Department of Computer Science and Engineering, Manipal University Jaipur, 303007, Rajasthan, India.
Department of Computer Science and Engineering, Manipal University Jaipur, 303007, Rajasthan, India.
Comput Biol Med. 2022 Oct;149:105979. doi: 10.1016/j.compbiomed.2022.105979. Epub 2022 Aug 25.
COVID-19 detection using Artificial Intelligence and Computer-Aided Diagnosis has been the subject of several studies. Deep Neural Networks with hundreds or even millions of parameters (weights) are referred to as "black boxes" because their behavior is difficult to comprehend, even when the model's structure and weights are visible. On the same dataset, different Deep Convolutional Neural Networks perform differently. So, we do not necessarily have to rely on just one model; instead, we can evaluate our final score by combining multiple models. While including multiple models in the voter pool, it is not always true that the accuracy will improve. So, In this regard, the authors proposed a novel approach to determine the voting ensemble score of individual classifiers based on Condorcet's Jury Theorem (CJT). The authors demonstrated that the theorem holds while ensembling the N number of classifiers in Neural Networks. With the help of CJT, the authors proved that a model's presence in the voter pool would improve the likelihood that the majority vote will be accurate if it is more accurate than the other models. Besides this, the authors also proposed a Domain Extended Transfer Learning (DETL) ensemble model as a soft voting ensemble method and compared it with CJT based ensemble method. Furthermore, as deep learning models typically fail in real-world testing, a novel dataset has been used with no duplicate images. Duplicates in the dataset are quite problematic since they might affect the training process. Therefore, having a dataset devoid of duplicate images is considered to prevent data leakage problems that might impede the thorough assessment of the trained models. The authors also employed an algorithm for faster training to save computational efforts. Our proposed method and experimental results outperformed the state-of-the-art with the DETL-based ensemble model showing an accuracy of 97.26%, COVID-19, sensitivity of 98.37%, and specificity of 100%. CJT-based ensemble model showed an accuracy of 98.22%, COVID-19, sensitivity of 98.37%, and specificity of 99.79%.
使用人工智能和计算机辅助诊断进行 COVID-19 检测已经成为了许多研究的主题。具有数百甚至数百万个参数（权重）的深度神经网络被称为“黑盒”，因为即使模型的结构和权重是可见的，其行为也难以理解。在相同的数据集上，不同的深度卷积神经网络的表现不同。因此，我们不一定非得只依赖于一个模型；相反，我们可以通过组合多个模型来评估最终的分数。虽然在投票池中包含多个模型，但并不总是会提高准确性。因此，在这方面，作者提出了一种新的方法，基于 Condorcet 的陪审团定理（CJT）来确定单个分类器投票组合的得分。作者证明，在神经网络中对 N 个分类器进行集成时，定理是成立的。借助 CJT，作者证明了如果一个模型比其他模型更准确，那么它在投票者群体中的存在将提高多数投票准确性的可能性。除此之外，作者还提出了一种域扩展迁移学习（DETL）集成模型作为软投票集成方法，并与基于 CJT 的集成方法进行了比较。此外，由于深度学习模型在实际测试中通常会失败，因此使用了一个没有重复图像的新数据集。数据集中的重复项是一个相当大的问题，因为它们可能会影响训练过程。因此，拥有一个没有重复图像的数据集被认为可以防止可能阻碍对训练模型进行全面评估的数据泄露问题。作者还采用了一种更快的训练算法来节省计算工作量。我们提出的方法和实验结果优于最先进的方法，基于 DETL 的集成模型的准确率为 97.26%，COVID-19 的敏感性为 98.37%，特异性为 100%。基于 CJT 的集成模型的准确率为 98.22%，COVID-19 的敏感性为 98.37%，特异性为 99.79%。
