Contourlet-based active contour model for PET image segmentation

Abstract

Purpose: PET-guided radiation therapy treatment planning, clinical diagnosis, assessment of tumor growth, and therapy response rely on the accurate delineation of the tumor volume and quantification of tracer uptake. Most PET image segmentation techniques proposed thus far are suboptimal in the presence of heterogeneity of tracer uptake within the lesion. This work presents an active contour model approach based on the method of Chan and Vese ["Active contours without edges," IEEE Trans. Image Process. 10, 266-277 (2001)] designed to take into account the high level of statistical uncertainty (noise) and to handle the heterogeneity of tumor uptake typically present in PET images. Methods: In the proposed method, the fitting terms in the Chan-Vese formulation are modified by introducing new input images, including the smoothed version of the original image using anisotropic diffusion filtering (ADF) and the contourlet transform of the image. The advantage of utilizing ADF for image smoothing is that it avoids blurring the object's edges and preserves the average activity within a region, which is important for accurate PET quantification. Moreover, incorporating the contourlet transform of the image into the fitting terms makes the energy functional more effective in directing the evolving curve toward the object boundaries due to the enhancement of the tumor-tobackground ratio (TBR). The proper choice of the energy functional parameters has been formulated by making a clear consensus based on tumor heterogeneity and TBR levels. This cautious parameter selection leads to proper handling of heterogeneous lesions. The algorithm was evaluated using simulated phantom and clinical studies, where the ground truth and histology, respectively, were available for accurate quantitative analysis of the segmentation results. The proposed technique was also compared to a number of previously reported image segmentation techniques. Results:The results were quantitatively analyzed using three evaluation metrics, including the spatial overlap index (SOI), the mean relative error (MRE), and the mean classification error (MCE). Although the performance of the proposed method was analogous to other methods for some datasets, overall the proposed algorithm outperforms all other techniques. In the largest clinical group comprising nine datasets, the proposed approach improved the SOI from 0.41 ± 0.14 obtained using the best-performing algorithm to 0.54 ± 0.12 and reduced the MRE from 54.23 ± 103.29 to 0.19 ± 16.63 and the MCE from 112.86 ± 69.07 to 60.58 ± 18.43. Conclusions:The proposed segmentation technique is superior to other representative segmentation techniques in terms of highest overlap between the segmented volume and the ground truth/histology and minimum relative and classification errors. Therefore, the proposed active contour model can result in more accurate tumor volume delineation from PET images.

Magnetic resonance imaging-guided attenuation correction in whole-body PET/MRI using a sorted atlas approach

“…This method was used because of its simplicity but other sophisticated PET segmentation approaches which might have better performance can be used in this context ( Abdoli et al, 2013 ). The application of this approach was restricted to the lung region where the corresponding density is assumed to be known a priori and equivalent to soft-tissue.…”

Pathology-validated PET image data sets and their role in PET segmentation

“…These authors also reported that all three techniques failed to fully encompass the macroscopic tumor volumes. Abdoli et al [49] also used the Louvain LSCC data set [25] to compare a contourlet-based active contour PET-AS tool aimed at accounting for the noise and heterogeneity of PET images and found it to be superior to adaptive threshold and two FCM methods. Zaidi et al [50] used the Louvain LSCC data set [25] to compare the performance of nine algorithms including five threshold methods, a level set method, a stochastic expectationmaximization method, fuzzy clustering-based segmentation (FCM) and a spatial wavelet-based FCM (FCM-SW) and found FCM-SW to be most accurate.…”

“…Threshold [27-29, 33, 43] Adaptive threshold [12,31,33,52] Gradient [47] Fuzzy C-means [48] Active contours [49] FLAB [54] Neural network [55] Multimodality using level sets [51] Cervical cancer Threshold [34] Colon, rectal and sigmoid cancer Threshold [39,45] Adaptive threshold [35,44] Gradient [35,39] multimodality segmentation tool using level sets and Jensen-Renyi divergence (JRD). They compared the results to those from Zaidi et al [50], and found that the JRD approach was second to the FCM-SW method.…”

“…Zaidi et al [50] used the Louvain LSCC data set [25] to compare the performance of nine algorithms including five threshold methods, a level set method, a stochastic expectationmaximization method, fuzzy clustering-based segmentation (FCM) and a spatial wavelet-based FCM (FCM-SW) and found FCM-SW to be most accurate. Markel et al [51] also used the Louvain LSCC data set [25] to evaluate a Fixed thresholds (SUV and % of maximum) [38,39,40] Adaptive threshold (signal-to-background ratio based) [25,46,50,52] Gradient [39,47] Fuzzy C-means [48,50] Active contours [49,50] Possibility theory [53] Multimodality using level sets [51] Esophagus Fixed threshold (SUV and % of maximum) [41,42] Visual [41,42] Non-small-cell lung cancer (NSCLC)…”

PET Image Segmentation Based on Gabor Annulus Filtering and Region Growing

“…Spectral clustering and graph based segmentation proposed by Bagci et al, and Yang and Grigsby mitigate the difficulty of segmenting complex boundaries in low contrast images and are found to be superior to the existing thresholding approaches in PET image segmentation [8], [9]. Abdoli et al presented a deformable active contour model based on the method proposed by Chan and Vese and obtained more accurate tumour volume delineation from PET images [10].…”