文献速递技术与安全甲状腺与浅表US

人工智能深度学习超声鉴别美容填充剂:一项多中心研究

Artificial Intelligence Deep Learning Ultrasound Discrimination of Cosmetic Fillers: A Multicenter Study.
PubMed 文献 · J Ultrasound Med · 2025-09-29

国际皮肤与美容超声协作组联合格拉纳达大学计算机科学与人工智能系,收集1432幅匿名超声图像,采用基于YOLO架构的深度学习模型鉴别透明质酸、聚甲基丙烯酸甲酯、羟基磷灰石钙和硅油填充剂。模型交叉验证平均准确率为0.92±0.04,YOLOv11对透明质酸和硅油检测的F1分数分别为0.96±0.02和0.94±0.04,对羟基磷灰石钙和聚甲基丙烯酸甲酯的F1分数约为0.83,作者认为需进一步开展人工智能深度学习专项工作以更准确识别羟基磷灰石钙和聚甲基丙烯酸甲酯。

要点

  • 深度学习模型在交叉验证中鉴别四类填充剂的平均准确率为0.92±0.04。
  • YOLOv11检测透明质酸和硅油的F1分数分别为0.96±0.02和0.94±0.04。
  • 羟基磷灰石钙和聚甲基丙烯酸甲酯的精确率与召回率较低且不稳定,F1分数约0.83。

核心结论

  • 基于YOLOv11的人工智能可在不同复杂度高频超声设备和操作者条件下可靠区分透明质酸与硅油,但鉴别羟基磷灰石钙和聚甲基丙烯酸甲酯的准确性仍需进一步人工智能深度学习专项研究。

研究设计与样本

  • 国际多中心协作研究,14名来自6个国家的医生参与,最终数据集包含1432幅超声图像,涵盖透明质酸、聚甲基丙烯酸甲酯、羟基磷灰石钙和硅油填充剂病例,采用基于YOLO架构的深度学习技术结合边界框标注工具由专家手动勾画感兴趣区。

诊断标准与关键数值

  • 模型交叉验证各折平均准确率为0.92±0.04。
  • YOLOv11检测透明质酸的F1分数为0.96±0.02。
  • YOLOv11检测硅油的F1分数为0.94±0.04。
  • 羟基磷灰石钙和聚甲基丙烯酸甲酯的精确率与召回率较低且不稳定,F1分数约为0.83。

临床应用与阅片要点

  • 作者认为人工智能深度学习专项工作需进一步开展,以更准确识别羟基磷灰石钙和聚甲基丙烯酸甲酯。

局限性

  • 原文指出需进一步开展人工智能深度学习专项工作以更准确识别羟基磷灰石钙和聚甲基丙烯酸甲酯。

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)。

英文原文(摘要)· 点击展开

OBJECTIVES: Despite the growing use of artificial intelligence (AI) in medicine, imaging, and dermatology, to date, there is no information on the use of AI for discriminating cosmetic fillers on ultrasound (US).

METHODS: An international collaborative group working in dermatologic and esthetic US was formed and worked with the staff of the Department of Computer Science and AI of the Universidad de Granada to gather and process a relevant number of anonymized images. AI techniques based on deep learning (DL) with YOLO (you only look once) architecture, together with a bounding box annotation tool, allowed experts to manually delineate regions of interest for the discrimination of common cosmetic fillers under real-world conditions.

RESULTS: A total of 14 physicians from 6 countries participated in the AI study and compiled a final dataset comprising 1432 US images, including HA (hyaluronic acid), PMMA (polymethylmethacrylate), CaHA (calcium hydroxyapatite), and SO (silicone oil) filler cases. The model exhibits robust and consistent classification performance, with an average accuracy of 0.92 ± 0.04 across the cross-validation folds. YOLOv11 demonstrated outstanding performance in the detection of HA and SO, yielding F1 scores of 0.96 ± 0.02 and 0.94 ± 0.04, respectively. On the other hand, CaHA and PMMA show somewhat lower and less consistent performance in terms of precision and recall, with F1-scores around 0.83.

CONCLUSIONS: AI using YOLOv11 allowed us to discriminate reliably between HA and SO using different complexity high-frequency US devices and operators. Further AI DL-specific work is needed to identify CaHA and PMMA more accurately.

来源:J Ultrasound Med,查看原文。版权归原作者所有。

引用

  1. Wortsman X, Lozano M, Rodriguez FJ, et al. Artificial Intelligence Deep Learning Ultrasound Discrimination of Cosmetic Fillers: A Multicenter Study. J Ultrasound Med. 2025. PMID: 41024593. doi:10.1002/jum.70079

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。