Ruixuan Wang

An automated pattern recognition system for classifying indirect immunofluorescence images of HEp-2 cells and specimens

Immunofluorescence antinuclear antibody tests are important for diagnosis and management of autoimmune conditions; a key step that would benefit from reliable automation is the recognition of subcellular patterns suggestive of different diseases. We present a system to recognize such patterns, at cellular and specimen levels, in images of HEp-2 cells. Ensembles of SVMs were trained to classify cells into six classes based on sparse encoding of texture features with cell pyramids, capturing spatial, multi-scale structure. A similar approach was used to classify specimens into seven classes. Software implementations were submitted to an international contest hosted by ICPR 2014 (Performance Evaluation of Indirect Immunofluorescence Image Analysis Systems). Mean class accuracies obtained on heldout test data sets were 87.1% and 88.5% for cell and specimen classification respectively. These were the highest achieved in the competition, suggesting that our methods are state-of-the-art. We provide detailed descriptions and extensive experiments with various features and encoding methods. HighlightsWe propose systems for classifying immunofluorescence images of HEp-2 cells.Images are classified at both the cell level and the specimen level.Ensemble SVM classification based on sparse coding of texture features was effective.Cell pyramids and artificial dataset augmentation increased mean class accuracy.The proposed systems came first in the I3A contest associated with ICPR 2014.

Automatic normal-abnormal video frame classification for colonoscopy

Two novel schemes are proposed to represent intermediate-scale features for normal-abnormal classification of colonoscopy images. The first scheme works on the full-resolution image, the second on a multi-scale pyramid space. Both schemes support any feature descriptor; here we use multi-resolution local binary patterns which outperformed other features reported in the literature in our comparative experiments. We also compared experimentally two types of features not previously used in colonoscopy image classification, bag of features and sparse coding, each with and without spatial pyramid matching (SPM). We find that SPM improves performance, therefore supporting the importance of intermediate-scale features as in the proposed schemes for classification. Within normal-abnormal frame classification, we show that our representational schemes outperforms other features reported in the literature in leave-N-out tests with a database of 2100 colonoscopy images.

Regular Texture Analysis as Statistical Model Selection

An approach to the analysis of images of regular texture is proposed in which lattice hypotheses are used to define statistical models. These models are then compared in terms of their ability to explain the image. A method based on this approach is described in which lattice hypotheses are generated using analysis of peaks in the image autocorrelation function, statistical models are based on Gaussian or Gaussian mixture clusters, and model comparison is performed using the marginal likelihood as approximated by the Bayes Information Criterion (BIC). Experiments on public domain regular texture images and a commercial textile image archive demonstrate substantially improved accuracy compared to two competing methods. The method is also used for classification of texture images as regular or irregular. An application to thumbnail image extraction is discussed.

Recognition of immunogold markers in electron micrographs

Immunoelectron microscopy is used in cell biological research to study the spatial distribution of intracellular macromolecules at the ultrastructural level. Colloidal gold particles (immunogold markers) are commonly used to localise molecules of interest on ultrathin sections and can be visualised in transmission electron micrographs as dark spots. Quantitative analysis involves detection of the immunogold markers, and is often performed manually or interactively as part of a stereological estimation technique. The method presented in this paper automatically detects and counts immunogold markers, estimating the location, size and type of each marker. It was evaluated on single-labelled as well as double-labelled images showing markers of two different sizes. This is a first step towards automatic analysis of immunoelectron micrographs, enabling a rapid and more complete quantitative analysis than is currently practicable.

High-entropy layouts for content-based browsing and retrieval

Multimedia browsing and retrieval systems can use dimensionality reduction methods to map from high-dimensional content-based feature distributions to low-dimensional layout spaces for visualization. However, this often results in displays in which many items are occluded whilst large regions are empty or only sparsely populated with items. Furthermore, such methods do not take into account the shape of the region of layout space to be populated. This paper proposes a layout method that addresses these limitations. Layout distributions with low Renyi quadratic entropy are penalized since these result in displays in which some regions are over-populated (i.e. many images are occluded), sparsely populated or empty. Experiments using two image datasets and a comparison with two related methods show the effectiveness of the proposed method.

Inter-Cluster Features for Medical Image Classification

Feature encoding plays an important role for medical image classification. Intra-cluster features such as bag of visual words have been widely used for feature encoding, which are based on the statistical information within each clusters of local features and therefore fail to capture the inter-cluster statistics, such as how the visual words co-occur in images. This paper proposes a new method to choose a subset of cluster pairs based on the idea of Latent Semantic Analysis (LSA) and proposes a new inter-cluster statistics which capture richer information than the traditional co-occurrence information. Since the cluster pairs are selected based on image patches rather than the whole images, the final representation also captures the local structures present in images. Experiments on medical datasets show that explicitly encoding inter-cluster statistics in addition to intra-cluster statistics significantly improves the classification performance, and adding the rich inter-cluster statistics performs better than the frequency based inter-cluster statistics.

Visualizing Image Collections Using High-Entropy Layout Distributions

Mechanisms for visualizing image collections are essential for browsing and exploring their content. This is especially true when metadata are ineffective in retrieving items due to the sparsity or esoteric nature of text. An obvious approach is to automatically lay out sets of images in ways that reflect relationships between the items. However, dimensionality reduction methods that map from high-dimensional content-based feature distributions to low-dimensional layout spaces for visualization often result in displays in which many items are occluded whilst large regions are empty or only sparsely populated. Furthermore, such methods do not consider the shape of the region of layout space to be populated. This paper proposes a method, high-entropy layout distributions. that addresses these limitations. Layout distributions with low differential entropy are penalized. An optimization strategy is presented that finds layouts that have high differential entropy and that reflect inter-image similarities. Efficient optimization is obtained using a step-size constraint and an approximation to quadratic (Renyi) entropy. Two image archives of cultural and commercial importance are used to illustrate and evaluate the method. A comparison with related methods demonstrates its effectiveness.

Boundary-aware Fully Convolutional Network for Brain Tumor Segmentation

We propose a novel, multi-task, fully convolutional network (FCN) architecture for automatic segmentation of brain tumor. This network extracts multi-level contextual information by concatenating hierarchical feature representations extracted from multimodal MR images along with their symmetric-difference images. It achieves improved segmentation performance by incorporating boundary information directly into the loss function. The proposed method was evaluated on the BRATS13 and BRATS15 datasets and compared with competing methods on the BRATS13 testing set. Segmented tumor boundaries obtained were better than those obtained by single-task FCN and by FCN with CRF. The method is among the most accurate available and has relatively low computational cost at test time.

Learning Query-Dependent Distance Metrics for Interactive Image Retrieval

An approach to target-based image retrieval is described based on on-line rank-based learning. User feedback obtained via interaction with 2D image layouts provides qualitative constraints that are used to adapt distance metrics for retrieval. The user can change the query during a search session in order to speed up the retrieval process. An empirical comparison of online learning methods including ranking-SVM is reported using both simulated and real users.

Retinal microvascular parameters are not associated with reduced renal function in a study of individuals with type 2 diabetes

The eye provides an opportunistic “window” to view the microcirculation. There is published evidence of an association between retinal microvascular calibre and renal function measured by estimated glomerular filtration rate (eGFR) in individuals with diabetes mellitus. Beyond vascular calibre, few studies have considered other microvascular geometrical features. Here we report novel null findings for measures of vascular spread (vessel fractal dimension), tortuosity, and branching patterns and their relationship with renal function in type 2 diabetes over a mean of 3 years. We performed a nested case-control comparison of multiple retinal vascular parameters between individuals with type 2 diabetes and stable (non-progressors) versus declining (progressors) eGFR across two time points within a subset of 1072 participants from the GoDARTS study cohort. Retinal microvascular were measured using VAMPIRE 3.1 software. In unadjusted analyses and following adjustment for age, gender, systolic blood pressure, HbA1C, and diabetic retinopathy, no associations between baseline retinal vascular parameters and risk of eGFR progression were observed. Cross-sectional analysis of follow-up data showed a significant association between retinal arteriolar diameter and eGFR, but this was not maintained following adjustment. These findings are consistent with a lack of predictive capacity for progressive loss of renal function in type 2 diabetes.