Hippocampus Segmentation Using Locally Integrated Prior-Based Level Set Guided By Assembled And Weighted Coherent Point Drift Registration

Achuthan, Anusha (2016) Hippocampus Segmentation Using Locally Integrated Prior-Based Level Set Guided By Assembled And Weighted Coherent Point Drift Registration. PhD thesis, Universiti Sains Malaysia.

[img]
Preview
PDF
Download (851Kb) | Preview

    Abstract

    Segmentasi hipokampus daripada struktur-struktur subkortikal otak bersebelahan merupakan satu tugas yang sangat mencabar, terutamanya akibat sempadan pemisahan struktur-struktur ini adalah lemah atau kurang jelas, seterusnya menyebabkan pendekatan berasaskan sempadan tidak berkesan untuk segmentasi hipokampus yang betul. Disamping itu, kedudukan hipokampus yang hampir dengan amygdala menyukarkan lagi isu segmentasi. Walau bagaimanapun, trend terkini telah beralih dari bergantung semata-mata kepada ciri-ciri imej kepada penggunaan model-model terdahulu dalam segmentasi. Secara amnya, model-model terdahulu dibina menggunakan segmentasi berasaskan atlas. Walau bagaimanapun, pendekatan ini sangat data intensif kerana ia menggunakan kaedah berasaskan volumetri untuk pembinaan model terdahulu. Oleh yang demikian, tesis ini mencadangkan satu pendekatan pembinaan model terdahulu yang bukan sahaja mampu mewakilkan maklumat bentuk dan lokasi ruang secara berkesan, malah mempunyai keperluan data intensif yang lebih rendah berbanding pendekatan berasaskan atlas. Secara terperinci, satu kaedah pendaftaran set titik yang novel dicadangkan dan disahkan bagi pembinaan model terdahulu. Hippocampus segmentation from neighbouring brain subcortical structures is a very challenging task mainly because boundaries separating these structures are weak or unclear, rendering conventional edge-based approaches ineffective for proper hippocampus segmentation. Besides that, close proximity of the hippocampus with the amygdala further complicates the segmentation issue. Recent trends, however have shifted from sole reliance on image features to utilization of prior models in the segmentation. Predominantly, the prior models are constructed using atlas-based segmentation. This approach however, is highly data intensive due to the volumetric-based methods used for prior model construction. Consequently, this thesis proposes a prior model construction method that not only effectively represents shape and spatial location information, but also requires lower data intensiveness compared to atlas-based approaches. Specifically, a novel point set registration method is proposed and validated for prior model construction.

    Item Type: Thesis (PhD)
    Subjects: Q Science > QA Mathematics > QA75.5-76.95 Electronic computers. Computer science
    Divisions: Pusat Pengajian Sains Komputer (School of Computer Sciences) > Thesis
    Depositing User: Mr Noorazilan Noordin
    Date Deposited: 05 Jan 2017 08:31
    Last Modified: 14 Apr 2017 20:18
    URI: http://eprints.usm.my/id/eprint/31409

    Actions (login required)

    View Item
    Share