Harry Strange

Topological Modeling and Classification of Mammographic Microcalcification Clusters

Goal: The presence of microcalcification clusters is a primary sign of breast cancer; however, it is difficult and time consuming for radiologists to classify microcalcifications as malignant or benign. In this paper, a novel method for the classification of microcalcification clusters in mammograms is proposed. Methods: The topology/connectivity of individual microcalcifications is analyzed within a cluster using multiscale morphology. This is distinct from existing approaches that tend to concentrate on the morphology of individual microcalcifications and/or global (statistical) cluster features. A set of microcalcification graphs are generated to represent the topological structure of microcalcification clusters at different scales. Subsequently, graph theoretical features are extracted, which constitute the topological feature space for modeling and classifying microcalcification clusters. k-nearest-neighbors-based classifiers are employed for classifying microcalcification clusters. Results: The validity of the proposed method is evaluated using two well-known digitized datasets (MIAS and DDSM) and a full-field digital dataset. High classification accuracies (up to 96%) and good ROC results (area under the ROC curve up to 0.96) are achieved. A full comparison with related publications is provided, which includes a direct comparison. Conclusion: The results indicate that the proposed approach is able to outperform the current state-of-the-art methods. Significance: This study shows that topology modeling is an important tool for microcalcification analysis not only because of the improved classification accuracy but also because the topological measures can be linked to clinical understanding.

Texture segmentation using different orientations of GLCM features

This paper describes the development of a new texture based segmentation algorithm which uses a set of features extracted from Grey-Level Co-occurrence Matrices. The proposed method segments different textures based on noise reduced features which are effective texture descriptor. Each of the features is processed including normalisation and noise removal. Principal Component Analysis is used to reduce the dimensionality of the resulting feature space. Gaussian Mixture Modelling is used for the subsequent segmentation and false positive regions are removed using morphology. The evaluation includes a wide range of textures (more than 80 Brodatz textures) and in comparison (both qualitative and quantitative) with state of the art techniques very good segmentation results have been obtained.

Modelling mammographic microcalcification clusters using persistent mereotopology

In mammographic imaging, the presence of microcalcifications, small deposits of calcium in the breast, is a primary indicator of breast cancer. However, not all microcalcifications are malignant and their distribution within the breast can be used to indicate whether clusters of microcalcifications are benign or malignant. Computer-aided diagnosis (CAD) systems can be employed to help classify such microcalcification clusters. In this paper a novel method for classifying microcalcification clusters is presented by representing discrete mereotopological relations between the individual microcalcifications over a range of scales in the form of a mereotopological barcode. This barcode based representation is able to model complex relations between multiple regions and the results on mammographic microcalcification data shows the effectiveness of this approach. Classification accuracies of 95% and 80% are achieved on the MIAS and DDSM datasets, respectively. These results are comparable to existing state-of-the art methods. This work also demonstrates that mereotopological barcodes could be used to help trained clinicians in their diagnosis by providing a clinical interpretation of barcodes that represent both benign and malignant cases.

Open Problems in Spectral Dimensionality Reduction

The last few years have seen a great increase in the amount of data available to scientists, yet many of the techniques used to analyse this data cannot cope with such large datasets. Therefore, strategies need to be employed as a pre-processing step to reduce the number of objects or measurements whilst retaining important information. Spectral dimensionality reduction is one such tool for the data processing pipeline. Numerous algorithms and improvements have been proposed for the purpose of performing spectral dimensionality reduction, yet there is still no gold standard technique. This book provides a survey and reference aimed at advanced undergraduate and postgraduate students as well as researchers, scientists, and engineers in a wide range of disciplines. Dimensionality reduction has proven useful in a wide range of problem domains and so this book will be applicable to anyone with a solid grounding in statistics and computer science seeking to apply spectral dimensionality to their work.

Automatic estimation of wheat grain morphometry from computed tomography data

Wheat (Triticum aestivum L.) grain size and morphology are playing an increasingly important role as agronomic traits. Whole spikes from two disparate strains, the commercial type Capelle and the landrace Indian Shot Wheat, were imaged using a commercial computed tomography system. Volumetric information was obtained using a standard back-propagation approach. To extract individual grains within the spikes, we used an image processing pipeline that included adaptive thresholding, morphological filtering, persistence aspects and volumetric reconstruction. This is a fully automated, data-driven pipeline. Subsequently, we extracted several morphometric measures from the individual grains. Taking the location and morphology of the grains into account, we show distinct differences between the commercial and landrace types. For example, average volume is significantly greater for the commercial type (P=0.0024), as is the crease depth (P=1.61×10-5). This pilot study shows that the fully automated approach described can retain developmental information and reveal new morphology information at an individual grain level.

Analysis of Mammographic Microcalcification Clusters Using Topological Features

In mammographic images, the presence of microcalcification clusters is a primary indicator of breast cancer. However, not all microcalcification clusters are malignant and it is difficult and time consuming for radiologists to discriminate between malignant and benign microcalcification clusters. In this paper, a novel method for classifying microcalcification clusters in mammograms is presented. The topology/connectivity of microcalcification clusters is analysed by representing their topological structure over a range of scales in graphical form. Graph theoretical features are extracted from microcalcification graphs to constitute the topological feature space of microcalcification clusters. This idea is distinct from existing approaches that tend to concentrate on the morphology of individual microcalcifications and/or global (statistical) cluster features. The validity of the proposed method is evaluated using two well-known digitised datasets (MIAS and DDSM) and a full-field digital dataset. High classification accuracies (up to 96%) and good ROC results (area under the ROC curve up to 0.96) are achieved. In addition, a full comparison with state-of-the-art methods is provided.

Fuzzy-entropy based image congealing

Group-wise image alignment or image congealing is an image processing technique which allows the joint alignment of a collection of images. Typically, information theoretic metrics have been employed as the objective function for the assessment of the process of alignment of the images for such methods. However, these objective functions rely on their probabilistic foundations and cannot model the underlying vagueness or uncertainty that is captured by approaches such as those based on fuzzy sets. In this paper a novel fuzzy-entropy based approach is presented for the task of image congealing. This approach allows for much flexibility in terms of employing different definitions for both similarity and fuzzy-entropy. Indeed, the existing approach for image congealing is subsumed as a special case of the approach proposed in this paper. The novel fuzzy-entropy congealing technique is applied to different benchmark problems and also to a medical imaging dataset with good results.

Manifold Learning for Density Segmentation in High Risk Mammograms

There is a strong correlation between relative mammographic breast density and the risk of developing breast cancer. As such, accurately modelling the percentage of a mammogram that is dense is a pivotal step in density based risk classification. In this work, a novel method based on manifold learning is used to segment high-risk mammograms into density regions. As such, finer details are present in the segmentations and more accurate measures of breast density are produced. A set of high risk (BI-RADS IV) full field digital mammograms with density annotations obtained from radiologists are used to test the validity of the proposed approach. By exploiting the manifold structure of the input space, segmentations with average accuracy of 87% when compared with radiologists’ segmentations can be obtained. This is an increase of over 12% compared with segmentation in the high-dimensional space.

Meningioma subtype classification using morphology features and random forests

The majority of meningiomas belong to one of four subtypes: fibroblastic, meningothelial, transitional and psammomatous. Classification of histopathology images of these meningioma is a time consuming and error prone task, and as such automatic methods aim to help reduce time spent and errors made. This work is concerned with classifying histopathology images into the above subtypes by extracting simple morphology features to represent each image subtype. Morphology features are identified based on the pathology of the meningioma subtypes and are used to classify each image into one of the four WHO Grade I subtypes. The morphology features correspond to visual changes in the appearance of cells, and the presence of psammoma bodies. Using morphological image processing these features can be extracted and the presence of each detected feature is used to build a vector for each meningioma image. These feature vectors are then classified using a Random Forest based classifier. A set of 80 images was used for experimentation with each subtype being represented by 20 images, and a ten-fold cross validation approach was used to obtain an overall classification accuracy. Using the above methodology a maximum classification accuracy of 91:25% is achieved across the four subtypes with coherent misclassification (e.g. no misclassification between fibroblastic and meningothelial). This work demonstrates that morphology features can be used to perform meningioma subtype classification and provide an understandable link between the features identified in the images and the classification results obtained.

Unsupervised Cell Nuclei Segmentation Based on Morphology and Adaptive Active Contour Modelling

This paper proposes an unsupervised segmentation scheme for cell nuclei. This method computes the cell nuclei by using adaptive active contour modelling which is driven by the morphology method. Firstly, morphology is used to enhance the gray level values of cell nuclei. Then binary cell nuclei is acquired by using an image subtraction technique. Secondly, the masks of cell nuclei are utilized to drive an adaptive region-based active contour modelling to segment the cell nuclei. In addition, an artificial interactive segmentation method is used to generate the ground truth of cell nuclei. This method can have an interest in several applications covering different kinds of cell nuclei. Experiments show that the proposed method can generate accurate segmentation results compared with alternative approaches.