基于鼻咽癌危及器官自动分割可变性及剂量学影响  

Auto-segmentation variability of organs at risk in patients with nasopharyngeal carcinoma and its dosimetric impacts

作　　者：张丽媛 胡金炎 辜石勇 魏夏平 Zhang Liyuan;Hu Jinyan;Gu Shiyong;Wei Xiaping(Department of Radiation Oncology,Jinshazhou Hospital of Guangzhou University of Chinese Medicine,Guangzhou 510168,China)

机构地区：[1]广州中医药大学金沙洲医院肿瘤放射治疗中心,广州510168

出　　处：《中华放射医学与防护杂志》2024年第11期944-952,共9页Chinese Journal of Radiological Medicine and Protection

摘　　要：目的探讨鼻咽癌危及器官(OAR)自动分割轮廓的调整范围,并评估来自不同源头的轮廓对放疗计划剂量效应的影响。方法对25例临床早期鼻咽癌患者的脊髓、脑干、视神经、视交叉、腮腺、口腔、下咽和下颌骨进行放疗专家勾画、深度学习和图谱库自动勾画,以及专家对这些自动勾画的校正,形成共5个结构集。靶区及其他OAR的专家轮廓被复制到上述图像中用于后续研究。计算结构集的戴斯相似性系数(DSC)。以专家轮廓优化的放疗计划为模板,为每个结构集生成相应的放疗计划和剂量分布。定义专家轮廓及经专家校正的自动轮廓为临床轮廓,设定3个研究目标观察者内临床轮廓变化的剂量学效应、轮廓变化对计划优化的影响和轮廓变化对计划评估的影响。结果视觉通路平均DSC为0.62±0.10,低于其他OAR的0.86±0.04,经专家校正后,深度学习和图谱库勾画轮廓的DSC分别提高了7.61%和10.69%。在观察者内临床轮廓变化的剂量效应中,视交叉Dmax最大为(3.96±6.02)Gy,而下咽Dmean最小为(0.81±0.55)Gy。在专家轮廓上评估轮廓变化对计划优化影响中,脊髓、脑干、视神经和视交叉的剂量差异(ΔD)分别有22%、14%、46%和42%超过±3 Gy,而其他OAR的ΔD超过±3 Gy的比例仅2%。经过专家校正后,自动轮廓与专家轮廓的ΔD有所减小,其中视神经和视交叉超过±3 Gy的ΔD分别降低了16%和14%。当重叠体积直方图(OVH)平均距离超过3.5 cm时,ΔDmax均在±3 Gy内;当OVH平均距离>1.5 cm时,ΔDmean均在±2 Gy内。深度学习和图谱库轮廓分别有50.0%±17.3%和52.6%±19.3%患者剂量落在临床勾画剂量范围内;脊髓、视神经和视交叉Dmax及下颌骨D1 cm3两种自动轮廓剂量落在临床轮廓范围的患者数差异具有统计学意义(t=-4.24、-3.99、-3.16、3.51,P<0.05)。结论专家参考不同来源的自动勾画结果校正后仍显示出一定的几何差异,校正降低了自动勾画轮ObjectiveTo explore the adjustment ranges of auto-segmentation contours for organs at risk(OAR)in patients with nasopharyngeal carcinoma and assess the dosimetric impacts of the contours from varying sources on radiotherapy plans.MethodsTwenty-five patients with early-stage nasopharyngeal carcinoma were investigated.Through expert delineation,deep learning-based automatic delineation,and atlas-based automatic delineation of their spinal cord,brainstem,optic nerves,optic chiasm,parotid glands,oral cavity,hypopharynx,and mandible,as well as expert correction of these automatic delineations,five structure sets were formed.Moreover,the contours delineated by experts(also referred to as the expert contours)of the target volumes and other OARs were copied into the images for subsequent research.The Dice similarity coefficients(DSCs)of the structure sets were calculated.Using the radiotherapy plans optimized based on expert contours as templates,the radiotherapy plans and dose distributions of all the structure sets were established.The expert contours and contours determined using automatic delineation and corrected by experts(also referred to as the corrected contours)were defined as clinical contours.Then,three research objectives were set:the dosimetric effects of inter-observer clinical contour variations,the impacts of contour variations on plan optimization,and the impacts of contour variations on plan evaluation.ResultsThe average DSC of the visual pathway was 0.62±0.10,lower than that of other OARs(0.86±0.04).After expert correction,the DSCs of contours obtained using deep learning-and atlas-based automatic delineation increased by 7.61%and 10.69%,respectively.For the dosimetric effects of inner-observer contour variations,the D max of the optic chiasm was the maximum(3.96±6.02)Gy,while the D mean of the hypopharynx was the minimum(0.81±0.55 Gy).When the impacts of contour variations on plan optimization were assessed based on expert contours,the dose differences(ΔD)exceeding±3 Gy accounted for 22%,14%,46

关 键 词：危及器官 自动分割 剂量差异 重叠体积直方图 

分 类 号：R739.63[医药卫生—肿瘤] R730.55[医药卫生—临床医学]