University of Shanghai for Science and Technology, Jungong 516 Rd, Shanghai, 200093, China.
Department of Radiology, Shanghai Chest Hospital, School of Medicine, Shanghai Jiao Tong University, Huaihai West Road NO.241, Shanghai, 200030, China.
BMC Pulm Med. 2024 Sep 20;24(1):465. doi: 10.1186/s12890-024-03272-7.
Currently, deep learning methods for the classification of benign and malignant lung nodules encounter challenges encompassing intricate and unstable algorithmic models, limited data adaptability, and an abundance of model parameters.To tackle these concerns, this investigation introduces a novel approach: the 3D Global Coordinated Attention Wide Inverted ResNet Network (GC-WIR). This network aims to achieve precise classification of benign and malignant pulmonary nodules, leveraging its merits of heightened efficiency, parsimonious parameterization, and robust stability.
Within this framework, a 3D Global Coordinate Attention Mechanism (3D GCA) is designed to compute the features of the input images by converting 3D channel information and multi-dimensional positional cues. By encompassing both global channel details and spatial positional cues, this approach maintains a judicious balance between flexibility and computational efficiency. Furthermore, the GC-WIR architecture incorporates a 3D Wide Inverted Residual Network (3D WIRN), which augments feature computation by expanding input channels. This augmentation mitigates information loss during feature extraction, expedites model convergence, and concurrently enhances performance. The utilization of the inverted residual structure imbues the model with heightened stability.
Empirical validation of the GC-WIR method is performed on the LUNA 16 dataset, yielding predictions that surpass those generated by previous models. This novel approach achieves an impressive accuracy rate of 94.32%, coupled with a specificity of 93.69%. Notably, the model's parameter count remains modest at 5.76M, affording optimal classification accuracy.
Furthermore, experimental results unequivocally demonstrate that, even under stringent computational constraints, GC-WIR outperforms alternative deep learning methodologies, establishing a new benchmark in performance.
目前，用于良性和恶性肺结节分类的深度学习方法面临着复杂且不稳定的算法模型、有限的数据适应性以及大量模型参数等挑战。为了解决这些问题，本研究引入了一种新的方法：3D 全局协调注意力宽反卷积残差网络（GC-WIR）。该网络旨在通过提高效率、简化参数化和增强稳定性来实现良性和恶性肺结节的精确分类。
在这个框架内，设计了一个 3D 全局坐标注意力机制（3D GCA），通过转换 3D 通道信息和多维位置线索来计算输入图像的特征。通过包含全局通道细节和空间位置线索，这种方法在灵活性和计算效率之间保持了恰当的平衡。此外，GC-WIR 架构采用了 3D 宽反卷积残差网络（3D WIRN），通过扩展输入通道来增强特征计算。这种扩充减轻了特征提取过程中的信息损失，加快了模型收敛速度，同时提高了性能。使用反卷积残差结构使模型具有更高的稳定性。
在 LUNA 16 数据集上对 GC-WIR 方法进行了实证验证，生成的预测结果优于以前的模型。这种新方法的准确率达到了 94.32%，特异性为 93.69%。值得注意的是，该模型的参数计数仍然保持在 576 万，实现了最佳的分类准确性。
此外，实验结果明确表明，即使在严格的计算约束下，GC-WIR 也优于其他深度学习方法，在性能方面树立了新的基准。
Zotero 插件
