Multi-parametric MRI lesion heterogeneity biomarkers for breast cancer diagnosis

MRI biomarkers and their correlation with the Oncotype DX test

Breast cancer (BC) has high rates of incidence and prevalence, causing significant impact in our society. Magnetic resonance imaging (MRI) plays a crucial role in its detection and staging. The Oncotype DX Breast Recurrence Score (ODXRS) test can be used to guide decision making regarding adjuvant chemotherapy (CT) in early-stage luminal BC to allow for more tailored cancer treatment. The aim of this article is to review knowledge regarding MRI biomarkers to date according to the BI-RADS® classification and the use of artificial intelligence (AI) in this imaging technique to establish its correlation with the ODXRS test. The latest studies published on AI and MRI present promising findings, and their standardisation could mark a turning point in breast radiology.

Clinical Breast MRI-based Radiomics for Distinguishing Benign and Malignant Lesions: An Analysis of Sequences and Enhanced Phases

BACKGROUND

Previous studies have used different imaging sequences and different enhanced phases for breast lesion calsification in radiomics. The optimal sequence and contrast enhanced phase is unclear.

PURPOSE

To identify the optimal magnetic resonance imaging (MRI) radiomics model for lesion clarification, and to simulate its incremental value for multiparametric MRI (mpMRI)-guided biopsy.

STUDY TYPE

Retrospective.

POPULATION

329 female patients (138 malignant, 191 benign), divided into a training set (first site, n = 192) and an independent test set (second site, n = 137).

FIELD STRENGTH/SEQUENCE

3.0-T, fast spoiled gradient-echo and fast spin-echo T1-weighted imaging (T1WI), fast spin-echo T2-weighted imaging (T2WI), echo-planar diffusion-weighted imaging (DWI), and fast spoiled gradient-echo contrast-enhanced MRI (CE-MRI).

ASSESSMENT

Two breast radiologists with 3 and 10 years' experience developed radiomics model on CE-MRI, CE-MRI + DWI, CE-MRI + DWI + T2WI, CE-MRI + DWI + T2WI + T1WI at each individual phase (P) and for multiple combinations of phases. The optimal radiomics model (Rad-score) was identified as having the highest area under the receiver operating characteristic curve (AUC) in the test set. Specificity was compared between a traditional mpMRI model and an integrated model (mpMRI + Rad-score) at sensitivity >98%.

STATISTICAL TESTS

Wilcoxon paired-samples signed rank test, Delong test, McNemar test. Significance level was 0.05 and Bonferroni method was used for multiple comparisons (P = 0.007, 0.05/7).

RESULTS

For radiomics models, CE-MRI/P3 + DWI + T2WI achieved the highest performance in the test set (AUC = 0.888, 95% confidence interval: 0.833-0.944). The integrated model had significantly higher specificity (55.3%) than the mpMRI model (31.6%) in the test set with a sensitivity of 98.4%.

DATA CONCLUSION

The CE-MRI/P3 + DWI + T2WI model is the optimized choice for breast lesion classification in radiomics, and has potential to reduce benign biopsies (100%-specificity) from 68.4% to 44.7% while retaining sensitivity >98%.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 2.

Kinetic Heterogeneity Improves the Specificity of Dynamic Enhanced MRI in Differentiating Benign and Malignant Breast Tumours

RATIONALE AND OBJECTIVES

To investigate whether kinetic heterogeneity in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) improves the specificity of breast cancer (BC) diagnosis.

MATERIALS AND METHODS

The DCE-MRI data of patients with benign breast tumours and BC from June 2020 to July 2022 were retrospectively evaluated. MATLAB and SPM were used to determine six major kinetic parameters: peak, enhancement volume, heterogeneity, as well as persistent, plateau, and washout proportions. Continuous variables were compared using the Student's t-test or Mann-Whitney U tests, and categorical variables were compared using the chi-square or Fisher's exact tests. Receiver operating characteristic curves were plotted. The intraclass correlation coefficient (ICC) was used to evaluate agreement between the two observers. Multivariate logistic regression analysis was conducted to calculate the odds ratios (ORs) with 95% confidence intervals (CIs) for the association between benign and malignant breast tumours.

RESULTS

In total, 147 patients (mean age, 47 years old) were included in the study, 76 of whom had BC. Data analysis by the two observers showed good consistency in the peak, enhancement volume, persistent proportion, plateau proportion, washout proportion, and heterogeneity, with ICCs of 0.865, 0.988, 0.906, 0.940, 0.740, and 0.867, respectively (p < 0.001). In the DCE kinetic analysis, differences in all the six kinetic parameters were statistically significant (p < 0.05). The area under the curve for heterogeneity was 0.92 (95% CI:0.88,0.97), and the sensitivity and specificity were 0.895 and 0.845, respectively. Multivariate logistic regression analysis showed that heterogeneity was an independent predictor of BC compared to benign breast tumours (OR=2.020; 95% CI:1.316, 3.100; p = 0.001).

CONCLUSION

The kinetic heterogeneity of DCE-MRI can effectively distinguish between benign and malignant breast tumours and improve the specificity of BC diagnosis.

Efficient 18F-fluorodeoxyglucose positron emission tomography/computed tomography-based machine learning model for predicting epidermal growth factor receptor mutations in non-small cell lung cancer

BACKGROUND

Beyond the human eye's limitations, radiomics provides more information that can be used for diagnosis. We develop a personalized and efficient model based on 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) to predict epidermal growth factor receptor (EGFR) mutations to help identify which non-small cell cancer (NSCLC) patients are candidates for EGFR-tyrosine kinase inhibitors (TKIs) therapy.

METHODS

We retrospectively included 100 patients with NSCLC and randomized them according to 70 patients in the training group and 30 patients in the validation group. The least absolute shrinkage and selection operator logistic regression (LLR) algorithm and support vector machine (SVM) classifier were used to build the models and predict whether EGFR is mutated or not. The predictive efficacy of the LLR algorithm-based model and the SVM classifier-based model was evaluated by plotting the receiver operating characteristic (ROC) curves and calculating the area under the curve (AUC).

RESULTS

The AUC, sensitivity and specificity of our radiomics model by LLR algorithm were 0.792, 0.967, and 0.600 for the training group and 0.643, 1.00, and 0.378 for the validation group, respectively, in predicting EGFR mutations. The AUC was 0.838 for the training group and 0.696 for the validation group after combining radiomics features with clinical features. The prediction results based on the SVM classifier showed that the validation group had the best performance when based on radial kernel function with AUC, sensitivity, and specificity of 0.741, 0.667, and 0.825, respectively.

CONCLUSIONS

Radiomics models based on 18F-FDG PET/CT modeled with different machine learning algorithms can improve the predictive efficacy of the models. Models that combine clinical features are more clinically valuable.

Whole-tumor histogram analysis of multiparametric breast magnetic resonance imaging to differentiate pure mucinous breast carcinomas from fibroadenomas with high-signal intensity on T2WI

PURPOSE

To investigate the utility of whole-tumor histogram analysis based on multiparametric MRI in distinguishing pure mucinous breast carcinomas (PMBCs) from fibroadenomas (FAs) with strong high-signal intensity on T2-weighted imaging (T2-SHi).

MATERIAL AND METHODS

The study included 20 patients (mean age, 55.80 ± 15.54 years) with single PBMCs and 29 patients (mean age, 42.31 ± 13.91 years) with single FAs exhibiting T2-SHi. A radiologist performed whole-tumor histogram analysis between PBMC and FA groups with T2-SHi using multiparametric MRI, including T2-weighted imaging (T2WI), diffusion weighted imaging (DWI) with apparent diffusion coefficient (ADC) maps, and the first (DCE_T1) and last (DCE_T4) phases of T1-weighted dynamic contrast-enhanced imaging (DCE) images, to extract 11 whole-tumor histogram parameters. Histogram parameters were compared between the two groups to identify significant variables using univariate analyses, and their diagnostic performance was assessed by receiver operating characteristic (ROC) curve analysis and logistic regression analyses. In addition, 15 breast lesions were randomly selected and histogram analysis was repeated by another radiologist to assess the intraclass correlation coefficient for each histogram feature. Pearson's correlation coefficients were used to analyze the correlations between histogram parameters and Ki-67 expression of PMBCs.

RESULTS

For T2WI images, mean, median, maximum, 90th percentile, variance, uniformity, and entropy significantly differed in PBMCs and FAs with T2-SHi (all P < 0.05), yielding a combined area under the curve (AUC) of 0.927. For ADC maps, entropy was significantly lower in FAs with T2-SHi than in PMBCs (P = 0.03). In both DCE_T1 and DCE_T4 sequences, FAs with T2-SHi showed significantly higher minimum values than PBMCs (P = 0.007 and 0.02, respectively). The highest AUC value of 0.956 (sensitivity, 0.862; specificity, 0.944; positive predictive value, 0.962; negative predictive value, 0.810) was obtained when all significant histogram parameters were combined.

CONCLUSIONS

Whole-tumor histogram analysis using multiparametric MRI is valuable for differentiating PBMCs from FAs with T2-SHi.

Fully automatic classification of breast lesions on multi-parameter MRI using a radiomics model with minimal number of stable, interpretable features

PURPOSE

To build an automatic computer-aided diagnosis (CAD) pipeline based on multiparametric magnetic resonance imaging (mpMRI) and explore the role of different imaging features in the classification of breast cancer.

MATERIALS AND METHODS

A total of 222 histopathology-confirmed breast lesions, together with their BI-RADS scores, were included in the analysis. The cohort was randomly split into training (159) and test (63) cohorts, and another 50 lesions were collected as an external cohort. An nnUNet-based lesion segmentation model was trained to automatically segment lesion ROI, from which radiomics features were extracted for diffusion-weighted imaging (DWI), T2-weighted imaging (T2WI), and contrast-enhanced (DCE) pharmacokinetic parametric maps. Models based on combinations of sequences were built using support vector machine (SVM) and logistic regression (LR). Also, the performance of these sequence combinations and BI-RADS scores were compared. The Dice coefficient and AUC were calculated  to evaluate the segmentation and classification results. Decision curve analysis (DCA) was used to assess clinical utility.

RESULTS

The segmentation model achieved a Dice coefficient of 0.831 in the test cohort. The radiomics model used only three features from diffusion coefficient (ADC) images, T2WI, and DCE-derived kinetic mapping, and achieved an AUC of 0.946 [0.883-0.990], AUC of 0.842 [0.6856-0.998] in the external cohort, which was higher than the BI-RADS score with an AUC of 0.872 [0.752-0.975]. The joint model using both radiomics score and BI-RADS score achieved the highest test AUC of 0.975 [0.935-1.000], with a sensitivity of 0.920 and a specificity of 0.923.

CONCLUSION

Three radiomics features can be used to construct an automatic radiomics-based pipeline to improve the diagnosis of breast lesions and reduce unnecessary biopsies, especially when using jointly with BI-RADS scores.

A delta-radiomic lymph node model using dynamic contrast enhanced MRI for the early prediction of axillary response after neoadjuvant chemotherapy in breast cancer patients

BACKGROUND

The objective of this paper is to explore the value of a delta-radiomic model of the axillary lymph node (ALN) using dynamic contrast-enhanced (DCE) MRI for early prediction of the axillary pathological complete response (pCR) of breast cancer patients after neoadjuvant chemotherapy (NAC).

METHODS

A total of 120 patients with ALN-positive breast cancer who underwent breast MRI before and after the first cycle of NAC between October 2018 and May 2021 were prospectively included in this study. Patients were divided into a training (n = 84) and validation (n = 36) cohort based on the temporal order of their treatments. Radiomic features were extracted from the largest slice of targeted ALN on DCE-MRI at pretreatment and after one cycle of NAC, and their changes (delta-) were calculated and recorded. Logistic regression was then applied to build radiomic models using the pretreatment (pre-), first-cycle(1st-), and changes (delta-) radiomic features separately. A clinical model was also built and combined with the radiomic models. The models were evaluated by discrimination, calibration, and clinical application and compared using DeLong test.

RESULTS

Among the three radiomic models, the ALN delta-radiomic model performed the best with AUCs of 0.851 (95% CI: 0.770-0.932) and 0.822 (95% CI: 0.685-0.958) in the training and validation cohorts, respectively. The clinical model yielded moderate AUCs of 0.742 (95% CI: 0.637-0.846) and 0.723 (95% CI: 0.550-0.896), respectively. After combining clinical features to the delta-radiomics model, the efficacy of the combined model (AUC = 0.932) in the training cohort was significantly higher than that of both the delta-radiomic model (Delong p = 0.017) and the clinical model (Delong p < 0.001) individually. Additionally, in the validation cohort, the combined model had the highest AUC (0.859) of any of the models we tested although this was not statistically different from any other individual model's validation AUC. Calibration and decision curves showed a good agreement and a high clinical benefit for the combined model.

CONCLUSION

This preliminary study indicates that ALN-based delta-radiomic model combined with clinical features is a promising strategy for the early prediction of downstaging ALN status after NAC. Future axillary MRI applications need to be further explored.

Predicting of Ki-67 Expression Level Using Diffusion-Weighted and Synthetic Magnetic Resonance Imaging in Invasive Ductal Breast Cancer

Objectives

To investigate the association between quantitative parameters generated using synthetic magnetic resonance imaging (SyMRI) and diffusion-weighted imaging (DWI) and Ki-67 expression level in patients with invasive ductal breast cancer (IDC).

Method

We retrospectively reviewed the records of patients with IDC who underwent SyMRI and DWI before treatment. Precontrast and postcontrast relaxation times (T1, longitudinal; T2, transverse), proton density (PD) parameters, and apparent diffusion coefficient (ADC) values were measured in breast lesions. Univariate and multivariate regression analyses were performed to screen for statistically significant variables to differentiate the high (≥30%) and low (<30%) Ki-67 expression groups. Their performance was evaluated by receiver operating characteristic (ROC) curve analysis.

Results

We analyzed 97 patients. Multivariate regression analysis revealed that the high Ki-67 expression group (n = 57) had significantly higher parameters generated using SyMRI (pre-T1, p=0.001) and lower ADC values (p=0.036) compared with the low Ki-67 expression group (n = 40). Pre-T1 showed the best diagnostic performance for predicting the Ki-67 expression level in patients with invasive ductal breast cancer (areas under the ROC curve (AUC), 0.711; 95% confidence interval (CI), 0.609-0.813).

Conclusions

Pre-T1 could be used to predict the pretreatment Ki-67 expression level in invasive ductal breast cancer.

Tuning the optimal diffusion-weighted MRI parameters on a 0.35-T MR-Linac for clinical implementation: A phantom study

PURPOSE

This study aims to assess the quality of a new diffusion-weighted imaging (DWI) sequence implemented on an MR-Linac MRIdian system, evaluating and optimizing the acquisition parameters to explore the possibility of clinically implementing a DWI acquisition protocol in a 0.35-T MR-Linac.

MATERIALS AND METHODS

All the performed analyses have been carried out on two types of phantoms: a homogeneous 24-cm diameter polymethylmethacrylate (PMMA) sphere (SP) and a homemade phantom (HMP) constating in a PMMA cylinder filled with distilled water with empty sockets into which five cylindrical vials filled with five different concentrations of methylcellulose water solutions have been inserted. SP was used to evaluate the dependence of diffusion gradient inhomogeneity artifacts on gantry position. Four diffusion sequences with b-values of 500 s/mm2 and 3 averages have been acquired: three with diffusion gradients in the three main directions (phase direction, read direction, slice direction) and one with the diffusion gradients switched off. The dependence of diffusion image uniformity and SNR on the number of averages in the MR sequences was also investigated to determine the optimal number of averages. Finally, the ADC values of HMP have been computed and then compared between images acquired in the scanners at 0.35 and 1.5 T.

RESULTS

In order to acquire high-quality artifact-free DWI images, the "slice" gradient direction has been identified to be the optimal one and 0° to be the best gradient angle. Both the SNR ratio and the uniformity increase with the number of averages. A threshold value of 80 for SNR and 85% for uniformity was adopted to choose the best number of averages. By making a compromise between time and quality and limiting the number of b-values, it is possible to reduce the acquisition time to 78 s. The Passing-Bablok test showed that the two methods, with 0.35 and 1.5 T scanners, led to similar results.

CONCLUSION

The quality of the DWI has been accurately evaluated in relation to different sequence parameters, and optimal parameters have been identified to select a clinical protocol for the acquisition of ADC maps sustainable in the workflow of a hybrid radiotherapy system with a 0.35-T MRI scanner.

Precision Medicine in Breast Cancer: Do MRI Biomarkers Identify Patients Who Truly Benefit from the Oncotype DX Recurrence Score® Test?

The aim of this study was to combine breast MRI-derived biomarkers with clinical-pathological parameters to identify patients who truly need an Oncotype DX Breast Recurrence Score® (ODXRS) genomic assay, currently used to predict the benefit of adjuvant chemotherapy in ER-positive/HER2-negative early breast cancer, with the ultimate goal of customizing therapeutic decisions while reducing healthcare costs. Patients who underwent a preoperative multiparametric MRI of the breast and ODXRS tumor profiling were retrospectively included in this study. Imaging sets were evaluated independently by two breast radiologists and classified according to the 2013 American College of Radiology Breast Imaging Reporting and Data System (ACR BI-RADS) lexicon. In a second step of the study, a combined oncologic and radiologic assessment based on clinical-pathological and radiological data was performed, in order to identify patients who may need adjuvant chemotherapy. Results were correlated with risk levels expressed by ODXRS, using the decision made on the basis of the ODXRS test as a gold standard. The χ2 test was used to evaluate associations between categorical variables, and significant ones were further investigated using logistic regression analyses. A total of 58 luminal-like, early-stage breast cancers were included. A positive correlation was found between ODXRS and tumor size (p = 0.003), staging (p = 0.001) and grading (p = 0.005), and between BI-RADS categories and ODXRS (p < 0.05 for both readers), the latter being confirmed at multivariate regression analysis. Moreover, BI-RADS categories proved to be positive predictors of the therapeutic decision taken after performing an ODXRS assay. A statistically significant association was also found between the therapeutic decision based on the ODXRS and the results of combined onco-radiologic assessment (p < 0.001). Our study suggests that there is a correlation between BI-RADS categories at MRI and ODXRS and that a combined onco-radiological assessment may predict the decision made on the basis of the results of ODXRS genomic test.

Artificial intelligence in multi-parametric magnetic resonance imaging: A review

Multi-parametric magnetic resonance imaging (mpMRI) is an indispensable tool in the clinical workflow for the diagnosis and treatment planning of various diseases. Machine learning-based artificial intelligence (AI) methods, especially those adopting the deep learning technique, have been extensively employed to perform mpMRI image classification, segmentation, registration, detection, reconstruction, and super-resolution. The current availability of increasing computational power and fast-improving AI algorithms have empowered numerous computer-based systems for applying mpMRI to disease diagnosis, imaging-guided radiotherapy, patient risk and overall survival time prediction, and the development of advanced quantitative imaging technology for magnetic resonance fingerprinting. However, the wide application of these developed systems in the clinic is still limited by a number of factors, including robustness, reliability, and interpretability. This survey aims to provide an overview for new researchers in the field as well as radiologists with the hope that they can understand the general concepts, main application scenarios, and remaining challenges of AI in mpMRI. This article is protected by copyright. All rights reserved.

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

Simple Summary

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

Abstract

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

MRI as a biomarker for breast cancer diagnosis and prognosis

Breast cancer (BC) is the most frequently diagnosed female invasive cancer in Western countries and the leading cause of cancer-related death worldwide. Nowadays, tumor heterogeneity is a well-known characteristic of BC, since it includes several nosological entities characterized by different morphologic features, clinical course and response to treatment. Thus, with the spread of molecular biology technologies and the growing knowledge of the biological processes underlying the development of BC, the importance of imaging biomarkers as non-invasive information about tissue hallmarks has progressively grown. To date, breast magnetic resonance imaging (MRI) is considered indispensable in breast imaging practice, with widely recognized indications such as BC screening in females at increased risk, locoregional staging and neoadjuvant therapy (NAT) monitoring. Moreover, breast MRI is increasingly used to assess not only the morphologic features of the pathological process but also to characterize individual phenotypes for targeted therapies, building on developments in genomics and molecular biology features. The aim of this review is to explore the role of breast multiparametric MRI in providing imaging biomarkers, leading to an improved differentiation of benign and malignant breast lesions and to a customized management of BC patients in monitoring and predicting response to treatment. Finally, we discuss how breast MRI biomarkers offer one of the most fertile ground for artificial intelligence (AI) applications. In the era of personalized medicine, with the development of omics-technologies, machine learning and big data, the role of imaging biomarkers is embracing new opportunities for BC diagnosis and treatment.

Radiomics in breast MRI: current progress toward clinical application in the era of artificial intelligence

Breast magnetic resonance imaging (MRI) is the most sensitive imaging modality for breast cancer diagnosis and is widely used clinically. Dynamic contrast-enhanced MRI is the basis for breast MRI, but ultrafast images, T2-weighted images, and diffusion-weighted images are also taken to improve the characteristics of the lesion. Such multiparametric MRI with numerous morphological and functional data poses new challenges to radiologists, and thus, new tools for reliable, reproducible, and high-volume quantitative assessments are warranted. In this context, radiomics, which is an emerging field of research involving the conversion of digital medical images into mineable data for clinical decision-making and outcome prediction, has been gaining ground in oncology. Recent development in artificial intelligence has promoted radiomics studies in various fields including breast cancer treatment and numerous studies have been conducted. However, radiomics has shown a translational gap in clinical practice, and many issues remain to be solved. In this review, we will outline the steps of radiomics workflow and investigate clinical application of radiomics focusing on breast MRI based on published literature, as well as current discussion about limitations and challenges in radiomics.

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.

Exploration of an Integrative Prognostic Model of Radiogenomics Features With Underlying Gene Expression Patterns in Clear Cell Renal Cell Carcinoma

Background

Clear cell renal cell carcinoma (ccRCC) is one of the most common malignancies in urinary system, and radiomics has been adopted in tumor staging and prognostic evaluation in renal carcinomas. This study aimed to integrate image features of contrast-enhanced CT and underlying genomics features to predict the overall survival (OS) of ccRCC patients.

Method

We extracted 107 radiomics features out of 205 patients with available CT images obtained from TCIA database and corresponding clinical and genetic information from TCGA database. LASSO-COX and SVM-RFE were employed independently as machine-learning algorithms to select prognosis-related imaging features (PRIF). Afterwards, we identified prognosis-related gene signature through WGCNA. The random forest (RF) algorithm was then applied to integrate PRIF and the genes into a combined imaging-genomics prognostic factors (IGPF) model. Furthermore, we constructed a nomogram incorporating IGPF and clinical predictors as the integrative prognostic model for ccRCC patients.

Results

A total of four PRIF and four genes were identified as IGPF and were represented by corresponding risk score in RF model. The integrative IGPF model presented a better prediction performance than the PRIF model alone (average AUCs for 1-, 3-, and 5-year were 0.814 vs. 0.837, 0.74 vs. 0.806, and 0.689 vs. 0.751 in test set). Clinical characteristics including gender, TNM stage and IGPF were independent risk factors. The nomogram integrating clinical predictors and IGPF provided the best net benefit among the three models.

Conclusion

In this study we established an integrative prognosis-related nomogram model incorporating imaging-genomic features and clinical indicators. The results indicated that IGPF may contribute to a comprehensive prognosis assessment for ccRCC patients.