize intensity information for each intra-retinal layer. The second one is boundary probability map generated by combining anatomical priors and adaptive thickness information to ensure surfaces evolve within a proper range. Then, the voxel probability representation is introduced into the proposed segmentation framework based on coupling probability level set to detect layer boundaries. A total of 1792 retinal B-scan images from 4 SD-OCT cubes in healthy eyes, 5 cubes in abnormal eyes with central serous chorioretinaopathy and 5 SD-OCT cubes in abnormal eyes with age-related macular disease are used to evaluate the proposed method. The experiment demonstrates that the segmentation results obtained by the proposed method have a good consistency with ground truth, and the proposed method outperforms six methods in the layer segmentation of uneven retinal SD-OCT images.
30 January 2020 in IEEE Geoscience and Remote Sensing Letters
Sparse subspace clustering (SSC), as a powerful tool in hyperspectral image (HSI) segmentation, has caused widespread attention recently. However, the existing methods are generally affected by the limitations of region consistency and time complexity. To address these issues, we propose a fast high-order SSC (FHoSSC) with the cumulative Markov random field (MRF) algorithm in this letter. By capturing high-order information, we explore the pixel-level contextual restraints within the same high-order data to preserve consistency. Also, a new regularization term is introduced by the spatial constraints among adjacent high-order data for improving segmentation accuracy. Finally, cumulative MRF, as a variant of MRF, is used to further refine the segmentation result through combining original HSI information. Experiments on real data sets demonstrate that the proposed method not only outperforms the state-of-the-art methods in segmentation accuracy but also reduces the time complexity significantly.
SAR image classification is one of the research hotspots in the field of remote sensing. The performance of SAR image classification greatly depends on the learning of features and the design of classifiers. However, traditional SAR image classification methods either focus on learning (deep) features or focus on designing discriminative classifiers, while ignoring the correlation between them, resulting in the learned features and classifiers often not matching. To address the above issues, in this paper a novel classifier, termed entropy based low-rank dictionary pair learning (ELRDPL) method is first designed, which introduces the entropy theory and low-rank constraints into the objective function of dictionary learning for increasing the discriminative ability and decreasing the space occupation. Based on the constructed classifier, an entropy based deep lowrank dictionary pair learning network (EDLRDPL Net) is then proposed, which performs joint learning of deep features and discriminative dictionaries by embedding the ELRDPL classifier into the deep neural network. Extensive experimental results on four SAR image classification datasets demonstrate the effectiveness of EDLRDPL Net.