The Department of School of Microelectronics, Shanghai University, Shanghai, 201800, People's Republic of China.
The School of Software Engineering, Sun Yat-sen University, Zhuhai, Guangdong Province, 519000, People's Republic of China.
Phys Med Biol. 2023 Aug 18;68(17). doi: 10.1088/1361-6560/aced79.
. This study aims to address the significant challenges posed by pneumothorax segmentation in computed tomography images due to the resemblance between pneumothorax regions and gas-containing structures such as the trachea and bronchus.. We introduce a novel dynamic adaptive windowing transformer (DAWTran) network incorporating implicit feature alignment for precise pneumothorax segmentation. The DAWTran network consists of an encoder module, which employs a DAWTran, and a decoder module. We have proposed a unique dynamic adaptive windowing strategy that enables multi-head self-attention to effectively capture multi-scale information. The decoder module incorporates an implicit feature alignment function to minimize information deviation. Moreover, we utilize a hybrid loss function to address the imbalance between positive and negative samples.. Our experimental results demonstrate that the DAWTran network significantly improves the segmentation performance. Specifically, it achieves a higher dice similarity coefficient (DSC) of 91.35% (a larger DSC value implies better performance), showing an increase of 2.21% compared to the TransUNet method. Meanwhile, it significantly reduces the Hausdorff distance (HD) to 8.06 mm (a smaller HD value implies better performance), reflecting a reduction of 29.92% in comparison to the TransUNet method. Incorporating the dynamic adaptive windowing (DAW) mechanism has proven to enhance DAWTran's performance, leading to a 4.53% increase in DSC and a 15.85% reduction in HD as compared to SwinUnet. The application of the implicit feature alignment (IFA) further improves the segmentation accuracy, increasing the DSC by an additional 0.11% and reducing the HD by another 10.01% compared to the model only employing DAW.. These results highlight the potential of the DAWTran network for accurate pneumothorax segmentation in clinical applications, suggesting that it could be an invaluable tool in improving the precision and effectiveness of diagnosis and treatment in related healthcare scenarios. The improved segmentation performance with the inclusion of DAW and IFA validates the effectiveness of our proposed model and its components.
. 本研究旨在解决 CT 图像中气胸分割所面临的重大挑战，因为气胸区域与含气结构（如气管和支气管）之间存在相似性。我们引入了一种新颖的动态自适应窗口变换（DAWTran）网络，该网络结合了隐式特征对齐，以实现精确的气胸分割。DAWTran 网络由一个编码器模块组成，该模块采用 DAWTran，以及一个解码器模块。我们提出了一种独特的动态自适应窗口策略，使多头自注意力能够有效地捕获多尺度信息。解码器模块包含一个隐式特征对齐函数，以最小化信息偏差。此外，我们利用混合损失函数来解决正负样本之间的不平衡问题。我们的实验结果表明，DAWTran 网络显著提高了分割性能。具体来说，它的 Dice 相似系数（DSC）达到了 91.35%（DSC 值越大表示性能越好），与 TransUNet 方法相比提高了 2.21%。同时，它的 Hausdorff 距离（HD）显著降低到 8.06 毫米（HD 值越小表示性能越好），与 TransUNet 方法相比降低了 29.92%。在 DAWTran 中加入动态自适应窗口（DAW）机制，证明了其性能的提高，与 SwinUnet 相比，DSC 提高了 4.53%，HD 降低了 15.85%。应用隐式特征对齐（IFA）进一步提高了分割精度，与仅使用 DAW 的模型相比，DSC 提高了 0.11%，HD 降低了 10.01%。这些结果表明，DAWTran 网络在临床应用中具有准确分割气胸的潜力，这表明它可能是提高相关医疗保健场景下诊断和治疗精度和效果的宝贵工具。通过包含 DAW 和 IFA，分割性能得到了提高，验证了我们提出的模型及其组件的有效性。
