This study explores the use of Federated Learning (FL) for stenosis detection
in coronary angiography images (CA). Two heterogeneous datasets from two
institutions were considered: Dataset 1 includes 1219 images from 200 patients,
which we acquired at the Ospedale Riuniti of Ancona (Italy); Dataset 2 includes
7492 sequential images from 90 patients from a previous study available in the
literature. Stenosis detection was performed by using a Faster R-CNN model. In
our FL framework, only the weights of the model backbone were shared among the
two client institutions, using Federated Averaging (FedAvg) for weight
aggregation. We assessed the performance of stenosis detection using Precision
(P rec), Recall (Rec), and F1 score (F1). Our results showed that the FL
framework does not substantially affects clients 2 performance, which already
achieved good performance with local training; for client 1, instead, FL
framework increases the performance with respect to local model of +3.76%,
+17.21% and +10.80%, respectively, reaching P rec = 73.56, Rec = 67.01 and F1 =
70.13. With such results, we showed that FL may enable multicentric studies
relevant to automatic stenosis detection in CA by addressing data heterogeneity
from various institutions, while preserving patient privacy.

本研究探讨了联邦学习在冠状动脉造影图像（CA）中用于狭窄检测的应用。研究使用两个异构数据集，分别来自意大利 Ancona 市的 Ospedale Riuniti 医院和前期研究的文献中的成像数据。使用 Faster R-CNN 模型进行狭窄检测，并通过联邦平均（FedAvg）对模型背骨权重进行共享。结果显示，联邦学习框架对第二客户端的性能影响不大，而对第一客户端，与本地模型相比，性能提升了分别为 + 3.76％，+17.21％和 + 10.80％，P_rec 为 73.56，Rec 为 67.01，F1 为 70.13。这些结果表明，联邦学习可实现不同机构之间相关的自动狭窄检测的多中心研究，同时保护患者隐私。