Pretreatment DCE-MRI-Based Deep Learning Outperforms Radiomics Analysis in Predicting Pathologic Complete Response to Neoadjuvant Chemotherapy in Breast Cancer

Deep-learning based discrimination of pathologic complete response using MRI in HER2-positive and triple-negative breast cancer

Distinguishing between pathologic complete response and residual cancer after neoadjuvant chemotherapy (NAC) is crucial for treatment decisions, but the current imaging methods face challenges. To address this, we developed deep-learning models using post-NAC dynamic contrast-enhanced MRI and clinical data. A total of 852 women with human epidermal growth factor receptor 2 (HER2)-positive or triple-negative breast cancer were randomly divided into a training set (n = 724) and a validation set (n = 128). A 3D convolutional neural network model was trained on the training set and validated independently. The main models were developed using cropped MRI images, but models using uncropped whole images were also explored. The delayed-phase model demonstrated superior performance compared to the early-phase model (area under the receiver operating characteristic curve [AUC] = 0.74 vs. 0.69, P = 0.013) and the combined model integrating multiple dynamic phases and clinical data (AUC = 0.74 vs. 0.70, P = 0.022). Deep-learning models using uncropped whole images exhibited inferior performance, with AUCs ranging from 0.45 to 0.54. Further refinement and external validation are necessary for enhanced accuracy.

Baseline [18F]FDG PET/CT and MRI first-order breast tumor features do not improve pathological complete response prediction to neoadjuvant chemotherapy

PURPOSE

To verify the ability of pretreatment [18F]FDG PET/CT and T1-weighed dynamic contrast-enhanced MRI to predict pathological complete response (pCR) after neoadjuvant chemotherapy (NAC) in breast cancer (BC) patients.

METHODS

This retrospective study includes patients with BC of no special type submitted to baseline [18F]FDG PET/CT, NAC and surgery. [18F]FDG PET-based features reflecting intensity and heterogeneity of tracer uptake were extracted from the primary BC and suspicious axillary lymph nodes (ALN), for comparative analysis related to NAC response (pCR vs. non-pCR). Multivariate logistic regression was performed for response prediction combining the breast tumor-extracted PET-based features and clinicopathological features. A subanalysis was performed in a patients' subsample by adding breast tumor-extracted first-order MRI-based features to the multivariate logistic regression.

RESULTS

A total of 170 tumors from 168 patients were included. pCR was observed in 60/170 tumors (20/107 luminal B-like, 25/45 triple-negative and 15/18 HER2-enriched surrogate molecular subtypes). Higher intensity and higher heterogeneity of [18F]FDG uptake in the primary BC were associated with NAC response in HER2-negative tumors (immunohistochemistry score 0, 1 + or 2 + non-amplified by in situ hybridization). Also, higher intensity of tracer uptake was observed in ALN in the pCR group among HER2-negative tumors. No [18F]FDG PET-based features were associated with pCR in the other subgroup analyses. A subsample of 103 tumors was also submitted to extraction of MRI-based features. When combined with clinicopathological features, neither [18F]FDG PET nor MRI-based features had additional value for pCR prediction. The only significant predictors were estrogen receptor status, HER2 expression and grade.

CONCLUSION

Pretreatment [18F]FDG PET-based features from primary BC and ALN are not associated with response to NAC, except in HER2-negative tumors. As compared with pathological features, no breast tumor-extracted PET or MRI-based feature improved response prediction.

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

This study assessed pretreatment breast MRI coupled with machine learning for predicting early clinical responses to neoadjuvant chemotherapy (NAC) in triple-negative breast cancer (TNBC), focusing on identifying non-responders. A retrospective analysis of 135 TNBC patients (107 responders, 28 non-responders) treated with NAC from January 2015 to October 2022 was conducted. Non-responders were defined according to RECIST guidelines. Data included clinicopathologic factors and clinical MRI findings, with radiomics features from contrast-enhanced T1-weighted images, to train a stacking ensemble of 13 machine learning models. For subgroup analysis, propensity score matching was conducted to adjust for clinical disparities in NAC response. The efficacy of the models was evaluated using the area under the receiver-operating-characteristic curve (AUROC) before and after matching. The model combining clinicopathologic factors and clinical MRI findings achieved an AUROC of 0.752 (95% CI 0.644-0.860) for predicting non-responders, while radiomics-based models showed 0.749 (95% CI 0.614-0.884). An integrated model of radiomics, clinicopathologic factors, and clinical MRI findings reached an AUROC of 0.802 (95% CI 0.699-0.905). After propensity score matching, the hierarchical order of key radiomics features remained consistent. Our study demonstrated the potential of using machine learning models based on pretreatment MRI to non-invasively predict TNBC non-responders to NAC.

AI Applications to Breast MRI: Today and Tomorrow

In breast imaging, there is an unrelenting increase in the demand for breast imaging services, partly explained by continuous expanding imaging indications in breast diagnosis and treatment. As the human workforce providing these services is not growing at the same rate, the implementation of artificial intelligence (AI) in breast imaging has gained significant momentum to maximize workflow efficiency and increase productivity while concurrently improving diagnostic accuracy and patient outcomes. Thus far, the implementation of AI in breast imaging is at the most advanced stage with mammography and digital breast tomosynthesis techniques, followed by ultrasound, whereas the implementation of AI in breast magnetic resonance imaging (MRI) is not moving along as rapidly due to the complexity of MRI examinations and fewer available dataset. Nevertheless, there is persisting interest in AI-enhanced breast MRI applications, even as the use of and indications of breast MRI continue to expand. This review presents an overview of the basic concepts of AI imaging analysis and subsequently reviews the use cases for AI-enhanced MRI interpretation, that is, breast MRI triaging and lesion detection, lesion classification, prediction of treatment response, risk assessment, and image quality. Finally, it provides an outlook on the barriers and facilitators for the adoption of AI in breast MRI. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 6.

Artificial Intelligence-Enhanced Breast MRI: Applications in Breast Cancer Primary Treatment Response Assessment and Prediction

ABSTRACT

Primary systemic therapy (PST) is the treatment of choice in patients with locally advanced breast cancer and is nowadays also often used in patients with early-stage breast cancer. Although imaging remains pivotal to assess response to PST accurately, the use of imaging to predict response to PST has the potential to not only better prognostication but also allow the de-escalation or omission of potentially toxic treatment with undesirable adverse effects, the accelerated implementation of new targeted therapies, and the mitigation of surgical delays in selected patients. In response to the limited ability of radiologists to predict response to PST via qualitative, subjective assessments of tumors on magnetic resonance imaging (MRI), artificial intelligence-enhanced MRI with classical machine learning, and in more recent times, deep learning, have been used with promising results to predict response, both before the start of PST and in the early stages of treatment. This review provides an overview of the current applications of artificial intelligence to MRI in assessing and predicting response to PST, and discusses the challenges and limitations of their clinical implementation.

Exploring Neoadjuvant Chemotherapy, Predictive Models, Radiomic, and Pathological Markers in Breast Cancer: A Comprehensive Review

Breast cancer retains its position as the most prevalent form of malignancy among females on a global scale. The careful selection of appropriate treatment for each patient holds paramount importance in effectively managing breast cancer. Neoadjuvant chemotherapy (NACT) plays a pivotal role in the comprehensive treatment of this disease. Administering chemotherapy before surgery, NACT becomes a powerful tool in reducing tumor size, potentially enabling fewer invasive surgical procedures and even rendering initially inoperable tumors amenable to surgery. However, a significant challenge lies in the varying responses exhibited by different patients towards NACT. To address this challenge, researchers have focused on developing prediction models that can identify those who would benefit from NACT and those who would not. Such models have the potential to reduce treatment costs and contribute to a more efficient and accurate management of breast cancer. Therefore, this review has two objectives: first, to identify the most effective radiomic markers correlated with NACT response, and second, to explore whether integrating radiomic markers extracted from radiological images with pathological markers can enhance the predictive accuracy of NACT response. This review will delve into addressing these research questions and also shed light on the emerging research direction of leveraging artificial intelligence techniques for predicting NACT response, thereby shaping the future landscape of breast cancer treatment.

Longitudinal dynamic contrast-enhanced MRI radiomic models for early prediction of response to neoadjuvant systemic therapy in triple-negative breast cancer

Early prediction of neoadjuvant systemic therapy (NAST) response for triple-negative breast cancer (TNBC) patients could help oncologists select individualized treatment and avoid toxic effects associated with ineffective therapy in patients unlikely to achieve pathologic complete response (pCR). The objective of this study is to evaluate the performance of radiomic features of the peritumoral and tumoral regions from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) acquired at different time points of NAST for early treatment response prediction in TNBC. This study included 163 Stage I-III patients with TNBC undergoing NAST as part of a prospective clinical trial (NCT02276443). Peritumoral and tumoral regions of interest were segmented on DCE images at baseline (BL) and after two (C2) and four (C4) cycles of NAST. Ten first-order (FO) radiomic features and 300 gray-level-co-occurrence matrix (GLCM) features were calculated. Area under the receiver operating characteristic curve (AUC) and Wilcoxon rank sum test were used to determine the most predictive features. Multivariate logistic regression models were used for performance assessment. Pearson correlation was used to assess intrareader and interreader variability. Seventy-eight patients (48%) had pCR (52 training, 26 testing), and 85 (52%) had non-pCR (57 training, 28 testing). Forty-six radiomic features had AUC at least 0.70, and 13 multivariate models had AUC at least 0.75 for training and testing sets. The Pearson correlation showed significant correlation between readers. In conclusion, Radiomic features from DCE-MRI are useful for differentiating pCR and non-pCR. Similarly, predictive radiomic models based on these features can improve early noninvasive treatment response prediction in TNBC patients undergoing NAST.

Deep learning radiomic analysis of DCE-MRI combined with clinical characteristics predicts pathological complete response to neoadjuvant chemotherapy in breast cancer

Objective

The aim of this study was to develop and validate a deep learning-based radiomic (DLR) model combined with clinical characteristics for predicting pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) in breast cancer. For early prediction of pCR, the DLR model was based on pre-treatment and early treatment dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) data.

Materials and methods

This retrospective study included 95 women (mean age, 48.1 years; range, 29-77 years) who underwent DCE-MRI before (pre-treatment) and after two or three cycles of NAC (early treatment) from 2018 to 2021. The patients in this study were randomly divided into a training cohort (n=67) and a validation cohort (n=28) at a ratio of 7:3. Deep learning and handcrafted features were extracted from pre- and early treatment DCE-MRI contoured lesions. These features contribute to the construction of radiomic signature RS1 and RS2 representing information from different periods. Mutual information and least absolute shrinkage and selection operator regression were used for feature selection. A combined model was then developed based on the DCE-MRI features and clinical characteristics. The performance of the models was assessed using the area under the receiver operating characteristic curve (AUC) and compared using the DeLong test.

Results

The overall pCR rate was 25.3% (24/95). One radiomic feature and three deep learning features in RS1, five radiomic features and 11 deep learning features in RS2, and five clinical characteristics remained in the feature selection. The performance of the DLR model combining pre- and early treatment information (AUC=0.900) was better than that of RS1 (AUC=0.644, P=0.068) and slightly higher that of RS2 (AUC=0.888, P=0.604) in the validation cohort. The combined model including pre- and early treatment information and clinical characteristics showed the best ability with an AUC of 0.925 in the validation cohort.

Conclusion

The combined model integrating pre-treatment, early treatment DCE-MRI data, and clinical characteristics showed good performance in predicting pCR to NAC in patients with breast cancer. Early treatment DCE-MRI and clinical characteristics may play an important role in evaluating the outcomes of NAC by predicting pCR.

Deep Learning Prediction of Pathologic Complete Response in Breast Cancer Using MRI and Other Clinical Data: A Systematic Review

Breast cancer patients who have pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) are more likely to have better clinical outcomes. The ability to predict which patient will respond to NAC early in the treatment course is important because it could help to minimize unnecessary toxic NAC and to modify regimens mid-treatment to achieve better efficacy. Machine learning (ML) is increasingly being used in radiology and medicine because it can identify relationships amongst complex data elements to inform outcomes without the need to specify such relationships a priori. One of the most popular deep learning methods that applies to medical images is the Convolutional Neural Networks (CNN). In contrast to supervised ML, deep learning CNN can operate on the whole images without requiring radiologists to manually contour the tumor on images. Although there have been many review papers on supervised ML prediction of pCR, review papers on deep learning prediction of pCR are sparse. Deep learning CNN could also incorporate multiple image types, clinical data such as demographics and molecular subtypes, as well as data from multiple treatment time points to predict pCR. The goal of this study is to perform a systematic review of deep learning methods that use whole-breast MRI images without annotation or tumor segmentation to predict pCR in breast cancer.

Multimodal Prediction of Five-Year Breast Cancer Recurrence in Women Who Receive Neoadjuvant Chemotherapy

In current clinical practice, it is difficult to predict whether a patient receiving neoadjuvant chemotherapy (NAC) for breast cancer is likely to encounter recurrence after treatment and have the cancer recur locally in the breast or in other areas of the body. We explore the use of clinical history, immunohistochemical markers, and multiparametric magnetic resonance imaging (DCE, ADC, Dixon) to predict the risk of post-treatment recurrence within five years. We performed a retrospective study on a cohort of 1738 patients from Institut Curie and analyzed the data using classical machine learning, image processing, and deep learning. Our results demonstrate the ability to predict recurrence prior to NAC treatment initiation using each modality alone, and the possible improvement achieved by combining the modalities. When evaluated on holdout data, the multimodal model achieved an AUC of 0.75 (CI: 0.70, 0.80) and 0.57 specificity at 0.90 sensitivity. We then stratified the data based on known prognostic biomarkers. We found that our models can provide accurate recurrence predictions (AUC > 0.89) for specific groups of women under 50 years old with poor prognoses. A version of our method won second place at the BMMR2 Challenge, with a very small margin from being first, and was a standout from the other challenge entries.