Preoperative prediction of sentinel lymph node metastasis in breast cancer based on radiomics of T2-weighted fat-suppression and diffusion-weighted MRI

Abstract

• SLN biopsy to access breast cancer metastasis has multiple complications. • Radiomics uses features extracted from medical images to characterise intratumour heterogeneity. • We combined T -FS and DWI textural features to predict SLN metastasis non-invasively.

MRI‐Based Radiomics Signature for the Preoperative Prediction of Extracapsular Extension of Prostate Cancer

“…With the hypothesis that intratumor heterogeneity exhibited on the spatial distribution of voxel intensities, radiomics could provide more information to distinguish tumors that are challenging for traditional radiologic interpretations . Our results demonstrated that the selected features associated with tumor invasion (which came from four main textural categories, ie, GLRLM, GLSZM, NGTDM, and GLCM) were also consistent with recently published findings concerning the risk stratification for PCa . In this sense, the identified radiomics features might have an impact for future applications of PCa aggressive analysis, providing the potential crucial clues to generalization of a radiomics model.…”

Preoperative prediction of sentinel lymph node metastasis in breast cancer by radiomic signatures from dynamic contrast‐enhanced MRI

“…Therefore, for patients without LVI, we also established a prediction model based on DCE‐MRI radiomic features alone. The prediction performance (AUC = 0.806) is very comparable to a 2017 study utilizing radiomic features from T 2 FS and DWI to predict SLN metastasis in breast cancer (AUC = 0.805). It is noted that DCE‐MRI has become a critical part of a routine clinical breast MRI protocol, while DWI is not available in every hospital.…”

“…In fact, the tumor boundaries were not clear on T 2 ‐weighted images, making it difficult to delineate the ROIs. Moreover, a previous study investigated T 2 FS radiomics, and the prediction performance for SLN metastasis was not satisfying (AUC = 0.77). We believe DCE‐MRI is able to provide more information about the tumor's characteristics compared to T 2 ‐weighted imaging.…”

Dynamic contrast‐enhanced and diffusion‐weighted MRI of invasive breast cancer for the prediction of sentinel lymph node status

“…The rate of axillary lymph node metastases was reported to increase from 11–36% when the tumor size increased from 10–25 mm . Furthermore, previous studies have reported that pathological tumor size is an independent predictive factor for SLN metastasis …”

“…DWI and the ADC value assess the restriction of water molecule diffusion, which is mostly dependent on the tissue cellularity . In centimetric‐sized tumors, ADC values in DWI have proven to be practicable when differentiating benign and malignant tumors.…”