Multiparametric magnetic resonance imaging for predicting pathological response after the first cycle of neoadjuvant chemotherapy in breast cancer

AI-Generated Annotations Dataset for Diverse Cancer Radiology Collections in NCI Image Data Commons

The National Cancer Institute (NCI) Image Data Commons (IDC) offers publicly available cancer radiology collections for cloud computing, crucial for developing advanced imaging tools and algorithms. Despite their potential, these collections are minimally annotated; only 4% of DICOM studies in collections considered in the project had existing segmentation annotations. This project increases the quantity of segmentations in various IDC collections. We produced high-quality, AI-generated imaging annotations dataset of tissues, organs, and/or cancers for 11 distinct IDC image collections. These collections contain images from a variety of modalities, including computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET). The collections cover various body parts, such as the chest, breast, kidneys, prostate, and liver. A portion of the AI annotations were reviewed and corrected by a radiologist to assess the performance of the AI models. Both the AI's and the radiologist's annotations were encoded in conformance to the Digital Imaging and Communications in Medicine (DICOM) standard, allowing for seamless integration into the IDC collections as third-party analysis collections. All the models, images and annotations are publicly accessible.

Advancing personalized oncology: a systematic review on the integration of artificial intelligence in monitoring neoadjuvant treatment for breast cancer patients

PURPOSE

Despite suffering from the same disease, each patient exhibits a distinct microbiological profile and variable reactivity to prescribed treatments. Most doctors typically use a standardized treatment approach for all patients suffering from a specific disease. Consequently, the challenge lies in the effectiveness of this standardized treatment and in adapting it to each individual patient. Personalized medicine is an emerging field in which doctors use diagnostic tests to identify the most effective medical treatments for each patient. Prognosis, disease monitoring, and treatment planning rely on manual, error-prone methods. Artificial intelligence (AI) uses predictive techniques capable of automating prognostic and monitoring processes, thus reducing the error rate associated with conventional methods.

METHODS

This paper conducts an analysis of current literature, encompassing the period from January 2015 to 2023, based on Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA).

RESULTS

In assessing 25 pertinent studies concerning predicting neoadjuvant treatment (NAT) response in breast cancer (BC) patients, the studies explored various imaging modalities (Magnetic Resonance Imaging, Ultrasound, etc.), evaluating results based on accuracy, sensitivity, and area under the curve. Additionally, the technologies employed, such as machine learning (ML), deep learning (DL), statistics, and hybrid models, were scrutinized. The presentation of datasets used for predicting complete pathological response (PCR) was also considered.

CONCLUSION

This paper seeks to unveil crucial insights into the application of AI techniques in personalized oncology, particularly in the monitoring and prediction of responses to NAT for BC patients. Finally, the authors suggest avenues for future research into AI-based monitoring systems.

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.

Non-contrast-enhanced breast MRI for evaluation of tumor volume change after neoadjuvant chemotherapy

PURPOSE

Three-dimensional contrast-enhanced magnetic resonance imaging (3D-Ce-MRI) is a most powerful tool for evaluation of neoadjuvant chemotherapy (NAC). However, the use of contrast agent is invasive, expensive, and time consuming, Thus, contrast agent-free imaging is preferable. We aimed to investigate the tumor volume change after NAC using maximum intensity projection diffusion-weighted image (MIP-DWI) and 3D-Ce-MRI.

METHOD

We finally enrolled 55 breast cancer patients who underwent NAC in 2018. All MRI analyses were performed using SYNAPSE VINCENT® medical imaging system (Fujifilm Medical, Tokyo, Japan). We evaluated the tumor volumes before, during, and after NAC. Tumor volume before NAC on 3D-Ce-MRI was termed Pre-CE and those during and after NAC were termed Post-CE. The observer raised the lower end of the window width until the tumor was clearly visible and then manually deleted the non-tumor tissues. A month thereafter, the same observer who was blinded to the 3D-Ce-MRI results randomly evaluated the tumor volumes (Pre-DWI and Post-DWI) using MIP-DWI with the same method. Tumor volume change between ΔCE (Pre-CE - Post-CE/Pre-CE) and ΔDWI (Pre-DWI - Post-DWI/Pre-DWI) and the processing time for both methods (Time-DWI and Time-CE) were compared.

RESULTS

We enrolled 55 patients. Spearman's rho between ΔDWI and ΔCE for pure mass lesions, and non-mass enhancement (NME) was 0.89 (p < 0.01), 0.63(p < 0.01) respectively. Time-DWI was significantly shorter than Time-CE (41.3 ± 21.2 and 199.5 ± 98.3 respectively, p < 0.01).

CONCLUSIONS

Non-contrast-enhanced Breast MRI enables appropriate and faster evaluation of tumor volume change after NAC than 3D-Ce-MRI especially for mass lesions.

Multiparametric MRI-based radiomic models for early prediction of response to neoadjuvant systemic therapy in triple-negative breast cancer

Triple-negative breast cancer (TNBC) is often treated with neoadjuvant systemic therapy (NAST). We investigated if radiomic models based on multiparametric Magnetic Resonance Imaging (MRI) obtained early during NAST predict pathologic complete response (pCR). We included 163 patients with stage I-III TNBC with multiparametric MRI at baseline and after 2 (C2) and 4 cycles of NAST. Seventy-eight patients (48%) had pCR, and 85 (52%) had non-pCR. Thirty-six multivariate models combining radiomic features from dynamic contrast-enhanced MRI and diffusion-weighted imaging had an area under the receiver operating characteristics curve (AUC) > 0.7. The top-performing model combined 35 radiomic features of relative difference between C2 and baseline; had an AUC = 0.905 in the training and AUC = 0.802 in the testing set. There was high inter-reader agreement and very similar AUC values of the pCR prediction models for the 2 readers. Our data supports multiparametric MRI-based radiomic models for early prediction of NAST response in TNBC.

Changes in Intratumor Blood Flow After Carbon-Ion Radiation Therapy for Early-Stage Breast Cancer

Purpose

This study aimed to quantify the changes in intratumoral blood flow after carbon-ion radiation therapy (CIRT) for early-stage breast cancer and analyze their clinical significance.

Patients and Methods

We included 38 patients with early-stage breast cancer who underwent CIRT. Dynamic imaging was performed using a 3T superconducting magnetic resonance scanner to quantify the washin index (idx), which reflects contrast uptake, and washout idx, which reflects the rate of contrast washout from tumor tissue. The changes in the apparent diffusion coefficient, washin idx, and washout idx were examined before CIRT and at 1 and 3 months after treatment. Clinical factors and imaging features were examined using univariate and receiver operating characteristic curve analyses to identify factors predicting clinical complete response (cCR).

Results

The median observation period after CIRT was 51 (range: 12-122) months. During the observation period, 31 of the 38 patients achieved cCR, and 22 achieved cCR within 12 months. Tumor size (P < .001), washin idx (P = .043), and washout idx (P < .001) decreased significantly 1-month after CIRT. In contrast, the apparent diffusion coefficient values (P < .001) increased significantly 1-month after CIRT. Univariate analysis suggested that the washin idx after 1 and 3 months of CIRT was associated with cCR by 12 months post-CIRT (P = .028 and .021, respectively). No other parameters were associated with cCR by 12 months post-CIRT. Furthermore, receiver operating characteristic curve analyses showed that the area under the curve values of washin idx after 1 and 3 months of CIRT was 0.78 (specificity 75%, sensitivity 80%) and 0.73 (specificity 75%, sensitivity 71%), respectively.

Conclusion

Tumor changes can be quantified early after CIRT using contrast-enhanced magnetic resonance imaging in patients with breast cancer. Washin idx values 1 and 3 months after CIRT were associated with cCR within 12 months post-CIRT.

Multitask Deep Learning-Based Whole-Process System for Automatic Diagnosis of Breast Lesions and Axillary Lymph Node Metastasis Discrimination from Dynamic Contrast-Enhanced-MRI: A Multicenter Study

BACKGROUND

Accurate diagnosis of breast lesions and discrimination of axillary lymph node (ALN) metastases largely depend on radiologist experience.

PURPOSE

To develop a deep learning-based whole-process system (DLWPS) for segmentation and diagnosis of breast lesions and discrimination of ALN metastasis.

STUDY TYPE

Retrospective.

POPULATION

1760 breast patients, who were divided into training and validation sets (1110 patients), internal (476 patients), and external (174 patients) test sets.

FIELD STRENGTH/SEQUENCE

3.0T/dynamic contrast-enhanced (DCE)-MRI sequence.

ASSESSMENT

DLWPS was developed using segmentation and classification models. The DLWPS-based segmentation model was developed by the U-Net framework, which combined the attention module and the edge feature extraction module. The average score of the output scores of three networks was used as the result of the DLWPS-based classification model. Moreover, the radiologists' diagnosis without and with the DLWPS-assistance was explored. To reveal the underlying biological basis of DLWPS, genetic analysis was performed based on RNA-sequencing data.

STATISTICAL TESTS

Dice similarity coefficient (DI), area under receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and kappa value.

RESULTS

The segmentation model reached a DI of 0.828 and 0.813 in the internal and external test sets, respectively. Within the breast lesions diagnosis, the DLWPS achieved AUCs of 0.973 in internal test set and 0.936 in external test set. For ALN metastasis discrimination, the DLWPS achieved AUCs of 0.927 in internal test set and 0.917 in external test set. The agreement of radiologists improved with the DLWPS-assistance from 0.547 to 0.794, and from 0.848 to 0.892 in breast lesions diagnosis and ALN metastasis discrimination, respectively. Additionally, 10 breast cancers with ALN metastasis were associated with pathways of aerobic electron transport chain and cytoplasmic translation.

DATA CONCLUSION

The performance of DLWPS indicates that it can promote radiologists in the judgment of breast lesions and ALN metastasis and nonmetastasis.

LEVEL OF EVIDENCE

4 TECHNICAL EFFICACY STAGE: 3.

Deep Semisupervised Transfer Learning for Fully Automated Whole-Body Tumor Quantification and Prognosis of Cancer on PET/CT

Automatic detection and characterization of cancer are important clinical needs to optimize early treatment. We developed a deep, semisupervised transfer learning approach for fully automated, whole-body tumor segmentation and prognosis on PET/CT. Methods: This retrospective study consisted of 611 18F-FDG PET/CT scans of patients with lung cancer, melanoma, lymphoma, head and neck cancer, and breast cancer and 408 prostate-specific membrane antigen (PSMA) PET/CT scans of patients with prostate cancer. The approach had a nnU-net backbone and learned the segmentation task on 18F-FDG and PSMA PET/CT images using limited annotations and radiomics analysis. True-positive rate and Dice similarity coefficient were assessed to evaluate segmentation performance. Prognostic models were developed using imaging measures extracted from predicted segmentations to perform risk stratification of prostate cancer based on follow-up prostate-specific antigen levels, survival estimation of head and neck cancer by the Kaplan-Meier method and Cox regression analysis, and pathologic complete response prediction of breast cancer after neoadjuvant chemotherapy. Overall accuracy and area under the receiver-operating-characteristic (AUC) curve were assessed. Results: Our approach yielded median true-positive rates of 0.75, 0.85, 0.87, and 0.75 and median Dice similarity coefficients of 0.81, 0.76, 0.83, and 0.73 for patients with lung cancer, melanoma, lymphoma, and prostate cancer, respectively, on the tumor segmentation task. The risk model for prostate cancer yielded an overall accuracy of 0.83 and an AUC of 0.86. Patients classified as low- to intermediate- and high-risk had mean follow-up prostate-specific antigen levels of 18.61 and 727.46 ng/mL, respectively (P < 0.05). The risk score for head and neck cancer was significantly associated with overall survival by univariable and multivariable Cox regression analyses (P < 0.05). Predictive models for breast cancer predicted pathologic complete response using only pretherapy imaging measures and both pre- and posttherapy measures with accuracies of 0.72 and 0.84 and AUCs of 0.72 and 0.76, respectively. Conclusion: The proposed approach demonstrated accurate tumor segmentation and prognosis in patients across 6 cancer types on 18F-FDG and PSMA PET/CT scans.

Early prediction of pathologic complete response of breast cancer after neoadjuvant chemotherapy using longitudinal ultrafast dynamic contrast-enhanced MRI

PURPOSE

The purpose of this study was to evaluate the temporal trends of ultrafast dynamic contrast-enhanced (DCE)-MRI during neoadjuvant chemotherapy (NAC) and to investigate whether the changes in DCE-MRI parameters could early predict pathologic complete response (pCR) of breast cancer.

MATERIALS AND METHODS

This longitudinal study prospectively recruited consecutive participants with breast cancer who underwent ultrafast DCE-MRI examinations before treatment and after two, four, and six NAC cycles between February 2021 and February 2022. Five ultrafast DCE-MRI parameters (maximum slope [MS], time-to-peak [TTP], time-to-enhancement [TTE], peak enhancement intensity [PEI], and initial area under the curve in 60 s [iAUC]) and tumor size were measured at each timepoint. The changes in parameters between each pair of adjacent timepoints were additionally measured and compared between the pCR and non-pCR groups. Longitudinal data were analyzed using generalized estimating equations. The performance for predicting pCR was assessed using area under the receiver operating characteristic curve (AUC).

RESULTS

Sixty-seven women (mean age, 50 ± 8 [standard deviation] years; age range: 25-69 years) were included, 19 of whom achieved pCR. MS, PEI, iAUC, and tumor size decreased, while TTP increased during NAC (all P < 0.001). The AUC (0.92; 95% confidence interval [CI]: 0.83-0.97) of the model incorporating ultrafast DCE-MRI parameter change values (from timepoints 1 to 2) and clinicopathologic characteristics was greater than that of the clinical model (AUC, 0.79; 95% CI: 0.68-0.88) and ultrafast DCE-MRI parameter model at timepoint 2 when combined with clinicopathologic characteristics (AUC, 0.82; 95% CI: 0.71-0.90) (P = 0.01 and 0.02).

CONCLUSION

Early changes in ultrafast DCE-MRI parameters after NAC combined with clinicopathologic characteristics could serve as predictive markers of pCR of breast cancer.

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.

Artificial intelligence in breast imaging: Current situation and clinical challenges

Breast cancer ranks among the most prevalent malignant tumours and is the primary contributor to cancer-related deaths in women. Breast imaging is essential for screening, diagnosis, and therapeutic surveillance. With the increasing demand for precision medicine, the heterogeneous nature of breast cancer makes it necessary to deeply mine and rationally utilize the tremendous amount of breast imaging information. With the rapid advancement of computer science, artificial intelligence (AI) has been noted to have great advantages in processing and mining of image information. Therefore, a growing number of scholars have started to focus on and research the utility of AI in breast imaging. Here, an overview of breast imaging databases and recent advances in AI research are provided, the challenges and problems in this field are discussed, and then constructive advice is further provided for ongoing scientific developments from the perspective of the National Natural Science Foundation of China.

A review of quantitative diffusion-weighted MR imaging for breast cancer: Towards noninvasive biomarker

Quantitative diffusion-weighted imaging (DWI) is an important adjunct to conventional breast MRI and shows promise as a noninvasive biomarker of breast cancer in multiple clinical scenarios, from the discrimination of benign and malignant lesions, prediction, and evaluation of treatment response to a prognostic assessment of breast cancer. Various quantitative parameters are derived from different DWI models based on special prior knowledge and assumptions, have different meanings, and are easy to confuse. In this review, we describe the quantitative parameters derived from conventional and advanced DWI models commonly used in breast cancer and summarize the promising clinical applications of these quantitative parameters. Although promising, it is still challenging for these quantitative parameters to become clinically useful noninvasive biomarkers in breast cancer, as multiple factors may result in variations in quantitative parameter measurements. Finally, we briefly describe some considerations regarding the factors that cause variations.

Multiround Transfer Learning and Modified Generative Adversarial Network for Lung Cancer Detection

Lung cancer has been the leading cause of cancer death for many decades. With the advent of artificial intelligence, various machine learning models have been proposed for lung cancer detection (LCD). Typically, challenges in building an accurate LCD model are the small-scale datasets, the poor generalizability to detect unseen data, and the selection of useful source domains and prioritization of multiple source domains for transfer learning. In this paper, a multiround transfer learning and modified generative adversarial network (MTL-MGAN) algorithm is proposed for LCD. The MTL transfers the knowledge between the prioritized source domains and target domain to get rid of exhaust search of datasets prioritization among multiple datasets, maximizing the transferability with a multiround transfer learning process, and avoiding negative transfer via customization of loss functions in the aspects of domain, instance, and feature. In regard to the MGAN, it not only generates additional training data but also creates intermediate domains to bridge the gap between the source domains and target domains. 10 benchmark datasets are chosen for the performance evaluation and analysis of the MTL-MGAN. The proposed algorithm has significantly improved the accuracy compared with related works. To examine the contributions of the individual components of the MTL-MGAN, ablation studies are conducted to confirm the effectiveness of the prioritization algorithm, the MTL, the negative transfer avoidance via loss functions, and the MGAN. The research implications are to confirm the feasibility of multiround transfer learning to enhance the optimal solution of the target model and to provide a generic approach to bridge the gap between the source domain and target domain using MGAN.

Analysis of simplicial complexes to determine when to sample for quantitative DCE MRI of the breast

PURPOSE

A method is presented to select the optimal time points at which to measure DCE-MRI signal intensities, leaving time in the MR exam for high-spatial resolution image acquisition.

THEORY

Simplicial complexes are generated from the Kety-Tofts model pharmacokinetic parameters Ktrans and ve . A geometric search selects optimal time points for accurate estimation of perfusion parameters.

METHODS

The DCE-MRI data acquired in women with invasive breast cancer (N = 27) were used to retrospectively compare parameter maps fit to full and subsampled time courses. Simplicial complexes were generated for a fixed range of Kety-Tofts model parameters and for the parameter ranges weighted by estimates from the fully sampled data. The largest-area manifolds determined the optimal three time points for each case. Simulations were performed along with retrospectively subsampled data fits. The agreement was computed between the model parameters fit to three points and those fit to all points.

RESULTS

The optimal three-point sample times were from the data-informed simplicial complex analysis and determined to be 65, 204, and 393 s after arrival of the contrast agent to breast tissue. In the patient data, tumor-median parameter values fit using all points and the three selected time points agreed with concordance correlation coefficients of 0.97 for Ktrans and 0.67 for ve .

CONCLUSION

It is possible to accurately estimate pharmacokinetic parameters from three properly selected time points inserted into a clinical DCE-MRI breast exam. This technique can provide guidance on when to capture images for quantitative data between high-spatial-resolution DCE-MRI images.

Machine learning with textural analysis of longitudinal multiparametric MRI and molecular subtypes accurately predicts pathologic complete response in patients with invasive breast cancer

PURPOSE

To predict pathological complete response (pCR) after neoadjuvant chemotherapy using extreme gradient boosting (XGBoost) with MRI and non-imaging data at multiple treatment timepoints.

MATERIAL AND METHODS

This retrospective study included breast cancer patients (n = 117) who underwent neoadjuvant chemotherapy. Data types used included tumor ADC values, diffusion-weighted and dynamic-contrast-enhanced MRI at three treatment timepoints, and patient demographics and tumor data. GLCM textural analysis was performed on MRI data. An extreme gradient boosting machine learning algorithm was used to predict pCR. Prediction performance was evaluated using the area under the curve (AUC) of the receiver operating curve along with precision and recall.

RESULTS

Prediction using texture features of DWI and DCE images at multiple treatment time points (AUC = 0.871; 95% CI: (0.768, 0.974; p<0.001) and (AUC = 0.903 95% CI: 0.854, 0.952; p<0.001) respectively), outperformed that using mean tumor ADC (AUC = 0.850 (95% CI: 0.764, 0.936; p<0.001)). The AUC using all MRI data was 0.933 (95% CI: 0.836, 1.03; p<0.001). The AUC using non-MRI data was 0.919 (95% CI: 0.848, 0.99; p<0.001). The highest AUC of 0.951 (95% CI: 0.909, 0.993; p<0.001) was achieved with all MRI and all non-MRI data at all time points as inputs.

CONCLUSION

Using XGBoost on extracted GLCM features and non-imaging data accurately predicts pCR. This early prediction of response can minimize exposure to toxic chemotherapy, allowing regimen modification mid-treatment and ultimately achieving better outcomes.

Early prediction of pathological complete response to neoadjuvant chemotherapy combining DCE-MRI and apparent diffusion coefficient values in breast Cancer

INTRODUCTION

Improving the early prediction of neoadjuvant chemotherapy (NAC) efficacy in breast cancer can lead to an improved prediction of the final prognosis of patients, which would be useful for promoting individualized treatment. This study aimed to explore the value of the combination of dynamic contrast-enhanced (DCE)-MRI parameters and apparent diffusion coefficient (ADC) values in the early prediction of pathological complete response (pCR) to NAC for breast cancer.

METHODS

A total of 119 (range, 28-69 years) patients with biopsy-proven breast cancer who received two cycles of NAC before breast surgery were retrospectively enrolled from our hospital database. Patients were divided into pCR and non pCR groups according to their pathological responses; a total of 24 patients achieved pCR, while 95 did not. The quantitative (K^trans; K_ep; V_e; IAUC) and semiquantitative parameters (W-in; W-out; TTP) of DCE-MRI that were significantly different between groups were combined with ADC values to explore their value in the early prediction of pCR to NAC for breast cancer. The independent T test was performed to compare the differences in DCE-MRI parameters and ADC values between the two groups. Receiver operating characteristic (ROC) curves were plotted, and the area under the ROC curve (AUC), sensitivity and specificity were calculated to evaluate the performance of the prediction.

RESULTS

The K^trans, K_ep, IAUC, ADC, W-in and TTP values were significantly different between the pCR and non pCR groups after NAC. The AUC (0.845) and specificity (95.79%) of the combined K^trans, K_ep, IAUC and ADC values were both higher than those of the individual parameters. The combination of W-in, TTP and ADC values had the highest AUC value (0.886) in predicting pCR, with a sensitivity and specificity of 87.5% and 82.11%, respectively.

CONCLUSIONS

The results suggested that the combination of ADC values and quantitative and semiquantitative DCE-MRI parameters, especially the combination of W-in, TTP, and ADC values, may improve the early prediction of pCR in breast cancer.

Predicting the Early Response to Neoadjuvant Therapy with Breast MR Morphological, Functional and Relaxometry Features-A Pilot Study

Aim: To evaluate the role of MR relaxometry and derived proton density analysis in the prediction of early treatment response after two cycles of neoadjuvant therapy (NAT), in patients with breast cancer. Methods: This was a prospective study that included 59 patients with breast cancer, who underwent breast MRI prior (MRI1) and after two cycles of NAT (MRI2). The MRI1 included a sequential acquisition with five different TE’s (50, 100, 150, 200 and 250 ms) and a TR of 5000 ms. Post-processing was used to obtain the T2 relaxometry map from the MR acquisition. The tumor was delineated and seven relaxometry and proton density parameters were extracted. Additional histopathology data, T2 features and ADC were included. The response to NAT was reported based on the MRI2 as responders: partial response (>30% decreased size) and complete response (no visible tumor stable disease (SD); and non-responders: stable disease or progression (>20% increased size). Statistics was done using Medcalc software. Results: There were 50 (79.3%) patients with response and 13 (20.7%) non-responders to NAT. Age, histologic type, “in situ” component, tumor grade, estrogen and progesterone receptors, ki67% proliferation index and HER2 status were not associated with NAT response (all p > 0.05). The nodal status (N) 0 was associated with early response, while N2 was associated with non-response (p = 0.005). The tumor (T) and metastatic (M) stage were not statistically significant associated with response (p > 0.05). The margins, size and ADC values were not associated with NAT response (p-value > 0.05). The T2 min relaxometry value was associated with response (p = 0.017); a cut-off value of 53.58 obtained 86% sensitivity (95% CI 73.3−94.2), 69.23 specificity (95% CI 38.6−90.9), with an AUC = 0.715 (p = 0.038). The combined model (T2 min and N stage) achieved an AUC of 0.826 [95% CI: 0.66−0.90, p-value < 0.001]. Conclusions: MR relaxometry may be a useful tool in predicting early treatment response to NAT in breast cancer patients.

Radiomic and Volumetric Measurements as Clinical Trial Endpoints—A Comprehensive Review

Simple Summary

The extraction of quantitative data from standard-of-care imaging modalities offers opportunities to improve the relevance and salience of imaging biomarkers used in drug development. This review aims to identify the challenges and opportunities for discovering new imaging-based biomarkers based on radiomic and volumetric assessment in the single-site solid tumor sites: breast cancer, rectal cancer, lung cancer and glioblastoma. Developing approaches to harmonize three essential areas: segmentation, validation and data sharing may expedite regulatory approval and adoption of novel cancer imaging biomarkers.

Abstract

Clinical trials for oncology drug development have long relied on surrogate outcome biomarkers that assess changes in tumor burden to accelerate drug registration (i.e., Response Evaluation Criteria in Solid Tumors version 1.1 (RECIST v1.1) criteria). Drug-induced reduction in tumor size represents an imperfect surrogate marker for drug activity and yet a radiologically determined objective response rate is a widely used endpoint for Phase 2 trials. With the addition of therapies targeting complex biological systems such as immune system and DNA damage repair pathways, incorporation of integrative response and outcome biomarkers may add more predictive value. We performed a review of the relevant literature in four representative tumor types (breast cancer, rectal cancer, lung cancer and glioblastoma) to assess the preparedness of volumetric and radiomics metrics as clinical trial endpoints. We identified three key areas—segmentation, validation and data sharing strategies—where concerted efforts are required to enable progress of volumetric- and radiomics-based clinical trial endpoints for wider clinical implementation.

Differences Between Ipsilateral and Contralateral Early Parenchymal Enhancement Kinetics Predict Response of Breast Cancer to Neoadjuvant Therapy

RATIONALE AND OBJECTIVES

To determine whether kinetics measured with ultrafast dynamic contrast-enhanced magnetic resonance imaging in tumor and normal parenchyma pre- and post-neoadjuvant therapy (NAT) can predict the response of breast cancer to NAT.

MATERIALS AND METHODS

Twenty-four patients with histologically confirmed invasive breast cancer were enrolled. They were scanned with ultrafast dynamic contrast-enhanced magnetic resonance imaging (3-7 seconds/frame) pre- and post-NAT. Four kinetic parameters were calculated in the segmented tumors, and ipsi- and contra-lateral normal parenchyma: (1) tumor (tSE30) or background parenchymal relative enhancement at 30 seconds (BPE30), (2) maximum relative enhancement slope (MaxSlope), (3) bolus arrival time (BAT), and (4) area under relative signal enhancement curve for the initial 30 seconds (AUC30). The tumor kinetics and the differences between ipsi- and contra-lateral parenchymal kinetics were compared for patients achieving pathologic complete response (pCR) vs those who had residual disease after NAT. The chi-squared test and two-sided t-test were used for baseline demographics. The Wilcoxon rank sum test and one-way analysis of variance were used for differential responses to therapy.

RESULTS

Patients with similar pre-NAT mean BPE30, median BAT and mean AUC30 in the ipsi- and contralateral normal parenchyma were more likely to achieve pCR following NAT (p < 0.02). Patients classified as having residual cancer burden (RCB) II after NAT showed higher post-NAT tSE30 and tumor AUC30 and higher post-NAT MaxSlope in ipsilateral normal parenchyma compared to those classified as RCB I or pCR (p < 0.05).

CONCLUSION

Bilateral asymmetry in normal parenchyma could predict treatment outcome prior to NAT. Post-NAT tumor kinetics could evaluate the aggressiveness of residual tumor.

A survey by the European Society of Breast Imaging on the implementation of breast diffusion-weighted imaging in clinical practice

OBJECTIVES

To perform a survey among all European Society of Breast Imaging (EUSOBI) radiologist members to gather representative data regarding the clinical use of breast DWI.

METHODS

An online questionnaire was developed by two board-certified radiologists, reviewed by the EUSOBI board and committees, and finally distributed among EUSOBI active and associated (not based in Europe) radiologist members. The questionnaire included 20 questions pertaining to technical preferences (acquisition time, magnet strength, breast coils, number of b values), clinical indications, imaging evaluation, and reporting. Data were analyzed using descriptive statistics, the Chi-square test of independence, and Fisher's exact test.

RESULTS

Of 1411 EUSOBI radiologist members, 275/1411 (19.5%) responded. Most (222/275, 81%) reported using DWI as part of their routine protocol. Common indications for DWI include lesion characterization (using an ADC threshold of 1.2-1.3 × 10-3 mm2/s) and prediction of response to chemotherapy. Members most commonly acquire two separate b values (114/217, 53%), with b value = 800 s/mm2 being the preferred value for appraisal among those acquiring more than two b values (71/171, 42%). Most did not use synthetic b values (169/217, 78%). While most mention hindered diffusion in the MRI report (161/213, 76%), only 142/217 (57%) report ADC values.

CONCLUSION

The utilization of DWI in clinical practice among EUSOBI radiologists who responded to the survey is generally in line with international recommendations, with the main application being the differentiation of benign and malignant enhancing lesions, treatment response assessment, and prediction of response to chemotherapy. Report integration of qualitative and quantitative DWI data is not uniform.

KEY POINTS

• Clinical performance of breast DWI is in good agreement with the current recommendations of the EUSOBI International Breast DWI working group. • Breast DWI applications in clinical practice include the differentiation of benign and malignant enhancing, treatment response assessment, and prediction of response to chemotherapy. • Report integration of DWI results is not uniform.

Evaluation of Monoexponential, Stretched-Exponential and Intravoxel Incoherent Motion MRI Diffusion Models in Early Response Monitoring to Neoadjuvant Chemotherapy in Patients With Breast Cancer-A Preliminary Study

BACKGROUND

There has been a growing interest in exploring the applications of stretched-exponential (SEM) and intravoxel incoherent motion (IVIM) models of diffusion-weighted imaging (DWI) in breast imaging, with the focus on differentiation of breast lesions. However, the use of SEM and IVIM models to predict early response to neoadjuvant chemotherapy (NACT) has received less attention.

PURPOSE

To investigate the value of monoexponential, SEM, and IVIM models to predict early response to NACT in patients with primary breast cancer.

STUDY TYPE

Prospective.

POPULATION

Thirty-seven patients with primary breast cancer (aged 46 ± 11 years) due to undergo NACT.

FIELD STRENGTH/SEQUENCES

A 1.5-T MR scanner, T1 -weighted three-dimensional spoiled gradient-echo, two-dimensional single-shot spin-echo echo-planar imaging sequence (DWI) at six b-values (0-800 s mm-2 ).

ASSESSMENT

Tumor volume, apparent diffusion coefficient, tissue diffusion (Dt ), pseudo-diffusion coefficient (Dp ), perfusion fraction (f), distributed diffusion coefficient, and alpha (α) were extracted, following volumetric sampling of the tumors, at three time-points: pretreatment, post one and three cycles of NACT.

STATISTICAL TESTS

Mann-Whitney test, receiver operating characteristic (ROC) curve. Statistical significance level was P < 0.05.

RESULTS

Following NACT, 17 patients were determined to be pathological responders and 20 nonresponders. Tumor volume was significantly larger in nonresponders at each MRI time-point and demonstrated reasonable performance in predicting response (area under the ROC curve [AUC] = 0.83-0.87). No significant differences between groups were found in the diffusion coefficients at each time-point (P = 0.09-1). The parameters α (SEM), f, and f × Dp (IVIM) were able to differentiate between response groups after one cycle of NACT (AUC = 0.73, 0.72, and 0.74, respectively).

CONCLUSION

Diffusion coefficients derived from the monoexponential, SEM, and IVIM models did not predict pathological response. However, the IVIM-derived parameters f and f × Dp and the SEM-derived parameter α were able to predict response to NACT in breast cancer patients following one cycle of NACT.

LEVEL OF EVIDENCE

2 TECHNICAL EFFICACY STAGE: 2.

MRI-Based Digital Models Forecast Patient-Specific Treatment Responses to Neoadjuvant Chemotherapy in Triple-Negative Breast Cancer

Triple-negative breast cancer (TNBC) is persistently refractory to therapy, and methods to improve targeting and evaluation of responses to therapy in this disease are needed. Here, we integrate quantitative MRI data with biologically based mathematical modeling to accurately predict the response of TNBC to neoadjuvant systemic therapy (NAST) on an individual basis. Specifically, 56 patients with TNBC enrolled in the ARTEMIS trial (NCT02276443) underwent standard-of-care doxorubicin/cyclophosphamide (A/C) and then paclitaxel for NAST, where dynamic contrast-enhanced MRI and diffusion-weighted MRI were acquired before treatment and after two and four cycles of A/C. A biologically based model was established to characterize tumor cell movement, proliferation, and treatment-induced cell death. Two evaluation frameworks were investigated using: (i) images acquired before and after two cycles of A/C for calibration and predicting tumor status after A/C, and (ii) images acquired before, after two cycles, and after four cycles of A/C for calibration and predicting response following NAST. For Framework 1, the concordance correlation coefficients between the predicted and measured patient-specific, post-A/C changes in tumor cellularity and volume were 0.95 and 0.94, respectively. For Framework 2, the biologically based model achieved an area under the receiver operator characteristic curve of 0.89 (sensitivity/specificity = 0.72/0.95) for differentiating pathological complete response (pCR) from non-pCR, which is statistically superior (P &lt; 0.05) to the value of 0.78 (sensitivity/specificity = 0.72/0.79) achieved by tumor volume measured after four cycles of A/C. Overall, this model successfully captured patient-specific, spatiotemporal dynamics of TNBC response to NAST, providing highly accurate predictions of NAST response.

SIGNIFICANCE

Integrating MRI data with biologically based mathematical modeling successfully predicts breast cancer response to chemotherapy, suggesting digital twins could facilitate a paradigm shift from simply assessing response to predicting and optimizing therapeutic efficacy.

Prospective Evaluation of Ultrafast Breast MRI for Predicting Pathologic Response after Neoadjuvant Therapies

Background Ultrafast dynamic contrast-enhanced (DCE) MRI parameters are associated with breast cancer aggressiveness. However, the role of these parameters as predictive biomarkers for pathologic response after neoadjuvant chemotherapy (NAC) has been poorly investigated. Purpose To assess whether semiquantitative perfusion parameters calculated at initial ultrafast DCE MRI are associated with early prediction for pathologic response after NAC in participants with breast cancer. Materials and Methods This prospective single-center study included consecutive women with nonmetastatic invasive breast cancer treated with NAC followed by surgery who underwent initial ultrafast DCE MRI between December 2020 and August 2021. Six semiquantitative ultrafast DCE MRI parameters were calculated for each participant from the fitted time-signal intensity curve. Multivariable logistic regression was used to identify independent predictors of pathologic complete response (pCR) and residual cancer burden (RCB). Results Fifty women (mean age, 49 years ± 12 [SD]) were included in the study; 20 achieved pCR and 25 achieved low RCB (RCB-0 and I). A wash-in slope (WIS) cutoff value of 1.6% per second had a sensitivity of 94% (17 of 18 participants) and a specificity of 59% (19 of 32 participants) for pCR. A WIS of more than 1.6% per second (odds ratio [OR], 8.4 [95% CI: 1.5, 48.2]; P = .02), human epidermal growth factor receptor 2 (HER2) positivity (OR, 6.3 [95% CI: 1.5, 27.4]; P = .01), and tumor-infiltrating lymphocytes of more than 10% (OR, 6.9 [95% CI: 1.3, 37.7]; P = .03) were independent predictive factors of pCR. The area under the receiver operating characteristic curve of the three-component model, which included WIS, tumor-infiltrating lymphocytes, and HER2 positivity, was 0.92 (95% CI: 0.84, 0.99). A WIS of more than 1.6% per second was associated with higher pCR rates in the HER2-positive (OR, 21.7 [95% CI: 1.8, 260.6]; P = .02) breast cancer subgroup. For luminal HER2-negative and triple-negative breast cancers, a WIS of more than 1.6% per second was associated with low RCB (OR, 11.0 [95% CI: 1.1, 106.4]; P = .04). Conclusion The wash-in slope (WIS) assessment at initial ultrafast dynamic contrast-enhanced MRI may be used to predict pathologic complete response (pCR) in participants with breast cancer. The WIS value was used to identify two subsets of human epidermal growth factor receptor 2-positive cancers with distinct pCR rates. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Lee and Moy in this issue.

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.

Integrating mechanism-based modeling with biomedical imaging to build practical digital twins for clinical oncology

Digital twins employ mathematical and computational models to virtually represent a physical object (e.g., planes and human organs), predict the behavior of the object, and enable decision-making to optimize the future behavior of the object. While digital twins have been widely used in engineering for decades, their applications to oncology are only just emerging. Due to advances in experimental techniques quantitatively characterizing cancer, as well as advances in the mathematical and computational sciences, the notion of building and applying digital twins to understand tumor dynamics and personalize the care of cancer patients has been increasingly appreciated. In this review, we present the opportunities and challenges of applying digital twins in clinical oncology, with a particular focus on integrating medical imaging with mechanism-based, tissue-scale mathematical modeling. Specifically, we first introduce the general digital twin framework and then illustrate existing applications of image-guided digital twins in healthcare. Next, we detail both the imaging and modeling techniques that provide practical opportunities to build patient-specific digital twins for oncology. We then describe the current challenges and limitations in developing image-guided, mechanism-based digital twins for oncology along with potential solutions. We conclude by outlining five fundamental questions that can serve as a roadmap when designing and building a practical digital twin for oncology and attempt to provide answers for a specific application to brain cancer. We hope that this contribution provides motivation for the imaging science, oncology, and computational communities to develop practical digital twin technologies to improve the care of patients battling cancer.

Contrast-free MRI quantitative parameters for early prediction of pathological response to neoadjuvant chemotherapy in breast cancer

OBJECTIVES

To assess early changes in synthetic relaxometry after neoadjuvant chemotherapy (NAC) for breast cancer and establish a model with contrast-free quantitative parameters for early prediction of pathological response.

METHODS

From March 2019 to January 2021, breast MRI were performed for a primary cohort of women with breast cancer before (n = 102) and after the first (n = 93) and second (n = 90) cycle of NAC. Tumor size, synthetic relaxometry (T1/T2 relaxation time [T1/T2], proton density), and ADC were obtained, and the changes after treatment were calculated. Prediction models were established by multivariate logistic regression; evaluated with discrimination, calibration, and clinical application; and compared with Delong tests, net reclassification (NRI), and integrated discrimination index (IDI). External validation was performed from February to June 2021 with an independent cohort of 35 patients.

RESULTS

In the primary cohort, all parameters changed after early treatment. Synthetic relaxometry decreased to a greater degree in major histologic responders (MHR, Miller-Payne G4-5) compared with non-MHR (Miller-Payne G1-3). A model combining ADC after treatment, changes in T1 and tumor size, and cancer subtype achieved the highest AUC after the first (primary/validation cohort, 0.83/0.82) and second cycles (primary/validation cohort, 0.85/0.84). No difference of AUC (p ≥ 0.27), NRI (p ≥ 0.31), and IDI (p ≥ 0.32) was found between models with different cycles and size-measured sequences. Model calibration and decision curves demonstrated a good fitness and clinical benefit, respectively.

CONCLUSIONS

Early reduction in synthetic relaxometry indicated pathological response to NAC. Contrast-free T1 and ADC combined with size and cancer subtype predicted effectively pathological response after one NAC cycle.

KEY POINTS

• Synthetic MRI relaxometry changed after early neoadjuvant chemotherapy, which demonstrated pathological response for mass-like breast cancers. • Contrast-free quantitative parameters including T1 relaxation time and apparent diffusion coefficient, combined with tumor size and cancer subtype, stratified major histologic responders. • A contrast-free model predicted an early pathological response after the first treatment cycle of neoadjuvant chemotherapy.

Impact of Alternate b-Value Combinations and Metrics on the Predictive Performance and Repeatability of Diffusion-Weighted MRI in Breast Cancer Treatment: Results from the ECOG-ACRIN A6698 Trial

In diffusion-weighted MRI (DW-MRI), choice of b-value influences apparent diffusion coefficient (ADC) values by probing different aspects of the tissue microenvironment. As a secondary analysis of the multicenter ECOG-ACRIN A6698 trial, the purpose of this study was to investigate the impact of alternate b-value combinations on the performance and repeatability of tumor ADC as a predictive marker of breast cancer treatment response. The final analysis included 210 women who underwent standardized 4-b-value DW-MRI (b = 0/100/600/800 s/mm2) at multiple timepoints during neoadjuvant chemotherapy treatment and a subset (n = 71) who underwent test−retest scans. Centralized tumor ADC and perfusion fraction (fp) measures were performed using variable b-value combinations. Prediction of pathologic complete response (pCR) based on the mid-treatment/12-week percent change in each metric was estimated by area under the receiver operating characteristic curve (AUC). Repeatability was estimated by within-subject coefficient of variation (wCV). Results show that two-b-value ADC calculations provided non-inferior predictive value to four-b-value ADC calculations overall (AUCs = 0.60−0.61 versus AUC = 0.60) and for HR+/HER2− cancers where ADC was most predictive (AUCs = 0.75−0.78 versus AUC = 0.76), p < 0.05. Using two b-values (0/600 or 0/800 s/mm2) did not reduce ADC repeatability over the four-b-value calculation (wCVs = 4.9−5.2% versus 5.4%). The alternate metrics ADCfast (b ≤ 100 s/mm2), ADCslow (b ≥ 100 s/mm2), and fp did not improve predictive performance (AUCs = 0.54−0.60, p = 0.08−0.81), and ADCfast and fp demonstrated the lowest repeatability (wCVs = 6.71% and 12.4%, respectively). In conclusion, breast tumor ADC calculated using a simple two-b-value approach can provide comparable predictive value and repeatability to full four-b-value measurements as a marker of treatment response.

MRI Radiomics for Assessment of Molecular Subtype, Pathological Complete Response, and Residual Cancer Burden in Breast Cancer Patients Treated With Neoadjuvant Chemotherapy

RATIONALE AND OBJECTIVES

There are limited data on pretreatment imaging features that can predict response to neoadjuvant chemotherapy (NAC). To extract volumetric pretreatment MRI radiomics features and assess corresponding associations with breast cancer molecular subtypes, pathological complete response (pCR), and residual cancer burden (RCB) in patients treated with NAC.

MATERIALS AND METHODS

In this IRB-approved study, clinical and pretreatment MRI data from patients with biopsy-proven breast cancer who received NAC between September 2009 and July 2016 were retrospectively analyzed. Tumors were manually identified and semi-automatically segmented on first postcontrast images. Morphological and three-dimensional textural features were computed, including unfiltered and filtered image data, with spatial scaling factors (SSF) of 2, 4, and 6 mm. Wilcoxon rank-sum tests and area under the receiver operating characteristic curve were used for statistical analysis.

RESULTS

Two hundred and fifty nine patients with unilateral breast cancer, including 73 (28.2%) HER2+, 112 (43.2%) luminal, and 74 (28.6%) triple negative breast cancers (TNBC), were included. There was a significant difference in the median volume (p = 0.008), median longest axial tumor diameter (p = 0.009), and median longest volumetric diameter (p = 0.01) among tumor subtypes. There was also a significant difference in minimum signal intensity and entropy among the tumor subtypes with SSF = 4 mm (p = 0.009 and p = 0.02 respectively) and SSF = 6 mm (p = 0.007 and p < 0.001 respectively). Additionally, sphericity (p = 0.04) in HER2+ tumors and entropy with SSF = 2, 4, 6 mm (p = 0.004, 0.02, 0.047 respectively) in luminal tumors were significantly associated with pCR. Multiple features demonstrated significant association (p < 0.05) with pCR in TNBC and with RCB in luminal tumors and TNBC, with standard deviation of intensity with SSF = 6 mm achieving the highest AUC (AUC = 0.734) for pCR in TNBC.

CONCLUSION

MRI radiomics features are associated with different molecular subtypes of breast cancer, pCR, and RCB. These features may be noninvasive imaging biomarkers to identify cancer subtype and predict response to NAC.

Nomogram for Early Prediction of Pathological Complete Response to Neoadjuvant Chemotherapy in Breast Cancer Using Dynamic Contrast-enhanced and Diffusion-weighted MRI

RATIONALE AND OBJECTIVES

The study investigated the potential of the combined use of dynamic contrast-enhanced MRI and diffusion-weighted imaging in predicting the pathological complete response (pCR) of neoadjuvant chemotherapy (NAC) after two cycles of NAC.

MATERIALS AND METHODS

Eighty-seven patients with breast cancer who underwent MR examination before and after two cycles of NAC were enrolled. The patients were randomly assigned to a training cohort and a validation cohort (3:1 ratio). MRI parameters including tumor longest diameter, time-signal intensity curve, early enhanced ratio (E₉₀), maximal enhanced ratio and ADC value were measured, and percentage change in MRI parameters were calculated. Univariate analysis and multivariate logistic regression analysis were used to evaluate independent predictors of pCR in the training cohort. The validation cohort was used to test the prediction model, and the nomogram was created based on the prediction model.

RESULTS

This study demonstrated that the ADC value after two cycles of NAC (OR = 1.041, 95% CI (1.002, 1.081); p = 0.037), percentage decrease in E₉₀ (OR = 0.927, 95% CI (0.881, 0.977); p =0.004) and percentage decrease in tumor size (OR = 0.948, 95% CI (0.909, 0.988); p = 0.011) were significantly important for independently predicting pCR. The prediction model yielded AUC of 0.939 and 0.944 in the training cohort and the validation cohort, respectively.

CONCLUSION

The combined use of dynamic contrast-enhanced MRI and diffusion-weighted imaging could accurately predict pCR after two cycles of NAC. The prediction model and the nomogram had strong predictive value to NAC.

Factors affecting the value of diffusion-weighted imaging for identifying breast cancer patients with pathological complete response on neoadjuvant systemic therapy: a systematic review

This review aims to identify factors causing heterogeneity in breast DWI-MRI and their impact on its value for identifying breast cancer patients with pathological complete response (pCR) on neoadjuvant systemic therapy (NST). A search was performed on PubMed until April 2020 for studies analyzing DWI for identifying breast cancer patients with pCR on NST. Technical and clinical study aspects were extracted and assessed for variability. Twenty studies representing 1455 patients/lesions were included. The studies differed with respect to study population, treatment type, DWI acquisition technique, post-processing (e.g., mono-exponential/intravoxel incoherent motion/stretched exponential modeling), and timing of follow-up studies. For the acquisition and generation of ADC-maps, various b-value combinations were used. Approaches for drawing regions of interest on longitudinal MRIs were highly variable. Biological variability due to various molecular subtypes was usually not taken into account. Moreover, definitions of pCR varied. The individual areas under the curve for the studies range from 0.50 to 0.92. However, overlapping ranges of mean/median ADC-values at pre- and/or during and/or post-NST were found for the pCR and non-pCR groups between studies. The technical, clinical, and epidemiological heterogeneity may be causal for the observed variability in the ability of DWI to predict pCR accurately. This makes implementation of DWI for pCR prediction and evaluation based on one absolute ADC threshold for all breast cancer types undesirable. Multidisciplinary consensus and appropriate clinical study design, taking biological and therapeutic variation into account, is required for obtaining standardized, reliable, and reproducible DWI measurements for pCR/non-pCR identification.

Quantitative multiparametric MRI predicts response to neoadjuvant therapy in the community setting

BACKGROUND

The purpose of this study was to determine whether advanced quantitative magnetic resonance imaging (MRI) can be deployed outside of large, research-oriented academic hospitals and into community care settings to predict eventual pathological complete response (pCR) to neoadjuvant therapy (NAT) in patients with locally advanced breast cancer.

METHODS

Patients with stage II/III breast cancer (N = 28) were enrolled in a multicenter study performed in community radiology settings. Dynamic contrast-enhanced (DCE) and diffusion-weighted (DW)-MRI data were acquired at four time points during the course of NAT. Estimates of the vascular perfusion and permeability, as assessed by the volume transfer rate (K^trans) using the Patlak model, were generated from the DCE-MRI data while estimates of cell density, as assessed by the apparent diffusion coefficient (ADC), were calculated from DW-MRI data. Tumor volume was calculated using semi-automatic segmentation and combined with K^trans and ADC to yield bulk tumor blood flow and cellularity, respectively. The percent change in quantitative parameters at each MRI scan was calculated and compared to pathological response at the time of surgery. The predictive accuracy of each MRI parameter at different time points was quantified using receiver operating characteristic curves.

RESULTS

Tumor size and quantitative MRI parameters were similar at baseline between groups that achieved pCR (n = 8) and those that did not (n = 20). Patients achieving a pCR had a larger decline in volume and cellularity than those who did not achieve pCR after one cycle of NAT (p < 0.05). At the third and fourth MRI, changes in tumor volume, K^trans, ADC, cellularity, and bulk tumor flow from baseline (pre-treatment) were all significantly greater (p < 0.05) in the cohort who achieved pCR compared to those patients with non-pCR.

CONCLUSIONS

Quantitative analysis of DCE-MRI and DW-MRI can be implemented in the community care setting to accurately predict the response of breast cancer to NAT. Dissemination of quantitative MRI into the community setting allows for the incorporation of these parameters into the standard of care and increases the number of clinical community sites able to participate in novel drug trials that require quantitative MRI.

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.

Quantitative magnetic resonance imaging and tumor forecasting of breast cancer patients in the community setting

This protocol describes a complete data acquisition, analysis and computational forecasting pipeline for employing quantitative MRI data to predict the response of locally advanced breast cancer to neoadjuvant therapy in a community-based care setting. The methodology has previously been successfully applied to a heterogeneous patient population. The protocol details how to acquire the necessary images followed by registration, segmentation, quantitative perfusion and diffusion analysis, model calibration, and prediction. The data collection portion of the protocol requires ~25 min of scanning, postprocessing requires 2-3 h, and the model calibration and prediction components require ~10 h per patient depending on tumor size. The response of individual breast cancer patients to neoadjuvant therapy is forecast by application of a biophysical, reaction-diffusion mathematical model to these data. Successful application of the protocol results in coregistered MRI data from at least two scan visits that quantifies an individual tumor's size, cellularity and vascular properties. This enables a spatially resolved prediction of how a particular patient's tumor will respond to therapy. Expertise in image acquisition and analysis, as well as the numerical solution of partial differential equations, is required to carry out this protocol.

The diagnostic performance of diffusion-weighted imaging and dynamic contrast-enhanced magnetic resonance imaging in evaluating the pathological response of breast cancer to neoadjuvant chemotherapy: A meta-analysis

PURPOSE

To evaluate and compare the diagnostic performance of diffusion-weighted imaging (DWI) and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in predicting the pathological response of breast cancer to neoadjuvant chemotherapy (NAC).

METHODS

We searched PubMed, EMBASE, Cochrane Library, and Web of Science systematically to identify relevant studies from inception to December 2020. The Quality Assessment of Diagnostic Accuracy Studies 2 tool was used to assess the methodological quality of the included studies. We extracted sufficient data to construct 2 × 2 tables and then used STATA 12.0 to perform data pooling, heterogeneity testing, meta-regression analysis and subgroup analysis.

RESULTS

A total of 41 articles were enrolled in this study, including 27 studies (2107 patients) on DCE-MRI and 23 studies (1321 patients) on DWI. The pooled sensitivity and specificity of DCE-MRI were 0.75 and 0.79, and the pooled sensitivity and specificity of DWI were 0.77 and 0.75. There was no significant difference in sensitivity (P = 0.598) and specificity (P = 0.218) ​​between DCE-MRI and DWI. And meta-regression analysis showed that both magnetic field strength and the time of examination had significant effects on heterogeneity.

CONCLUSIONS

DWI might be a potential substitute for DCE-MRI in predicting the pathological response of breast cancer to NAC as there was no significant difference in the diagnostic performance between the two. However, considering that not all included studies directly compared the diagnostic performance of DWI and DCE-MRI in the same patients and the heterogeneity of the included studies, caution should be exercised in applying our results.

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.

Toward Computer-Assisted Triaging of Magnetic Resonance Imaging-Guided Biopsy in Preoperative Breast Cancer Patients

OBJECTIVES

Incidental MR-detected breast lesions (ie, additional lesions to the index cancer) pose challenges in the preoperative workup of patients with early breast cancer. We pursue computer-assisted triaging of magnetic resonance imaging (MRI)-guided breast biopsy of additional lesions at high specificity.

MATERIALS AND METHODS

We investigated 316 consecutive female patients (aged 26 to 76 years; mean, 54 years) with early breast cancer who received preoperative multiparametric breast MRI between 2013 and 2016. In total, 82 (26%) of 316 patients had additional breast lesions on MRI. These 82 patients had 101 additional lesions in total, 51 were benign and 50 were malignant. We collected 4 clinical features and 46 MRI radiomic features from T1-weighted dynamic contrast-enhanced imaging, high-temporal-resolution dynamic contrast-enhanced imaging, T2-weighted imaging, and diffusion-weighted imaging. A multiparametric computer-aided diagnosis (CAD) model using 10-fold cross-validated ridge regression was constructed. The sensitivities were calculated at operating points corresponding to 98%, 95%, and 90% specificity. The model calibration performance was evaluated by calibration plot analysis and goodness-of-fit tests. The model was tested in an independent testing cohort of 187 consecutive patients from 2017 and 2018 (aged 35 to 76 years; mean, 59 years). In this testing cohort, 45 (24%) of 187 patients had 55 additional breast lesions in total, 23 were benign and 32 were malignant.

RESULTS

The multiparametric CAD model correctly identified 48% of the malignant additional lesions with a specificity of 98%. At specificity 95% and 90%, the sensitivity was 62% and 72%, respectively. Calibration plot analysis and goodness-of-fit tests indicated that the model was well fitted.In the independent testing cohort, the specificity was 96% and the sensitivity 44% at the 98% specificity operating point of the training set. At operating points 95% and 90%, the specificity was 83% at 69% sensitivity and the specificity was 78% at 81% sensitivity, respectively.

CONCLUSIONS

The multiparametric CAD model showed potential to identify malignant disease extension with near-perfect specificity in approximately half the population of preoperative patients originally indicated for a breast biopsy. In the other half, patients would still proceed to MRI-guided biopsy to confirm absence of malignant disease. These findings demonstrate the potential to triage MRI-guided breast biopsy.

Breast tumour volume and blood flow measured by MRI after one cycle of epirubicin and cyclophosphamide-based neoadjuvant chemotherapy as predictors of pathological response

OBJECTIVES

Better markers of early response to neoadjuvant chemotherapy (NACT) in patients with breast cancer are required to enable the timely identification of non-responders and reduce unnecessary treatment side-effects. Early functional imaging may better predict response to treatment than conventional measures of tumour size. The purpose of this study was to test the hypothesis that the change in tumour blood flow after one cycle of NACT would predict pathological response.

METHODS

In this prospective cohort study, dynamic contrast-enhanced MRI was performed in 35 females with breast cancer before and after one cycle of epirubicin and cyclophosphamide-based NACT (EC90). Estimates of tumour blood flow and tumour volume were compared with pathological response obtained at surgery following completion of NACT.

RESULTS

Tumour blood flow at baseline (mean ± SD; 0.32 ± 0.17 ml/min/ml) reduced slightly after one cycle of NACT (0.28 ± 0.18 ml/min/ml). Following treatment 15 patients were identified as pathological responders and 20 as non-responders. There were no relationships found between tumour blood flow and pathological response. Conversely, tumour volume was found to be a good predictor of pathological response (smaller tumours did better) at both baseline (area under the receiver operating characteristic curve 0.80) and after one cycle of NACT (area under the receiver operating characteristic curve 0.81).

CONCLUSION & ADVANCES IN KNOWLEDGE

The change in breast tumour blood flow following one cycle of EC90 did not predict pathological response. Tumour volume may be a better early marker of response with such agents.

The use of breast ultrasound for prediction of pathologic complete response in different subtypes of early breast cancer within the WSG-ADAPT subtrials

OBJECTIVE

We assessed the value of breast ultrasound (US) performed at week 3 and 6 and at the end (EOT) of neoadjuvant therapy (NAT) for prediction of pathologic complete response (pCR, ypT0/is ypN0) in patients with HR+/HER2+, HR-/HER2-or HR-/HER2+ early breast cancer enrolled in the WSG-ADAPT subtrials.

METHODS

US was performed at week 3 and 6 of NAT and at EOT in 401, 517, and 553 patients, respectively. Tumors with complete or partial response by US (RECIST 1.1) were classified as responders and those with stable or progressive disease as non-responders.

RESULTS

pCR rate was higher in US responders than in non-responders. US tended to yield the highest positive predictive value in HR-/HER2+ (69%) and HR-/HER2-tumors (65%) at week 3, and the highest negative predictive value in HR+/HER2+ tumors at week 6 and at EOT (88.9% and 86.9%, respectively) and in HR-/HER2-tumors at EOT (87.9%). Multivariable analysis of patients with US at week 3 and 6 identified tumor subtype (HR-/HER2+ vs HR+/HER2+; odds ratio (OR) 2.77, 95%CI 1.45-5.29, and OR 4.17, 95%CI 2.26-7.68, respectively) and each 10% change in lesion dimension on US from baseline (OR 1.15, 95%CI 1.08-1.24, and OR 1.25, 95%CI 1.16-1.35, respectively) as parameters associated with pCR.

CONCLUSIONS

Our data support the use of week 3 and EOT US for prediction of pCR in response-guided NAT and in planning of breast-conserving surgery. Change in tumor diameter on US as a continuous variable could be a valuable alternative to categorical RECIST 1.1 criteria.

Diffusion-weighted MRI for predicting pathologic response to neoadjuvant chemotherapy in breast cancer: evaluation with mono-, bi-, and stretched-exponential models

Background

To investigate the performance of diffusion-weighted (DW) MRI with mono-, bi- and stretched-exponential models in predicting pathologic complete response (pCR) to neoadjuvant chemotherapy (NACT) for breast cancer, and further outline a predictive model of pCR combining DW MRI parameters, contrast-enhanced (CE) MRI findings, and/or clinical-pathologic variables.

Methods

In this retrospective study, 144 women who underwent NACT and subsequently received surgery for invasive breast cancer were included. Breast MRI including multi-b-value DW imaging was performed before (pre-treatment), after two cycles (mid-treatment), and after all four cycles (post-treatment) of NACT. Quantitative DW imaging parameters were computed according to the mono-exponential (apparent diffusion coefficient [ADC]), bi-exponential (pseudodiffusion coefficient and perfusion fraction), and stretched-exponential (distributed diffusion coefficient and intravoxel heterogeneity index) models. Tumor size and relative enhancement ratio of the tumor were measured on contrast-enhanced MRI at each time point. Pre-treatment parameters and changes in parameters at mid- and post-treatment relative to baseline were compared between pCR and non-pCR groups. Receiver operating characteristic analysis and multivariate regression analysis were performed.

Results

Of the 144 patients, 54 (37.5%) achieved pCR after NACT. Overall, among all DW and CE MRI measures, flow-insensitive ADC change (ΔADC_200,1000) at mid-treatment showed the highest diagnostic performance for predicting pCR, with an area under the receiver operating characteristic curve (AUC) of 0.831 (95% confidence interval [CI]: 0.747, 0.915; P < 0.001). The model combining pre-treatment estrogen receptor and human epidermal growth factor receptor 2 statuses and mid-treatment ΔADC_200,1000 improved the AUC to 0.905 (95% CI: 0.843, 0.966; P < 0.001).

Conclusion

Mono-exponential flow-insensitive ADC change at mid-treatment was a predictor of pCR after NACT in breast cancer.

Fusion of high b-value diffusion-weighted and unenhanced T1-weighted images to diagnose invasive breast cancer: factors associated with false-negative results

OBJECTIVES

We sought factors associated with false-negative results in the diagnosis of invasive breast cancer via non-contrast breast magnetic resonance imaging (MRI) using fused high b-value diffusion-weighted imaging (DWI) and unenhanced T1-weighted images (T1WI).

METHODS

Between 2018 and 2019, 316 consecutive women (mean age, 54.6 years) with invasive breast cancer who underwent preoperative breast MRI, including fused high b-value DWI and unenhanced T1WI, were retrospectively evaluated. Malignancy confidence ratings of the most suspicious breast lesions evident on fused DWI were derived by two radiologists using a 6-point Likert-type scale. Both clinicopathological and imaging features were analyzed. Multivariate regression analysis was performed to identify factors associated with false-negative DWI results in the diagnosis of invasive breast cancer.

RESULTS

Of the 316 breast cancers, fused DWI yielded 289 (91.5%) true-positive and 27 (8.5%) false-negative results. Multivariate analysis showed that small tumor size (≤ 1 cm) (odds ratio [OR], 5.95; 95% confidence interval [CI], 2.11, 16.81; p = 0.001), presence of calcifications in the tumor (OR, 3.41; 95% CI, 1.27, 9.15; p = 0.015), and a moderate/marked background diffusion signal (ORs, 4.23 and 19.18; 95% CI, 1.31, 13.67 and 6.51, 56.46; p = 0.016 and p < 0.001, respectively) were significantly associated with false-negative results. In subgroup analysis of 141 screening-detected cancers, a marked background diffusion signal (OR, 7.94; 95% CI, 2.30, 27.35; p = 0.001) remained significantly associated with false-negative results in the multivariate analysis.

CONCLUSIONS

In addition to histopathological features, a higher background diffusion signal was associated with false-negative results in the diagnosis of invasive breast cancer via non-contrast MRI using fused high b-value DWI and unenhanced T1WI.

KEY POINTS

• Subcentimeter tumors and presence of calcifications in the tumor are associated with false-negative diffusion-weighted imaging results in the diagnosis of invasive breast cancer. • A higher degree of background diffusion signal may lead to false-negative interpretation of diffusion-weighted imaging in patients with invasive breast cancer.

Predicting breast cancer response to neoadjuvant chemotherapy using ensemble deep transfer learning based on CT images

OBJECTIVE

To develop an ensemble a deep transfer learning model of CT images for predicting pathologic complete response (pCR) in breast cancer patients undergoing neoadjuvant chemotherapy (NAC).

METHODS

The data were obtained from the public dataset 'QIN-Breast' from The Cancer Imaging Archive (TCIA). CT images were gathered before and after the first cycle of NAC. CT images of 121 breast cancer patients were used to train and test the model. Among these patients, 58 achieved a pCR and 63 showed a non-pCR based pathology examination of surgical results after NAC. The dataset was split into training and testing subsets with a ratio of 7:3. In addition, the number of training samples in the dataset was increased from 656 to 1,968 by performing an image augmentation method. Two deep transfer learning models namely, DenseNet201 and ResNet152V2, and the ensemble model with a concatenation of two models, were trained and tested using CT images.

RESULTS

The ensemble model obtained the highest accuracy of 100% on the testing dataset. Furthermore, we received the best performance of 100% in recall, precision and f1-score value for the ensemble model. This supports the fact that the ensemble model results in better-generalized model and leads to efficient framework. Although a 0.004 and 0.003 difference were seen between the AUC of two base models (DenseNet201 and ResNet152V2) and the proposed ensemble, this increase in the model quality is critical in medical research. T-SNE revealed that in the proposed ensemble, no points were clustered into the wrong class. These results expose the strong performance of the proposed ensemble.

CONCLUSION

The study concluded that the ensemble model can increase the ability to predict breast cancer response to first-cycle NAC than two DenseNet201 and ResNet152V2 models.

Quantitative assessment of renal structural and functional changes in chronic kidney disease using multi-parametric magnetic resonance imaging

Background

Multi-parametric magnetic resonance imaging (MRI) provides the potential for a more comprehensive non-invasive assessment of organ structure and function than individual MRI measures, but has not previously been comprehensively evaluated in chronic kidney disease (CKD).

Methods

We performed multi-parametric renal MRI in persons with CKD (n = 22, 61 ± 24 years) who had a renal biopsy and measured glomerular filtration rate (mGFR), and matched healthy volunteers (HV) (n = 22, 61 ± 25 years). Longitudinal relaxation time (T₁), diffusion-weighted imaging, renal blood flow (phase contrast MRI), cortical perfusion (arterial spin labelling) and blood-oxygen-level-dependent relaxation rate (R₂*) were evaluated.

Results

MRI evidenced excellent reproducibility in CKD (coefficient of variation <10%). Significant differences between CKD and HVs included cortical and corticomedullary difference (CMD) in T₁, cortical and medullary apparent diffusion coefficient (ADC), renal artery blood flow and cortical perfusion. MRI measures correlated with kidney function in a combined CKD and HV analysis: estimated GFR correlated with cortical T₁ (r = −0.68), T₁ CMD (r = −0.62), cortical (r = 0.54) and medullary ADC (r = 0.49), renal artery flow (r = 0.78) and cortical perfusion (r = 0.81); log urine protein to creatinine ratio (UPCR) correlated with cortical T₁ (r = 0.61), T₁ CMD (r = 0.61), cortical (r = −0.45) and medullary ADC (r = −0.49), renal artery flow (r = −0.72) and cortical perfusion (r = −0.58). MRI measures (cortical T₁ and ADC, T₁ and ADC CMD, cortical perfusion) differed between low/high interstitial fibrosis groups at 30–40% fibrosis threshold.

Conclusion

Comprehensive multi-parametric MRI is reproducible and correlates well with available measures of renal function and pathology. Larger longitudinal studies are warranted to evaluate its potential to stratify prognosis and response to therapy in CKD.

Prior to Initiation of Chemotherapy, Can We Predict Breast Tumor Response? Deep Learning Convolutional Neural Networks Approach Using a Breast MRI Tumor Dataset

We hypothesize that convolutional neural networks (CNN) can be used to predict neoadjuvant chemotherapy (NAC) response using a breast MRI tumor dataset prior to initiation of chemotherapy. An institutional review board-approved retrospective review of our database from January 2009 to June 2016 identified 141 locally advanced breast cancer patients who (1) underwent breast MRI prior to the initiation of NAC, (2) successfully completed adriamycin/taxane-based NAC, and (3) underwent surgical resection with available final surgical pathology data. Patients were classified into three groups based on their NAC response confirmed on final surgical pathology: complete (group 1), partial (group 2), and no response/progression (group 3). A total of 3107 volumetric slices of 141 tumors were evaluated. Breast tumor was identified on first T1 postcontrast dynamic images and underwent 3D segmentation. CNN consisted of ten convolutional layers, four max-pooling layers, and dropout of 50% after a fully connected layer. Dropout, augmentation, and L2 regularization were implemented to prevent overfitting of data. Non-linear functions were modeled by a rectified linear unit (ReLU). Batch normalization was used between the convolutional and ReLU layers to limit drift of layer activations during training. A three-class neoadjuvant prediction model was evaluated (group 1, group 2, or group 3). The CNN achieved an overall accuracy of 88% in three-class prediction of neoadjuvant treatment response. Three-class prediction discriminating one group from the other two was analyzed. Group 1 had a specificity of 95.1% ± 3.1%, sensitivity of 73.9% ± 4.5%, and accuracy of 87.7% ± 0.6%. Group 2 (partial response) had a specificity of 91.6% ± 1.3%, sensitivity of 82.4% ± 2.7%, and accuracy of 87.7% ± 0.6%. Group 3 (no response/progression) had a specificity of 93.4% ± 2.9%, sensitivity of 76.8% ± 5.7%, and accuracy of 87.8% ± 0.6%. It is feasible for current deep CNN architectures to be trained to predict NAC treatment response using a breast MRI dataset obtained prior to initiation of chemotherapy. Larger dataset will likely improve our prediction model.

Imaging for Response Assessment in Cancer Clinical Trials

The use of biomarkers is integral to the routine management of cancer patients, including diagnosis of disease, clinical staging and response to therapeutic intervention. Advanced imaging metrics with computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET) are used to assess response during new drug development and in cancer research for predictive metrics of response. Key components and challenges to identifying an appropriate imaging biomarker are selection of integral vs integrated biomarkers, choosing an appropriate endpoint and modality, and standardization of the imaging biomarkers for cooperative and multicenter trials. Imaging biomarkers lean on the original proposed quantified metrics derived from imaging such as tumor size or longest dimension, with the most commonly implemented metrics in clinical trials coming from the Response Evaluation Criteria in Solid Tumors (RECIST) criteria, and then adapted versions such as immune-RECIST (iRECIST) and Positron Emission Tomography Response Criteria in Solid Tumors (PERCIST) for immunotherapy response and PET imaging, respectively. There have been many widely adopted biomarkers in clinical trials derived from MRI including metrics that describe cellularity and vascularity from diffusion-weighted (DW)-MRI apparent diffusion coefficient (ADC) and Dynamic Susceptibility Contrast (DSC) or dynamic contrast enhanced (DCE)-MRI (Ktrans, relative cerebral blood volume (rCBV)), respectively. Furthermore, Fluorodexoyglucose (FDG), fluorothymidine (FLT), and fluoromisonidazole (FMISO)-PET imaging, which describe molecular markers of glucose metabolism, proliferation and hypoxia have been implemented into various cancer types to assess therapeutic response to a wide variety of targeted- and chemotherapies. Recently, there have been many functional and molecular novel imaging biomarkers that are being developed that are rapidly being integrated into clinical trials (with anticipation of being implemented into clinical workflow in the future), such as artificial intelligence (AI) and machine learning computational strategies, antibody and peptide specific molecular imaging, and advanced diffusion MRI. These include prostate-specific membrane antigen (PSMA) and trastuzumab-PET, vascular tumor burden extracted from contrast-enhanced CT, diffusion kurtosis imaging, and CD8 or Granzyme B PET imaging. Further excitement surrounds theranostic procedures such as the combination of 68Ga/111In- and 177Lu-DOTATATE to use integral biomarkers to direct care and personalize therapy. However, there are many challenges in the implementation of imaging biomarkers that remains, including understand the accuracy, repeatability and reproducibility of both acquisition and analysis of these imaging biomarkers. Despite the challenges associated with the biological and technical validation of novel imaging biomarkers, a distinct roadmap has been created that is being implemented into many clinical trials to advance the development and implementation to create specific and sensitive novel imaging biomarkers of therapeutic response to continue to transform medical oncology.

Diffusion MRI of the breast: Current status and future directions

Diffusion-weighted imaging (DWI) is increasingly being incorporated into routine breast MRI protocols in many institutions worldwide, and there are abundant breast DWI indications ranging from lesion detection and distinguishing malignant from benign tumors to assessing prognostic biomarkers of breast cancer and predicting treatment response. DWI has the potential to serve as a noncontrast MR screening method. Beyond apparent diffusion coefficient (ADC) mapping, which is a commonly used quantitative DWI measure, advanced DWI models such as intravoxel incoherent motion (IVIM), non-Gaussian diffusion MRI, and diffusion tensor imaging (DTI) are extensively exploited in this field, allowing the characterization of tissue perfusion and architecture and improving diagnostic accuracy without the use of contrast agents. This review will give a summary of the clinical literature along with future directions. Level of Evidence: 5 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2020;52:70-90.

Quantitative Comparison of Prone and Supine PERCIST Measurements in Breast Cancer

Positron emission tomography (PET) is typically performed in the supine position. However, breast magnetic resonance imaging (MRI) is performed in prone, as this improves visibility of deep breast tissues. With the emergence of hybrid scanners that integrate molecular information from PET and functional information from MRI, it is of great interest to determine if the prognostic utility of prone PET is equivalent to supine. We compared PERCIST (PET Response Criteria in Solid Tumors) measurements between prone and supine FDG-PET in patients with breast cancer and the effect of orientation on predicting pathologic complete response (pCR). In total, 47 patients were enrolled and received up to 6 cycles of neoadjuvant therapy. Prone and supine FDG-PET were performed at baseline (t₀; n = 46), after cycle 1 (t₁; n = 1) or 2 (t₂; n = 10), or after all neoadjuvant therapy (t₃; n = 19). FDG uptake was quantified by maximum and peak standardized uptake value (SUV) with and without normalization to lean body mass; that is, SUV_max, SUV_peak, SUL_max, and SUL_peak. PERCIST measurements were performed for each paired baseline and post-treatment scan. Receiver operating characteristic analysis for the prediction of pCR was performed using logistic regression that included age and tumor size as covariates. SUV and SUL metrics were significantly different between orientation (P < .001), but were highly correlated (P > .98). Importantly, no differences were observed with the PERCIST measurements (P > .6). Overlapping 95% confidence intervals for the receiver operating characteristic analysis suggested no difference at predicting pCR. Therefore, prone and supine PERCIST in this data set were not statistically different.

Dynamic MR image reconstruction based on total generalized variation and low-rank decomposition

PURPOSE

Propose a novel decomposition-based model employing the total generalized variation (TGV) and the nuclear norm, which can be used in compressed sensing-based dynamic MR reconstructions.

THEORY AND METHODS

We employ the nuclear norm to represent the time-coherent background and the spatiotemporal TGV functional for the sparse dynamic component above. We first design an algorithm using the classical first-order primal-dual method for solving the proposed model and then give the norm estimation for the convergence condition. The proposed model is compared with the state-of-the-art methods on different data sets under different sampling schemes and acceleration factors.

RESULTS

The proposed model achieves higher SERs and SSIMs than kt-SLR, kt-RPCA, L+S, and ICTGV on cardiac perfusion and breast DCE-MRI data sets under both the pseudoradial and the Cartesian sampling schemes. In addition, the proposed model better suppresses the spatial artifacts and preserves the edges.

CONCLUSIONS

The proposed model outperforms the state-of-the-art methods and generates high-quality reconstructions under different sampling schemes and different acceleration factors.