深度学习与基于图谱的模型在头颈部 CT 图像咀嚼肌自动分割中的比较。

Deep learning vs. atlas-based models for fast auto-segmentation of the masticatory muscles on head and neck CT images.

机构信息

Department of Radiation Oncology, Xiangya Hospital, Central South University, Changsha, China.

Department of Radiation Oncology, University of California Davis Medical Center, 4501 X Street, Suite 0152, Sacramento, California, 95817, USA.

出版信息

Radiat Oncol. 2020 Jul 20;15(1):176. doi: 10.1186/s13014-020-01617-0.

DOI:10.1186/s13014-020-01617-0

PMID:32690103

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC7372849/

Abstract

BACKGROUND

Impaired function of masticatory muscles will lead to trismus. Routine delineation of these muscles during planning may improve dose tracking and facilitate dose reduction resulting in decreased radiation-related trismus. This study aimed to compare a deep learning model with a commercial atlas-based model for fast auto-segmentation of the masticatory muscles on head and neck computed tomography (CT) images.

MATERIAL AND METHODS

Paired masseter (M), temporalis (T), medial and lateral pterygoid (MP, LP) muscles were manually segmented on 56 CT images. CT images were randomly divided into training (n = 27) and validation (n = 29) cohorts. Two methods were used for automatic delineation of masticatory muscles (MMs): Deep learning auto-segmentation (DLAS) and atlas-based auto-segmentation (ABAS). The automatic algorithms were evaluated using Dice similarity coefficient (DSC), recall, precision, Hausdorff distance (HD), HD95, and mean surface distance (MSD). A consolidated score was calculated by normalizing the metrics against interobserver variability and averaging over all patients. Differences in dose (∆Dose) to MMs for DLAS and ABAS segmentations were assessed. A paired t-test was used to compare the geometric and dosimetric difference between DLAS and ABAS methods.

RESULTS

DLAS outperformed ABAS in delineating all MMs (p < 0.05). The DLAS mean DSC for M, T, MP, and LP ranged from 0.83 ± 0.03 to 0.89 ± 0.02, the ABAS mean DSC ranged from 0.79 ± 0.05 to 0.85 ± 0.04. The mean value for recall, HD, HD95, MSD also improved with DLAS for auto-segmentation. Interobserver variation revealed the highest variability in DSC and MSD for both T and MP, and the highest scores were achieved for T by both automatic algorithms. With few exceptions, the mean ∆D98%, ∆D95%, ∆D50%, and ∆D2% for all structures were below 10% for DLAS and ABAS and had no detectable statistical difference (P > 0.05). DLAS based contours had dose endpoints more closely matched with that of the manually segmented when compared with ABAS.

CONCLUSIONS

DLAS auto-segmentation of masticatory muscles for the head and neck radiotherapy had improved segmentation accuracy compared with ABAS with no qualitative difference in dosimetric endpoints compared to manually segmented contours.

摘要

背景

咀嚼肌功能障碍会导致牙关紧闭。在计划中常规勾画这些肌肉可以提高剂量跟踪的准确性，并有助于降低剂量，从而减少与放疗相关的牙关紧闭。本研究旨在比较深度学习模型与商业图谱基模型在头颈部 CT 图像上快速自动勾画咀嚼肌的性能。

材料与方法

在 56 幅 CT 图像上手动分割双侧咬肌（M）、颞肌（T）、内、外侧翼内肌（MP、LP）。CT 图像随机分为训练集（n=27）和验证集（n=29）。使用两种方法进行咀嚼肌自动勾画：深度学习自动勾画（DLAS）和图谱基自动勾画（ABAS）。使用 Dice 相似系数（DSC）、召回率、精确度、Hausdorff 距离（HD）、HD95 和平均表面距离（MSD）评估自动勾画算法。通过归一化各指标的观察者间变异性并对所有患者进行平均计算，得出综合评分。比较了 DLAS 和 ABAS 勾画结果对咀嚼肌的剂量差异（∆Dose）。采用配对 t 检验比较 DLAS 和 ABAS 方法的几何和剂量学差异。

结果

DLAS 在勾画所有咀嚼肌方面均优于 ABAS（p<0.05）。DLAS 勾画的 M、T、MP 和 LP 的平均 DSC 范围分别为 0.83±0.03 至 0.89±0.02，ABAS 勾画的 M、T、MP 和 LP 的平均 DSC 范围分别为 0.79±0.05 至 0.85±0.04。DLAS 自动勾画的召回率、HD、HD95 和 MSD 平均值也有所提高。观察者间变异性显示，T 和 MP 的 DSC 和 MSD 变异最大，两种自动算法的 T 得分最高。除少数情况外，DLAS 和 ABAS 勾画的所有结构的∆D98%、∆D95%、∆D50%和∆D2%均值均低于 10%，且无统计学差异（P>0.05）。与 ABAS 相比，基于 DLAS 的轮廓在剂量终点方面与手动勾画更为匹配。