(For USM Staff/Student Only)

EngLib USM > Ω School of Electrical & Electronic Engineering >

Development of semi-automatic liver segmentation method for three-dimensional computed tomography dataset

Development of semi-automatic liver segmentation method for three-dimensional computed tomography dataset / Chiang Yi Fan
Peruasan hati daripada dataset tiga dimensi tomografi berkomputer (CT) adalah sangat penting dalam diagnosis dan perancangan rawatan penyakit hati. Peruasan manual memberi keputusan yang lebih tepat tetapi meletihkan dan memakan masa kerana kepingan imej yang banyak dihasilkan oleh mesin CT. Beza jelas yang rendah pada sempadan hati dengan organorgan berjiranan, kepelbagaian yang tinggi bentuk-bentuk hati dan kehadiran pathologi hati akan menjejaskan ketepatan peruasan hati automatik dan menjadikan peruasan hati automatic satu tugas yang mencabar. Oleh itu, perisian peruasan separa-automatik telah dibina dalam projek ini untuk memperoleh ketepatan peruasan hati yang tinggi dan mengurangkan masa yang digunakan untuk peruasan hati secara manual. Algoritma yang dicadangkan boleh dibahagikan kepada tiga peringkat. Peringkat pertama ialah persiapan parameter dan pra-pemprosesan. Dalam praprosesan, keadah resapan tak-isotropi digunakan untuk mengurangkan hingar dalam imej dan melicinkan imej. Dalam peringkat kedua, teknik pengambangan digunakan untuk mendapatkan kawasan hati dalam imej CT. Selepas itu, mophologi penutupan dan pembukaan digunakan untuk menutup lubang-lubang kecil dalam kawasan hati dan memutuskan sambungan nipis di antara hati dengan organ-organ berjiranan. Kemudian, penutupan lubang digunakan untuk mengisi lubang-lubang besar dalam kawasan hati. Selepas itu, analisis komponen-komponen bersambung akan dijalankan untuk menyarikan kawasan hati daripada kepingan imej CT. Peringkat terakhir merupakan pasca-pemprosesan. Dalam pasca-pemprosesan, kontur hati dilicinkan dengan turas Gauss perduaan. Perisian peruasan hati dengan algoritma yang dicadangkan dinilai dengan menggunakan dataset CT yang diperoleh daripada SLIVER07 untuk membuktikan keberkesanannya dalam peruasan hati. Keputusan peruasan hati mencapai purata VOE 9.93 ± 4.36 %, purata RVD -0.03 ± 3.76 %, purata ASD 2.57 ± 1.73 mm, purata RMSD 5.82 ± 3.56 mm dan purata MSD 39.90 ± 17.23 mm. Jumlah masa yang diperlukan oleh perisian yang dibina untuk menyelesaikan proses peruasan hati adalah di antara 2 hingga 4 minit. Algoritma yang dicadangkan dapat meruas hati yang sihat dengan cekap dan berkesan walaupun terdapat masalah peruasan berlebihan dan masalah peruasan berkurangan disebabkan kehadiran penyakit dan beza jelas yang rendah di antara hati dengan organ-organ berjiranan. _______________________________________________________________________________________________________ Segmentation of liver from 3D computed tomography (CT) dataset is very important in hepatic disease diagnosis and treatment planning. Manual segmentation gives accurate result but the process is tedious and time-consuming due to a large number of slices produced by the CT scanner. Low contrast of liver boundary with neighbouring organs, high shape variability of liver and presence of various liver pathologies will affect the accuracy of automatic liver segmentation and thus make automatic liver segmentation a challenging task. Therefore, a semi-automated liver segmentation program is developed in this project in order to obtain high accuracy in liver segmentation and reduce the time required for manual liver segmentation. The proposed algorithm can be divided into three stages. The first stage is parameter setup and pre-processing. User interaction is required to setup the segmentation parameters. For pre-processing, anisotropic diffusion filtering is applied to reduce noise in the image and smooth the image. In second stage, thresholding is applied to CT images to extract the possible liver regions. Then, morphological closing and opening are used close small holes inside liver region and break the thin connections between liver and neighbouring organs. Hole-filling is employed to fill up the large holes inside liver region. Next, the connected component analysis is performed to extract liver region from the CT slices. The last stage is post-processing. In post-processing, the contour of liver is smooth by binary Gaussian filter. The liver segmentation program with proposed algorithm is evaluated with CT datasets obtained from SLIVER07 to prove its effectiveness in liver segmentation. The results of liver segmentation achieved average VOE of 9.93 ± 4.36 %, average RVD of -0.03 ± 3.76 %, average ASD of 2.57 ± 1.73 mm, average RMSD of 5.82 ± 3.56 mm, and average MSD of 39.90 ± 17.23 mm. The total time required for the program developed to complete liver segmentation process is between 2 to 4 minutes. The proposed algorithm was able to segment the healthy liver effectively and efficiently even though there were over-segmentation and undersegmentation problem due to the presence of pathologies and low contrast between liver and neighbouring organs.
Contributor(s):
Chiang Yi Fan - Author
Primary Item Type:
Final Year Project
Identifiers:
Accession Number : 875007138
Barcode : 00003107016
Language:
English
Subject Keywords:
3D computed tomography; Segmentation of liver; hepatic disease diagnosis
First presented to the public:
6/1/2017
Original Publication Date:
4/19/2018
Previously Published By:
Universiti Sains Malaysia
Place Of Publication:
School of Electrical & Electronic Engineering
Citation:
Extents:
Number of Pages - 84
License Grantor / Date Granted:
  / ( View License )
Date Deposited
2018-04-19 15:15:34.462
Date Last Updated
2019-01-07 11:24:32.9118
Submitter:
Mohd Jasnizam Mohd Salleh

All Versions

Thumbnail Name Version Created Date
Development of semi-automatic liver segmentation method for three-dimensional computed tomography dataset1 2018-04-19 15:15:34.462