Tabatabaei Zahra, Wang Yuandou, Colomer Adrián, Oliver Moll Javier, Zhao Zhiming, Naranjo Valery
Department of Artificial Intelligence, Tyris Tech S.L., 46021 Valencia, Spain.
Instituto Universitario de Investigación en Tecnología Centrada en el Ser Humano, HUMAN-Tech, Universitat Politècnica de València, 46021 Valencia, Spain.
Bioengineering (Basel). 2023 Sep 28;10(10):1144. doi: 10.3390/bioengineering10101144.
The paper proposes a federated content-based medical image retrieval (FedCBMIR) tool that utilizes federated learning (FL) to address the challenges of acquiring a diverse medical data set for training CBMIR models. CBMIR is a tool to find the most similar cases in the data set to assist pathologists. Training such a tool necessitates a pool of whole-slide images (WSIs) to train the feature extractor (FE) to extract an optimal embedding vector. The strict regulations surrounding data sharing in hospitals makes it difficult to collect a rich data set. FedCBMIR distributes an unsupervised FE to collaborative centers for training without sharing the data set, resulting in shorter training times and higher performance. FedCBMIR was evaluated by mimicking two experiments, including two clients with two different breast cancer data sets, namely BreaKHis and Camelyon17 (CAM17), and four clients with the BreaKHis data set at four different magnifications. FedCBMIR increases the F1 score (F1S) of each client from 96% to 98.1% in CAM17 and from 95% to 98.4% in BreaKHis, with 11.44 fewer hours in training time. FedCBMIR provides 98%, 96%, 94%, and 97% F1S in the BreaKHis experiment with a generalized model and accomplishes this in 25.53 fewer hours of training.
本文提出了一种基于联合内容的医学图像检索（FedCBMIR）工具，该工具利用联合学习（FL）来应对获取用于训练CBMIR模型的多样化医学数据集所面临的挑战。CBMIR是一种在数据集中查找最相似病例以协助病理学家的工具。训练这样一个工具需要一组全切片图像（WSIs）来训练特征提取器（FE）以提取最优嵌入向量。医院围绕数据共享的严格规定使得收集丰富的数据集变得困难。FedCBMIR将一个无监督的FE分发给协作中心进行训练，而不共享数据集，从而缩短了训练时间并提高了性能。通过模拟两个实验对FedCBMIR进行了评估，其中一个实验有两个客户端，分别使用两个不同的乳腺癌数据集，即BreaKHis和Camelyon17（CAM17），另一个实验有四个客户端，使用四个不同放大倍数的BreaKHis数据集。在CAM17中，FedCBMIR将每个客户端的F1分数（F1S）从96%提高到98.1%，在BreaKHis中从95%提高到98.4%，训练时间减少了11.44小时。在BreaKHis实验中，FedCBMIR使用一个通用模型提供了98%、96%、94%和97%的F1S，并且在少25.53小时的训练中完成了这一目标。
