[論文レビュー] Experiments of Federated Learning for COVID-19 Chest X-ray Images

Boyi Liu, Bingjie Yan+3 more|arXiv (Cornell University)|Jul 5, 2020

COVID-19 diagnosis using AI参考文献 4被引用数 52

ひとこと要約

この論文はCOVID-19胸部X線分類のための連邦学習（FL）を4つのモデル（COVID-Net、ResNet18、ResNeXt、MobileNet-v2）を用いて評価し、COVIDxデータセットでFLと中央集権的トレーニングを比較します。

ABSTRACT

AI plays an important role in COVID-19 identification. Computer vision and deep learning techniques can assist in determining COVID-19 infection with Chest X-ray Images. However, for the protection and respect of the privacy of patients, the hospital's specific medical-related data did not allow leakage and sharing without permission. Collecting such training data was a major challenge. To a certain extent, this has caused a lack of sufficient data samples when performing deep learning approaches to detect COVID-19. Federated Learning is an available way to address this issue. It can effectively address the issue of data silos and get a shared model without obtaining local data. In the work, we propose the use of federated learning for COVID-19 data training and deploy experiments to verify the effectiveness. And we also compare performances of four popular models (MobileNet, ResNet18, MoblieNet, and COVID-Net) with the federated learning framework and without the framework. This work aims to inspire more researches on federated learning about COVID-19.

研究の動機と目的

• COVID-19 CXR分類における病院間のプライバシー保護付き協調学習を動機づける。
• COVID-19 CXRデータに対する4つのネットワークのFL性能を調査する。
• FLと非FLの収束と精度のトレードオフを評価する。

提案手法

• 5 agents and 0.4 participation per roundとして連邦学習設定を定義する。
• FLの下で四つのモデル（COVID-Net、ResNet18、ResNeXt、MobileNet-v2）をPyTorchで訓練する。
• 学習率2e-5とウェイト減衰1e-7を用いたAdamオプティマイザを使用する。
• Dataset: COVIDx (15,282 images) with Normal, non-COVID pneumonia, and COVID-19 labels.
• Compare FL-trained models against centralized training baselines.
• Evaluate performance (accuracy per set and per label) and provide Grad-CAM++ visual explanations.

実験結果

リサーチクエスチョン

• RQ1 Can federated learning achieve comparable accuracy to centralized training on COVID-19 CXR classification?
• RQ2 Which model yields the best accuracy under FL for COVID-19 CXR images?
• RQ3 How does FL affect convergence speed and label-wise performance for COVID-19 detection?

主な発見

• ResNet18 achieves the highest accuracy on both training (96.15%) and testing (91.26%) under FL.
• COVID-Net under FL achieves 89.17% testing accuracy and 92.40% training accuracy.
• ResNeXt under FL achieves 90.37% testing accuracy and 94.66% training accuracy.
• MobileNet-v2 under FL achieves 86.83% testing accuracy and 91.16% training accuracy.
• Under centralized training, the four models show varying performance, with ResNet18 still performing strongest overall among FL and non-FL settings.
• MobileNet-v2 has the fewest parameters among the four models.