On the correlation between second order texture features and human observer detection performance in digital images

Abstract

image texture, the relative spatial arrangement of intensity values in an image, encodes valuable information about the scene. As it stands, much of this potential information remains untapped. Understanding how to decipher textural details would afford another method of extracting knowledge of the physical world from images. In this work, we attempt to bridge the gap in research between quantitative texture analysis and the visual perception of textures. the impact of changes in image texture on human observer's ability to perform signal detection and localization tasks in complex digital images is not understood. We examine this critical question by studying task-based human observer performance in detecting and localizing signals in tomographic breast images. We have also investigated how these changes impact the formation of second-order image texture. We used digital breast tomosynthesis (DBT) an FDA approved tomographic X-ray breast imaging method as the modality of choice to show our preliminary results. our human observer studies involve localization ROC (LROC) studies for low contrast mass detection in DBT. Simulated images are used as they offer the benefit of known ground truth. Our results prove that changes in system geometry or processing leads to changes in image texture magnitudes. We show that the variations in several well-known texture features estimated in digital images correlate with human observer detection-localization performance for signals embedded in them. This insight can allow efficient and practical techniques to identify the best imaging system design and algorithms or filtering tools by examining the changes in these texture features. This concept linking texture feature estimates and task based image quality assessment can be extended to several other imaging modalities and applications as well. it can also offer feedback in system and algorithm designs with a goal to improve perceptual benefits. Broader impact can be in wide array of areas including imaging system design, image processing, data science, machine learning, computer vision, perceptual and vision science. our results also point to the caution that must be exercised in using these texture features as image-based radiomic features or as predictive markers for risk assessment as they are sensitive to system or image processing changes.

Combining Molecular and Radiomic Features for Risk Assessment in Breast Cancer

“…As data become more readily available, data-driven feature extraction will need to be carefully considered. Caution must be taken when texture features used for risk assessment are sensitive to system differences and varying image processing techniques (87). ComBat, a feature-level harmonization method, has been proposed to help alleviate the potential loss of information in feature selection methods that may incorrectly eliminate features due to variation derived from imaging parameters that otherwise would turn out to be useful and informative (88,89).…”

Predicting the gist of breast cancer on a screening mammogram using global radiomic features

“…False positives could trigger large yearly healthcare costs (for example, US$2.8 billion was reported in the United States) and increased patient psychological distress [17; 18], while false negative mistakes might lead to delayed detection of disease, increased treatment complications and poor survival [19; 20]. Moreover, textural features (involving first-and secondorder gray level co-occurrence matrix/GLCM-based statistics) have been shown to be helpful in identifying the global gist of natural scenes [21][22][23][24]. However, it is unknown if a set of these global features from mammograms using radiomics approach [25] can distinguish the strongly perceived (i.e., high-gist) from the poorly perceived gist of breast cancer images (i.e., low-gist).…”

Image texture-based classification methods to mimic perceptual models of search and localization in medical images

“…Recently, our group has shown that certain second-order statistical image texture features can predict signal detection difficulty in tomographic breast images [1]. In parallel, our group has also been developing visual search model observers that accurately mimic search and localization in medical images when average target features are known to the observer (through training) [2][3][4][5].…”