Lung 4D computed tomography (4D-CT) plays an important role in high-precision radiotherapy because it characterizes respiratory motion, which is crucial for accurate target definition. However, the manual segmentation of a lung tumor is a heavy workload for doctors because of the large number of lung 4D-CT data slices. Meanwhile, tumor segmentation is still a notoriously challenging problem in computer-aided diagnosis. In this paper, we propose a new method based on an improved graph cut algorithm with context information constraint to find a convenient and robust approach of lung 4D-CT tumor segmentation. We combine all phases of the lung 4D-CT into a global graph, and construct a global energy function accordingly. The sub-graph is first constructed for each phase. A context cost term is enforced to achieve segmentation results in every phase by adding a context constraint between neighboring phases. A global energy function is finally constructed by combining all cost terms. The optimization is achieved by solving a max-flow/min-cut problem, which leads to simultaneous and robust segmentation of the tumor in all the lung 4D-CT phases. The effectiveness of our approach is validated through experiments on 10 different lung 4D-CT cases. The comparison with the graph cut without context constraint, the level set method and the graph cut with star shape prior demonstrates that the proposed method obtains more accurate and robust segmentation results.

Background Both patient-specific dose recalculation and γ passing rate analysis are important for the quality assurance (QA) of intensity modulated radiotherapy (IMRT) plans. The aim of this study was to analyse the correlation between the γ passing rates and the volumes of air cavities (Vair) and bony structures (Vbone) in target volume of head and neck cancer. Methods Twenty nasopharyngeal carcinoma and twenty nasal natural killer T-cell lymphoma patients were enrolled in this study. Nine-field sliding window IMRT plans were produced and the dose distributions were calculated by anisotropic analytical algorithm (AAA), Acuros XB algorithm (AXB) and SciMoCa based on the Monte Carlo (MC) technique. The dose distributions and γ passing rates of the targets, organs at risk, air cavities and bony structures were compared among the different algorithms. Results The γ values obtained with AAA and AXB were 95.6 ± 1.9% and 96.2 ± 1.7%, respectively, with 3%/2 mm criteria (p > 0.05). There were significant differences (p < 0.05) in the γ values between AAA and AXB in the air cavities (86.6 ± 9.4% vs. 98.0 ± 1.7%) and bony structures (82.7 ± 13.5% vs. 99.0 ± 1.7%). Using AAA, the γ values were proportional to the natural logarithm of Vair (R2 = 0.674) and inversely proportional to the natural logarithm of Vbone (R2 = 0.816). When the Vair in the targets was smaller than approximately 80 cc or the Vbone in the targets was larger than approximately 6 cc, the γ values of AAA were below 95%. Using AXB, no significant relationship was found between the γ values and Vair or Vbone. Conclusion In clinical head and neck IMRT QA, greater attention should be paid to the effect of Vair and Vbone in the targets on the γ passing rates when using different dose calculation algorithms.

Pre-trained DCNN trained on a large-scale image database can be used as a universal feature representation for image classification, which has achieved significant progress in some image recognition tasks. Compared with other image recognition tasks, directly utilizing a single convolutional feature as feature representation for vein recognition task cannot achieve the impressive result due to the sparse distribution of vein information. Therefore, to obtain more representative and discriminative convolutional feature for vein recognition, a novel multi-layer convolutional features' concatenation with semantic feature selector is proposed in this paper. In the pre-trained DCNN, different convolutional layers can encode different-level feature information. High-level convolutional features with vein information cover more semantic information and low-level convolutional features with vein information cover more detail information. However, low-level convolutional features also contain some background information. Therefore, in order to remove the background information of low-level convolutional features, a novel semantic feature selector is presented. First, the proposed local max-pooling of preserving spatial position (LMP-PSP) information is applied on activation map obtained by adding up all feature maps of the high-level convolutional layer to generate the semantic weighting map, which reflects key vein information of high-level convolutional features. Then, semantic weighting map is regarded as a feature selector to discard the background information of the low-level convolutional features and preserve the detail information of low level convolutional features. Finally, low-level convolutional features with vein information are selectively linked to high-level convolutional features with vein information based on the proposed semantic feature selector. A series of rigorous experiments on two lab-made vein databases named CUMT-Hand-Dorsa Vein database and CUMT-Palm Vein database is conducted to verify the effectiveness and feasibility of the proposed model. Besides, additional experiments with PUT Palm Vein database and the subset of PolyU database illustrate its generalization ability and robustness.

No abstract