Manual segmentation of brain tumours is a time consuming process, results often show high variability, and there is a call for automation in clinical practice. In this thesis the use of deep convolutional networks for automatic glioma segmentation in MRI is investigated. The implemented networks are evaluated on data used in the brain tumor segmentation challenge (BraTS). It is found that 3D convolutional networks generally outperform 2D convolutional networks, and that the best networks can produce segmentations that closely resemble human segmentations. Convolutional networks are also evaluated as feature extractors with linear SVM classifiers on top, and although the sensitivity is improved considerably, the segmentations are heavily oversegmented. The importance of the amount of data available is investigated as well by comparing results from networks trained on both 2013 and the greatly extended 2014 data set, but it is found that the method of producing ground-truth was also a contributing factor. The networks does not beat the previous high-scores on the BraTS data, but several simple improvement areas are identified to take the networks further. / Manuell segmentering av hjärntumörer är en tidskrävande process, segmenteringarna är ofta varierade mellan experter, och automatisk segmentering skulle vara användbart för kliniskt bruk. Den här rapporten undersöker användningen av deep convolutional networks (ConvNets) för automatisk segmentering av gliom i MR-bilder. De implementerade nätverken utvärderas med hjälp av data från brain tumor segmentation challenge (BraTS). Studien finner att 3D-nätverk har generellt bättre resultat än 2D-nätverk, och att de bästa nätverken har förmågan att ge segmenteringar som liknar mänskliga segmenteringar. ConvNets utvärderas också som feature extractors, med linjära SVM som klassificerare. Den här metoden ger segmenteringar med hög känslighet, men är också till hög grad översegmenterade. Vikten av att ha mer träningsdata undersöks också genom att träna på två olika stora dataset, men metoden för att få fram de riktiga segmenteringarna har troligen också stor påverkan på resultatet. Nätverken slår inte de tidigare rekorden på BraTS, men flera viktiga men enkla förbättringsområden är identifierade som potentiellt skulle förbättra resultaten.

We study modifications to the novel stochastic watershed method for segmentation of digital images. This is a stochastic version of the original watershed method which is repeatedly realized in order to create a probability density function for the segmentation. The study is primarily done on synthetic images with both same-sized regions and differently sized regions, and at the end we apply our methods on two endothelial cell images of the human cornea. We find that, for same-sized regions, the seeds should be placed in a spaced grid instead of a random uniform distribution in order to yield a more accurate segmentation. When images with differently sized regions are being segmented, the seeds should be placed dependent on the gradient, and by also adding uniform or gaussian noise to the image in every iteration a satisfactory result is obtained.

Peripheral Artery Disease (PAD) is an often occurring problem caused by narrowed veins. With this type of disease, mostly the legs receive an insufficient supply of blood to sustain their functions. This can result in an amputation of extremities or strokes. In order to quantify the risks, doctors consult a classification table which is based on the pain response of a patient. This classification is subjective and does not indicate the exact origin of the PAD symptoms. Resulting from this, complications can occur unprompted. We present the first results for an image-based indicator assisting medical doctors in estimating the stage of PAD and its location. Therefore, a segmentation tree is utilized to compare the changes in a healthy versus diseased leg. We provide a highlighting mechanism that allows users to review the location of changes in selected structures. To show the effectiveness of the presented approach, we demonstrate a localization of the PAD and show how the presented technique can be utilized for a novel image-based indicator of PAD stages.

Algorithmic Information Theory (AIT), also known as Kolmogorov complexity, is a quantitative approach to defining information. AIT is mainly used to measure the amount of information present in the observations of a given phenomenon. In this dissertation we explore the applications of AIT in two case studies. The first examines bright field cell image segmentation and the second examines the information complexity of multicellular patterns. In the first study we demonstrate that our proposed AIT-based algorithm provides an accurate and robust bright field cell segmentation. Cell segmentation is the process of detecting cells in microscopy images, which is usually a challenging task for bright field microscopy due to the low contrast of the images. In the second study, which is the primary contribution of this dissertation, we employ an AIT-based algorithm to quantify the complexity of information content that arises during the development of multicellular organisms. We simulate multicellular organism development by coupling the Gene Regulatory Networks (GRN) within an epithelial field. Our results show that the configuration of GRNs influences the information complexity in the resultant multicellular patterns.

A long standing debate in computer vision community concerns the link between segmentation and recognition. The question I am trying to answer here is, Does image segmentation as a preprocessing step help image recognition? In spite of a plethora of the literature to the contrary, some authors have suggested that recognition driven by high quality segmentation is the most promising approach in image recognition because the recognition system will see only the relevant features on the object and not see redundant features outside the object (Malisiewicz and Efros 2007; Rabinovich, Vedaldi, and Belongie 2007). This thesis explores the following question: If segmentation precedes recognition, and segments are directly fed to the recognition engine, will it help the recognition machinery? Another question I am trying to address in this thesis is of scalability of recognition systems. Any computer vision system, concept or an algorithm, without exception, if it is to stand the test of time, will have to address the issue of scalability.

No description available.

No description available.

We propose two different methods for image segmentation with the objective of marking contaminated regions in images from biochemical tests. The contaminated regions consists of thin hair or fibers and the purpose of this thesis is to eliminate the tedious task of masking the contaminated regions by hand by implementing automatic hair masking. Initially an algorithm based on Morphological Image Processing is presented, followed by solving the problem of pixelwise classification using a Convolutional Neural Network (CNN). Finally, the performance of each implementation is measured by comparing the segmented images with labelled images which are considered to be the ground truth. The result shows that both implementations have strong potential at successfully performing semantic segmentation on the images from the biochemical tests.

Even with the recent advances of deep learning pushing the field of medical image analysis further than ever before, progress is still slow due to limited availability of annotated data. There are multiple reasons for this, but perhaps the most prominent one is the amount of time manual annotation of medical images takes. In this project a semi-automated algorithm is proposed, approaching the segmentation problem in a slice by slice manner utilising the prediction of a previous slice as a prior for the next. This both allows the algorithm to segment entirely new cases and gives the user the ability to correct faulty slices, propagating the correction throughout. Results on par with current state of the art is achieved within the domain of the training data. In addition to this, cases outside of the training domain can also be segmented with some accuracy, paving the way for further improvement. The strategy for training the network to utilise auxiliary input lies in the heavy online data augmentation, forcing the network to rely on the provided prior. / Trots att framstegen inom djupinlärning banar vägen för medicinsk bildanalys snabbare än någonsin så finns det ett stort problem, mängden annoterad bilddata. Det har bland annat att göra med att medicinsk bilddata tar väldigt lång tid att annotera manuellt. I detta projektet har en semi-automatisk algoritm utvecklats som tar sig an 3D-segmentering från ett 2D-perspektiv. En bildvolym segmenteras genom att en initialiseringbild annoteras manuellt och används som hjälp för att annotera närliggande bilder i volymen. Detta upprepas sedan för resterande bilder men istället för att manuellt annotera används föregående segmentering av närverket som hjälp. Detta tillåter att algoritmen både kan generalisera till helt nya fall som ej är representerade av träningsdatan, och gör även att felaktigt segmenterade bilder kan korrigeras i efterhand. Korrigeringar kommer då att propageras genom volymen genom att varje segmentering används som hjälp för nästkommande bild. Resultaten är i nivå med motsvarande helautomatiska algoritmer inom träningsdomänen. Den största fördelen gentemot dessa är möjligheten att segmentera helt nya fall. Metoden som används för att träna nätverket att förlita sig på hjälpbilder bygger på kraftig bilddistortion av bilden som ska segmenteras. Detta tvingar nätverket att ta vara på informationen i segmenteringen av föregående bild.

<p>    </p> <p>Meeting the nutritional requirements of an increasing population in a changing climate is the foremost concern of agricultural research in recent years. A solution to some of the many questions posed by this existential threat is breeding crops that more efficiently produce food with respect to land and water use. A key aspect to this optimization is geometric aspects of plant physiology such as canopy architecture that, while based in the actual 3D structure of the organism, does not necessarily require such a representation to measure. Although deep learning is a powerful tool to answer phenotyping questions that do not require an explicit intermediate 3D representation, training a network traditionally requires a large number of hand-segmented ground truth images. To bypass the enormous time and expense of hand- labeling datasets, we utilized a procedural sorghum image pipeline from another student in our group that produces images similar enough to the ground truth images from the phenotyping facility that the network can be directly used on real data while training only on automatically generated data. The synthetic data was used to train a deep segmentation network to identify which pixels correspond to which leaves. The segmentations were then processed to find the number of leaves identified in each image to use for the leaf-counting task in high-throughput phenotyping. Overall, our method performs comparably with human annotation accuracy by correctly predicting within a 90% confidence interval of the true leaf count in 97% of images while being faster and cheaper. This helps to add another expensive- to-collect phenotypic trait to the list of those that can be automatically collected. </p>