Clinical implementation of deep learning contour autosegmentation for prostate radiotherapy.
Clinical implementation of deep learning contour autosegmentation for prostate radiotherapy.
复制标题
深度学习轮廓自动分割在前列腺放疗中的临床应用。
DOI：
10.1016/j.radonc.2021.02.040
复制
发表时间：
2021-06
影响因子：
5.7
通讯作者：
Gillespie, Erin F.
中科院分区：
文献类型：
--
作者：
Cha, Elaine;Elguindi, Sharif;Onochie, Ifeanyirochukwu;Gorovets, Daniel;Deasy, Joseph O.;Zelefsky, Michael;Gillespie, Erin F.
人工智能的进步刺激了新一代的自动分割，然而缺乏对这些算法的临床评估。本研究评估了基于深度学习的自动分割在基于磁共振的前列腺放疗计划中的临床应用。前瞻性收集了2019年6月至12月在我们机构接受前列腺放射治疗的患者的数据。几何指标（体积dice - s - ørensen系数，VDSC，表面dice - s - ørensen系数，SDSC，添加路径长度，APL）将自动轮廓与最终轮廓进行比较。医生报告了轮廓时间，并在3点协议偏差量表上评定了自动轮廓。描述性统计和单变量分析评估了上述指标之间的关系。173例患者中，85%接受了SBRT治疗。167例（97%）患者可获得CTV， CTV（前列腺和SV）的中位VDSC、SDSC和APL分别为0.89 （IQR 0.83-0.95）、0.91 （IQR 0.75-0.96）和1801 mm （IQR 1140-2703）。医生完成了43/55例患者的调查（RR 78%）。33%的自动轮廓（14/43）需要进行重大的“临床意义”编辑。医生绘制轮廓的平均时间为28分钟（IQR为20-30），与历史对照组相比节省了12分钟（30%）的时间（中位数为40分钟，IQR为25-68，n = 21, p < 0.01）。几何指标与等高线时间呈弱相关，与质量分数无相关性。成功实现了基于深度学习的自动分割，提高了分割效率。重大的“临床意义”的编辑是不常见的，不与几何指数相关。APL作为一种有临床意义的定量指标得到了支持。需要努力教育和在医生之间达成共识，并建立机制来标记病例以保证质量。
Artificial intelligence advances have stimulated a new generation of autosegmentation, however clinical evaluations of these algorithms are lacking. This study assesses the clinical utility of deep learning-based autosegmentation for MR-based prostate radiotherapy planning. Data was collected prospectively for patients undergoing prostate-only radiation at our institution from June to December 2019. Geometric indices (volumetric Dice-Sørensen Coefficient, VDSC; surface Dice-Sørensen Coefficient, SDSC; added path length, APL) compared automated to final contours. Physicians reported contouring time and rated autocontours on 3-point protocol deviation scales. Descriptive statistics and univariable analyses evaluated relationships between the aforementioned metrics. Among 173 patients, 85% received SBRT. The CTV was available for 167 (97%) with median VDSC, SDSC, and APL for CTV (prostate and SV) 0.89 (IQR 0.83–0.95), 0.91 (IQR 0.75–0.96), and 1801 mm (IQR 1140–2703), respectively. Physicians completed surveys for 43/55 patients (RR 78%). 33% of autocontours (14/43) required major “clinically significant” edits. Physicians spent a median of 28 min contouring (IQR 20–30), representing a 12-minute (30%) time savings compared to historic controls (median 40, IQR 25–68, n = 21, p < 0.01). Geometric indices correlated weakly with contouring time, and had no relationship with quality scores. Deep learning-based autosegmentation was implemented successfully and improved efficiency. Major “clinically significant” edits are uncommon and do not correlate with geometric indices. APL was supported as a clinically meaningful quantitative metric. Efforts are needed to educate and generate consensus among physicians, and develop mechanisms to flag cases for quality assurance.
登录
查看更多内容
DOI：
10.3390/diagnostics10110959
发表时间：
2020-11-17
期刊：
Diagnostics (Basel, Switzerland)
影响因子：
--
作者：
Kiljunen T;Akram S;Niemelä J;Löyttyniemi E;Seppälä J;Heikkilä J;Vuolukka K;Kääriäinen OS;Heikkilä VP;Lehtiö K;Nikkinen J;Gershkevitsh E;Borkvel A;Adamson M;Zolotuhhin D;Kolk K;Pang EPP;Tuan JKL;Master Z;Chua MLK;Joensuu T;Kononen J;Myllykangas M;Riener M;Mokka M;Keyriläinen J
通讯作者：
Keyriläinen J
影响因子：
3.3
作者：
Morgan, Scott C.;Hoffman, Karen;Sandler, Howard
通讯作者：
Sandler, Howard
影响因子：
2.4
作者：
Nakamura, Katsumasa;Shioyama, Yoshiyuki;Jingu, Kenichi
通讯作者：
Jingu, Kenichi
DOI：
10.1016/0360-3016(95)00215-4
发表时间：
1995-12-01
影响因子：
7
作者：
AustinSeymour, M;Chen, GTY;Goitein, M
通讯作者：
Goitein, M
影响因子：
5.7
作者：
Francolini, Giulio;Thomsen, Mette S.;Offersen, Birgitte V.
通讯作者：
Offersen, Birgitte V.