Predicting the level of tumor-infiltrating lymphocytes in patients with triple-negative breast cancer: Usefulness of breast MRI computer-aided detection and diagnosis

Purpose To evaluate the usefulness of magnetic resonance imaging (MRI) computer-aided detection and diagnosis (CAD) for the detection of tumor-infiltrating lymphocytes (TILs) in triple-negative breast cancer (TNBC) patients. TNBC is a heterogeneous malignancy with a varying prognosis. Recently, the importance of TILs in TNBC has been determined. Materials and Methods We retrospectively enrolled 60 lesions of TNBC. Either at 1.5T or 3T MRI, including T1, T2-weighted, and dynamic contrast-enhanced, images were obtained. The CAD results for all lesions were obtained, and we analyzed quantitative kinetic features including the initial peak enhancement and enhancement profiles. We divided the tumors into two groups: those with a TIL level of less than 50%, and those with a TIL level of 50% or more. Kinetic parameters were compared using Student's t-tests and chi-square tests. Results There were 48 low-TIL lesions and 12 high-TIL lesions. The portion of persistent enhancement of tumors was negatively associated with the TIL levels (P = 0.003). The persistent minus washout value of the low-TIL group was higher than that of the high-TIL group (P = 0.008). The odds ratios were 0.944 (P = 0.012) for the persistent portion and 0.971 (P = 0.008) for the persistent minus washout value. Conclusion The prediction model using kinetic enhancement parameters, particularly persistent proportion and plateau minus washout value, could be helpful for identifying TIL levels in TNBC and may be used as an imaging biomarker to guide the treatment plan. Level of Evidence: 4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2017.