Aim: Accurate prediction of preoperative molecular subtypes of breast cancer is crucial for treatment planning and prognosis evaluation of patients. This systematic review aims to investigate the capacity of ultrasound radiomics in accurately identifying the molecular subtypes of breast cancer.
Material and methods: We conducted a thorough search of PubMed, Embase, and Cochrane databases to identify relevant research up until May 2024. We pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, diagnostic odds ratio, and the area under the curve (AUC) to summarize the ability of ultrasound radiomics to predict Luminal type and triple negative breast cancer (TNBC) type in patient with breast cancer. Results: Our meta-analysis found that nine studies provided ultrasound radiomics predictions for TNBC. Pooled sensitivity, specificity, and AUC were 0.64, 0.89, and 0.86, respectively. Four studies have provided the ultrasound radiomics prediction of Luminal molecular subtype breast cancer. Pooled sensitivity, specificity, and AUC were 0.89, 0.79, and 0.90, respectively. There are two studies that predict Luminal A, Luminal B and Her 2+molecular subtype by ultrasound radiology, but they cannot be synthesized quantitatively because of the small number of studies.
Conclusion: Ultrasound radiomics has a good diagnostic performance in predicting molecular subtypes in breast cancer.