文献速递头颈外科咽喉与嗓音

深度学习在白光与窄带成像喉镜下实时界定喉癌边界

Real-Time Laryngeal Cancer Boundaries Delineation on White Light and Narrow-Band Imaging Laryngoscopy with Deep Learning.
PubMed 文献 · Laryngoscope · 2024-01-04

回顾性研究提取并标注557例患者3933张喉癌内镜图像训练分割模型SegMENT-Plus,并在两个外部数据集及术中视频上验证。模型中位DSC=0.83、IoU=0.83、准确率=0.97、推理速度25.6帧/秒,与两名耳鼻咽喉科住院医师表现无显著差异,外部数据集泛化良好,可用于模拟实时视频喉镜。

要点

  • SegMENT-Plus在喉癌内镜图像上中位DSC=0.83、IoU=0.83、准确率=0.97。
  • 模型与两名耳鼻咽喉科住院医师的DSC(p=0.06)和IoU无显著差异。
  • 模型推理速度25.6帧/秒,可应用于模拟实时使用的视频喉镜。

核心结论

  • SegMENT-Plus能准确界定内镜图像中的喉癌边界,性能与两名耳鼻咽喉科住院医师相当。
  • 在两个外部数据集上的结果证明其具有优异的泛化能力。
  • 模型的计算速度使其可应用于模拟实时使用的视频喉镜。
  • 需要临床试验评估该技术在外科实践和切缘改善中的作用。

研究设计与样本

  • 回顾性研究,提取并标注白光(WL)和窄带成像(NBI)帧以训练分割模型SegMENT-Plus。
  • 使用两个外部数据集进行验证。
  • 模型性能与两名耳鼻咽喉科住院医师进行比较。
  • 模型在真实术中喉镜视频上进行测试。

主要发现

  • 共使用557例患者的3933张喉癌图像。
  • 模型中位值(四分位距):DSC=0.83(0.70-0.90),IoU=0.83(0.73-0.90),准确率=0.97(0.95-0.99),推理速度=25.6(25.1-26.1)帧/秒。
  • 外部测试队列分别包含156张和200张图像。
  • SegMENT-Plus在三个数据集上的DSC(p=0.05)和IoU(p=0.07)表现相似。
  • 分别分析WL和NBI测试图像时,DSC(p=0.06)和IoU(p=0.78)无显著差异;模型与两名住院医师比较,DSC(p=0.06)和IoU(高年资 vs. SegMENT-Plus,p=0.13;低年资 vs. SegMENT-Plus,p=1.00)无显著差异。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 需要临床试验评估该技术在外科实践和切缘改善中的作用。

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

OBJECTIVE: To investigate the potential of deep learning for automatically delineating (segmenting) laryngeal cancer superficial extent on endoscopic images and videos. METHODS: A retrospective study was conducted extracting and annotating white light (WL) and Narrow-Band Imaging (NBI) frames to train a segmentation model (SegMENT-Plus). Two external datasets were used for validation. The model's performances were compared with those of two otolaryngology residents. In addition, the model was tested on real intraoperative laryngoscopy videos. RESULTS: A total of 3933 images of laryngeal cancer from 557 patients were used. The model achieved the following median values (interquartile range): Dice Similarity Coefficient (DSC) = 0.83 (0.70-0.90), Intersection over Union (IoU) = 0.83 (0.73-0.90), Accuracy = 0.97 (0.95-0.99), Inference Speed = 25.6 (25.1-26.1) frames per second. The external testing cohorts comprised 156 and 200 images. SegMENT-Plus performed similarly on all three datasets for DSC (p = 0.05) and IoU (p = 0.07). No significant differences were noticed when separately analyzing WL and NBI test images on DSC (p = 0.06) and IoU (p = 0.78) and when analyzing the model versus the two residents on DSC (p = 0.06) and IoU (Senior vs. SegMENT-Plus, p = 0.13; Junior vs. SegMENT-Plus, p = 1.00). The model was then tested on real intraoperative laryngoscopy videos. CONCLUSION: SegMENT-Plus can accurately delineate laryngeal cancer boundaries in endoscopic images, with performances equal to those of two otolaryngology residents. The results on the two external datasets demonstrate excellent generalization capabilities. The computation speed of the model allowed its application on videolaryngoscopies simulating real-time use. Clinical trials are needed to evaluate the role of this technology in surgical practice and resection margin improvement. LEVEL OF EVIDENCE: III Laryngoscope, 134:2826-2834, 2024.

来源:Laryngoscope,查看原文。版权归原作者所有。

引用

  1. Sampieri C, Azam MA, Ioppi A, et al. Real-Time Laryngeal Cancer Boundaries Delineation on White Light and Narrow-Band Imaging Laryngoscopy with Deep Learning. Laryngoscope. 2024. PMID: 38174772. doi:10.1002/lary.31255

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。