No description available.

No description available.

Histologic analysis of tissue samples is often a critical step in the diagnosis of disease. However, this type of assessment is inherently subjective, and consequently a high degree of variability may occur between results produced by different pathologists. Histologic analysis is also a very time-consuming task for pathologists. Computer-based quantitative analysis of tissue samples shows promise for both reducing the subjectivity of traditional manual tissue assessments, as well as potentially reducing the time required to analyze each sample. <p>The objective of this thesis project was to investigate image processing techniques and to develop software which could be used as a diagnostic aid in pathology assessments of cattle lung tissue samples. The software examines digital images of tissue samples, identifying and highlighting the presence of a set of features that indicate disease, and that can be used to distinguish various pulmonary diseases from one another. The output of the software is a series of segmented images with relevant disease indicators highlighted, and measurements quantifying the occurrence of these features within the tissue samples. Results of the software analysis of a set of 50 cattle lung tissue samples were compared to the detailed manual analysis of these samples by a pathology expert.<p>The combination of image analysis techniques implemented in the thesis software shows potential. Detection of each of the disease indicators is successful to some extent, and in some cases the analysis results are extremely good. There is a large difference in accuracy rates for identification of the set of disease indicators, however, with sensitivity values ranging from a high of 94.8% to a low of 22.6%. This wide variation in result scores is partially due to limitations of the methodology used to determine accuracy.

No description available.

Texture can be broadly stated as spatial variation of image intensities. Texture analysis and classification is a well researched area for its importance to many computer vision applications. Consequently, much research has focussed on deriving powerful and efficient texture descriptors. Local binary patterns (LBP) and its variants are simple yet powerful texture descriptors. LBP features describe the texture neighbourhood of a pixel using simple comparison operators, and are often calculated based on varying neighbourhood radii to provide multi-resolution texture descriptions. A comprehensive evaluation of different LBP variants on a common benchmark dataset is missing in the literature. This thesis presents the performance for different LBP variants on texture classification and retrieval tasks. The results show that multi-scale local binary pattern variance (LBPV) gives the best performance over eight benchmarked datasets. Furthermore, improvements to the Dominant LBP (D-LBP) by ranking dominant patterns over complete training set and Compound LBP (CM-LBP) by considering 16 bits binary codes are suggested which are shown to outperform their original counterparts. The main contribution of the thesis is the introduction of multi-dimensional LBP features, which preserve the relationships between different scales by building a multi-dimensional histogram. The results on benchmarked classification and retrieval datasets clearly show that the multi-dimensional LBP (MD-LBP) improves the results compared to conventional multi-scale LBP. The same principle is applied to LBPV (MD-LBPV), again leading to improved performance. The proposed variants result in relatively large feature lengths which is addressed using three different feature length reduction techniques. Principle component analysis (PCA) is shown to give the best performance when the feature length is reduced to match that of conventional multi-scale LBP. The proposed multi-dimensional LBP variants are applied for medical image analysis application. The first application is nailfold capillary (NC) image classification. Performance of MD-LBPV on NC images is highest, whereas for second application, HEp-2 cell classification, performance of MD-LBP is highest. It is observed that the proposed texture descriptors gives improved texture classification accuracy.

Modern medical imaging devices are able to generate highly detailed three-dimensional (3D) images of the skeleton. Computerized image processing and analysis methods, combined with real-time volume visualization techniques, can greatly facilitate the interpretation of such images and are increasingly used in surgical planning to aid reconstruction of the skeleton after trauma or disease. Two key challenges are to accurately separate (segment) bone structures or cavities of interest from the rest of the image and to interact with the 3D data in an efficient way. This thesis presents efficient and precise interactive methods for segmenting, visualizing, and analysing 3D computed tomography (CT) images of the skeleton. The methods are validated on real CT datasets and are primarily intended to support planning and evaluation of cranio-maxillofacial (CMF) and orthopedic surgery. Two interactive methods for segmenting the orbit (eye-socket) are introduced. The first method implements a deformable model that is guided and fitted to the orbit via haptic 3D interaction, whereas the second method implements a user-steered volumetric brush that uses distance and gradient information to find exact object boundaries. The thesis also presents a semi-automatic method for measuring 3D angulation changes in wrist fractures. The fractured bone is extracted with interactive mesh segmentation, and the angulation is determined with a technique based on surface registration and RANSAC. Lastly, the thesis presents an interactive and intuitive tool for segmenting individual bones and bone fragments. This type of segmentation is essential for virtual surgery planning, but takes several hours to perform with conventional manual methods. The presented tool combines GPU-accelerated random walks segmentation with direct volume rendering and interactive 3D texture painting to enable quick marking and separation of bone structures. It enables the user to produce an accurate segmentation within a few minutes, thereby removing a major bottleneck in the planning procedure.

This thesis proposes different models for a variety of applications, such as semantic segmentation, in-the-wild face recognition, microscopy cell counting and detection, standardized re-orientation of 3D ultrasound fetal brain and Magnetic Resonance (MR) cardiac video segmentation. Our approach is to employ the large-scale machine learning models, in particular deep neural networks. Expert knowledge is either mathematically modelled as a differentiable hidden layer in the Artificial Neural Networks, or we tried to break the complex tasks into several small and easy-to-solve tasks. Multi-scale contextual information plays an important role in pixel-wise predic- tion, e.g. semantic segmentation. To capture the spatial contextual information, we present a new block for learning receptive field adaptively by within-layer recurrence. While interleaving with the convolutional layers, receptive fields are effectively enlarged, reaching across the entire feature map or image. The new block can be initialized as identity and inserted into any pre-trained networks, therefore taking benefit from the "pre-train and fine-tuning" paradigm. Current face recognition systems are mostly driven by the success of image classification, where the models are trained to by identity classification. We propose a multi-column deep comparator networks for face recognition. The architecture takes two sets (each contains an arbitrary number of faces) of images or frames as inputs, facial part-based (e.g. eyes, noses) representations of each set are pooled out, dynamically calibrated based on the quality of input images, and further compared with local "experts" in a pairwise way. Unlike the computer vision applications, collecting data and annotation is usually more expensive in biomedical image analysis. Therefore, the models that can be trained with fewer data and weaker annotations are of great importance. We approach the microscopy cell counting and detection based on density estimation, where only central dot annotations are needed. The proposed fully convolutional regression networks are first trained on a synthetic dataset of cell nuclei, later fine-tuned and shown to generalize to real data. In 3D fetal ultrasound neurosonography, establishing a coordinate system over the fetal brain serves as a precursor for subsequent tasks, e.g. localization of anatomical landmarks, extraction of standard clinical planes for biometric assessment of fetal growth, etc. To align brain volumes into a common reference coordinate system, we decompose the complex transformation into several simple ones, which can be easily tackled with Convolutional Neural Networks. The model is therefore designed to leverage the closely related tasks by sharing low-level features, and the task-specific predictions are then combined to reproduce the transformation matrix as the desired output. Finally, we address the problem of MR cardiac video analysis, in which we are interested in assisting clinical diagnosis based on the fine-grained segmentation. To facilitate segmentation, we present one end-to-end trainable model that achieves multi-view structure detection, alignment (standardized re-orientation), and fine- grained segmentation simultaneously. This is motivated by the fact that the CNNs in essence is not rotation equivariance or invariance, therefore, adding the pre-alignment into the end-to-end trainable pipeline can effectively decrease the complexity of segmentation for later stages of the model.

Tissue microarrays (TMAs) are a high-throughput technique that facilitates the survey of very large numbers of tumours, important both in clinical and research applications. However, the assessment of stained TMA sections is laborious and still needs to be carried manually, constituting a bottleneck in the pathologist?s work-flow. This process is also prone to perceptual errors and observer variability.Thus, there is strong motivation for the development of automated quantitative analysis of TMA image data. The analysis of breast TMA sections subjected to nuclear immunostaining begins with the classification of each spot as to the maintype of tissue that it contains, namely tumour, normal, stroma, or fat. Tumour and normal spots are then assigned a so-called quickscore composed of a pair or integer values, the first reflecting the proportion of epithelial nuclei that are stained, and the second reflecting the strength of staining of those nuclei. In this work, an approach was developed to analyse breast TMA spots subjectedto progesterone receptor immunohistochemistry. Spots were classified into their four main types through a method that combined a bag of features approachand classifiers based on either multi-layer perceptrons or latent Dirichlet allocation models. A classification accuracy of 74.6 % was achieved. Tumour and normal spots were scored via an approach that involved the computation of global features formalising the quickscore values used by pathologists, and the use of Gaussian processes for ordinal regression to predict actual quickscores based on global features. Mean absolute errors of 0.888 and 0.779 were achieved in the prediction of the first and second quickscore values, respectively. By setting thresholds on prediction confidence, it was possible to classify and score fractions of spots with substantially higher accuracies and lower mean absolute errors. Amethod for the segmentation of TMA spots into regions of different types was also investigated, to explore the generative nature of latent Dirichlet allocation models.

This paper presents a statistical framework which combines the registration of an atlas with the segmentation of MR images. We use an Expectation Maximization-based algorithm to find a solution within the model, which simultaneously estimates image inhomogeneities, anatomical labelmap, and a mapping from the atlas to the image space. An example of the approach is given for a brain structure-dependent affine mapping approach. The algorithm produces high quality segmentations for brain tissues as well as their substructures. We demonstrate the approach on a set of 30 brain MR images. In addition, we show that the approach performs better than similar methods which separate the registration from the segmentation problem.

This master thesis investigates different approaches for integrating prior information into a neural network for segmentation of medical images. In the study, liver and liver tumor segmentation is performed in a cascading fashion. Context channels in the form of previous segmentations are integrated into a segmentation network at multiple positions and network depths using different integration strategies. Comparisons are made with the traditional integration approach where an input image is concatenated with context channels at a network’s input layer. The aim is to analyze if context information is lost in the upper network layers when the traditional approach is used, and if better results can be achieved if prior information is propagated to deeper layers. The intention is to support further improvements in interactive image segmentation where extra input channels are common. The results that are achieved are, however, inconclusive. It is not possible to differentiate the methods from each other based on the quantitative results, and all the methods show the ability to generalize to an unseen object class after training. Compared to the other evaluated methods there are no indications that the traditional concatenation approach is underachieving, and it cannot be declared that meaningful context information is lost in the deeper network layers.