基于深度学习的面部对称度自动评分
Andreas Heinrich1, Gerd Fabian Volk2,3,4, Christian Dobel2,3,4
1Department of Radiology, Jena University Hospital - Friedrich Schiller University, Am Klinikum 1, 07747, Jena, Germany. andreas.heinrich@med.uni-jena.de.
Scientific reports
|August 27, 2025
概括
这项研究引入了一种使用二维照片的自动化方法,以客观地评估外围面患者的面部对称性. 该工具提供可靠的对称性得分,以改善临床评估和康复监测.
科学领域:
- 医学成像
- 计算机视觉
- 康复科学
背景情况:
- 单侧外围面 (PFP) 导致面部不对称和功能缺陷,影响患者的生活质量.
- 客观评估工具对于有效的PFP监测和康复策略至关重要.
- 目前的评估方法在量化面部运动对称性方面可能缺乏客观性和精确性.
研究的目的:
- 开发和验证PFP患者客观面部对称性评估的自动化方法.
- 使用热图和从标准化的2D照片中获得的对称性得分来量化面部运动对称性.
- 将自动对称得分与临床Stennert运动得分相关联.
主要方法:
- 使用了198名PFP患者405张面部图像的数据集.
- 采用深度学习来检测面部地标和相似对齐算法.
- 从灰度差异图像生成热图,并通过比较面部半径计算对称性得分.
主要成果:
- 自动化方法成功处理了所有数据集,产生了从0到0.99的对称性得分 (平均值为0.85±0.12).
- 热图显示了与临床观察一致的不对称性.
- 显著的负相关性 (r = - 0. 32 至 - 0. 66) 表明较高的临床严重性与较低的对称性得分相关.
结论:
- 开发的自动化方法提供了一个客观,可靠和可访问的工具来评估PFP的面部对称性.
- 这种方法提高了临床评估的准确性,并允许精确监测康复进展.
- 与传统评分相比,该方法在检测微妙变化方面具有更高的灵敏度.
相关概念视频
01:14Muscles for Facial Expressions
2.7K
The craniofacial muscles are a collection of approximately 20 thin skeletal muscles situated beneath the skin of the face and scalp. These muscles, primarily responsible for the vast array of human facial expressions, originate from the bones or fibrous structures of the skull and extend outwards to connect with the skin. While most skeletal muscles in the body are enveloped in thick fascia, facial muscles generally have a more delicate fascial covering, with the buccinator muscle being a...
2.7K
01:24Facial Feedback Hypothesis
244
Charles Darwin proposed that facial expressions are an evolutionary adaptation for communication. He argued that these expressions are not influenced by culture but are universal across species. For example, a snarling expression with exposed teeth signals a threat in many animals, including humans. Darwin also suggested that displaying an emotion can intensify the feeling. Smiling, for example, could enhance one's sense of happiness. This idea laid the foundation for understanding the role...
244