Abstract:
This study focuses on developing a model for the precise determination of ultrasound image density and classification using convolutional neural networks (CNNs) for rapid, timely, and accurate identification of hypoxic-ischemic encephalopathy (HIE). Image density is measured by comparing two regions of interest on ultrasound images of the choroid plexus and brain parenchyma using the Delta E CIE76 value. These regions are then combined and serve as input to the CNN model for classification. The classification results of images into three groups (Normal, Moderate, and Intensive) demonstrate high model efficiency, with an overall accuracy of 88.56%, precision of 90% for Normal, 85% for Moderate, and 88% for Intensive. The overall F-measure is 88.40%, indicating a successful combination of accuracy and completeness in classification. This study is significant as it enables rapid and accurate identification of hypoxic-ischemic encephalopathy in newborns, which is crucial for the timely implementation of appropriate therapeutic measures and improving long-term outcomes for these patients. The application of such advanced techniques allows medical personnel to manage treatment more efficiently, reducing the risk of complications and improving the quality of care for newborns with HIE.
摘要:
本研究的重点是开发一个模型,用于使用卷积神经网络(CNN)精确确定超声图像密度和分类,以快速,及时,和准确识别缺氧缺血性脑病(HIE)。通过使用DeltaECIE76值比较脉络丛和脑实质的超声图像上的两个感兴趣区域来测量图像密度。然后将这些区域组合并用作CNN模型的输入以进行分类。将图像的分类结果分为三组(Normal,中等,和密集)展示了高模型效率,总体准确率为88.56%,Normal的精度为90%,85%为中度,和88%为密集。总的F值是88.40%,表明分类的准确性和完整性的成功结合。这项研究具有重要意义,因为它可以快速准确地识别新生儿缺氧缺血性脑病,这对于及时实施适当的治疗措施和改善这些患者的长期结局至关重要。这种先进技术的应用使医务人员能够更有效地管理治疗,降低并发症的风险并提高HIE新生儿的护理质量。