INTRODUCTION Adequate head and neck (HN) organ-at-risk (OAR) delineation is crucial for HN radiotherapy and for investigating the relationships between radiation dose to OARs and radiation-induced side effects. The automatic contouring algorithms that are currently in clinical use, such as atlas-based contouring (ABAS), leave room for improvement. The aim of this study was to use a comprehensive evaluation methodology to investigate the performance of HN OAR auto-contouring when using deep learning contouring (DLC), compared to ABAS. METHODS The DLC neural network was trained on 589 HN cancer patients. DLC was compared to ABAS by providing each method with an independent validation cohort of 104 patients, which had also been manually contoured. For each of the 22 OAR contours - glandular, upper digestive tract and central nervous system (CNS)-related structures - the dice similarity coefficient (DICE), and absolute mean and max dose differences (|Δmean-dose| and |Δmax-dose|) performance measures were obtained. For a subset of 7 OARs, an evaluation of contouring time, inter-observer variation and subjective judgement was performed. RESULTS DLC resulted in equal or significantly improved quantitative performance measures in 19 out of 22 OARs, compared to the ABAS (DICE/|Δmean dose|/|Δmax dose|: 0.59/4.2/4.1 Gy (ABAS); 0.74/1.1/0.8 Gy (DLC)). The improvements were mainly for the glandular and upper digestive tract OARs. DLC significantly reduced the delineation time for the inexperienced observer. The subjective evaluation showed that DLC contours were more often preferable to the ABAS contours overall, were considered to be more precise, and more often confused with manual contours. Manual contours still outperformed both DLC and ABAS; however, DLC results were within or bordering the inter-observer variability for the manual edited contours in this cohort. CONCLUSION The DLC, trained on a large HN cancer patient cohort, outperformed the ABAS for the majority of HN OARs.

中文翻译：

---

通过深度学习轮廓改进对有风险的头颈部器官的自动描绘

引言 充分的头颈部 (HN) 危及器官 (OAR) 描绘对于 HN 放射治疗以及研究 OAR 的辐射剂量与辐射引起的副作用之间的关系至关重要。目前临床使用的自动轮廓绘制算法，例如基于图谱的轮廓绘制 (ABAS)，还有改进的余地。本研究的目的是使用综合评估方法来研究使用深度学习轮廓 (DLC) 时 HN OAR 自动轮廓与 ABAS 相比的性能。方法 DLC 神经网络对 589 名 HN 癌症患者进行了训练。通过为每种方法提供由 104 名患者组成的独立验证队列，将 DLC 与 ABAS 进行比较，这些队列也已手动绘制轮廓。对于 22 个 OAR 轮廓中的每一个 - 腺体，获得了上消化道和中枢神经系统 (CNS) 相关结构 - 骰子相似系数 (DICE)，以及绝对平均和最大剂量差异（|Δmean-dose| 和 |Δmax-dose|）性能指标。对于 7 个 OAR 的子集，进行了轮廓绘制时间、观察者间差异和主观判断的评估。结果 与 ABAS 相比，DLC 在 22 个 OAR 中的 19 个中产生了相等或显着改善的定量性能指标（DICE/|Δ平均剂量|/|Δ最大剂量|：0.59/4.2/4.1 Gy (ABAS)；0.74/1.1/0.8 Gy (DLC))。改进主要针对腺体和上消化道 OAR。DLC 显着减少了没有经验的观察者的描绘时间。主观评估表明 DLC 轮廓总体上比 ABAS 轮廓更可取，被认为更精确，并且更常与手动轮廓混淆。手动轮廓仍然优于 DLC 和 ABAS；然而，DLC 结果在该队列中手动编辑轮廓的观察者间变异性之内或接近。结论 DLC 在大型 HN 癌症患者队列中进行训练，在大多数 HN OAR 上的表现优于 ABAS。