An image quality assessment index based on image features and keypoints for X-ray CT images

Abstract

Optimization tasks in diagnostic radiological imaging require objective quantitative metrics that correlate with the subjective perception of observers. However, although one such metric, the structural similarity index (SSIM), is popular, it has limitations across various aspects in its application to medical images. In this study, we introduce a novel image quality evaluation approach based on keypoints and their associated unique image feature values, focusing on developing a framework to address the need for robustness and interpretability that are lacking in conventional methodologies. The proposed index quantifies and visualizes the distance between feature vectors associated with keypoints, which varies depending on changes in the image quality. This metric was validated on images with varying noise levels and resolution characteristics, and its applicability and effectiveness were examined by evaluating images subjected to various affine transformations. In the verification of X-ray computed tomography imaging using a head phantom, the distances between feature descriptors for each keypoint increased as the image quality degraded, exhibiting a strong correlation with the changes in the SSIM. Notably, the proposed index outperformed conventional full-reference metrics in terms of robustness to various transformations which are without changes in the image quality. Overall, the results suggested that image analysis performed using the proposed framework could effectively visualize the corresponding feature points, potentially harnessing lost feature information owing to changes in the image quality. These findings demonstrate the feasibility of applying the novel index to analyze changes in the image quality. This method may overcome limitations inherent in conventional evaluation methodologies and contribute to medical image analysis in the broader domain.

Fig 1. Overview of the proposed method for image quality evaluation.

(a) The detected keypoints are represented by red dots. (b) Corresponding points are determined based on the features of the keypoints. (c) Calculation process under the proposed metric using keypoints and features.

Fig 2. Image data set used for the validation.

Target images with (a) different noise characteristics and (b) different resolution characteristics.

Fig 3. Overview of the image set used for usefulness verification.

Targets are images with (a) different levels of translation, (b) different degrees of rotation angles, and (c) different levels of scales.

Fig 4. Changes in feature point correspondences with variations in image noise levels.

When the image quality changes, the features no longer match properly, even at the same position in the image. The left and right sides represent the reference and target images, respectively, for each algorithm. The red dots represent the keypoints extracted for each image, and the green lines represent matches between the keypoints.

Fig 5

Scatter plots of the SSIM and proposed index obtained in the validation when there were changes in the (a) exposure dose levels and (b) intensity of Gaussian processing. Statistically significant correlations were obtained for all algorithms in both conditions.

Fig 6. Scatter plots of the SSIM and proposed index in the usefulness verification.

(a) There are changes in the amount of translation, (b) there are changes in the angle of rotation processing, (c) several downscaling transformations have been performed, and (d) several enlargement processing steps have been performed.