Preoperative Prediction Power of Radiomics for Breast Cancer: A Systemic Review and Meta-Analysis

Abstract

Background: To evaluate the preoperative predictive value of radiomics in the diagnosis of breast cancer (BC).

Methods: By searching PubMed and Embase libraries, our study identified 19 eligible studies. We conducted a meta-analysis to assess the differential value in the preoperative assessment of BC using radiomics methods.

Results: Nineteen radiomics studies focusing on the diagnostic efficacy of BC and involving 5865 patients were enrolled. The integrated sensitivity and specificity were 0.84 (95% CI: 0.80-0.87, I ^{2 =} 76.44%) and 0.83 (95% CI: 0.78-0.87, I ^{2 =} 81.79%), respectively. The AUC based on the SROC curve was 0.91, indicating a high diagnostic value.

Conclusion: Radiomics has shown excellent diagnostic performance in the preoperative prediction of BC and is expected to be a promising method in clinical practice.

Keywords: breast cancer; cancer prediction; meta-analysis; radiomics; systematic review.

Figure 1

Flow diagram of literature screening according to PRISMA. PRISMA, Preferred Reported Items for Systematic Reviews and Metaanalyses.

Figure 2

Methodological quality of the studies included in the meta-analysis according to the QUADAS 2 tool for risk of bias and applicability concerns. Green, yellow, and red circles represent low, unclear, and high risk of bias, respectively. (A) Individual studies, (B) summary.

Figure 3

Forrest plot of the effect size calculated as log odds ratio for 19 studies investigating the diagnostic accuracy of radiomics in the differentiation of BC from breast masses. Numbers are pooled estimates, with 95% confidence intervals (CIs) depicted with horizontal lines. Heterogeneity statistics are shown at bottom right.

Figure 4

Hierarchical summary receiver operating characteristic curve (SROC) plot of diagnostic performance in predicting BC of the included radiomic models. The numbers in circles correspond to the order of the articles in Table 1 .