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.
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.
Actions (login required)
 |
View Item |
![[img]](http://eprints.usm.my/style/images/fileicons/application_pdf.png)
