Machine learning applications within medical imaging often suffer from a lack of data, as a consequence of restrictions that hinder the free distribution of patient information. In this project, GANs (generative adversarial networks) are used to generate data synthetically, in an effort to circumvent this issue. The GAN framework PGAN is trained on the brain tumor segmentation dataset BraTS to generate new, synthetic brain tumor masks with the same visual characteristics as the real samples. The image-to-image translation network SPADE is subsequently trained on the image pairs in the real dataset, to learn a transformation from segmentation masks to brain MR images, and is in turn used to map the artificial segmentation masks generated by PGAN to corresponding artificial MR images. The images generated by these networks form a new, synthetic dataset, which is used to augment the original dataset. Different quantities of real and synthetic data are then evaluated in three different brain tumor segmentation tasks, where the image segmentation network U-Net is trained on this data to segment (real) MR images into the classes in question. The final segmentation performance of each training instance is evaluated over test data from the real dataset with the Weighted Dice Loss metric. The results indicate a slight increase in performance across all segmentation tasks evaluated in this project, when including some quantity of synthetic images. However, the differences were largest when the experiments were restricted to using only 20 % of the real data, and less significant when the full dataset was made available. A majority of the generated segmentation masks appear visually convincing to an extent (although somewhat noisy with regards to the intra-tumoral classes), while a relatively large proportion appear heavily noisy and corrupted. However, the translation of segmentation masks to MR images via SPADE proved more reliable and consistent.

Made available in DSpace on 2014-12-17T14:55:35Z (GMT). No. of bitstreams: 1 JacksonGS.pdf: 1963039 bytes, checksum: ed3464892d7bb73b5dcab563e42f0e01 (MD5) Previous issue date: 2009-09-28 / Image segmentation is one of the image processing problems that deserves special attention from the scientific community. This work studies unsupervised methods to clustering and pattern recognition applicable to medical image segmentation. Natural Computing based methods have shown very attractive in such tasks and are studied here as a way to verify it's applicability in medical image segmentation. This work treats to implement the following methods: GKA (Genetic K-means Algorithm), GFCMA (Genetic FCM Algorithm), PSOKA (PSO and K-means based Clustering Algorithm) and PSOFCM (PSO and FCM based Clustering Algorithm). Besides, as a way to evaluate the results given by the algorithms, clustering validity indexes are used as quantitative measure. Visual and qualitative evaluations are realized also, mainly using data given by the BrainWeb brain simulator as ground truth / Segmenta??o de imagens ? um dos problemas de processamento de imagens que merece especial interesse da comunidade cient?fica. Neste trabalho, s?o estudado m?todos n?o-supervisionados para detec??o de algomerados (clustering) e reconhecimento de padr?es (pattern recognition) em segmenta??o de imagens m?dicas M?todos baseados em t?cnicas de computa??o natural t?m se mostrado bastante atrativos nestas tarefas e s?o estudados aqui como uma forma de verificar a sua aplicabilidade em segmenta??o de imagens m?dicas. Este trabalho trata de implementa os m?todos GKA (Genetic K-means Algorithm), GFCMA (Genetic FCM Algorithm) PSOKA (Algoritmo de clustering baseado em PSO (Particle Swarm Optimization) e K means) e PSOFCM (Algoritmo de clustering baseado em PSO e FCM (Fuzzy C Means)). Al?m disso, como forma de avaliar os resultados fornecidos pelos algoritmos s?o utilizados ?ndices de valida??o de clustering como forma de medida quantitativa Avalia??es visuais e qualitativas tamb?m s?o realizadas, principalmente utilizando dados do sistema BrainWeb, um gerador de imagens do c?rebro, como ground truth