A radiomic model to classify response to neoadjuvant chemotherapy in breast cancer

Abstract

Background Medical image analysis has evolved to facilitate the development of methods for high-throughput extraction of quantitative features that can potentially contribute to the diagnostic and treatment paradigm of cancer. There is a need for further improvement in the accuracy of predictive markers of response to neo-adjuvant chemotherapy (NAC). The aim of this study was to develop a radiomic classifier to enhance current approaches to predicting the response to NAC breast cancer. Methods Data on patients treated for breast cancer with NAC prior to surgery who had a pre-NAC dynamic contrast enhanced breast MRI were included. Response to NAC was assessed using the Miller–Payne system on the excised tumor. Tumor segmentation was carried out manually under the supervision of a consultant breast radiologist. Features were selected using least absolute shrinkage selection operator regression. A support vector machine learning model was used to classify response to NAC. Results 74 patients were included. Patients were classified as having a poor response to NAC (reduction in cellularity < 90%, n = 44) and an excellent response (> 90% reduction in cellularity, n = 30). 4 radiomics features (discretized kurtosis, NGDLM contrast, GLZLM_SZE and GLZLM_ZP) were identified as pertinent predictors of response to NAC. A SVM model using these features stratified patients into poor and excellent response groups producing an AUC of 0.75. Addition of estrogen receptor status improved the accuracy of the model with an AUC of 0.811. Conclusion This study identified a radiomic classifier incorporating 4 radiomics features to augment subtype based classification of response to NAC in breast cancer.

Freehand 1.5T MR-Guided Vacuum-Assisted Breast Biopsy (MR-VABB): Contribution of Radiomics to the Differentiation of Benign and Malignant Lesions

“…In addition, the radiomic logistic regression model could noninvasively predict the likelihood of malignancy of breast lesions amenable to breast biopsy. Although in the medical literature many studies are devoted to assessing the possibility of differentiating between benign and malignant lesions for MRI data [ 7 , 8 , 9 , 10 , 11 , 12 , 13 , 38 , 39 , 40 , 41 , 42 , 43 , 44 , 45 ], there are currently no public and widely accepted radiomics-based guidelines for the pre-operative prediction of malignancy likelihood in patients amenable to MR-VABB. Some recent studies have paved the way to a radiomics-driven exploratory research phase [ 33 , 34 ], and much effort should be made to realize translation into clinical settings.…”

“…However, this study has strict clinical inclusion criteria; indeed, we focused only on patients undergoing MR-VABB, who make up a very small portion of all patients undergoing breast MRI in our center. From this perspective, for this population our dataset can be considered large enough (the minimum caseload for a breast radiologist suggested by the European Society of Breast Cancer Specialists (EUSOMA) is 50 guided interventions per year as a whole, and MR-VABB cases are only a small part of them [ 45 , 46 , 47 ]). We also point out that increasing the sample size could imply the need for multicentric studies, and this would pose data homogenization issues.…”

Machine learning and new insights for breast cancer diagnosis

“…124 The current review extracted and organized the data in tabular form and summarized the application of MRI in breast cancer diagnosis (Table 3). 109,119,120,123,125–166…”

Prediction of early clinical response to neoadjuvant chemotherapy in Triple-negative breast cancer: Incorporating Radiomics through breast MRI

“…The recent explosive growth in radiomics work has proven its role in various elds of analyzing medical images, involving extracting and analyzing multiple quantitative features using advanced computational techniques. In recent years, several studies have been conducted to assess the role of quantitative radiomics features extracted from MR images in predicting prognosis and treatment response in patients with breast cancer [17][18][19] , however, most studies anchor their ndings to post-surgical pathological evaluations such as pCR or residual cancer burden. To our knowledge, a signi cant research gap persists in the early identi cation of TNBC non-responders to NAC using radiological and clinical assessments.…”