Asano Hidetsugu, Hirakawa Eiji, Hayashi Hayato, Hamada Keisuke, Asayama Yuto, Oohashi Masaaki, Uchiyama Akira, Higashino Teruo
Technical Department, Atom Medical Corporation, 2-2-1, Dojo, Sakura-ku, Saitama city, Saitama, 338-0835, Japan.
Department of Neonatology, Nagasaki Harbor Medical Center, 6-39, Shinchi-machi, Nagasaki City, Nagasaki, 850-8555, Japan.
BMC Med Imaging. 2022 Jan 3;22(1):1. doi: 10.1186/s12880-021-00730-0.
Regulation of temperature is clinically important in the care of neonates because it has a significant impact on prognosis. Although probes that make contact with the skin are widely used to monitor temperature and provide spot central and peripheral temperature information, they do not provide details of the temperature distribution around the body. Although it is possible to obtain detailed temperature distributions using multiple probes, this is not clinically practical. Thermographic techniques have been reported for measurement of temperature distribution in infants. However, as these methods require manual selection of the regions of interest (ROIs), they are not suitable for introduction into clinical settings in hospitals. Here, we describe a method for segmentation of thermal images that enables continuous quantitative contactless monitoring of the temperature distribution over the whole body of neonates.
The semantic segmentation method, U-Net, was applied to thermal images of infants. The optimal combination of Weight Normalization, Group Normalization, and Flexible Rectified Linear Unit (FReLU) was evaluated. U-Net Generative Adversarial Network (U-Net GAN) was applied to thermal images, and a Self-Attention (SA) module was finally applied to U-Net GAN (U-Net GAN + SA) to improve precision. The semantic segmentation performance of these methods was evaluated.
The optimal semantic segmentation performance was obtained with application of FReLU and Group Normalization to U-Net, showing accuracy of 92.9% and Mean Intersection over Union (mIoU) of 64.5%. U-Net GAN improved the performance, yielding accuracy of 93.3% and mIoU of 66.9%, and U-Net GAN + SA showed further improvement with accuracy of 93.5% and mIoU of 70.4%.
FReLU and Group Normalization are appropriate semantic segmentation methods for application to neonatal thermal images. U-Net GAN and U-Net GAN + SA significantly improved the mIoU of segmentation.
体温调节在新生儿护理中具有重要的临床意义，因为它对预后有重大影响。尽管与皮肤接触的探头被广泛用于监测体温并提供局部中心和外周温度信息，但它们无法提供身体周围温度分布的详细情况。虽然使用多个探头可以获得详细的温度分布，但这在临床上并不实用。已有报道使用热成像技术测量婴儿的温度分布。然而，由于这些方法需要手动选择感兴趣区域（ROI），因此不适合引入医院临床环境。在此，我们描述了一种热图像分割方法，该方法能够对新生儿全身的温度分布进行连续定量的非接触式监测。
将语义分割方法U-Net应用于婴儿的热图像。评估了权重归一化、组归一化和灵活整流线性单元（FReLU）的最佳组合。将U-Net生成对抗网络（U-Net GAN）应用于热图像，最后将自注意力（SA）模块应用于U-Net GAN（U-Net GAN + SA）以提高精度。评估了这些方法的语义分割性能。
将FReLU和组归一化应用于U-Net时获得了最佳语义分割性能，准确率为92.9%，平均交并比（mIoU）为64.5%。U-Net GAN提高了性能，准确率为93.3%，mIoU为66.9%，而U-Net GAN + SA显示出进一步的改进，准确率为93.5%，mIoU为70.4%。
FReLU和组归一化是适用于新生儿热图像的语义分割方法。U-Net GAN和U-Net GAN + SA显著提高了分割的mIoU。
