Diagnostic value of radiomics and machine learning with dynamic contrast-enhanced magnetic resonance imaging for patients with atypical ductal hyperplasia in predicting malignant upgrade

Abstract

Purpose To investigate whether radiomics features extracted from magnetic resonance imaging (MRI) of patients with biopsy-proven atypical ductal hyperplasia (ADH) coupled with machine learning can differentiate high-risk lesions that will upgrade to malignancy at surgery from those that will not, and to determine if qualitatively and semi-quantitatively assessed imaging features, clinical factors, and image-guided biopsy technical factors are associated with upgrade rate. Methods This retrospective study included 127 patients with 139 breast lesions yielding ADH at biopsy who were assessed with multiparametric MRI prior to biopsy. Two radiologists assessed all lesions independently and with a third reader in consensus according to the BI-RADS lexicon. Univariate analysis and multivariate modeling were performed to identify significant radiomic features to be included in a machine learning model to discriminate between lesions that upgraded to malignancy on surgery from those that did not. Results Of 139 lesions, 28 were upgraded to malignancy at surgery, while 111 were not upgraded. Diagnostic accuracy was 53.6%, specificity 79.2%, and sensitivity 15.3% for the model developed from pre-contrast features, and 60.7%, 86%, and 22.8% for the model developed from delta radiomics datasets. No significant associations were found between any radiologist-assessed lesion parameters and upgrade status. There was a significant correlation between the number of specimens sampled during biopsy and upgrade status (p = 0.003). Conclusion Radiomics analysis coupled with machine learning did not predict upgrade status of ADH. The only significant result from this analysis is between the number of specimens sampled during biopsy procedure and upgrade status at surgery.

Multiparametric 18F-FDG PET/MRI-Based Radiomics for Prediction of Pathological Complete Response to Neoadjuvant Chemotherapy in Breast Cancer

“…Radiomics-based analysis of breast cancer has emerged to become a well-investigated research focus in assessing its potential for predicting various endpoints, such as relapse, progression-free survival, subtype, or tumor phenotyping [ 7 , 8 , 9 , 10 , 13 , 14 , 23 , 24 , 25 ]. PCR after NAC has been shown to imply prolonged disease-free and overall survival [ 26 ] and has therefore been proposed as a surrogate early clinical endpoint for long-term survival [ 27 ].…”

Third International Consensus Conference on lesions of uncertain malignant potential in the breast (B3 lesions)

“…Since the last consensus conference, several studies reported an upgrade rate of ADH into malignancy (DCIS or invasive cancer) between 7.3 and 57% in targeted OE. Consequently, the majority of these studies recommended OE, although increasingly considering other options such as imaging follow-up after VAB, when the calcifications in clinical imaging have been completely removed [6,19,[22][23][24][25][26][27][28][29][30][31]. In the MIBB database, patients with ADH underwent OE in the majority of cases (62.7%), and an upgrade rate of 25.2% was observed.…”

Multiparametric Integrated 18F-FDG PET/MRI-Based Radiomics for Breast Cancer Phenotyping and Tumor Decoding

“…Over the past few years, a number of publications have investigated the potential of radiomics-based analyses for determination of different genomic and phenotypic characteristics of breast cancer as well as more fundamental features such as grading or metastatic spread [9,10,32]. Leithner et al published a study focused exclusively on DCE-MRI for the differentiation of two important tumor characteristics, by means of molecular subtype and receptor status.…”