Diagnostic accuracy of (18)F-FDG PET/CT compared with that of contrast-enhanced MRI of the breast at 3 T

Prospective validation of 18F-Fluoroethylcholine as a tracer in PET/MRI for the evaluation of breast lesions and prediction of lymph node status

PURPOSE

To assess 18F-Fluoroethylcholine (18F-FEC) as a PET/MRI tracer in the evaluation of breast lesions, breast cancer aggressiveness, and prediction of lymph node status.

MATERIALS AND METHODS

This prospective, monocentric study was approved by the ethics committee and patients gave written, informed consent. This clinical trial was registered in the EudraCT database (Number 2017-003089-29). Women who presented with suspicious breast lesions were included. Histopathology was used as reference standard. Simultaneous 18F-FEC PET/MRI of the breast was performed in a prone position with a dedicated breast coil. MRI was performed using a standard protocol before and after contrast agent administration. A simultaneous read by nuclear medicine physicians and radiologists collected the imaging data of MRI-detected lesions, including the maximum standardized 18F-FEC-uptake value of breast lesions (SUV_maxT) and axillary lymph nodes (SUV_maxLN). Differences in SUV_max were evaluated with the Mann-Whitney U test. To calculate diagnostic performance, the area under the receiver operating characteristics curve (ROC) was used.

RESULTS

There were 101 patients (mean age 52.3 years, standard deviation 12.0) with 117 breast lesions included (30 benign, 7 ductal carcinomas in situ, 80 invasive carcinomas). 18F-FEC was well tolerated by all patients. The ROC to distinguish benign from malignant breast lesions was 0.846. SUV_maxT was higher if lesions were malignant (p < 0.001), had a higher proliferation rate (p = 0.011), and were HER2-positive (p = 0.041). SUV_maxLN was higher in metastatic lymph nodes, with an ROC of 0.761 for SUV_maxT and of 0.793 for SUV_maxLN. CONCLUSION: Simultaneous 18F-FEC PET/MRI is safe and has the potential to be used for the evaluation of breast cancer aggressiveness, and prediction of lymph node status.

Clinical advances in PET-MRI for breast cancer

Imaging is paramount for the early detection and clinical staging of breast cancer, as well as to inform management decisions and direct therapy. PET-MRI is a quantitative hybrid imaging technology that combines metabolic and functional PET data with anatomical detail and functional perfusion information from MRI. The clinical applicability of PET-MRI for breast cancer is an active area of research. In this Review, we discuss the rationale and summarise the clinical evidence for the use of PET-MRI in the diagnosis, staging, prognosis, tumour phenotyping, and assessment of treatment response in breast cancer. The continued development and approval of targeted radiopharmaceuticals, together with radiomics and automated analysis tools, will further expand the opportunity for PET-MRI to provide added value for breast cancer imaging and patient care.

AI-enhanced simultaneous multiparametric 18F-FDG PET/MRI for accurate breast cancer diagnosis

Purpose

To assess whether a radiomics and machine learning (ML) model combining quantitative parameters and radiomics features extracted from simultaneous multiparametric ¹⁸F-FDG PET/MRI can discriminate between benign and malignant breast lesions.

Methods

A population of 102 patients with 120 breast lesions (101 malignant and 19 benign) detected on ultrasound and/or mammography was prospectively enrolled. All patients underwent hybrid ¹⁸F-FDG PET/MRI for diagnostic purposes. Quantitative parameters were extracted from DCE (MTT, VD, PF), DW (mean ADC of breast lesions and contralateral breast parenchyma), PET (SUVmax, SUVmean, and SUVminimum of breast lesions, as well as SUVmean of the contralateral breast parenchyma), and T2-weighted images. Radiomics features were extracted from DCE, T2-weighted, ADC, and PET images. Different diagnostic models were developed using a fine Gaussian support vector machine algorithm which explored different combinations of quantitative parameters and radiomics features to obtain the highest accuracy in discriminating between benign and malignant breast lesions using fivefold cross-validation. The performance of the best radiomics and ML model was compared with that of expert reader review using McNemar’s test.

Results

Eight radiomics models were developed. The integrated model combining MTT and ADC with radiomics features extracted from PET and ADC images obtained the highest accuracy for breast cancer diagnosis (AUC 0.983), although its accuracy was not significantly higher than that of expert reader review (AUC 0.868) (p = 0.508).

Conclusion

A radiomics and ML model combining quantitative parameters and radiomics features extracted from simultaneous multiparametric ¹⁸F-FDG PET/MRI images can accurately discriminate between benign and malignant breast lesions.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00259-021-05492-z.

Breast Tumor Characterization Using [18F]FDG-PET/CT Imaging Combined with Data Preprocessing and Radiomics

Simple Summary

Breast cancer is the second most common diagnosed malignancy in women worldwide. In this study, we examine the feasibility of breast tumor characterization based on [¹⁸F]FDG-PET/CT images using machine learning (ML) approaches in combination with data-preprocessing techniques. ML prediction models for breast cancer detection and the identification of breast cancer receptor status, proliferation rate, and molecular subtypes were established and evaluated. Furthermore, the importance of most repeatable features was investigated. Results displayed high performance of malignant/benign tumor differentiation and triple negative tumor subtype ML models. We observed high repeatability of radiomic features for both high performing predictive models.

Abstract

Background: This study investigated the performance of ensemble learning holomic models for the detection of breast cancer, receptor status, proliferation rate, and molecular subtypes from [¹⁸F]FDG-PET/CT images with and without incorporating data pre-processing algorithms. Additionally, machine learning (ML) models were compared with conventional data analysis using standard uptake value lesion classification. Methods: A cohort of 170 patients with 173 breast cancer tumors (132 malignant, 38 benign) was examined with [¹⁸F]FDG-PET/CT. Breast tumors were segmented and radiomic features were extracted following the imaging biomarker standardization initiative (IBSI) guidelines combined with optimized feature extraction. Ensemble learning including five supervised ML algorithms was utilized in a 100-fold Monte Carlo (MC) cross-validation scheme. Data pre-processing methods were incorporated prior to machine learning, including outlier and borderline noisy sample detection, feature selection, and class imbalance correction. Feature importance in each model was assessed by calculating feature occurrence by the R-squared method across MC folds. Results: Cross validation demonstrated high performance of the cancer detection model (80% sensitivity, 78% specificity, 80% accuracy, 0.81 area under the curve (AUC)), and of the triple negative tumor identification model (85% sensitivity, 78% specificity, 82% accuracy, 0.82 AUC). The individual receptor status and luminal A/B subtype models yielded low performance (0.46–0.68 AUC). SUV_max model yielded 0.76 AUC in cancer detection and 0.70 AUC in predicting triple negative subtype. Conclusions: Predictive models based on [¹⁸F]FDG-PET/CT images in combination with advanced data pre-processing steps aid in breast cancer diagnosis and in ML-based prediction of the aggressive triple negative breast cancer subtype.

Progress and Future Trends in PET/CT and PET/MRI Molecular Imaging Approaches for Breast Cancer

Breast cancer is a major disease with high morbidity and mortality in women worldwide. Increased use of imaging biomarkers has been shown to add more information with clinical utility in the detection and evaluation of breast cancer. To date, numerous studies related to PET-based imaging in breast cancer have been published. Here, we review available studies on the clinical utility of different PET-based molecular imaging methods in breast cancer diagnosis, staging, distant-metastasis detection, therapeutic and prognostic prediction, and evaluation of therapeutic responses. For primary breast cancer, PET/MRI performed similarly to MRI but better than PET/CT. PET/CT and PET/MRI both have higher sensitivity than MRI in the detection of axillary and extra-axillary nodal metastases. For distant metastases, PET/CT has better performance in the detection of lung metastasis, while PET/MRI performs better in the liver and bone. Additionally, PET/CT is superior in terms of monitoring local recurrence. The progress in novel radiotracers and PET radiomics presents opportunities to reclassify tumors by combining their fine anatomical features with molecular characteristics and develop a beneficial pathway from bench to bedside to predict the treatment response and prognosis of breast cancer. However, further investigation is still needed before application of these modalities in clinical practice. In conclusion, PET-based imaging is not suitable for early-stage breast cancer, but it adds value in identifying regional nodal disease and distant metastases as an adjuvant to standard diagnostic imaging. Recent advances in imaging techniques would further widen the comprehensive and convergent applications of PET approaches in the clinical management of breast cancer.

PIK3CA Mutational Status Is Associated with High Glycolytic Activity in ER+/HER2- Early Invasive Breast Cancer: a Molecular Imaging Study Using [18F]FDG PET/CT

PURPOSE

In PIK3CA mutant breast cancer, downstream hyperactivation of the PI3K/AKT/mTOR pathway may be associated with increased glycolysis of cancer cells. The purpose of this study was to investigate the functional association of PIK3CA mutational status and tumor glycolysis in invasive ER+/HER2- early breast cancer.

PROCEDURES

This institutional review board-approved retrospective study included a dataset of 67 ER+/HER2- early breast cancer patients. All patients underwent 2-deoxy-2-[¹⁸F]fluoro-D-glucose positron emission tomography/X-ray computed tomography ([¹⁸F]FDG PET/CT) and clinico-pathologic assessments as part of a prospective study. For this retrospective analysis, pyrosequencing was used to detect PIK3CA mutations of exons 4, 7, 9, and 20. Tumor glucose metabolism was assessed semi-quantitatively with [¹⁸F]FDG PET/CT using maximum standardized uptake values (SUV_max). SUV_max values were corrected for the partial volume effect, and metabolic tumor volume was calculated using the volume of interest automated lesion growing function 2D tumor size, i.e., maximum tumor diameter was assessed on concurrent pre-treatment contrast-enhanced magnetic resonance imaging.

RESULTS

PIK3CA mutations were present in 45 % of all tumors. Mutations were associated with a small tumor diameter (p < 0.01) and with low nuclear grade (p = 0.04). Glycolytic activity was positively associated with nuclear grade (p = 0.01), proliferation (p = 0.002), regional lymph node metastasis (p = 0.015), and metabolic tumor volume (p = 0.001) but not with tumor size/T-stage. In invasive ductal carcinomas, median SUV_max was increased in PIK3CA-mutated compared to wild-type tumors; however, this increase did not reach statistical significance (p = 0.05). Multivariate analysis of invasive ductal carcinomas revealed [¹⁸F]FDG uptake to be independently associated with PIK3CA status (p = 0.002) and nuclear tumor grade (p = 0.046). Size, volume, and regional nodal status had no influence on glycolytic activity. PIK3CA mutational status did not influence glycolytic metabolism in lobular carcinomas. Glycolytic activity and PIK3CA mutational status had no significant influence on recurrence-free survival or disease-specific survival.

CONCLUSIONS

In ER+/HER2- invasive ductal carcinomas of the breast, glucose uptake is independently associated with PIK3CA mutations. Initial data suggest that [¹⁸F]FDG uptake reflects complex genomic alterations and may have the potential to be used as candidate biomarker for monitoring therapeutic response and resistance mechanisms in emerging therapies that target the PI3K/AKT/mTOR pathway.

Multiparametric 18F-FDG PET/MRI of the Breast: Are There Differences in Imaging Biomarkers of Contralateral Healthy Tissue Between Patients With and Without Breast Cancer?

The rationale was to assess whether there are differences in multiparametric 18F-FDG PET/MRI biomarkers of contralateral healthy breast tissue in patients with benign and malignant breast tumors. Methods: In this institutional review board-approved prospective single-institution study, 141 women with imaging abnormalities on mammography or sonography (BI-RADS 4/5) underwent combined 18F-FDG PET/MRI of the breast at 3T with dynamic contrast-enhanced MRI, diffusion-weighted imaging, and the radiotracer 18F-FDG. In all patients, the following imaging biomarkers were recorded for the contralateral (tumor-free) breast: breast parenchymal uptake (BPU) (from 18F-FDG PET), mean apparent diffusion coefficient (from diffusion-weighted imaging), background parenchymal enhancement (BPE), and amount of fibroglandular tissue (FGT) (from MRI). Appropriate statistical tests were used to assess differences in 18F-FDG PET/MRI biomarkers between patients with benign and malignant lesions. Results: There were 100 malignant and 41 benign lesions. BPE was minimal in 61 patients, mild in 56, moderate in 19, and marked in 5. BPE differed significantly (P < 0.001) between patients with benign and malignant lesions, with patients with cancer demonstrating decreased BPE in the contralateral tumor-free breast. FGT approached but did not reach significance (P = 0.055). BPU was 1.5 for patients with minimal BPE, 1.9 for mild BPE, 2.2 for moderate BPE, and 1.9 for marked BPE. BPU differed significantly between patients with benign lesions (mean, 1.9) and patients with malignant lesions (mean, 1.8) (P < 0.001). Mean apparent diffusion coefficient did not differ between groups (P = 0.19). Conclusion: Differences in multiparametric 18F-FDG PET/MRI biomarkers, obtained from contralateral tumor-free breast tissue, exist between patients with benign and patients with malignant breast tumors. Contralateral BPE, BPU, and FGT are decreased in breast cancer patients and may potentially serve as imaging biomarkers for the presence of malignancy.

A multiparametric [18F]FDG PET/MRI diagnostic model including imaging biomarkers of the tumor and contralateral healthy breast tissue aids breast cancer diagnosis

Purpose

To develop a multiparametric [¹⁸F]FDG positron emission tomography/magnetic resonance imaging (PET/MRI) model for breast cancer diagnosis incorporating imaging biomarkers of breast tumors and contralateral healthy breast tissue.

Methods

In this prospective study and retrospective data analysis, 141 patients (mean 57 years) with an imaging abnormality detected on mammography and/or ultrasound (BI-RADS 4/5) underwent combined multiparametric [¹⁸F]FDG PET/MRI with PET/computed tomography and multiparametric MRI of the breast at 3 T. Images were evaluated and the following were recorded: for the tumor, BI-RADS descriptors on dynamic contrast-enhanced (DCE)-MRI, mean apparent diffusion co-efficient (ADCmean) on diffusion-weighted imaging (DWI), and maximum standard uptake value (SUVmax) on [¹⁸F]FDG-PET; and for the contralateral healthy breast, background parenchymal enhancement (BPE) and amount of fibroglandular tissue (FGT) on DCE-MRI, ADCmean on DWI, and SUVmax. Histopathology served as standard of reference. Uni-, bi-, and multivariate logistic regression analyses were performed to assess the relationships between malignancy and imaging features. Predictive discrimination of benign and malignant breast lesions was examined using area under the receiver operating characteristic curve (AUC).

Results

There were 100 malignant and 41 benign lesions (size: median 1.9, range 0.5–10 cm). The multivariate regression model incorporating significant univariate predictors identified tumor enhancement kinetics (P = 0.0003), tumor ADCmean (P < 0.001), and BPE of the contralateral healthy breast (P = 0.0019) as independent predictors for breast cancer diagnosis. Other biomarkers did not reach significance. Combination of the three significant biomarkers achieved an AUC value of 0.98 for breast cancer diagnosis.

Conclusion

A multiparametric [¹⁸F]FDG PET/MRI diagnostic model incorporating both qualitative and quantitative parameters of the tumor and the healthy contralateral tissue aids breast cancer diagnosis.

Automatic segmentation and classification of breast lesions through identification of informative multiparametric PET/MRI features

Background

Multiparametric positron emission tomography/magnetic resonance imaging (mpPET/MRI) shows clinical potential for detection and classification of breast lesions. Yet, the contribution of features for computer-aided segmentation and diagnosis (CAD) need to be better understood. We proposed a data-driven machine learning approach for a CAD system combining dynamic contrast-enhanced (DCE)-MRI, diffusion-weighted imaging (DWI), and ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG)-PET.

Methods

The CAD incorporated a random forest (RF) classifier combined with mpPET/MRI intensity-based features for lesion segmentation and shape features, kinetic and spatio-temporal texture features, for lesion classification. The CAD pipeline detected and segmented suspicious regions and classified lesions as benign or malignant. The inherent feature selection method of RF and alternatively the minimum-redundancy-maximum-relevance feature ranking method were used.

Results

In 34 patients, we report a detection rate of 10/12 (83.3%) and 22/22 (100%) for benign and malignant lesions, respectively, a Dice similarity coefficient of 0.665 for segmentation, and a classification performance with an area under the curve at receiver operating characteristics analysis of 0.978, a sensitivity of 0.946, and a specificity of 0.936. Segmentation but not classification performance of DCE-MRI improved with information from DWI and FDG-PET. Feature ranking revealed that kinetic and spatio-temporal texture features had the highest contribution for lesion classification. ¹⁸F-FDG-PET and morphologic features were less predictive.

Conclusion

Our CAD enables the assessment of the relevance of mpPET/MRI features on segmentation and classification accuracy. It may aid as a novel computational tool for exploring different modalities/features and their contributions for the detection and classification of breast lesions.

Electronic supplementary material

The online version of this article (10.1186/s41747-019-0096-3) contains supplementary material, which is available to authorized users.

[Multiparametric and molecular imaging of breast tumors with MRI and PET/MRI]

CLINICAL/METHODICAL ISSUE

Magnetic resonance imaging (MRI) of the breast is an indispensable tool in breast imaging for many indications. Several functional parameters with MRI and positron emission tomography (PET) have been assessed for imaging of breast tumors and their combined application is defined as multiparametric imaging. Available data suggest that multiparametric imaging using different functional MRI and PET parameters can provide detailed information about the hallmarks of cancer and may provide additional specificity.

STANDARD RADIOLOGICAL METHODS

Multiparametric and molecular imaging of the breast comprises established MRI parameters, such as dynamic contrast-enhanced MRI, diffusion-weighted imaging (DWI), MR proton spectroscopy ((1)H-MRSI) as well as combinations of radiological and MRI techniques (e. g. PET/CT and PET/MRI) using radiotracers, such as fluorodeoxyglucose (FDG).

METHODICAL INNOVATIONS

Multiparametric and molecular imaging of the breast can be performed at different field-strengths (range 1.5-7 T). Emerging parameters comprise novel promising techniques, such as sodium imaging ((23)Na MRI), phosphorus spectroscopy ((31)P-MRSI), chemical exchange saturation transfer (CEST) imaging, blood oxygen level-dependent (BOLD) and hyperpolarized MRI as well as various specific radiotracers.

ACHIEVEMENTS

Multiparametric and molecular imaging has multiple applications in breast imaging. Multiparametric and molecular imaging of the breast is an evolving field that will enable improved detection, characterization, staging and monitoring for personalized medicine in breast cancer.

A simple classification system (the Tree flowchart) for breast MRI can reduce the number of unnecessary biopsies in MRI-only lesions

OBJECTIVES

To assess whether using the Tree flowchart obviates unnecessary magnetic resonance imaging (MRI)-guided biopsies in breast lesions only visible on MRI.

METHODS

This retrospective IRB-approved study evaluated consecutive suspicious (BI-RADS 4) breast lesions only visible on MRI that were referred to our institution for MRI-guided biopsy. All lesions were evaluated according to the Tree flowchart for breast MRI by experienced readers. The Tree flowchart is a decision rule that assigns levels of suspicion to specific combinations of diagnostic criteria. Receiver operating characteristic (ROC) curve analysis was used to evaluate diagnostic accuracy. To assess reproducibility by kappa statistics, a second reader rated a subset of 82 patients.

RESULTS

There were 454 patients with 469 histopathologically verified lesions included (98 malignant, 371 benign lesions). The area under the curve (AUC) of the Tree flowchart was 0.873 (95% CI: 0.839-0.901). The inter-reader agreement was almost perfect (kappa: 0.944; 95% CI 0.889-0.998). ROC analysis revealed exclusively benign lesions if the Tree node was ≤2, potentially avoiding unnecessary biopsies in 103 cases (27.8%).

CONCLUSIONS

Using the Tree flowchart in breast lesions only visible on MRI, more than 25% of biopsies could be avoided without missing any breast cancer.

KEY POINTS

• The Tree flowchart may obviate >25% of unnecessary MRI-guided breast biopsies. • This decrease in MRI-guided biopsies does not cause any false-negative cases. • The Tree flowchart predicts 30.6% of malignancies with >98% specificity. • The Tree's high specificity aids in decision-making after benign biopsy results.

Breast PET/MR Imaging

Breast and whole-body PET/MR imaging is being used to detect local and metastatic disease and is being investigated for potential imaging biomarkers, which may eventually help personalize treatments and prognoses. This article provides an overview of breast and whole-body PET/MR exam techniques, summarizes PET and MR breast imaging for lesion detection, outlines investigations into multi-parametric breast PET/MR, looks at breast PET/MR in the setting of neo-adjuvant chemotherapy, and reviews the pros and cons of whole-body PET/MR in the setting of metastatic or suspected metastatic breast cancer.

Quantitative Assessment of Breast Parenchymal Uptake on 18F-FDG PET/CT: Correlation with Age, Background Parenchymal Enhancement, and Amount of Fibroglandular Tissue on MRI

Background parenchymal enhancement (BPE), and the amount of fibroglandular tissue (FGT) assessed with MRI have been implicated as sensitive imaging biomarkers for breast cancer. The purpose of this study was to quantitatively assess breast parenchymal uptake (BPU) on ¹⁸F-FDG PET/CT as another valuable imaging biomarker and examine its correlation with BPE, FGT, and age.

METHODS

This study included 129 patients with suspected breast cancer and normal imaging findings in one breast (BI-RADS 1), whose cases were retrospectively analyzed. All patients underwent prone ¹⁸F-FDG PET/CT and 3-T contrast-enhanced MRI of the breast. In all patients, interpreter 1 assessed BPU quantitatively using SUV_max Interpreters 1 and 2 assessed amount of FGT and BPE in the normal contralateral breast by subjective visual estimation, as recommended by BI-RADS. Interpreter 1 reassessed all cases and repeated the BPU measurements. Statistical tests were used to assess correlations between BPU, BPE, FGT, and age, as well as inter- and intrainterpreter agreement.

RESULTS

BPU on ¹⁸F-FDG PET/CT varied among patients. The mean BPU SUV_max ± SD was 1.57 ± 0.6 for patients with minimal BPE, 1.93 ± 0.6 for mild BPE, 2.42 ± 0.5 for moderate BPE, and 1.45 ± 0.3 for marked BPE. There were significant (P < 0.001) moderate to strong correlations among BPU, BPE, and FGT. BPU directly correlated with both BPE and FGT on MRI. Patient age showed a moderate to strong indirect correlation with all 3 imaging-derived tissue biomarkers. The coefficient of variation for quantitative BPU measurements with SUV_max was 5.6%, indicating a high reproducibility. Interinterpreter and intrainterpreter agreement for BPE and FGT was almost perfect, with a κ-value of 0.860 and 0.822, respectively.

CONCLUSION

The results of our study demonstrate that BPU varied among patients. BPU directly correlated with both BPE and FGT on MRI, and BPU measurements were highly reproducible. Patient age showed a strong inverse correlation with all 3 imaging-derived tissue biomarkers. These findings indicate that BPU may serve as a sensitive imaging biomarker for breast cancer prediction, prognosis, and risk assessment.