Indian Institute of Technology Jodhpur, Jodhpur, Rajasthan, India.
Med Phys. 2023 Dec;50(12):7568-7578. doi: 10.1002/mp.16722. Epub 2023 Sep 4.
In recent years, deep learning methods have been successfully used for chest x-ray diagnosis. However, such deep learning models often contain millions of trainable parameters and have high computation demands. As a result, providing the benefits of cutting-edge deep learning technology to areas with low computational resources would not be easy. Computationally lightweight deep learning models may potentially alleviate this problem.
We aim to create a computationally lightweight model for the diagnosis of chest radiographs. Our model has only 0.14M parameters and 550 KB size. These make the proposed model potentially useful for deployment in resource-constrained environments.
We fuse the concept of depthwise convolutions with squeeze and expand blocks to design the proposed architecture. The basic building block of our model is called Depthwise Convolution In Squeeze and Expand (DCISE) block. Using these DCISE blocks, we design an extremely lightweight convolutional neural network model (ExLNet), a computationally lightweight convolutional neural network (CNN) model for chest x-ray diagnosis.
We perform rigorous experiments on three publicly available datasets, namely, National Institutes of Health (NIH), VinBig ,and Chexpert for binary and multi-class classification tasks. We train the proposed architecture on NIH dataset and evaluate the performance on VinBig and Chexpert datasets. The proposed method outperforms several state-of-the-art approaches for both binary and multi-class classification tasks despite having a significantly less number of parameters.
We design a lightweight CNN architecture for the chest x-ray classification task by introducing ExLNet which uses a novel DCISE blocks to reduce the computational burden. We show the effectiveness of the proposed architecture through various experiments performed on publicly available datasets. The proposed architecture shows consistent performance in binary as well as multi-class classification tasks and outperforms other lightweight CNN architectures. Due to a significant reduction in the computational requirements, our method can be useful for resource-constrained clinical environment as well.
近年来，深度学习方法已成功应用于胸部 X 光诊断。然而，这些深度学习模型通常包含数百万个可训练参数，并且计算需求很高。因此，为计算资源有限的地区提供前沿的深度学习技术的好处并不容易。计算轻量级的深度学习模型可能会缓解这个问题。
我们旨在为胸部 X 光诊断创建一个计算轻量级的模型。我们的模型仅有 0.14M 参数和 550KB 大小。这些使得所提出的模型有可能在资源受限的环境中部署。
我们融合了深度卷积的概念和挤压和扩展块来设计所提出的架构。我们模型的基本构建块称为深度卷积挤压和扩展（DCISE）块。使用这些 DCISE 块，我们设计了一个极其轻量级的卷积神经网络模型（ExLNet），一个用于胸部 X 光诊断的计算轻量级卷积神经网络（CNN）模型。
我们在三个公开可用的数据集上进行了严格的实验，即美国国立卫生研究院（NIH）、VinBig 和 Chexpert，用于二进制和多类分类任务。我们在 NIH 数据集上训练所提出的架构，并在 VinBig 和 Chexpert 数据集上评估性能。尽管参数数量明显较少，但所提出的方法在二进制和多类分类任务中均优于几种最先进的方法。
我们通过引入 ExLNet 设计了一种用于胸部 X 光分类任务的轻量级 CNN 架构，该架构使用新颖的 DCISE 块来减轻计算负担。我们通过在公开数据集上进行的各种实验证明了所提出架构的有效性。所提出的架构在二进制和多类分类任务中均表现出一致的性能，并且优于其他轻量级 CNN 架构。由于计算需求的显著减少，我们的方法也可以用于资源受限的临床环境。
