Advances in Analysis and Exploration in Medical Imaging

Loading...
Thumbnail Image
Journal Title
Journal ISSN
Volume Title
School of Science | Doctoral thesis (article-based) | Defence date: 2014-12-05
Checking the digitized thesis and permission for publishing
Instructions for the author
Date
2014
Major/Subject
Mcode
Degree programme
Language
en
Pages
134 + app. 126
Series
Aalto University publication series DOCTORAL DISSERTATIONS, 178/2014
Abstract
With an ever increasing life expectancy, we see a concomitant increase in diseases capable of disrupting normal cognitive processes. Their diagnoses are difficult, and occur usually after daily living activities have already been compromised. This dissertation proposes machine learning methods for the study of the neurological implications of brain lesions. It addresses the analysis and exploration of medical imaging data, with particular emphasis to (f)MRI. Two main research directions are proposed. In the first, a brain tissue segmentation approach is detailed. In the second, a document mining framework, applied to reports of neuroscientific studies, is described. Both directions are based on retrieving consistent information from multi-modal data. A contribution in this dissertation is the application of a semi-supervised method, discriminative clustering, to identify different brain tissues and their partial volume information. The proposed method relies on variations of tissue distributions in multi-spectral MRI, and reduces the need for a priori information. This methodology was successfully applied to the study of multiple sclerosis and age related white matter diseases. It was also showed that early-stage changes of normal-appearing brain tissue can already predict decline in certain cognitive processes. Another contribution in this dissertation is in neuroscience meta-research. One limitation in neuroimage processing relates to data availability. Through document mining of neuroscientific reports, using images as source of information, one can harvest research results dealing with brain lesions. The context of such results can be extracted from textual information, allowing for an intelligent categorisation of images. This dissertation proposes new principles, and a combination of several techniques to the study of published fMRI reports. These principles are based on a number of distance measures, to compare various brain activity sites. Application to studies of the default mode network validated the proposed approach. The aforementioned methodologies rely on clustering approaches. When dealing with such strategies, most results depend on the choice of initialisation and parameter settings. By defining distance measures that search for clusters of consistent elements, one can estimate a degree of reliability for each data grouping. In this dissertation, it is shown that such principles can be applied to multiple runs of various clustering algorithms, allowing for a more robust estimation of data agglomeration.
Description
Supervising professor
Oja, Erkki, Aalto Distinguished Prof., Aalto University, Department of Information and Computer Science, Finland
Thesis advisor
Vigário, Ricardo, Doc., Aalto University, Department of Information and Computer Science, Finland
Keywords
magnetic resonance imaging (MRI), functional MRI, clustering, image segmentation, brain, self-supervised, machine learning, document mining, consistency estimation, neural diseases
Other note
Parts
  • [Publication 1]: Nicolau Gonçalves and Ricardo Vigário. Clustering through SOM Consistency. In Lecture Notes on Computer Science - Image Analysis and Recognition, A. Campilho and M. Kamel (Eds.): Proceedings of the 9th International Conference on Image Analysis and Recognition, ICIAR 2012, pages 61-68, June 2012, DOI 10.1007/978-3-642-31295-3_8
  • [Publication 2]: Nicolau Gonçalves, Janne Nikkilä and Ricardo Vigário. Partial Clustering for Tissue Segmentation in MRI. In Lecture Notes in Advances in Neuro-Information Processing, M. Köppen and N. Kasabov and G. Coghill (Eds.): Proceedings of the 15th International Conference on Neuro-Information Processing, ICONIP 2008, pages 559-566, November 2008.
    DOI: 10.1007/978-3-642-03040-6_68 View at publisher
  • [Publication 3]: Nicolau Gonçalves, Janne Nikkilä and Ricardo Vigário. Self–supervised MRI Tissue Segmentation by Discriminative Clustering. International Journal of Neural Systems, Volume 24, Number 1, 16 pages, January 2014, DOI 10.1142/S012906571450004X
  • [Publication 4]: Hanna Jokinen, Nicolau Gonçalves, Ricardo Vigário, Jari Lipsanen, Franz Fazekas, Reinhold Schmidt, Frederik Barkhof, Philip Scheltens, Sofia Madureira, José M. Ferro, Domenico Inzitari, Leonardo Pantoni, Timo Erkinjuntti and the LADIS Study Group. A novel multispectral MRI tissue segmentation approach reveals early stage white matter lesions and predicts cognitive decline. Submitted to journal publication, October 2014.
  • [Publication 5]: Nicolau Gonçalves, Hanna Jokinen, Franz Fazekas, Reinhold Schmidt, Frederik Barkhof, Philip Scheltens, Sofia Madureira, Ana Verdelho, Domenico Inzitari, Leonardo Pantoni, Timo Erkinjuntti and Ricardo Vigário. Prediction of cerebral white matter lesion evolution through self-supervised tissue segmentation. Submitted to journal publication, October 2014.
  • [Publication 6]: Jayaprakash Rajasekharan, Ulrike Scharfenberger, Nicolau Gonçalves and Ricardo Vigário. Image Approach towards Document Mining in Neuroscientific Publications. In Lecture Notes in Advances in Intelligent Data Analysis IX, Paul R. Cohen and Niall M. Adams and Michael R. Berthold (Eds.): Proceedings of the 9th International Symposium, Intelligent Data Analysis 2010, pages 147-158, May 2010, DOI 10.1007/978-3-642-13062-5_15
  • [Publication 7]: Nicolau Gonçalves, Gabriela Vranou and Ricardo Vigário. Towards automated image mining from reported medical images. In Computational Vision and Medical Image Processing IV, Proceedings of VipIMAGE 2013 - 4th ECCOMAS Thematic Conference on Computational Vision and Medical Image Processing, pages 255-261, October 2013, DOI 10.1201/b15810-46
  • [Publication 8]: Nicolau Gonçalves, Erkki Oja and Ricardo Vigário. Medical document mining combining image exploration and text characterization. In Lecture Notes in Artificial Intelligence, Sašo Džeroski, Panče Panov, Dragi Kocev and Ljupčo Todorovski (Eds.): Proceedings of the 17th International Conference on Discovery Science, Discovery Science 2014, pages 99-110, October 2014, DOI 10.1007/978-3-319-11812-3_9
Citation