School of Engineering and Technology, Christ (Deemed to be University), Bangalore 560074, India.
Bharati Vidyapeeth's College of Engineering, New Delhi 110063, India.
Comput Biol Med. 2022 Nov;150:106092. doi: 10.1016/j.compbiomed.2022.106092. Epub 2022 Sep 28.
Covid-19 disease has had a disastrous effect on the health of the global population, for the last two years. Automatic early detection of Covid-19 disease from Chest X-Ray (CXR) images is a very crucial step for human survival against Covid-19. In this paper, we propose a novel data-augmentation technique, called SVD-CLAHE Boosting and a novel loss function Balanced Weighted Categorical Cross Entropy (BWCCE), in order to detect Covid 19 disease efficiently from a highly class-imbalanced Chest X-Ray image dataset. Our proposed SVD-CLAHE Boosting method is comprised of both oversampling and under-sampling methods. First, a novel Singular Value Decomposition (SVD) based contrast enhancement and Contrast Limited Adaptive Histogram Equalization (CLAHE) methods are employed for oversampling the data in minor classes. Simultaneously, a Random Under Sampling (RUS) method is incorporated in major classes, so that the number of images per class will be more balanced. Thereafter, Balanced Weighted Categorical Cross Entropy (BWCCE) loss function is proposed in order to further reduce small class imbalance after SVD-CLAHE Boosting. Experimental results reveal that ResNet-50 model on the augmented dataset (by SVD-CLAHE Boosting), along with BWCCE loss function, achieved 95% F1 score, 94% accuracy, 95% recall, 96% precision and 96% AUC, which is far better than the results by other conventional Convolutional Neural Network (CNN) models like InceptionV3, DenseNet-121, Xception etc. as well as other existing models like Covid-Lite and Covid-Net. Hence, our proposed framework outperforms other existing methods for Covid-19 detection. Furthermore, the same experiment is conducted on VGG-19 model in order to check the validity of our proposed framework. Both ResNet-50 and VGG-19 model are pre-trained on the ImageNet dataset. We publicly shared our proposed augmented dataset on Kaggle website (https://www.kaggle.com/tr1gg3rtrash/balanced-augmented-covid-cxr-dataset), so that any research community can widely utilize this dataset. Our code is available on GitHub website online (https://github.com/MrinalTyagi/SVD-CLAHE-and-BWCCE).
新冠疾病在过去两年对全球人口的健康造成了灾难性的影响。从胸部 X 光（CXR）图像中自动早期检测新冠疾病是人类对抗新冠病毒的至关重要的一步。在本文中，我们提出了一种新颖的数据增强技术，称为 SVD-CLAHE 增强和一种新颖的损失函数平衡加权分类交叉熵（BWCCE），以便从高度类别不平衡的胸部 X 射线图像数据集高效检测新冠疾病。我们提出的 SVD-CLAHE 增强方法由过采样和欠采样方法组成。首先，使用一种新颖的基于奇异值分解（SVD）的对比度增强和对比度受限自适应直方图均衡化（CLAHE）方法对少数类别的数据进行过采样。同时，在多数类中采用随机欠采样（RUS）方法，以使每个类别的图像数量更加平衡。此后，提出了平衡加权分类交叉熵（BWCCE）损失函数，以便在 SVD-CLAHE 增强之后进一步减少小类别的不平衡。实验结果表明，在增强数据集上的 ResNet-50 模型（通过 SVD-CLAHE 增强），结合 BWCCE 损失函数，达到了 95%的 F1 得分、94%的准确率、95%的召回率、96%的精度和 96%的 AUC，这远优于其他传统卷积神经网络（CNN）模型（如 InceptionV3、DenseNet-121、Xception 等）以及其他现有模型（如 Covid-Lite 和 Covid-Net）的结果。因此，我们提出的框架在新冠检测方面优于其他现有方法。此外，我们还在 VGG-19 模型上进行了相同的实验，以检查我们提出的框架的有效性。ResNet-50 和 VGG-19 模型均在 ImageNet 数据集上进行预训练。我们在 Kaggle 网站（https://www.kaggle.com/tr1gg3rtrash/balanced-augmented-covid-cxr-dataset）上公开共享了我们提出的增强数据集，以便任何研究社区都可以广泛利用该数据集。我们的代码可在 GitHub 网站上在线获取（https://github.com/MrinalTyagi/SVD-CLAHE-and-BWCCE）。
Clin Respir J. 2023-5
Int J Comput Assist Radiol Surg. 2021-2
Biogerontology. 2022-2
BMC Med Imaging. 2023-6-15
BMC Bioinformatics. 2024-1-17
BMC Med Imaging. 2025-3-4
Zotero 插件
