Premium
Poster — Thur Eve — 05: Semi‐Automated Segmentation of Lung Tumours on CT Scans Using Level Set Sparse Field Active Model
Author(s) -
Awad J,
Wilson L,
Parraga G,
Fenster A
Publication year - 2010
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1118/1.3476110
Subject(s) - thresholding , segmentation , active contour model , artificial intelligence , image segmentation , pattern recognition (psychology) , computer science , standard deviation , level set (data structures) , nuclear medicine , computer vision , mathematics , medicine , image (mathematics) , statistics
We present a semi‐automated algorithm for segmenting lung tumours on chest computed tomography (CT) images to be utilized for monitoring tumour response or progression. Seven lung tumours were evaluated; each tumour was radially sliced into 10 slices for a total of 70 radial slices, and manually segmented. The manual segmentations were used as the ground truth for evaluating the proposed algorithm. The tumour image on each radial slice was classified into two categories: (1) well‐defined boundaries, located centrally in the lung parenchyma without significant vasculature; and (2) vascularized or juxtapleural (VJ). To segment the well‐defined boundaries, a shape constrained multi‐thresholding technique with one user‐defined seed point on the tumour is applied. For vascularized and juxtapleural tumours, this multi‐thresholding technique provided an initial contour that was deformed by a level set sparse field active model to produce the final segmentation for these tumours. The dice index (DI) measure was adopted to evaluate the segmentation results. The average and standard deviation values of the DI for the well‐defined and VJ images were 96.32 ± 1.12% and 95.19 ± 1.58%, respectively. The DI overall average and standard deviation of the 70 slices was 95.50 ± 1.55%. The preliminary results show that using the proposed algorithm produced accurate results.