Validation of no-reference image quality index for the assessment of digital mammographic images

Abstract

To ensure optimal clinical performance of digital mammography, it is necessary to obtain images with high spatial resolution and low noise, keeping radiation exposure as low as possible. These requirements directly affect the interpretation of radiologists. The quality of a digital image should be assessed using objective measurements. In general, these methods measure the similarity between a degraded image and an ideal image without degradation (ground-truth), used as a reference. These methods are called Full-Reference Image Quality Assessment (FR-IQA). However, for digital mammography, an image without degradation is not available in clinical practice; thus, an objective method to assess the quality of mammograms must be performed without reference. The purpose of this study is to present a Normalized Anisotropic Quality Index (NAQI), based on the Rényi entropy in the pseudo-Wigner domain, to assess mammography images in terms of spatial resolution and noise without any reference. The method was validated using synthetic images acquired through an anthropomorphic breast software phantom, and the clinical exposures on anthropomorphic breast physical phantoms and patient's mammograms. The results reported by this noreference index follow the same behavior as other well-established full-reference metrics, e.g., the peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). Reductions of 50% on the radiation dose in phantom images were translated as a decrease of 4dB on the PSNR, 25% on the SSIM and 33% on the NAQI, evidencing that the proposed metric is sensitive to the noise resulted from dose reduction. The clinical results showed that images reduced to 53% and 30% of the standard radiation dose reported reductions of 15% and 25% on the NAQI, respectively. Thus, this index may be used in clinical practice as an image quality indicator to improve the quality assurance programs in mammography; hence, the proposed method reduces the subjectivity inter-observers in the reporting of image quality assessment.

Analysis of feature relevance using an image quality index applied to digital mammography

“…2 The NAQI is comparable to well-established full-reference metrics when assessing the quality of digital breast phantoms and clinical mammograms in terms of noise and spatial resolution. 2 We have also investigated the influence of breast anatomy on the NAQI values. 3 This particular study used a digital anthropomorphic phantom to simulate a range of breast anatomies.…”

“…We have demonstrated and validated the use of the normalized AQI (NAQI) for assessing the quality of clinical mammograms. [2][3][4] NAQI can be used for image quality assessment in clinical practice where subject ground-truth does not exist. 2 The NAQI is comparable to well-established full-reference metrics when assessing the quality of digital breast phantoms and clinical mammograms in terms of noise and spatial resolution.…”

“…[2][3][4] NAQI can be used for image quality assessment in clinical practice where subject ground-truth does not exist. 2 The NAQI is comparable to well-established full-reference metrics when assessing the quality of digital breast phantoms and clinical mammograms in terms of noise and spatial resolution. 2 We have also investigated the influence of breast anatomy on the NAQI values.…”

Anisotropic blind image quality assessment: Survey and analysis with current methods

“…In [5], AQI was applied in different biometric applications (face, fingerprints and hand veins). AQI was used in different surveillance scenarios under the presence of atmospheric distortions [6] and for biomedical image classification [7].…”

Método baseado em médias não-locais para filtragem do ruído quântico de imagens mamográficas digitais adquiridas com dose de radiação reduzida

“…O método baseia-se na medição da anisotropia como indicador da qualidade da imagem, e segundo Gabarda, et al (2007), imagens com baixa anisotropia apresentam menor qualidade, ou seja, níveis mais elevados de ruído e menor resolução espacial (GABARDA, 2007). Esse método tem sido aplicado com sucesso na avaliação de qualidade de imagens mamográficas digitais e possui comportamento similar ao PSNR quando a imagem é degradada com inserção de ruído e perda de resolução espacial (OLIVEIRA, 2016). No entanto, a vantagem dessa métrica em relação ao PSNR é que ela não precisa da imagem referência (sem ruído) para ser calculada.…”