Engineering Technology and Automation Combat Casualty Care Research Team, United States Army Institute of Surgical Research, Ft. Sam Houston, TX, USA.
Sci Rep. 2022 May 19;12(1):8427. doi: 10.1038/s41598-022-12367-2.
Ultrasound imaging is essential for non-invasively diagnosing injuries where advanced diagnostics may not be possible. However, image interpretation remains a challenge as proper expertise may not be available. In response, artificial intelligence algorithms are being investigated to automate image analysis and diagnosis. Here, we highlight an image classification convolutional neural network for detecting shrapnel in ultrasound images. As an initial application, different shrapnel types and sizes were embedded first in a tissue mimicking phantom and then in swine thigh tissue. The algorithm architecture was optimized stepwise by minimizing validation loss and maximizing F1 score. The final algorithm design trained on tissue phantom image sets had an F1 score of 0.95 and an area under the ROC curve of 0.95. It maintained higher than a 90% accuracy for each of 8 shrapnel types. When trained only on swine image sets, the optimized algorithm format had even higher metrics: F1 and area under the ROC curve of 0.99. Overall, the algorithm developed resulted in strong classification accuracy for both the tissue phantom and animal tissue. This framework can be applied to other trauma relevant imaging applications such as internal bleeding to further simplify trauma medicine when resources and image interpretation are scarce.
超声成像是对无法进行高级诊断的损伤进行非侵入性诊断的关键。然而，图像解释仍然是一个挑战，因为可能无法获得适当的专业知识。为了应对这一挑战，人们正在研究人工智能算法来实现图像分析和诊断的自动化。在这里，我们重点介绍了一种用于在超声图像中检测弹片的图像分类卷积神经网络。作为初步应用，首先将不同类型和大小的弹片嵌入在组织模拟体模中，然后嵌入在猪大腿组织中。通过最小化验证损失和最大化 F1 分数，逐步优化算法架构。在组织体模图像集上训练的最终算法设计的 F1 得分为 0.95，ROC 曲线下的面积为 0.95。它对 8 种弹片类型的准确率都保持在 90%以上。当仅在猪的图像集上进行训练时，优化后的算法格式具有更高的指标：F1 和 ROC 曲线下的面积为 0.99。总的来说，该算法对组织体模和动物组织都具有很强的分类准确性。该框架可应用于其他与创伤相关的成像应用，例如内出血，以便在资源和图像解释稀缺的情况下进一步简化创伤医学。
