通过 CNN 和各向异性扩散高效压缩远程干预的 3D 医学图像。

AVITECH, University of Engineering and Technology, VNU, Hanoi, Vietnam.

Department of Radiology and Nuclear Medicine, Erasmus MC, Rotterdam, the Netherlands.

Med Phys. 2021 Jun;48(6):2877-2890. doi: 10.1002/mp.14814. Epub 2021 Apr 5.

PURPOSE

Efficient compression of images while preserving image quality has the potential to be a major enabler of effective remote clinical diagnosis and treatment, since poor Internet connection conditions are often the primary constraint in such services. This paper presents a framework for organ-specific image compression for teleinterventions based on a deep learning approach and anisotropic diffusion filter.

METHODS

The proposed method, deep learning and anisotropic diffusion (DLAD), uses a convolutional neural network architecture to extract a probability map for the organ of interest; this probability map guides an anisotropic diffusion filter that smooths the image except at the location of the organ of interest. Subsequently, a compression method, such as BZ2 and HEVC-visually lossless, is applied to compress the image. We demonstrate the proposed method on three-dimensional (3D) CT images acquired for radio frequency ablation (RFA) of liver lesions. We quantitatively evaluate the proposed method on 151 CT images using peak-signal-to-noise ratio ( ), structural similarity ( ), and compression ratio ( ) metrics. Finally, we compare the assessments of two radiologists on the liver lesion detection and the liver lesion center annotation using 33 sets of the original images and the compressed images.

RESULTS

The results show that the method can significantly improve of most well-known compression methods. DLAD combined with HEVC-visually lossless achieves the highest average of 6.45, which is 36% higher than that of the original HEVC and outperforms other state-of-the-art lossless medical image compression methods. The means of and are 70 dB and 0.95, respectively. In addition, the compression effects do not statistically significantly affect the assessments of the radiologists on the liver lesion detection and the lesion center annotation.

CONCLUSIONS

We thus conclude that the method has a high potential to be applied in teleintervention applications.

目的

在保持图像质量的同时实现图像的高效压缩，有可能成为有效远程临床诊断和治疗的主要推动因素，因为在这类服务中，较差的网络连接条件通常是主要限制因素。本文提出了一种基于深度学习方法和各向异性扩散滤波器的用于远程干预的器官特异性图像压缩框架。

方法

所提出的方法，即深度学习和各向异性扩散（DLAD），使用卷积神经网络架构来提取目标器官的概率图；该概率图指导各向异性扩散滤波器对图像进行平滑处理，除了目标器官的位置外。随后，应用 BZ2 和 HEVC-视觉无损等压缩方法来压缩图像。我们在用于射频消融（RFA）肝脏病变的三维（3D）CT 图像上演示了所提出的方法。我们使用峰值信噪比（PSNR）、结构相似性（SSIM）和压缩比（CR）指标对 151 张 CT 图像进行了定量评估。最后，我们比较了两位放射科医生对原始图像和压缩图像的肝脏病变检测和肝脏病变中心标注的评估。

结果

结果表明，该方法可以显著提高大多数知名压缩方法的 PSNR。DLAD 与 HEVC-视觉无损相结合，实现了最高平均 PSNR 为 6.45，比原始 HEVC 高 36%，优于其他最先进的无损医学图像压缩方法。均值和 SSIM 分别为 70 dB 和 0.95。此外，压缩效果在统计学上不会显著影响放射科医生对肝脏病变检测和病变中心标注的评估。