双深度神经网络在宫颈癌放疗自动勾画中的临床验证
本研究回顾性收集203例宫颈癌患者数据开发SegNet自动勾画临床靶区(CTV)和危及器官(OARs),并另用20例比较AI辅助与全手动勾画的工作量和质量;多组数据训练的SegNet勾画CTV的DSC达0.85±0.02,临床评分352/360,自动勾画CTV手动修改时间9.54±2.42分钟,优于全手动勾画的30.95±15.24分钟。
要点
- 多组数据训练的SegNet勾画CTV的DSC为0.85±0.02,优于单独训练的三个模型。
- SegNet在膀胱、直肠、肠袋、双侧股骨头等OARs的DSC与UNet比较,部分有统计学差异。
- 自动勾画CTV的修改时间9.54±2.42分钟,短于全手动勾画的30.95±15.24分钟。
核心结论
- 纳入多组数据训练的SegNet能提升宫颈癌放疗自动勾画的性能。
- AI辅助系统可在不损失质量的前提下缩短手动勾画时间,具有临床适用性。
研究设计与样本
- 回顾性收集四川大学华西医院203例宫颈癌患者数据,开发并训练名为SegNet的自动勾画方法。
- 采用定量指标和基于临床的评分比较多组自动勾画轮廓的差异。
- 另取20例比较AI辅助勾画与从零开始手动勾画的工作量和质量。
主要发现
- 多组数据训练的SegNet勾画CTV的DSC为0.85±0.02,高于SegNet(A)的0.82±0.04、SegNet(B)的0.82±0.03和SegNet(C)的0.81±0.04,差异有统计学意义。
- SegNet与UNet的DSC分别为:CTV 0.85 vs 0.82(P < 0.001)、膀胱0.93 vs 0.92(P = 0.44)、直肠0.84 vs 0.81(P = 0.02)、肠袋0.89 vs 0.84(P < 0.001)、右侧股骨头0.93 vs 0.92(P = 0.17)、左侧股骨头0.92 vs 0.91(P = 0.25)。
- 基于临床的评分显示多组数据训练的SegNet得分为352/360,高于SegNet(A)的334/360、SegNet(B)的333/360和SegNet(C)的320/360。
- 自动勾画CTV(尚未包括OARs)的手动修改时间为9.54±2.42分钟,全手动勾画为30.95±15.24分钟。
关键数值与推荐
- 多组数据训练的SegNet勾画CTV的DSC为0.85±0.02。
- SegNet与UNet勾画CTV的DSC分别为0.85和0.82(P < 0.001)。
- 基于临床的评分:多组数据训练的SegNet为352/360,SegNet(A)为334/360,SegNet(B)为333/360,SegNet(C)为320/360。
- 自动勾画CTV的手动修改时间为9.54±2.42分钟,全手动勾画为30.95±15.24分钟。
临床怎么用
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: Artificial intelligence (AI) algorithms are capable of automatically detecting contouring boundaries in medical images. However, the algorithms impact on clinical practice of cervical cancer are unclear. We aimed to develop an AI-assisted system for automatic contouring of the clinical target volume (CTV) and organs-at-risk (OARs) in cervical cancer radiotherapy and conduct clinical-based observations. METHODS: We first retrospectively collected data of 203 patients with cervical cancer from West China Hospital. The proposed method named as SegNet was developed and trained with different data groups. Quantitative metrics and clinical-based grading were used to evaluate differences between several groups of automatic contours. Then, 20 additional cases were conducted to compare the workload and quality of AI-assisted contours with manual delineation from scratch. RESULTS: For automatic CTVs, the dice similarity coefficient (DSC) values of the SegNet trained with incorporating multi-group data achieved 0.85 ± 0.02, which was statistically better than the DSC values of SegNet independently trained with the SegNet(A) (0.82 ± 0.04), SegNet(B) (0.82 ± 0.03) or SegNet(C) (0.81 ± 0.04). Moreover, the DSC values of the SegNet and UNet, respectively, 0.85 and 0.82 for the CTV (P < 0.001), 0.93 and 0.92 for the bladder (P = 0.44), 0.84 and 0.81 for the rectum (P = 0.02), 0.89 and 0.84 for the bowel bag (P < 0.001), 0.93 and 0.92 for the right femoral head (P = 0.17), and 0.92 and 0.91 for the left femoral head (P = 0.25). The clinical-based grading also showed that SegNet trained with multi-group data obtained better performance of 352/360 relative to it trained with the SegNet(A) (334/360), SegNet(B) (333/360) or SegNet(C) (320/360). The manual revision time for automatic CTVs (OARs not yet include) was 9.54 ± 2.42 min relative to fully manual delineation with 30.95 ± 15.24 min. CONCLUSION: The proposed SegNet can improve the performance at automatic delineation for cervical cancer radiotherapy by incorporating multi-group data. It is clinically applicable that the AI-assisted system can shorten manual delineation time at no expense of quality.
引用
- Nie S, Wei Y, Zhao F, et al. A dual deep neural network for auto-delineation in cervical cancer radiotherapy with clinical validation. Radiat Oncol. 2022. PMID: 36380378. doi:10.1186/s13014-022-02157-5
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。