文献速递咽喉与嗓音头颈外科

可解释计算机视觉在数字柔性喉镜图像中检测和分类喉部结构性病变

Interpretable Computer Vision to Detect and Classify Structural Laryngeal Lesions in Digital Flexible Laryngoscopic Images.
PubMed 文献 · Otolaryngol Head Neck Surg · 2023-06-23

该横断面诊断研究从147例患者的数字频闪喉镜视频中提取8172张图像,由人工标注病灶边界框,采用四种检测模型同时定位并分类喉部结构性病变为良性或可疑恶性。单张图像分类准确率为88.5,同一视频序列所有图像综合考虑时准确率升至92.0;四种检测模型在IoU阈值0.5下的平均精度均值(mAP)为50.1。作者认为基于深度神经网络的检测模型有潜力对喉部结构性病变进行分类和定位。

要点

  • 147例患者共8172张喉镜图像纳入数据集,病灶由人工标注边界框。
  • 单张图像分类准确率88.5,同一视频序列整体分类准确率升至92.0。
  • 四种检测模型在IoU阈值0.5下平均精度均值(mAP)为50.1。

核心结论

  • 使用标注数字喉镜图像数据集训练的深度神经网络检测模型有潜力将喉部结构性病变分类为良性或可疑恶性,并在图像中定位病变。
  • 该方法可揭示模型用于诊断的图像区域,使临床医生能够独立评估模型预测。

研究设计与样本

  • 横断面诊断研究,设置于三级医疗嗓音门诊。
  • 从因喉部结构性病变接受评估的患者中采集数字频闪喉镜视频、人口学和临床数据。
  • 从视频中提取喉镜图像并人工标注涵盖病灶的边界框。
  • 采用四种检测模型同时定位并分类喉镜图像中的喉部结构性病变。
  • 以分类准确率、交并比(IoU)和平均精度均值(mAP)分别评估分类、定位和整体性能。

主要发现

  • 喉镜图像数据集共纳入147例患者的8172张图像。
  • 单张喉镜图像分类准确率为88.5,同一视频序列所有图像综合考虑时分类准确率升至92.0。
  • 四种检测模型在IoU阈值0.5判定定位成功时的平均精度均值为50.1。

临床怎么用

  • 原文未据此给出临床推荐。

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

OBJECTIVE: To localize structural laryngeal lesions within digital flexible laryngoscopic images and to classify them as benign or suspicious for malignancy using state-of-the-art computer vision detection models. STUDY DESIGN: Cross-sectional diagnostic study SETTING: Tertiary care voice clinic METHODS: Digital stroboscopic videos, demographic and clinical data were collected from patients evaluated for a structural laryngeal lesion. Laryngoscopic images were extracted from videos and manually labeled with bounding boxes encompassing the lesion. Four detection models were employed to simultaneously localize and classify structural laryngeal lesions in laryngoscopic images. Classification accuracy, intersection over union (IoU) and mean average precision (mAP) were evaluated as measures of classification, localization, and overall performance, respectively. RESULTS: In total, 8,172 images from 147 patients were included in the laryngeal image dataset. Classification accuracy was 88.5 for individual laryngeal images and increased to 92.0 when all images belonging to the same sequence (video) were considered. Mean average precision across all four detection models was 50.1 using an IoU threshold of 0.5 to determine successful localization. CONCLUSION: Results of this study showed that deep neural network-based detection models trained using a labeled dataset of digital laryngeal images have the potential to classify structural laryngeal lesions as benign or suspicious for malignancy and to localize them within an image. This approach provides valuable insight into which part of the image was used by the model to determine a diagnosis, allowing clinicians to independently evaluate models' predictions.

来源:Otolaryngol Head Neck Surg,查看原文。版权归原作者所有。

引用

  1. Bur AM, Zhang T, Chen X, et al. Interpretable Computer Vision to Detect and Classify Structural Laryngeal Lesions in Digital Flexible Laryngoscopic Images. Otolaryngol Head Neck Surg. 2023. PMID: 37350279. doi:10.1002/ohn.411

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。