通过对视觉转换器进行对齐,解决医学联合学习中的异质性问题
Erfan Darzi1, Yiqing Shen2, Yangming Ou1
1Boston Children's Hospital, Boston, MA, United States; Harvard Medical School, Boston, MA, United States.
Artificial intelligence in medicine
|July 30, 2024
概括
医疗成像的联合学习面临着各种数据的挑战. 我们的方法使用Vision Transformers中的多头注意力来调整数据,改善模型性能和公平性,特别是对于代表性不足的群体.
科学领域:
- 人工智能的人工智能
- 医疗成像医学成像
- 机器学习 机器学习
背景情况:
- 联合学习 (FL) 在分散的,敏感的医疗数据上训练模型.
- 各机构的数据异质性降低了FL模型的性能和公平性.
- 在FL中代表性不足的数据集特别容易受到性能差异的影响.
研究的目的:
- 通过解决数据异质性,增强医学成像的联合学习.
- 在分散的医疗数据培训中提高模型准确性和公平性.
- 为了利用视觉转换器的多头注意力来实现数据表示对齐.
主要方法:
- 提出了一个联合学习方法,利用视觉转换器中的多头注意力机制.
- 专注于注意力机制作为客户之间调整异质数据表示的核心目标.
- 在IQ-OTH/NCCD肺癌数据集上评估了该方法,模拟了隐性迪里克莱特分配 (LDA) 的异质性.
主要成果:
- 拟议的方法实现了与各种数据异质性水平的先进联合学习技术相比具有竞争力的性能.
- 对代表性不足的客户来说,在模型性能方面取得了显著的改进,从而提高了公平性.
- 成功对齐异质医学成像数据的表示.
结论:
- 在视觉转换器中利用多头注意力是一个有希望的策略,以减轻医学联合学习中的数据异质性挑战.
- 该方法有效地平衡了分散的医疗成像分析中的准确性和公平性.
- 这项工作通过促进公平的模型性能,推进了联合学习在敏感医疗领域的应用.
相关概念视频
Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...


