Image retrieval‐based parenchymal analysis for breast cancer risk assessment

Abstract

This research on breast cancer risk assessment aims to develop models that predict the likelihood of breast cancer. In recent years, the computerized analysis of visual texture patterns in mammograms,namely parenchymal analysis, has shown great potential for risk assessment. However, the visual complexity and heterogeneity of visual patterns limit the performance of parenchymal analysis in large populations. In this work, we propose a method to create individualized risk assessment models based on the radiological visual appearance (radiomic phenotypes) of the mammograms. Methods: We developed a content-based image retrieval system to stratify mammographic analysis according to the similarities of their radiomic phenotypes. We collected 1144 mammograms from 286 women following a casecontrol study design. We compared the classical parenchymal analysis with the proposed approach using the area under the ROC curve (AUC) with 95% confidence intervals (CI). Statistical significance was assessed using DeLong's test (p <0.05). Results: At a patient level,AUC values of 0.504 (95% CI:0.398-0.611) with classical parenchymal analysis increased to 0.813 (95% CI: 0.734-0.892) when the radiomic phenotypes are incorporated with the proposed method. In risk estimation from individual, standard mammographic views, the highest performance was obtained with the mediolateral oblique view of the right breast (RMLO), with an AUC value of 0.727 (95% CI: 0.634-0.820). Differences in performance among views were statistically significant (p < 0.05) Conclusions: These results indicate that the utilization of radiomic phenotypes increases the performance of computerized risk assessment based on parenchymal analysis of mammographic images. Significance: The creation of individualized risk assessment models may be leveraged to target personalized screening and prevention recommendations according to the person's risk.

Saliency of breast lesions in breast cancer detection using artificial intelligence

“…This retrospective study did not change either the diagnostic decisions or the management of the patients. Of the 382 women included in this study (191 cases plus 191 controls), 228 had been included in previous reports 10,11 . These reports concerned radiomic analysis for assessing the risk of breast cancer in future screening rounds, whereas in this work we are interested in breast cancer detection in the current screening round.…”

Combining Molecular and Radiomic Features for Risk Assessment in Breast Cancer

“…This method allows for an automated development of risk models based on images, making it a data-driven approach that could learn new patterns to stratify breast cancer risk. Padilla et al (66) developed a content-based image retrieval system to stratify risk based on radiomic phenotype similarities. After generating the reference feature vector set, new images are queried, compared for similarity, and then used to create a model to produce a risk score.…”