MaLGa-DIBRIS, Università degli Studi di Genova, Genova, Italy.
Esaote S.p.A, Genova, Italy.
Med Biol Eng Comput. 2024 Jan;62(1):73-82. doi: 10.1007/s11517-023-02881-4. Epub 2023 Sep 1.
In clinical practice, ultrasound standard planes (SPs) selection is experience-dependent and it suffers from inter-observer and intra-observer variability. Automatic recognition of SPs can help improve the quality of examinations and make the evaluations more objective. In this paper, we propose a method for the automatic identification of SPs, to be installed onboard a portable ultrasound system with limited computational power. The deep Learning methodology we design is based on the concept of Knowledge Distillation, transferring knowledge from a large and well-performing teacher to a smaller student architecture. To this purpose, we evaluate a set of different potential teachers and students, as well as alternative knowledge distillation techniques, to balance a trade-off between performances and architectural complexity. We report a thorough analysis of fetal ultrasound data, focusing on a benchmark dataset, to the best of our knowledge the only one available to date.
在临床实践中，超声标准平面（SP）的选择依赖于经验，并且存在观察者间和观察者内的变异性。SP 的自动识别可以帮助提高检查质量，使评估更加客观。在本文中，我们提出了一种用于自动识别 SP 的方法，该方法将安装在具有有限计算能力的便携式超声系统上。我们设计的深度学习方法基于知识蒸馏的概念，将知识从一个性能良好的大型教师模型转移到一个较小的学生模型架构中。为此，我们评估了一组不同的潜在教师和学生，以及替代的知识蒸馏技术，以在性能和架构复杂性之间取得平衡。据我们所知，我们报告了对胎儿超声数据的全面分析，重点是基准数据集。
