Generic and robust method for automatic segmentation of PET images using an active contour model

Abstract

Purpose: Although positron emission tomography (PET) images have shown potential to improve the accuracy of targeting in radiation therapy planning and assessment of response to treatment, the boundaries of tumors are not easily distinguishable from surrounding normal tissue owing to the low spatial resolution and inherent noisy characteristics of PET images. The objective of this study is to develop a generic and robust method for automatic delineation of tumor volumes using an active contour model and to evaluate its performance using phantom and clinical studies. Methods: MASAC, a method for automatic segmentation using an active contour model, incorporates the histogram fuzzy C-means clustering, and localized and textural information to constrain the active contour to detect boundaries in an accurate and robust manner. Moreover, the lattice Boltzmann method is used as an alternative approach for solving the level set equation to make it faster and suitable for parallel programming. Twenty simulated phantom studies and 16 clinical studies, including six cases of pharyngolaryngeal squamous cell carcinoma and ten cases of nonsmall cell lung cancer, were included to evaluate its performance. Besides, the proposed method was also compared with the contourlet-based active contour algorithm (CAC) and Schaefer's thresholding method (ST). The relative volume error (RE), Dice similarity coefficient (DSC), and classification error (CE) metrics were used to analyze the results quantitatively. Results: For the simulated phantom studies (PSs), MASAC and CAC provide similar segmentations of the different lesions, while ST fails to achieve reliable results. For the clinical datasets (2 cases with connected high-uptake regions excluded) (CSs), CAC provides for the lowest mean RE (−8.38% ± 27.49%), while MASAC achieves the best mean DSC (0.71 ± 0.09) and mean CE (53.92% ± 12.65%), respectively. MASAC could reliably quantify different types of lesions assessed in this work with good accuracy, resulting in a mean RE of −13.35% ± 11.87% and −11.15% ± 23.66%, a mean DSC of 0.89 ± 0.05 and 0.71 ± 0.09, and a mean CE of 19.19% ± 7.89% and 53.92% ± 12.65%, for PSs and CSs, respectively. Conclusions:The authors' results demonstrate that the developed novel PET segmentation algorithm is applicable to various types of lesions in the authors' study and is capable of producing accurate and consistent target volume delineations, potentially resulting in reduced intraobserver and interobserver variabilities observed when using manual delineation and improved accuracy in treatment planning and outcome evaluation. C

Variability and Repeatability of Quantitative Uptake Metrics in 18F-FDG PET/CT of Non–Small Cell Lung Cancer: Impact of Segmentation Method, Uptake Interval, and Reconstruction Protocol

“…Lesions were identified by a nuclear physician. For each lesion, 8 automated segmentation methods were applied (Supplemental Table 1): a method for automated segmentation using an active contour model (MASAC) (11), an affinity propagation algorithm (AP) (12), a contourlet-based active contour algorithm (CAC) (13), the contrast-oriented thresholding method (ST) of Schaefer et al (14), segmentation using 41% of the maximum tumor value as a threshold (41MAX) (15), segmentation using 50% of the peak tumor value as a threshold, adapted for local background (A50P) (15), segmentation using an SUV of 2.5 as a threshold (SUV25), and segmentation using an SUV of 4.0 as a threshold (SUV40).…”

Quantitative Analysis of Heterogeneous [18F]FDG Static (SUV) vs. Patlak (Ki) Whole-body PET Imaging Using Different Segmentation Methods: a Simulation Study

“…211, a high variability is observed between different segmentation methods [27]. To assess the impact of tumor delineation, two different segmentation methods, namely a method for automatic segmentation using an active contour model (MASAC) [28] and an affinity propagation algorithm (AP) [29], were employed. These algorithms underwent extensive testing in our lab and were chosen owing to their accuracy and consistency as reported in previous studies using phantom and clinical studies.…”

“…These algorithms underwent extensive testing in our lab and were chosen owing to their accuracy and consistency as reported in previous studies using phantom and clinical studies. In particular, the parameter lambda in the implementation of MASAC was set to 3 [28] whereas the default parameters…”

Comparison of different automated lesion delineation methods for metabolic tumor volume of 18F-FDG PET/CT in patients with stage I lung adenocarcinoma

“…However, there is no appropriate reference for the evaluation of volumes. Although a number of recent papers use macroscopic specimen obtained from histology as reference, [ 40 , 41 ] there is still problematic since the irregular contraction can occur during tissue fixation, and the criterion of contraction rate is quite different. In Schaefer et al's [ 42 ] research, they used pathology as the ground truth or CT as a ground truth surrogate, and recommended consensus contours from multiple PET segmentations as a new reference.…”