In the segmentation of sequential treatment-timeCT prostate images acquired in image-guidedradiotherapy, accurately capturing the intrapatient variation of the patient under therapy is more important than capturing interpatient variation. However, using the traditional deformable-model-based segmentation methods, it is difficult to capture intrapatient variation when the number of samples from the same patient is limited. This article presents a new deformable model, designed specifically for segmenting sequential CTimages of the prostate, which leverages both population and patient-specific statistics to accurately capture the intrapatient variation of the patient under therapy.Methods:
The novelty of the proposed method is twofold:First, a weighted combination of gradient and probability distribution function (PDF) features is used to build the appearance model to guide model deformation. The strengths of each feature type are emphasized by dynamically adjusting the weight between the profile-based gradient features and the local-region-based PDF features during the optimization process. An additional novel aspect of the gradient-based features is that, to alleviate the effect of feature inconsistency in the regions of gas and bone adjacent to the prostate, the optimal profile length at each landmark is calculated by statistically investigating the intensity profile in the training set. The resulting gradient-PDF combined feature produces more accurate and robust segmentations than general gradient features. Second, an online learning mechanism is used to build shape and appearance statistics for accurately capturing intrapatient variation.Results:
The performance of the proposed method was evaluated on 306 images of the 24 patients. Compared to traditional gradient features, the proposed gradient-PDF combination features brought 5.2% increment in the success ratio of segmentation (from 94.1% to 99.3%). To evaluate the effectiveness of online learning mechanism, the authors carried out a comparison between partial online update strategy and full online update strategy. Using the full online update strategy, the mean DSC was improved from 86.6% to 89.3% with 2.8% gain. On the basis of full online update strategy, the manual modification before online update strategy was introduced and tested, the best performance was obtained; here, the mean DSC and the mean ASD achieved 92.4% and 1.47 mm, respectively.Conclusions:
The proposed prostate segmentation method provided accurate and robust segmentation results for CTimages even under the situation where the samples of patient under radiotherapy were limited. A conclusion that the proposed method is suitable for clinical application can be drawn.
This research was supported by the grants from the National Basic Research Program of China (973 Program) (Grant No. 2010CB732505), National Natural Science Funds of China (Grant No. 30800254, No. 30730036, and No. 30900380), Natural Science Funds of Guangdong Province (No. 9151051501000026) and National Institutes of Health under Grant NIH grant R01CA140413.
I.A. Improving the statistical modeling of shape
I.B. Identification of optimal image features for appearance modeling
II.A. Surface construction
II.A.1. Deformable-model-based algorithm for surface construction
II.A.2. Template-based framework for surface construction
II.B. Deformable-model-based segmentation
II.B.1. Cost function
II.B.2. Feature selection
II.B.3. Rectum gas and bone
II.B.4. Initialization and optimization strategy
II.C. Online learning mechanism
II.C.1. Shape model online learning
II.C.2. Appearance model online learning
III. EXPERIMENTAL RESULTS
III.A. Testing data and quantitative measures
III.B.1. Effectiveness of gradient-PDF combination features
III.B.2. Effectiveness of the online learning mechanism
III.B.3. Comparison with the other methods
Data & Media loading...
Article metrics loading...
Full text loading...