Yan Nei Law

A Multiresolution Stochastic Level Set Method for Mumford–Shah Image Segmentation

The Mumford-Shah model is one of the most successful image segmentation models. However, existing algorithms for the model are often very sensitive to the choice of the initial guess. To make use of the model effectively, it is essential to develop an algorithm which can compute a global or near global optimal solution efficiently. While gradient descent based methods are well-known to find a local minimum only, even many stochastic methods do not provide a practical solution to this problem either. In this paper, we consider the computation of a global minimum of the multiphase piecewise constant Mumford-Shah model. We propose a hybrid approach which combines gradient based and stochastic optimization methods to resolve the problem of sensitivity to the initial guess. At the heart of our algorithm is a well-designed basin hopping scheme which uses global updates to escape from local traps in a way that is much more effective than standard stochastic methods. In our experiments, a very high-quality solution is obtained within a few stochastic hops whereas the solutions obtained with simulated annealing are incomparable even after thousands of steps. We also propose a multiresolution approach to reduce the computational cost and enhance the search for a global minimum. Furthermore, we derived a simple but useful theoretical result relating solutions at different spatial resolutions.

A Semisupervised Segmentation Model for Collections of Images

In this paper, we consider the problem of segmentation of large collections of images. We propose a semisupervised optimization model that determines an efficient segmentation of many input images. The advantages of the model are twofold. First, the segmentation is highly controllable by the user so that the user can easily specify what he/she wants. This is done by allowing the user to provide, either offline or interactively, some (fully or partially) labeled pixels in images as strong priors for the model. Second, the model requires only minimal tuning of model parameters during the initial stage. Once initial tuning is done, the setup can be used to automatically segment a large collection of images that are distinct but share similar features. We will show the mathematical properties of the model such as existence and uniqueness of solution and establish a maximum/minimum principle for the solution of the model. Extensive experiments on various collections of biological images suggest that the proposed model is effective for segmentation and is computationally efficient.

Semi-Supervised Subspace Learning for Mumford-Shah Model Based Texture Segmentation

We propose a novel image segmentation model which incorporates subspace clustering techniques into a Mumford-Shah model to solve texture segmentation problems. While the natural unsupervised approach to learn a feature subspace can easily be trapped in a local solution, we propose a novel semi-supervised optimization algorithm that makes use of information derived from both the intermediate segmentation results and the regions-of-interest (ROI) selected by the user to determine the optimal subspaces of the target regions. Meanwhile, these subspaces are embedded into a Mumford-Shah objective function so that each segment of the optimal partition is homogeneous in its own subspace. The method outperforms standard Mumford-Shah models since it can separate textures which are less separated in the full feature space. Experimental results are presented to confirm the usefulness of subspace clustering in texture segmentation.

Automatic measurement of volume percentage stroma in endometrial images using texture segmentation.

The popularity of digital microscopy and tissue microarrays allow the use of high‐throughput imaging for pathology research. To coordinate with this new technique, it is essential to automate the process of extracting information from such high amount of images. In this paper, we present a new model called the Subspace Mumford‐Shah model for texture segmentation of microscopic endometrial images. The model incorporates subspace clustering techniques into a Mumford‐Shah model to solve texture segmentation problems. The method first uses a supervised procedure to determine several optimal subspaces. These subspaces are then embedded into a Mumford‐Shah objective function so that each segment of the optimal partition is homogeneous in its own subspace. The method outperforms a widely used method in bioimaging community called k‐means segmentation since it can separate textures which are less separated in the full feature space, which confirm the usefulness of subspace clustering in texture segmentation. Experimental results also show that the proposed method is well performed on diagnosing premalignant endometrial disease and is very practical for segmenting image set sharing similar properties.

A Variational Model for Segmentation of Overlapping Objects With Additive Intensity Value

We propose a variant of the Mumford-Shah model for the segmentation of a pair of overlapping objects with additive intensity value. Unlike standard segmentation models, it does not only determine distinct objects in the image, but also recover the possibly multiple membership of the pixels. To accomplish this, some a priori knowledge about the smoothness of the object boundary is integrated into the model. Additivity is imposed through a soft constraint which allows the user to control the degree of additivity and is more robust than the hard constraint. We also show analytically that the additivity parameter can be chosen to achieve some stability conditions. To solve the optimization problem involving geometric quantities efficiently, we apply a multiphase level set method. Segmentation results on synthetic and real images validate the good performance of our model, and demonstrate the models applicability to images with multiple channels and multiple objects.

Subspace learning for Mumford–Shah-model-based texture segmentation through texture patches

In this paper, we develop a robust and effective algorithm for texture segmentation and feature selection. The approach is to incorporate a patch-based subspace learning technique into the subspace Mumford-Shah (SMS) model to make the minimization of the SMS model robust and accurate. The proposed method is fully unsupervised in that it removes the need to specify training data, which is required by existing methods for the same model. We further propose a novel (to our knowledge) pairwise dissimilarity measure for pixels. Its novelty lies in the use of the relevance scores of the features of each pixel to improve its discriminating power. Some superior results are obtained compared to existing unsupervised algorithms, which do not use a subspace approach. This confirms the usefulness of the subspace approach and the proposed unsupervised algorithm.

Automated Protein Distribution Detection in High-Throughput Image-Based siRNA Library Screens

The availability of RNA interference (RNAi) libraries, automated microscopy and computational methods enables millions of biochemical assays to be carried out simultaneously. This allows systematic, data driven high-throughput experiments to generate biological hypotheses that can then be verified with other techniques. Such high-throughput screening holds great potential for new discoveries and is especially useful in drug screening. In this study, we present a computational framework for an automatic detection of changes in images of in vitro cultured keratinocytes when phosphatase genes are silenced using RNAi technology. In these high-throughput assays, the change in pattern only happens in 1–2% of the cells and fewer than one in ten genes that are silenced cause phenotypic changes in the keratin intermediate filament network, with small keratin aggregates appearing in cells in addition to the normal reticular network seen in untreated cells. By taking advantage of incorporating prior biological knowledge about phenotypic changes into our algorithm, it can successfully filter out positive ‘hits’ in this assay which is shown in our experiments. We have taken a stepwise approach to the problem, combining different analyses, each of which is well-designed to solve a portion of the problem. These include, aggregate enhancement, edge detection, circular object detection, aggregate clustering, prior to final classification. This strategy has been instrumental in our ability to successfully detect cells containing protein aggregates.

Automated breast tissue density assessment using high order regional texture descriptors in mammography

Breast cancer is the most common cancer and second leading cause of cancer death among women in the US. The relative survival rate is lower among women with a more advanced stage at diagnosis. Early detection through screening is vital. Mammography is the most widely used and only proven screening method for reliably and effectively detecting abnormal breast tissues. In particular, mammographic density is one of the strongest breast cancer risk factors, after age and gender, and can be used to assess the future risk of disease before individuals become symptomatic. A reliable method for automatic density assessment would be beneficial and could assist radiologists in the evaluation of mammograms. To address this problem, we propose a density classification method which uses statistical features from different parts of the breast. Our method is composed of three parts: breast region identification, feature extraction and building ensemble classifiers for density assessment. It explores the potential of the features extracted from second and higher order statistical information for mammographic density classification. We further investigate the registration of bilateral pairs and time-series of mammograms. The experimental results on 322 mammograms demonstrate that (1) a classifier using features from dense regions has higher discriminative power than a classifier using only features from the whole breast region; (2) these high-order features can be effectively combined to boost the classification accuracy; (3) a classifier using these statistical features from dense regions achieves 75% accuracy, which is a significant improvement from 70% accuracy obtained by the existing approaches.

Cell tracking using phase-adaptive shape prior.

Automated tracking of cell population is very crucial for quantitative measurements of dynamic cell‐cycle behaviour of individual cells. This problem involves several subproblems and a high accuracy of each step is essential to avoid error propagation. In this paper, we propose a holistic three‐component system to tackle this problem. For each phase, we first learn a mean shape as well as a model of the temporal dynamics of transformation, which are used for estimating a shape prior for the cell in the current frame. We then segment the cell using a level set‐based shape prior model. Finally, we identify its phase based on the goodness‐of‐fit of the data to the segmentation model. This phase information is also used for fine‐tuning the segmentation result. We evaluate the performance of our method empirically in various aspects and in tracking individual cells from HeLa H2B‐GFP cell population. Highly accurate validation results confirm the robustness of our method in many realistic scenarios and the essentiality of each component of our integrating system.

Accurate single-molecule localization of super-resolution microscopy images using multiscale products

Recently, a class of single-molecule based localization techniques such as the Photo-activated Localization Mi- croscopy (PALM) or the Stochastic Optical Reconstruction Microscopy (STORM) has ingeniously brought light- microscopy beyond the diraction limit. However, as the single-molecule images contain point source objects (which have no clear edges, alignment and usually superimposed to the background), traditional restoration techniques used for industrial vision images do not give satisfactory result on the PALM/STORM dataset. In this work, we apply the multi-scale product of sub-band images resulting from the wavelet transformation, a technique originally used for astronomical image restoration, for the noise ltering and single-molecule detection in the Super-resolution images. This is an extension of the work by J.C Olivo-Marin1 on spot detection in bio- logical images. Experimental results on real and synthetic datasets with ground-truth show that our approach achieves very good detection rates as compared to the QuickPALM or the rapidSTORM software.