Saihood Ahmed, Abdulhussien Wijdan Rashid, Alzubaid Laith, Manoufali Mohamed, Gu Yuantong
College of Computer Science and Mathematics, University of Thi-Qar, Thi Qar, Iraq.
School of Mechanical, Medical, and Process Engineering, Queensland University of Technology, Brisbane, QLD, 4000, Australia.
BMC Med Inform Decis Mak. 2024 Dec 24;24(1):403. doi: 10.1186/s12911-024-02820-9.
The detection and classification of lung nodules are crucial in medical imaging, as they significantly impact patient outcomes related to lung cancer diagnosis and treatment. However, existing models often suffer from mode collapse and poor generalizability, as they fail to capture the complete diversity of the data distribution. This study addresses these challenges by proposing a novel generative adversarial network (GAN) architecture tailored for semi-supervised lung nodule classification.
The proposed DDDG-GAN model consists of dual generators and discriminators. Each generator specializes in benign or malignant nodules, generating diverse, high-fidelity synthetic images for each class. This dual-generator setup prevents mode collapse. The dual-discriminator framework enhances the model's generalization capability, ensuring better performance on unseen data. Feature fusion techniques are incorporated to refine the model's discriminatory power between benign and malignant nodules. The model is evaluated in two scenarios: (1) training and testing on the LIDC-IDRI dataset and (2) training on LIDC-IDRI, testing on the unseen LUNA16 dataset and the unseen LUNGx dataset.
In Scenario 1, the DDDG-GAN achieved an accuracy of 92.56%, a precision of 90.12%, a recall of 95.87%, and an F1 score of 92.77%. In Scenario 2, the model demonstrated robust performance with an accuracy of 72.6%, a precision of 72.3%, a recall of 73.82%, and an F1 score of 73.39% when testing using Luna16 and an accuracy of 71.23%, a precision of 67.56%, a recall of 73.52%, and an F1 score of 70.42% when testing using LungX. The results indicate that the proposed model outperforms state-of-the-art semi-supervised learning approaches.
The DDDG-GAN model mitigates mode collapse and improves generalizability in lung nodule classification. It demonstrates superior performance on both the LIDC-IDRI and the unseen LUNA16 and LungX datasets, offering significant potential for improving diagnostic accuracy in clinical practice.
肺结节的检测和分类在医学成像中至关重要，因为它们对与肺癌诊断和治疗相关的患者预后有重大影响。然而，现有模型常常存在模式崩溃和泛化能力差的问题，因为它们未能捕捉到数据分布的完整多样性。本研究通过提出一种专门为半监督肺结节分类量身定制的新型生成对抗网络（GAN）架构来应对这些挑战。
所提出的DDDG-GAN模型由双生成器和判别器组成。每个生成器专门处理良性或恶性结节，为每个类别生成多样的、高保真的合成图像。这种双生成器设置可防止模式崩溃。双判别器框架增强了模型的泛化能力，确保在未见数据上有更好的性能。采用特征融合技术来提升模型区分良性和恶性结节的能力。该模型在两种场景下进行评估：（1）在LIDC-IDRI数据集上进行训练和测试，以及（2）在LIDC-IDRI上进行训练，在未见的LUNA16数据集和未见的LUNGx数据集上进行测试。
在场景1中，DDDG-GAN的准确率为92.56%，精确率为90.12%，召回率为95.87%，F1分数为92.77%。在场景2中，当使用Luna16进行测试时，该模型表现出稳健的性能，准确率为72.6%，精确率为72.3%，召回率为73.82%，F1分数为73.39%；当使用LungX进行测试时，准确率为71.23%精确率为67.56%，召回率为73.52%，F1分数为70.42%。结果表明，所提出的模型优于当前最先进的半监督学习方法。
DDDG-GAN模型减轻了模式崩溃并提高了肺结节分类中的泛化能力。它在LIDC-IDRI以及未见的LUNA16和LungX数据集上均表现出卓越性能，在提高临床实践中的诊断准确性方面具有巨大潜力。
