No description available.

No description available.

No description available.

No description available.

No description available.

Convolution neural networks have achieved a state of the art accuracy for multi-class segmentation in biomedical image science. In this thesis, a 2-Stage binary 2D UNet and MultiResUNet are used to segment the 3D cardiac CT Volumes. 3D volumes have been sliced into 2D images. The 2D networks learned to classify the pixels by transforming the information about the segmentation into latent feature space in a contracting path and upsampling them to semantic segmentation in an expanding path. The network trained on diastole and systole timestamp volumes will be able to handle much more extreme morphological differences between the subjects. Evaluation of the results is based on the Dice coefficient as a segmentation metric. The thesis work also explores the impact of the various loss function in image segmentation for the imbalanced dataset. Results show that2-Stage binary UNet has higher performance than MultiResUnet considering segmentation done in all planes. In this work, Convolution neural network prediction uncertainty is estimated using Monte Carlo dropout estimation and it shows that 2-Stage Binary UNet has lower prediction uncertainty than MultiResUNet.

Graph signal processing is a field concerning theprocessing of graphs with data associated to their vertices, oftenin the purpose of modeling networks. One area of this fieldthat has been under research in recent years is the developmentof frameworks for learning graph topologies from such data.This may be useful in situations where one wants to representa phenomenon with a graph, but where an obvious topologyis not available. The aim of this project was to evaluate theusefulness of one such proposed learning framework in thecontext of image segmentation. The method used for achievingthis consisted in constructing graph representations of imagesfrom said framework, and clustering their vertices with anestablished graph-based segmentation algorithm. The resultsdemonstrate that this approach may well be useful, although theimplementation used in the project carried out segmentationssignificantly slower than state of the art methods. A numberof possible improvements to be made regarding this aspect arehowever pointed out and may be subject for future work. / Grafsignalbehandling är ett ämnesområde vars syfte är att behandla grafer med data associerat till deras noder, ofta inom nätverksmodelleringen. Inom detta område pågår aktiv forskning med att utveckla tekniker för att konstruera graftopologier från sådana data. Dessa tekniker kan vara användbara när man vill representera ett fenomen med grafer, men då uppenbara grafstrukturer inte finns tillgängliga. Syftet med detta projekt var att utvärdera användbarheten hos en sådan teknik när den appliceras inom bildsegmentering. Metoden som användes bestod i att konstruera grafrepresentationer av bilder med hjälp av denna teknik, för att sedan behandla dessa med en etablerad, grafbaserad segmenteringsalgoritm. Resultaten påvisar att detta tillvägagångssätt under rätt förutsättningar kan producera tillfredsställande bildsegmenteringar. Dock är implementeringen som nyttjats i projektet betydligt långsammare än de metoder som vanligen används inom området. Ett antal förslag till prestandaförbättring utpekas, och kan vara föremål för framtida studier. / Kandidatexjobb i elektroteknik 2020, KTH, Stockholm

During the last few years, segmentation architectures based on deep learning achieved promising results. On the other hand, attention networks have been invented years back and used in different tasks but rarely used in medical applications. This thesis investigated four main attention mechanisms; Squeeze and Excitation, Dual Attention Network, Pyramid Attention Network, and Attention UNet to be used in medical image segmentation. Also, different hybrid architectures proposed by the author were tested. Methods were tested on a kidney tumor dataset and against UNet architecture as a baseline. One version of Squeeze and Excitation attention outperformed the baseline. Original Dual Attention Network and Pyramid Attention Network showed very poor performance, especially for the tumor class. Attention UNet architecture achieved close results to the baseline but not better. Two more hybrid architectures achieved better results than the baseline. The first is a modified version of Squeeze and Excitation attention. The second is a combination between Dual Attention Networks and UNet architecture. Proposed architectures outperformed the baseline by up to 3% in tumor Dice coefficient. The thesis also shows the difference between 2D architectures and their 3D counterparts. 3D architectures achieved more than 10% higher tumor Dice coefficient than 2D architectures.

Image and video enhancement, a classical problem of signal processing, has remained a very active research topic for past decades. This technical subject will not become obsolete even as the sensitivity and quality of modern image sensors steadily improve. No matter what level of sophistication cameras reach, there will always be more extreme and complex lighting conditions, in which the acquired images are improperly exposed and thus need to be enhanced. The central theme of enhancement is to algorithmically compensate for sensor limitations under ill lighting and make illegible details conspicuous, while maintaining a degree of naturalness. In retrospect, all existing contrast enhancement methods focus on heightening of spatial details in the luminance channel to fulfil the goal, with no or little consideration of the colour fidelity of the processed images; as a result they can introduce highly noticeable distortions in chrominance. This long-time much overlooked problem is addressed and systematically investigated by the thesis. We then propose a novel optimization-based enhancement algorithm, generating optimal tone mapping that not only makes maximal gain of contrast but also constrains tone and chrominance distortion, achieving superior output perceptual quality against severe underexposure and/or overexposure. Besides, we present a novel solution to restore images captured under more challenging backlit scenes, by combining the above enhancement method and feature-driven, machine learning based segmentation. We demonstrate the superior performance of the proposed method in terms of segmentation accuracy and restoration results over state-of-the-art methods. We also shed light on a common yet largely untreated video restoration problem called Yin-Yang Phasing (YYP), featured by involuntary, intense fluctuation in intensity and chrominance of an object as the video plays. We propose a novel video restoration technique to suppress YYP artifacts while retaining temporal consistency of objects appearance via inter-frame, spatially-adaptive optimal tone mapping. Experimental results are encouraging, pointing to an effective and practical solution to the problem. / Thesis / Doctor of Philosophy (PhD)

Yes / In recent years, deep learning has been increasingly used for several applications such as object analysis, feature extraction and image classification. This paper explores the use of deep learning in a flood monitoring application in the context of an EC-funded project, Smart Cities and Open Data REuse (SCORE). IoT sensors for detecting blocked gullies and drainages are notoriously hard to build, hence we propose a novel technique to utilise deep learning for building an IoT-enabled smart camera to address this need. In our work, we apply deep leaning to classify drain blockage images to develop an effective image classification model for different severity of blockages. Using this model, an image can be analysed and classified in number of classes depending upon the context of the image. In building such model, we explored the use of filtering in terms of segmentation as one of the approaches to increase the accuracy of classification by concentrating only into the area of interest within the image. Segmentation is applied in data pre-processing stage in our application before the training. We used crowdsourced publicly available images to train and test our model. Our model with segmentation showed an improvement in the classification accuracy. / Research presented in this paper is funded by the European Commission Interreg project Smart Cities and Open Data REuse (SCORE).