Compared with the previous automatic segmentation neural network for the target area which considered the target area as an independent area, a stacked neural network which uses the position and shape information of the organs around the target area to regulate the shape and position of the target area through the superposition of multiple networks and fusion of spatial position information to improve the segmentation accuracy on medical images was proposed in this paper. Taking the Graves’ ophthalmopathy disease as an example, the left and right radiotherapy target areas were segmented by the stacked neural network based on the fully convolutional neural network. The volume Dice similarity coefficient (DSC) and bidirectional Hausdorff distance (HD) were calculated based on the target area manually drawn by the doctor. Compared with the full convolutional neural network, the stacked neural network segmentation results can increase the volume DSC on the left and right sides by 1.7% and 3.4% respectively, while the two-way HD on the left and right sides decrease by 0.6. The results show that the stacked neural network improves the degree of coincidence between the automatic segmentation result and the doctor's delineation of the target area, while reducing the segmentation error of small areas. The stacked neural network can effectively improve the accuracy of the automatic delineation of the radiotherapy target area of Graves' ophthalmopathy.
【摘要】 目的 分析重力因素对二维探测器阵列验证静态调强计划的影响，判断机架角度归为0°的测量方法是否安全可靠。 方法 在0°机架角和实际治疗机架角分别测量静态调强计划的剂量分布，以3 mm范围内偏差lt;3%(3% 3 mm)标准进行γ分析，获得相对于参考剂量分布的通过率，分析通过率变化规律。分析两种方法测量的等中心点绝对剂量的差异。 结果 通过率的变化呈随机分布，96.9%的照射野偏差lt;2.5%。所有计划的85.7%绝对剂量偏差lt;2%，最大偏差为4.75%。 结论 使用二维探测器阵列在0°角进行调强计划的日常验证是安全可靠的。【Abstract】 Objective To analyze impacts of gravity on the verification of IMRT plans with 2-Dimensional detector arrays and to evaluate the reliability of the measurements in vertical direction (gantry angle=0). Methods The dose distributions for each beam in IMRT plans were measured with 0 degree gantry angle and actual gantry angle respectively. The γ percentage pass rate (according to 3% 3 mm) for each beam under each angle condition was obtained by the comparison between the measured dose distribution and the calculated dose map from the treatment planning system which was treated as the reference distribution. Then the absolute dose at the isocenter for each plan was measured at each angle condition and was analyzed. Results The variations of γ percentage pass rates between the two types of measurements were randomly distributed, and the deviations for 96.9% beams were less than±2.5%. The differences between absolute doses for 85.7% beams were less than±2% and the biggest deviation was -4.75%. Conclusion Verification of IMRT plans for the radiotherapy quality assurance using 2-Dimensional detector arrays in 0 degree gantry angle is safe and reliable.