Non-Mass Enhancements on DCE-MRI: Development and Validation of a Radiomics-Based Signature for Breast Cancer Diagnoses

Abstract

PurposeWe aimed to assess the additional value of a radiomics-based signature for distinguishing between benign and malignant non-mass enhancement lesions (NMEs) on dynamic contrast-enhanced breast magnetic resonance imaging (breast DCE-MRI).MethodsIn this retrospective study, 232 patients with 247 histopathologically confirmed NMEs (malignant: 191; benign: 56) were enrolled from December 2017 to October 2020 as a primary cohort to develop the discriminative models. Radiomic features were extracted from one post-contrast phase (around 90s after contrast injection) of breast DCE-MRI images. The least absolute shrinkage and selection operator (LASSO) regression model was adapted to select features and construct the radiomics-based signature. Based on clinical and routine MR features, radiomics features, and combined information, three discriminative models were built using multivariable logistic regression analyses. In addition, an independent cohort of 72 patients with 72 NMEs (malignant: 50; benign: 22) was collected from November 2020 to April 2021 for the validation of the three discriminative models. Finally, the combined model was assessed using nomogram and decision curve analyses.ResultsThe routine MR model with two selected features of the time-intensity curve (TIC) type and MR-reported axillary lymph node (ALN) status showed a high sensitivity of 0.942 (95%CI, 0.906 - 0.974) and low specificity of 0.589 (95%CI, 0.464 - 0.714). The radiomics model with six selected features was significantly correlated with malignancy (P<0.001 for both primary and validation cohorts). Finally, the individual combined model, which contained factors including TIC types and radiomics signatures, showed good discrimination, with an acceptable sensitivity of 0.869 (95%CI, 0.816 to 0.916), improved specificity of 0.839 (95%CI, 0.750 to 0.929). The nomogram was applied to the validation cohort, reaching good discrimination, with a sensitivity of 0.820 (95%CI, 0.700 to 0.920), specificity of 0.864 (95%CI,0.682 to 1.000). The combined model was clinically helpful, as demonstrated by decision curve analysis.ConclusionsOur study added radiomics signatures into a conventional clinical model and developed a radiomics nomogram including radiomics signatures and TIC types. This radiomics model could be used to differentiate benign from malignant NMEs in patients with suspicious lesions on breast MRI.

Development of an ultrasound-based radiomics nomogram to preoperatively predict Ki-67 expression level in patients with breast cancer

“…radiomics signature and clinicopathological variables (including SWE) could preoperatively predict the Ki-67 expression level in BC patients with a satisfactory performance. Radiomics has shown a great capability in differentiating benign and malignant tumors (20, 21, 30), discriminating molecular subtypes (31), distinguishing between benign and malignant non-mass enhancement lesions (32), predicting ALN metastasis (24,33) (35,36), this study, on the one hand, adopted a more convenient and economical ultrasound imaging means, while also taking into account the hardness assessment of shear wave elastography; on the other hand, the training and validation sets achieved AUC values of 0.904 and 0.890, with better diagnostic performance.…”

“…Radiomics has shown a great capability in differentiating benign and malignant tumors ( 20 , 21 , 30 ), discriminating molecular subtypes ( 31 ), distinguishing between benign and malignant non-mass enhancement lesions ( 32 ), predicting ALN metastasis ( 24 , 33 ), and responding to neoadjuvant chemotherapy ( 34 ) based on MRI, CT or US findings. A recent research showed that MRI- or digital breast tomosynthesis-based radiomics can be used for prediction of Ki-67 expression level in BC patients.…”

Role of combined clinical-radiomics model based on contrast-enhanced MRI in predicting the malignancy of breast non-mass enhancements without an additional diffusion-weighted imaging sequence

“…This study reviewed 4,519 consecutive patients who underwent breast DCE-MRI in our hospital between December 2017 and November 2021 (including the patients examined between December 2017 and April 2021 described in our previous study). As previously reported ( 9 ), the inclusion criteria included (I) lesions presenting as NMEs in DCE-MRI images, (II) complete clinical and pathological data, (III) the absence of lactation or pregnancy, and (IV) the absence of breast implants or previous treatments. Lesions with (I) maximal a diameter less than 5 mm, (II) apparent hemorrhage after biopsy, and (III) poor image quality were excluded.…”

“…All MR images were obtained using the protocols described in our previous study ( 9 ). The imaging parameters for the multi-b value DWI with readout-segmented echo-planar imaging (RESOLVE DWI) sequence was as follows: repetition time (TR) =5,000 ms; echo time (TE) =70 ms; field of view (FOV) =169×280 mm 2 ; matrix size =114×188; slice thickness =5.0 mm; readout segment =5, average =1; diffusion gradient mode =3-scan trace; and b values =0, 50, and 1,000 s/mm 2 .…”

“…In our previous study, we developed a combined diagnostic model based on time­intensity curve (TIC) types and a radiomics signature on CE-MRI ( 9 ). Even without an additional diffusion-weighted imaging (DWI) sequence, this model had a high diagnostic ability in differentiation.…”