Response Predictivity to Neoadjuvant Therapies in Breast Cancer: A Qualitative Analysis of Background Parenchymal Enhancement in DCE-MRI

The contrast-free diffusion MRI multiple index for the early prediction of pathological response to neoadjuvant chemotherapy in breast cancer

Early tumor response prediction can help avoid overtreatment with unnecessary chemotherapy sessions. It is important to determine whether multiple apparent diffusion coefficient indices (S index, ADC-diff) are effective in the early prediction of pathological response to neoadjuvant chemotherapy (NAC) in breast cancer (BC). Patients with stage II and III BCs who underwent T1WI, diffusion-weighted imaging (DWI), and dynamic contrast-enhanced MRI using a 3 T system were included. They were divided into two groups: major histological responders (MHRs, Miller-Payne G4/5) and nonmajor histological responders (nMHRs, Miller-Payne G1-3). Three b values were used for DWI to derive the S index; ADC-diff values were obtained using b = 0 and 1000 s/mm2. The different interquartile ranges of percentile S-index and ADC-diff values after treatment were calculated and compared. The assessment was performed at baseline and after two and four NAC cycles. A total of 59 patients were evaluated. There are some correlations of interquartile ranges of S-index parameters and ADC-diff values with histopathological prognostic factors (such as estrogen receptor and human epidermal growth factor receptor 2 expression, all p < 0.05), but no significant differences were found in some other interquartile ranges of S-index parameters or ADC-diff values between progesterone receptor positive and negative or for Ki-67 tumors (all P > 0.05). No differences were found in the dynamic contrast-enhanced MRI characteristics between the two groups. HER-2 expression and kurtosis of the S-index distribution were screened out as independent risk factors for predicting MHR group (p < 0.05, area under the curve (AUC) = 0.811) before NAC. After early NAC (two cycles), only the 10th percentile S index was statistically significant between the two groups (p < 0.05, AUC = 0.714). No significant differences were found in ADC-diff value at any time point of NAC between the two groups (P > 0.1). These findings demonstrate that the S-index value may be used as an early predictor of pathological response to NAC in BC; the value of ADC-diff as an imaging biomarker of NAC needs to be further confirmed by ongoing multicenter prospective trials.

Predicting pathological complete response to neoadjuvant chemotherapy in breast cancer patients: use of MRI radiomics data from three regions with multiple machine learning algorithms

OBJECTIVE

To construct a multi-region MRI radiomics model for predicting pathological complete response (pCR) in breast cancer (BCa) patients who received neoadjuvant chemotherapy (NACT) and provide a theoretical basis for the peritumoral microenvironment affecting the efficacy of NACT.

METHODS

A total of 133 BCa patients who received NACT, including 49 with confirmed pCR, were retrospectively analyzed. The radiomics features of the intratumoral region, peritumoral region, and background parenchymal enhancement (BPE) were extracted, and the most relevant features were obtained after dimensional reduction. Then, combining different areas, multivariate logistic regression analysis was used to select the optimal feature set, and six different machine learning models were used to predict pCR. The optimal model was selected, and its performance was evaluated using receiver operating characteristic (ROC) analysis. SHAP analysis was used to examine the relationship between the features of the model and pCR.

RESULTS

For signatures constructed using three individual regions, BPE provided the best predictions of pCR, and the diagnostic performance of the intratumoral and peritumoral regions improved after adding the BPE signature. The radiomics signature from the combination of all the three regions with the XGBoost machine learning algorithm provided the best predictions of pCR based on AUC (training set: 0.891, validation set: 0.861), sensitivity (training set: 0.882, validation set: 0.800), and specificity (training set: 0.847, validation set: 0.84). SHAP analysis demonstrated that LZ_log.sigma.2.0.mm.3D_glcm_ClusterShade_T12 made the greatest contribution to the predictions of this model.

CONCLUSION

The addition of the BPE MRI signature improved the prediction of pCR in BCa patients who received NACT. These results suggest that the features of the peritumoral microenvironment are related to the efficacy of NACT.

Predictive value of background parenchymal enhancement on breast magnetic resonance imaging for pathological tumor response to neoadjuvant chemotherapy in breast cancers: a systematic review

OBJECTIVES

This review aimed to assess the predictive value of background parenchymal enhancement (BPE) on breast magnetic resonance imaging (MRI) as an imaging biomarker for pathologic complete response (pCR) after neoadjuvant chemotherapy (NACT).

METHODS

Two reviewers independently performed a systemic literature search using the PubMed, MEDLINE, and Embase databases for studies published up to 11 June 2022. Data from relevant articles were extracted to assess the relationship between BPE and pCR.

RESULTS

This systematic review included 13 studies with extensive heterogeneity in population characteristics, MRI follow-up points, MRI protocol, NACT protocol, pCR definition, and BPE assessment. Baseline BPE levels were not associated with pCR, except in 1 study that reported higher baseline BPE of the younger participants (< 55 years) in the pCR group than the non-pCR group. A total of 5 studies qualitatively assessed BPE levels and indicated a correlation between reduced BPE after NACT and pCR; however, among the studies that quantitatively measured BPE, the same association was observed only in the subgroup analysis of 2 articles that assessed the status of hormone receptor and human epidermal growth factor receptor 2. In addition, the predictive ability of early BPE changes for pCR was reported in several articles and remains controversial.

CONCLUSIONS

Changes in BPE may be a promising imaging biomarker for predicting pCR in breast cancer. Because current studies remain insufficient, particularly those that quantitatively measure BPE, prospective and multicenter large-sample studies are needed to confirm this relationship.

Radiomic model based on magnetic resonance imaging for predicting pathological complete response after neoadjuvant chemotherapy in breast cancer patients

Purpose

To establish a model combining radiomic and clinicopathological factors based on magnetic resonance imaging to predict pathological complete response (pCR) after neoadjuvant chemotherapy in breast cancer patients.

Method

MRI images and clinicopathologic data of 329 eligible breast cancer patients from the Affiliated Hospital of Qingdao University from August 2018 to August 2022 were included in this study. All patients received neoadjuvant chemotherapy (NAC), and imaging examinations were performed before and after NAC. A total of 329 patients were randomly allocated to a training set and a test set at a ratio of 7:3. We mainly studied the following three types of prediction models: radiomic models, clinical models, and clinical-radiomic models. All models were evaluated using subject operating characteristic curve analysis and area under the curve (AUC), decision curve analysis (DCA) and calibration curves.

Results

The AUCs of the clinical prediction model, independent imaging model and clinical combined imaging model in the training set were 0.864 0.968 and 0.984, and those in the test set were 0.724, 0.754 and 0.877, respectively. According to DCA and calibration curves, the clinical-radiomic model showed good predictive performance in both the training set and the test set, and we found that we had developed a more concise clinical-radiomic nomogram.

Conclusion

We have developed a clinical-radiomic model by integrating radiomic features and clinical factors to predict pCR after NAC in breast cancer patients, thereby contributing to the personalized treatment of patients.

Prediction of neoadjuvant chemotherapy pathological complete response for breast cancer based on radiomics nomogram of intratumoral and derived tissue

BACKGROUND

Non-invasive identification of breast cancer (BCa) patients with pathological complete response (pCR) after neoadjuvant chemotherapy (NACT) is critical to determine appropriate surgical strategies and guide the resection range of tumor. This study aimed to examine the effectiveness of a nomogram created by combining radiomics signatures from both intratumoral and derived tissues with clinical characteristics for predicting pCR after NACT.

METHODS

The clinical data of 133 BCa patients were analyzed retrospectively and divided into training and validation sets. The radiomics features for Intratumoral, peritumoral, and background parenchymal enhancement (BPE) in the training set were dimensionalized. Logistic regression analysis was used to select the optimal feature set, and a radiomics signature was constructed using a decision tree. The signature was combined with clinical features to build joint models and generate nomograms. The area under curve (AUC) value of receiver operating characteristic (ROC) curve was then used to assess the performance of the nomogram and independent predictors.

RESULTS

Among single region, intratumoral had the best predictive value. The diagnostic performance of the intratumoral improved after adding the BPE features. The AUC values of the radiomics signature were 0.822 and 0.82 in the training and validation sets. Multivariate logistic regression analysis revealed that age, ER, PR, Ki-67, and radiomics signature were independent predictors of pCR in constructing a nomogram. The AUC of the nomogram in the training and validation sets were 0.947 and 0.933. The DeLong test showed that the nomogram had statistically significant differences compared to other independent predictors in both the training and validation sets (P < 0.05).

CONCLUSION

BPE has value in predicting the efficacy of neoadjuvant chemotherapy, thereby revealing the potential impact of tumor growth environment on the efficacy of neoadjuvant chemotherapy.

Early Assessment of Neoadjuvant Chemotherapy Response Using Multiparametric Magnetic Resonance Imaging in Luminal B-like Subtype of Breast Cancer Patients: A Single-Center Prospective Study

This study aimed to evaluate the performance of multiparametric breast magnetic resonance imaging (mpMRI) for predicting response to neoadjuvant chemotherapy (NAC) in patients with luminal B subtype breast cancer. The prospective study included thirty-five patients treated with NAC for both early and locally advanced breast cancer of the luminal B subtype at the University Hospital Centre Zagreb between January 2015 and December 2018. All patients underwent breast mpMRI before and after two cycles of NAC. Evaluation of mpMRI examinations included analysis of both morphological (shape, margins, and pattern of enhancement) and kinetic characteristics (initial signal increase and post-initial behavior of the time-signal intensity curve), which were additionally interpreted with a Göttingen score (GS). Histopathological analysis of surgical specimens included grading the tumor response based on the residual cancer burden (RCB) grading system and revealed 29 NAC responders (RCB-0 (pCR), I, II) and 6 NAC non-responders (RCB-III). Changes in GS were compared with RCB classes. A lack of GS decrease after the second cycle of NAC is associated with RCB class and non-responders to NAC.

Analyzing breast cancer invasive disease event classification through explainable artificial intelligence

Introduction

Recently, accurate machine learning and deep learning approaches have been dedicated to the investigation of breast cancer invasive disease events (IDEs), such as recurrence, contralateral and second cancers. However, such approaches are poorly interpretable.

Methods

Thus, we designed an Explainable Artificial Intelligence (XAI) framework to investigate IDEs within a cohort of 486 breast cancer patients enrolled at IRCCS Istituto Tumori "Giovanni Paolo II" in Bari, Italy. Using Shapley values, we determined the IDE driving features according to two periods, often adopted in clinical practice, of 5 and 10 years from the first tumor diagnosis.

Results

Age, tumor diameter, surgery type, and multiplicity are predominant within the 5-year frame, while therapy-related features, including hormone, chemotherapy schemes and lymphovascular invasion, dominate the 10-year IDE prediction. Estrogen Receptor (ER), proliferation marker Ki67 and metastatic lymph nodes affect both frames.

Discussion

Thus, our framework aims at shortening the distance between AI and clinical practice.

Tumor immune microenvironment components and the other markers can predict the efficacy of neoadjuvant chemotherapy for breast cancer

Breast cancer is an epithelial malignant tumor that occurs in the terminal ducts of the breast. Neoadjuvant chemotherapy (NACT) is an important part of breast cancer treatment. Its purpose is to use systemic treatment for some locally advanced breast cancer patients, to decrease the tumor size and clinical stage so that non-operable breast cancer patients can have a chance to access surgical treatment, or patients who are not suitable for breast-conserving surgery can get the opportunity of breast-conserving. However, some patients who do not respond to NACT will lead deterioration in their condition. Therefore, prediction of NACT efficacy in breast cancer is vital for precision therapy. The tumor microenvironment (TME) has a crucial role in the carcinogenesis and therapeutic response of breast cancer. In this review, we summarized the immune cells, immune checkpoints, and other biomarkers in the TME that can evaluate the efficacy of NACT in treating breast cancer. We believe that the detection and evaluation of the TME components in breast cancer are helpful to predict the efficacy of NACT, and the prediction methods are in the prospect. In addition, we also summarized other predictive factors of NACT, such as imaging examination, biochemical markers, and multigene/multiprotein profiling.

Lean Perspectives in an Organizational Change in a Scientific Direction of an Italian Research Institute: Experience of the Cancer Institute of Bari

Lean management is a relatively new organizational vision transferred from the automotive industry to the healthcare and administrative sector based on analyzing a production process to emphasize value and reduce waste. This approach is particularly interesting in a historical moment of cuts and scarcity of economic resources and could represent a low-cost organizational solution in many production companies. In this work, we analyzed the presentation and the initial management of current ministerial research projects up to the approval by the Scientific Directorate of an Italian research institute. Furthermore, the initial mode in 2021 ("as is") and the potential mode ("to be") according to a Lean model are studied, according to the current barriers highlighted by the final users of the process and carrying out some perspective analyses with some reference indicators.

Delta-Radiomics Based on Dynamic Contrast-Enhanced MRI Predicts Pathologic Complete Response in Breast Cancer Patients Treated with Neoadjuvant Chemotherapy

Simple Summary

Neoadjuvant chemotherapy (NAC) followed with surgery is the standard strategy in the treatment of locally advanced breast cancer, but the individual efficacy varies. Early and accurate prediction of complete responders determines the NAC regimens and prognosis. Breast MRI has been recommended to monitor NAC response before, during, and after treatment. Radiomics has been heralded as a breakthrough in medicine and regarded to have changed the landscape of biomedical research in oncology. Delta-radiomics characterizing the change in feature values by applying radiomics to multiple time points, is a promising strategy for predicting response after NAC. In our study, the delta-radiomics model built with the change of radiomic features before and after one cycle NAC could effectively predict pathological complete response (pCR) in breast cancer. The model provides strong support for clinical decision-making at the earliest stage and helps patients benefit the most from NAC.

Abstract

Objective: To investigate the value of delta-radiomics after the first cycle of neoadjuvant chemotherapy (NAC) using dynamic contrast-enhanced (DCE) MRI for early prediction of pathological complete response (pCR) in patients with breast cancer. Methods: From September 2018 to May 2021, a total of 140 consecutive patients (training, n = 98: validation, n = 42), newly diagnosed with breast cancer who received NAC before surgery, were prospectively enrolled. All patients underwent DCE-MRI at pre-NAC (pre-) and after the first cycle (1st-) of NAC. Radiomic features were extracted from the postcontrast early, peak, and delay phases. Delta-radiomics features were computed in each contrast phases. Least absolute shrinkage and selection operator (LASSO) and a logistic regression model were used to select features and build models. The model performance was assessed by receiver operating characteristic (ROC) analysis and compared by DeLong test. Results: The delta-radiomics model based on the early phases of DCE-MRI showed a highest AUC (0.917/0.842 for training/validation cohort) compared with that using the peak and delay phases images. The delta-radiomics model outperformed the pre-radiomics model (AUC = 0.759/0.617, p = 0.011/0.047 for training/validation cohort) in early phase. Based on the optimal model, longitudinal fusion radiomic models achieved an AUC of 0.871/0.869 in training/validation cohort. Clinical-radiomics model generated good calibration and discrimination capacity with AUC 0.934 (95%CI: 0.882, 0.986)/0.864 (95%CI: 0.746, 0.982) for training and validation cohort. Delta-radiomics based on early contrast phases of DCE-MRI combined clinicopathology information could predict pCR after one cycle of NAC in patients with breast cancer.

A Novel Combined Nomogram Model for Predicting the Pathological Complete Response to Neoadjuvant Chemotherapy in Invasive Breast Carcinoma of No Specific Type: Real-World Study

Objective

To explore the value of a predictive model combining the multiparametric magnetic resonance imaging (mpMRI) radiomics score (RAD-score), clinicopathologic features, and morphologic features for the pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) in invasive breast carcinoma of no specific type (IBC-NST).

Methods

We enrolled, retrospectively and consecutively, 206 women with IBC-NST who underwent surgery after NAC and obtained pathological results from August 2018 to October 2021. Four RAD-scores were constructed for predicting the pCR based on fat-suppression T2-weighted imaging (FS-T2WI), diffusion-weighted imaging (DWI), contrast-enhanced T1-weighted imaging (T1WI+C) and their combination, which was called mpMRI. The best RAD-score was combined with clinicopathologic and morphologic features to establish a nomogram model through binary logistic regression. The predictive performance of the nomogram was evaluated using the area under receiver operator characteristic (ROC) curve (AUC) and calibration curve. The clinical net benefit of the model was evaluated using decision curve analysis (DCA).

Results

The mpMRI RAD-score had the highest diagnostic performance, with AUC of 0.848 among the four RAD-scores. T stage, human epidermal growth factor receptor-2 (HER2) status, RAD-score, and roundness were independent factors for predicting the pCR (P < 0.05 for all). The combined nomogram model based on these factors achieved AUCs of 0.930 and 0.895 in the training cohort and validation cohort, respectively, higher than other models (P < 0.05 for all). The calibration curve showed that the predicted probabilities of the nomogram were in good agreement with the actual probabilities, and DCA indicated that it provided more net benefit than the treat-none or treat-all scheme by decision curve analysis in both training and validation datasets.

Conclusion

The combined nomogram model based on the mpMRI RAD-score combined with clinicopathologic and morphologic features may improve the predictive performance for the pCR of NAC in patients with IBC-NST.

Robustness Evaluation of a Deep Learning Model on Sagittal and Axial Breast DCE-MRIs to Predict Pathological Complete Response to Neoadjuvant Chemotherapy

To date, some artificial intelligence (AI) methods have exploited Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) to identify finer tumor properties as potential earlier indicators of pathological Complete Response (pCR) in breast cancer patients undergoing neoadjuvant chemotherapy (NAC). However, they work either for sagittal or axial MRI protocols. More flexible AI tools, to be used easily in clinical practice across various institutions in accordance with its own imaging acquisition protocol, are required. Here, we addressed this topic by developing an AI method based on deep learning in giving an early prediction of pCR at various DCE-MRI protocols (axial and sagittal). Sagittal DCE-MRIs refer to 151 patients (42 pCR; 109 non-pCR) from the public I-SPY1 TRIAL database (DB); axial DCE-MRIs are related to 74 patients (22 pCR; 52 non-pCR) from a private DB provided by Istituto Tumori “Giovanni Paolo II” in Bari (Italy). By merging the features extracted from baseline MRIs with some pre-treatment clinical variables, accuracies of 84.4% and 77.3% and AUC values of 80.3% and 78.0% were achieved on the independent tests related to the public DB and the private DB, respectively. Overall, the presented method has shown to be robust regardless of the specific MRI protocol.

Generative models improve radiomics performance in different tasks and different datasets: An experimental study

PURPOSE

Radiomics is an active area of research focusing on high throughput feature extraction from medical images with a wide array of applications in clinical practice, such as clinical decision support in oncology. However, noise in low dose computed tomography (CT) scans can impair the accurate extraction of radiomic features. In this article, we investigate the possibility of using deep learning generative models to improve the performance of radiomics from low dose CTs.

METHODS

We used two datasets of low dose CT scans - NSCLC Radiogenomics and LIDC-IDRI - as test datasets for two tasks - pre-treatment survival prediction and lung cancer diagnosis. We used encoder-decoder networks and conditional generative adversarial networks (CGANs) trained in a previous study as generative models to transform low dose CT images into full dose CT images. Radiomic features extracted from the original and improved CT scans were used to build two classifiers - a support vector machine (SVM) and a deep attention based multiple instance learning model - for survival prediction and lung cancer diagnosis respectively. Finally, we compared the performance of the models derived from the original and improved CT scans.

RESULTS

Denoising with the encoder-decoder network and the CGAN improved the area under the curve (AUC) of survival prediction from 0.52 to 0.57 (p-value < 0.01). On the other hand, the encoder-decoder network and the CGAN improved the AUC of lung cancer diagnosis from 0.84 to 0.88 and 0.89 respectively (p-value < 0.01). Finally, there are no statistically significant improvements in AUC using encoder-decoder networks and CGAN (p-value = 0.34) when networks trained at 75 and 100 epochs.

CONCLUSION

Generative models can improve the performance of low dose CT-based radiomics in different tasks. Hence, denoising using generative models seems to be a necessary pre-processing step for calculating radiomic features from low dose CTs.

Radiomics in Triple Negative Breast Cancer: New Horizons in an Aggressive Subtype of the Disease

In the last decade, the analysis of the medical images has evolved significantly, applications and tools capable to extract quantitative characteristics of the images beyond the discrimination capacity of the investigator's eye being developed. The applications of this new research field, called radiomics, presented an exponential growth with direct implications in the diagnosis and prediction of response to therapy. Triple negative breast cancer (TNBC) is an aggressive breast cancer subtype with a severe prognosis, despite the aggressive multimodal treatments applied according to the guidelines. Radiomics has already proven the ability to differentiate TNBC from fibroadenoma. Radiomics features extracted from digital mammography may also distinguish between TNBC and non-TNBC. Recent research has identified three distinct subtypes of TNBC using IRM breast images voxel-level radiomics features (size/shape related features, texture features, sharpness). The correlation of these TNBC subtypes with the clinical response to neoadjuvant therapy may lead to the identification of biomarkers in order to guide the clinical decision. Furthermore, the variation of some radiomics features in the neoadjuvant settings provides a tool for the rapid evaluation of treatment efficacy. The association of radiomics features with already identified biomarkers can generate complex predictive and prognostic models. Standardization of image acquisition and also of radiomics feature extraction is required to validate this method in clinical practice.

Radiomics Analysis of Multi-Phase DCE-MRI in Predicting Tumor Response to Neoadjuvant Therapy in Breast Cancer

Objective: To explore whether the pretreatment dynamic contrast enhancement magnetic resonance imaging (DCE-MRI) and radiomics signatures were associated with pathologic complete response (pCR) to neoadjuvant therapy (NAT) in breast cancer. Method: A retrospective review of 70 patients with breast invasive carcinomas proved by biopsy between June 2017 and October 2020 (26 patients were pathological complete response, and 44 patients were non-pathological complete response). Within the pre-contrast and five post-contrast dynamic series, a total of 1037 quantitative imaging features were extracted from in each phase. Additionally, the Δfeatures (the difference between the features before and after the comparison) were used for subsequent analysis. The least absolute shrinkage and selection operator (LASSO) regression method was used to select features related to pCR, and then use these features to train multiple machine learning classifiers to predict the probability of pCR for a given patient. The area under the curve (AUC), accuracy, sensitivity, and specificity were calculated to assess the predictive performances of the radiomics model for each of the five phases of time points. Result: Among the five phases, each individual phase performed with AUCs ranging from 0.845 to 0.919 in predicting pCR. The best single phases performance was given by the 3rd phase (AUC = 0.919, sensitivity 0.885, specificity 0.864). 5 of the features have significant differences between pCR and non-pCR groups in each phase, most features reach their maximum or minimum in the 2nd or 3rd phase. Conclusion: The radiomic features extracted from each phase of pre-treatment DCE-MRI possess discriminatory power to predict tumor response.

Analysis of mammograms using artificial intelligence to predict response to neoadjuvant chemotherapy in breast cancer patients: proof of concept

Objectives

In this proof of concept study, a deep learning–based method for automatic analysis of digital mammograms (DM) as a tool to aid in assessment of neoadjuvant chemotherapy (NACT) treatment response in breast cancer (BC) was examined.

Methods

Baseline DM from 453 patients receiving NACT between 2005 and 2019 were included in the study cohort. A deep learning system, using the aforementioned baseline DM, was developed to predict pathological complete response (pCR) in the surgical specimen after completion of NACT. Two image patches, one extracted around the detected tumour and the other from the corresponding position in the reference image, were fed into a classification network. For training and validation, 1485 images obtained from 400 patients were used, and the model was ultimately applied to a test set consisting of 53 patients.

Results

A total of 95 patients (21%) achieved pCR. The median patient age was 52.5 years (interquartile range 43.7–62.1), and 255 (56%) were premenopausal. The artificial intelligence (AI) model predicted the pCR as represented by the area under the curve of 0.71 (95% confidence interval 0.53–0.90; p = 0.035). The sensitivity was 46% at a fixed specificity of 90%.

Conclusions

Our study describes an AI platform using baseline DM to predict BC patients’ responses to NACT. The initial AI performance indicated the potential to aid in clinical decision-making. In order to continue exploring the clinical utility of AI in predicting responses to NACT for BC, further research, including refining the methodology and a larger sample size, is warranted.

Key Points

• We aimed to answer the following question: Prior to initiation of neoadjuvant chemotherapy, can artificial intelligence (AI) applied to digital mammograms (DM) predict breast tumour response?

• DMs contain information that AI can make use of for predicting pathological complete (pCR) response after neoadjuvant chemotherapy for breast cancer.

• By developing an AI system designed to focus on relevant parts of the DM, fully automatic pCR prediction can be done well enough to potentially aid in clinical decision-making.

Contrast-Enhanced Spectral Mammography Assessment of Patients Treated with Neoadjuvant Chemotherapy for Breast Cancer

Background: Evaluating the tumor response to neoadjuvant chemotherapy is key to planning further therapy of breast cancer. Our study aimed to evaluate the effectiveness of low-energy and subtraction contrast-enhanced spectral mammography (CESM) images in the detection of complete response (CR) for neoadjuvant chemotherapy (NAC) in breast cancer. Methods: A total of 63 female patients were qualified for our retrospective analysis. Low-energy and subtraction CESM images just before the beginning of NAC and as a follow-up examination 2 weeks before the end of chemotherapy were compared with one another and assessed for compliance with the postoperative histopathological examination (HP). The response to preoperative chemotherapy was evaluated based on the RECIST 1.1 criteria (Response Evaluation Criteria in Solid Tumors). Results: Low-energy images tend to overestimate residual lesions (6.28 mm) and subtraction images tend to underestimate them (2.75 mm). The sensitivity of low-energy images in forecasting CR amounted to 33.33%, while the specificity was 92.86%. In the case of subtraction CESM, the sensitivity amounted to 85.71% and the specificity to 71.42%. Conclusions: CESM is characterized by high sensitivity in the assessment of CR after NAC. The use of only morphological assessment is insufficient. CESM correlates well with the size of residual lesions on histopathological examination but tends to underestimate the dimensions.

Early prediction of neoadjuvant chemotherapy response by exploiting a transfer learning approach on breast DCE-MRIs

The dynamic contrast-enhanced MR imaging plays a crucial role in evaluating the effectiveness of neoadjuvant chemotherapy (NAC) even since its early stage through the prediction of the final pathological complete response (pCR). In this study, we proposed a transfer learning approach to predict if a patient achieved pCR (pCR) or did not (non-pCR) by exploiting, separately or in combination, pre-treatment and early-treatment exams from I-SPY1 TRIAL public database. First, low-level features, i.e., related to local structure of the image, were automatically extracted by a pre-trained convolutional neural network (CNN) overcoming manual feature extraction. Next, an optimal set of most stable features was detected and then used to design an SVM classifier. A first subset of patients, called fine-tuning dataset (30 pCR; 78 non-pCR), was used to perform the optimal choice of features. A second subset not involved in the feature selection process was employed as an independent test (7 pCR; 19 non-pCR) to validate the model. By combining the optimal features extracted from both pre-treatment and early-treatment exams with some clinical features, i.e., ER, PgR, HER2 and molecular subtype, an accuracy of 91.4% and 92.3%, and an AUC value of 0.93 and 0.90, were returned on the fine-tuning dataset and the independent test, respectively. Overall, the low-level CNN features have an important role in the early evaluation of the NAC efficacy by predicting pCR. The proposed model represents a first effort towards the development of a clinical support tool for an early prediction of pCR to NAC.