(For USM Staff/Student Only)

EngLib USM > Ω School of Electrical & Electronic Engineering >

Segmentation of liver structure from computed tomogrhapy dataset / Thong Kee Sin

Segmentation of liver structure from computed tomogrhapy dataset_Thong Kee Sin_E3_2010_875003566_0003084256_NI
Peruasan struktur hati yang tepat daripada imej tomografi berkomputer merupakan langkah yang amat diperlukan dalam bidang perubatan seperti dalam perancangan pembedahan dan diagnosa penyakit hati. Peruasan secara manual dilakukan dengan mengesan pinggir hati dalam setiap hiris imej merupakan satu proses yang perlahan dan memakan masa. Dalam projek ini, satu algoritma baru untuk peruasan hati dicadangkan. Gagasan algoritma yang dicadangkan berdasarkan kombinasi dari pelbagai teknik pemprosesan imej. Aliran proses algoritma boleh dibahagikan kepada empat tahap. Pada tahap pertama, satu kawasan kepentingan ditakrifkan dengan menggunakan pengetahuan tentang kedudukan hati untuk mendapat nilai ambang awal untuk peruasan automatik. Tahap kedua menyepadukan peruasan berasakan kawasan dan ‘thresholding’ untuk mengesan objek hati secara kasar. Tahap ketiga ialah pemprosesan ‘selepas’ yang memanfaatkan operasi morfologi dengan kawasan berlabel secara ulangan. Untuk melakukan peruasan yang tepat, tahap terakhir ialah pembaikan imej dengan morfologi tiga dimensi. Algoritma yang dilaksanakan diuji dengan satu set data tomografi berkomputer untuk menilai keberkesanannya dalam peruasan dengan membandingkan keputusannya dengan piawai. Secara keseluruhannya, algoritma yang dicadangkan berjaya meruaskan hati dalam kebanyakan hiris imej dengan keputusan yang memuaskan, walaupun sebahagian daripadanya terlebih diruas dan sebahagiannya terkurang diruas. ____________________________________________________________________________________ Accurate segmentation of liver structure from CT images is an essential step in the medical field such as surgery planning and diagnosis of liver disease. Manual segmentation is done by manually tracing the liver contour on each image slice, which is a slow and time-consuming process. In this project, a new algorithm of the liver segmentation is proposed. The idea of the proposed algorithm is based on the combination of various image processing techniques. The algorithm’s process flow can be divided into four stages. In the first stage, a ROI is defined by using prior knowledge about the liver position to obtain the initial threshold values for automatic segmentation. The second stage integrates region-based segmentation with thresholding to detect coarse liver object. The third stage is post-processing that utilizes morphological operations iteratively with region-labeling. In order to perform accurate segmentation, the last stage is image refinement with 3D morphology. The implemented algorithm is tested on a given CT dataset to evaluate the effectiveness in the liver segmentation by comparing the results to ground truth. Overall, the proposed algorithm successfully segments the liver in most of the slices with satisfying results, although some of the results are under-segmented or over-segmented.
Contributor(s):
Thong, Kee Sin - Author
Primary Item Type:
Final Year Project
Identifiers:
Accession Number : 875003566
Barcode : 0003084256
Language:
English
Subject Keywords:
Accurate segmentation of liver structure from CT images is an essential step in the medical field such as surgery planning and diagnosis of liver disease; post-processing that utilizes morphological operations iteratively with region-labeling; Manual segmentation is done by manually tracing the liver contour on each image slice.
First presented to the public:
1/4/2010
Original Publication Date:
4/10/2018
Previously Published By:
Universiti Sains Malaysia
Place Of Publication:
School of Electrical & Electronic Engineering
Citation:
Extents:
Number of Pages - 55
License Grantor / Date Granted:
  / ( View License )
Date Deposited
2018-04-10 15:54:50.022
Date Last Updated
2019-01-07 11:24:32.9118
Submitter:
Nor Hayati Ismail

All Versions

Thumbnail Name Version Created Date
Segmentation of liver structure from computed tomogrhapy dataset / Thong Kee Sin1 2018-04-10 15:54:50.022