A radiomics pipeline dedicated to Breast MRI: validation on a multi-scanner phantom study

Breast MRI radiomics and machine learning-based predictions of response to neoadjuvant chemotherapy - How are they affected by variations in tumor delineation?

Manual delineation of volumes of interest (VOIs) by experts is considered the gold-standard method in radiomics analysis. However, it suffers from inter- and intra-operator variability. A quantitative assessment of the impact of variations in these delineations on the performance of the radiomics predictors is required to develop robust radiomics based prediction models. In this study, we developed radiomics models for the prediction of pathological complete response to neoadjuvant chemotherapy in patients with two different breast cancer subtypes based on contrast-enhanced magnetic resonance imaging acquired prior to treatment (baseline MRI scans). Different mathematical operations such as erosion, smoothing, dilation, randomization, and ellipse fitting were applied to the original VOIs delineated by experts to simulate variations of segmentation masks. The effects of such VOI modifications on various steps of the radiomics workflow, including feature extraction, feature selection, and prediction performance, were evaluated. Using manual tumor VOIs and radiomics features extracted from baseline MRI scans, an AUC of up to 0.96 and 0.89 was achieved for human epidermal growth receptor 2 positive and triple-negative breast cancer, respectively. For smoothing and erosion, VOIs yielded the highest number of robust features and the best prediction performance, while ellipse fitting and dilation lead to the lowest robustness and prediction performance for both breast cancer subtypes. At most 28% of the selected features were similar to manual VOIs when different VOI delineation data were used. Differences in VOI delineation affect different steps of radiomics analysis, and their quantification is therefore important for development of standardized radiomics research.

Exploring the added value of pretherapeutic MR descriptors in predicting breast cancer pathologic complete response to neoadjuvant chemotherapy

OBJECTIVES

To evaluate the association between pretreatment MRI descriptors and breast cancer (BC) pathological complete response (pCR) to neoadjuvant chemotherapy (NAC).

MATERIALS AND METHODS

Patients with BC treated by NAC with a breast MRI between 2016 and 2020 were included in this retrospective observational single-center study. MR studies were described using the standardized BI-RADS and breast edema score on T2-weighted MRI. Univariable and multivariable logistic regression analyses were performed to assess variables association with pCR according to residual cancer burden. Random forest classifiers were trained to predict pCR on a random split including 70% of the database and were validated on the remaining cases.

RESULTS

Among 129 BC, 59 (46%) achieved pCR after NAC (luminal (n = 7/37, 19%), triple negative (n = 30/55, 55%), HER2 + (n = 22/37, 59%)). Clinical and biological items associated with pCR were BC subtype (p < 0.001), T stage 0/I/II (p = 0.008), higher Ki67 (p = 0.005), and higher tumor-infiltrating lymphocytes levels (p = 0.016). Univariate analysis showed that the following MRI features, oval or round shape (p = 0.047), unifocality (p = 0.026), non-spiculated margins (p = 0.018), no associated non-mass enhancement (p = 0.024), and a lower MRI size (p = 0.031), were significantly associated with pCR. Unifocality and non-spiculated margins remained independently associated with pCR at multivariable analysis. Adding significant MRI features to clinicobiological variables in random forest classifiers significantly increased sensitivity (0.67 versus 0.62), specificity (0.69 versus 0.67), and precision (0.71 versus 0.67) for pCR prediction.

CONCLUSION

Non-spiculated margins and unifocality are independently associated with pCR and can increase models performance to predict BC response to NAC.

CLINICAL RELEVANCE STATEMENT

A multimodal approach integrating pretreatment MRI features with clinicobiological predictors, including tumor-infiltrating lymphocytes, could be employed to develop machine learning models for identifying patients at risk of non-response. This may enable consideration of alternative therapeutic strategies to optimize treatment outcomes.

KEY POINTS

• Unifocality and non-spiculated margins are independently associated with pCR at multivariable logistic regression analysis. • Breast edema score is associated with MR tumor size and TIL expression, not only in TN BC as previously reported, but also in luminal BC. • Adding significant MRI features to clinicobiological variables in machine learning classifiers significantly increased sensitivity, specificity, and precision for pCR prediction.

Machine learning models based on multi-parameter MRI radiomics for prediction of molecular glioblastoma: a new study based on the 2021 World Health Organization classification

BACKGROUND

The 2021 World Health Organization (WHO) classification considers a histological low grade glioma with specific molecular characteristics as molecular glioblastoma (mGBM). Accurate identification of mGBM will aid in risk stratification of glioma patients.

PURPOSE

To explore the value of machine learning models based on magnetic resonance imaging (MRI) radiomics features in predicting mGBM.

MATERIAL AND METHODS

In total, 166 patients histologically diagnosed as low-grade diffuse glioma (WHO II and III) were included in the study. Fifty-three cases were reclassified as mGBM based on molecular status. Four dimensionality reduction methods including distance correlation (DC), gradient boosted decision tree (GBDT), least absolute shrinkage and selection operator (LASSO) and minimal redundancy maximal relevance (MRMR) were used to select the optimal signatures. Six machine learning algorithms including support vector machine (SVM), linear discriminant analysis (LDA), neural network (NN), logistic regression (LR), K-nearest neighbour (KNN) and decision tree (DT) were used to develop the classifiers. The relative SD was used to evaluate the stability of the models, and the area under the curve values in the independent test group were used to evaluate their performances.

RESULTS

NN_DC was determined as the optimal classifier due to the highest area under the curve of 0.891 in the test group. The classification accuracy, sensitivity, specificity, positive predictive value and negative predictive value of NN_DC were 0.915, 0.842, 0.950, 0.889 and 0.927, respectively.

CONCLUSION

Machine learning models can predict mGBM non-invasively, which may help to develop personalized treatment strategies for neurosurgeons and provide an effective tool for accurate stratification in clinical trials.

Topology-based radiomic features for prediction of parotid gland cancer malignancy grade in magnetic resonance images

PURPOSE

The malignancy grades of parotid gland cancer (PGC) have been assessed for a decision of treatment policies. Therefore, we have investigated the feasibility of topology-based radiomic features for the prediction of parotid gland cancer (PGC) malignancy grade in magnetic resonance (MR) images.

MATERIALS AND METHODS

Two-dimensional T1- and T2-weighted MR images of 39 patients with PGC were selected for this study. Imaging properties of PGC can be quantified using the topology, which could be useful for assessing the number of the k-dimensional holes or heterogeneity in PGC regions using invariants of the Betti numbers. Radiomic signatures were constructed from 41,472 features obtained after a harmonization using an elastic net model. PGC patients were stratified using a logistic classification into low/intermediate- and high-grade malignancy groups. The training data were increased by four times to avoid the overfitting problem using a synthetic minority oversampling technique. The proposed approach was assessed using a 4-fold cross-validation test.

RESULTS

The highest accuracy of the proposed approach was 0.975 for the validation cases, whereas that of the conventional approach was 0.694.

CONCLUSION

This study indicated that topology-based radiomic features could be feasible for the noninvasive prediction of the malignancy grade of PGCs.

A segmentation-based method improving the performance of N4 bias field correction on T2weighted MR imaging data of the prostate

Magnetic Resonance (MR) images suffer from spatial inhomogeneity, known as bias field corruption. The N4ITK filter is a state-of-the-art method used for correcting the bias field to optimize MR-based quantification. In this study, a novel approach is presented to quantitatively evaluate the performance of N4 bias field correction for pelvic prostate imaging. An exploratory analysis, regarding the different values of convergence threshold, shrink factor, fitting level, number of iterations and use of mask, is performed to quantify the performance of N4 filter in pelvic MR images. The performance of a total of 240 different N4 configurations is examined using the Full Width at Half Maximum (FWHM) of the segmented periprostatic fat distribution as evaluation metric. Phantom T2weighted images were used to assess the performance of N4 for a uniform test tissue mimicking material, excluding factors such as patient related susceptibility and anatomy heterogeneity. Moreover, 89 and 204 T2weighted patient images from two public datasets acquired by scanners with a combined surface and endorectal coil at 1.5 T and a surface coil at 3 T, respectively, were utilized and corrected with a variable set of N4 parameters. Furthermore, two external public datasets were used to validate the performance of the N4 filter in T2weighted patient images acquired by various scanning conditions with different magnetic field strengths and coils. The results show that the set of N4 parameters, converging to optimal representations of fat in the image, were: convergence threshold 0.001, shrink factor 2, fitting level 6, number of iterations 100 and the use of default mask for prostate images acquired by a combined surface and endorectal coil at both 1.5 T and 3 T. The corresponding optimal N4 configuration for MR prostate images acquired by a surface coil at 1.5 T or 3 T was: convergence threshold 0.001, shrink factor 2, fitting level 5, number of iterations 25 and the use of default mask. Hence, periprostatic fat segmentation can be used to define the optimal settings for achieving T2weighted prostate images free from bias field corruption to provide robust input for further analysis.

ComBat Harmonization of Myocardial Radiomic Features Sensitive to Cardiac MRI Acquisition Parameters

Purpose

To investigate the effect of ComBat harmonization methods on the robustness of cardiac MRI-derived radiomic features to variations in imaging parameters.

Materials and Methods

This Health Insurance Portability and Accountability Act-compliant retrospective study used a publicly available data set of 11 healthy controls (mean age, 33 years ± 16 [SD]; six men) and five patients (mean age, 52 years ± 16; four men). A single midventricular short-axis section was acquired with 3-T MRI using cine balanced steady-state free precision, T1-weighted, T2-weighted, T1 mapping, and T2 mapping imaging sequences. Each sequence was acquired using baseline parameters and after variations in flip angle, spatial resolution, section thickness, and parallel imaging. Image registration was performed for all sequences at a per-individual level. Manual myocardial contouring was performed, and 1652 radiomic features per sequence were extracted using baseline and variations in imaging parameters. Radiomic feature stability to change in imaging parameters was assessed using Cohen d sensitivity. The stability of radiomic features was assessed both without and after ComBat harmonization of radiomic features. Three ComBat methods were studied: parametric, nonparametric, and Gaussian mixture model (GMM).

Results

For all sequences combined, 51.4% of features were robust to changes in imaging parameters when no ComBat method was applied. ComBat harmonization substantially increased the number of stable features to 95.1% (95% CI: 94.9, 95.3) when parametric ComBat was used and 90.9% (95% CI: 90.6, 91.2) when nonparametric ComBat was used. GMM combat resulted in only 52.6% stable features.

Conclusion

ComBat harmonization improved the stability of radiomic features to changes in imaging parameters across all cardiac MRI sequences.Keywords: Cardiac MRI, Radiomics, ComBat, Harmonization Supplemental material is available for this article. © RSNA, 2023.

Image harmonization: A review of statistical and deep learning methods for removing batch effects and evaluation metrics for effective harmonization

Magnetic resonance imaging and computed tomography from multiple batches (e.g. sites, scanners, datasets, etc.) are increasingly used alongside complex downstream analyses to obtain new insights into the human brain. However, significant confounding due to batch-related technical variation, called batch effects, is present in this data; direct application of downstream analyses to the data may lead to biased results. Image harmonization methods seek to remove these batch effects and enable increased generalizability and reproducibility of downstream results. In this review, we describe and categorize current approaches in statistical and deep learning harmonization methods. We also describe current evaluation metrics used to assess harmonization methods and provide a standardized framework to evaluate newly-proposed methods for effective harmonization and preservation of biological information. Finally, we provide recommendations to end-users to advocate for more effective use of current methods and to methodologists to direct future efforts and accelerate development of the field.

Prediction of early improvement of major depressive disorder to antidepressant medication in adolescents with radiomics analysis after ComBat harmonization based on multiscale structural MRI

BACKGROUND

Due to individual differences and lack of objective biomarkers, only 30-40% patients with major depressive disorder (MDD) achieve remission after initial antidepressant medication (ADM). We aimed to employ radiomics analysis after ComBat harmonization to predict early improvement to ADM in adolescents with MDD by using brain multiscale structural MRI (sMRI) and identify the radiomics features with high prediction power for selection of selective serotonin reuptake inhibitors (SSRIs) and serotonin norepinephrine reuptake inhibitors (SNRIs).

METHODS

121 MDD patients were recruited for brain sMRI, including three-dimensional T1 weighted imaging (3D-T₁WI)and diffusion tensor imaging (DTI). After receiving SSRIs or SNRIs for 2 weeks, the subjects were divided into ADM improvers (SSRIs improvers and SNRIs improvers) and non-improvers according to reduction rate of the Hamilton Depression Rating Scale, 17 item (HAM-D₁₇) score. Then, sMRI data were preprocessed, and conventional imaging indicators and radiomics features of gray matter (GM) based on surface-based morphology (SBM) and voxel-based morphology (VBM) and diffusion properties of white matter (WM) were extracted and harmonized with ComBat harmonization. Two-level reduction strategy with analysis of variance (ANOVA) and recursive feature elimination (RFE) was utilized sequentially to decrease high-dimensional features. Support vector machine with radial basis function kernel (RBF-SVM) was used to integrate multiscale sMRI features to construct models for early improvement prediction. Area under the curve (AUC), accuracy, sensitivity, and specificity based on the leave-one-out cross-validation (LOO-CV) and receiver operating characteristic (ROC) curve analysis were calculated to evaluate the model performance. Permutation tests were used for assessing the generalization rate.

RESULTS

After 2-week ADM, 121 patients were divided into 67 ADM improvers (31 SSRIs improvers and 36 SNRIs improvers) and 54 ADM non-improvers. After two-level dimensionality reduction, 8 conventional indicators (2 VBM-based features and 6 diffusion features) and 49 radiomics features (16 VBM-based features and 33 diffusion features) were selected. The overall accuracy of RBF-SVM models based on conventional indicators and radiomics features was 74.80% and 88.19%. The radiomics model achieved the AUC, sensitivity, specificity, and accuracy of 0.889, 91.2%, 80.1% and 85.1%, 0.954, 89.2%, 87.4% and 88.5%, 0.942, 91.9%, 82.5% and 86.8% for predicting ADM improvers, SSRIs improvers and SNRIs improvers, respectively. P value of permutation tests were less than 0.001. The radiomics features predicting ADM improver were mainly located in the hippocampus, medial orbitofrontal gyrus, anterior cingulate gyrus, cerebellum (lobule vii-b), body of corpus callosum, etc. The radiomics features predicting SSRIs improver were primarily distributed in hippocampus, amygdala, inferior temporal gyrus, thalamus, cerebellum (lobule vi), fornix, cerebellar peduncle, etc. The radiomics features predicting SNRIs improver were primarily located in the medial orbitofrontal cortex, anterior cingulate gyrus, ventral striatum, corpus callosum, etc. CONCLUSIONS: These findings suggest the radiomics analysis based on brain multiscale sMRI after ComBat harmonization could effectively predict the early improvement of ADM in adolescent MDD patients with a high accuracy, which was superior to the model based on the conventional indicators. The radiomics features with high prediction power may help for the individual selection of SSRIs and SNRIs.

Diagnostic Performance of Selected MRI-Derived Radiomics Able to Discriminate Progression-Free and Overall Survival in Patients with Midline Glioma and the H3F3AK27M Mutation

BACKGROUND

Radiomics refers to a recent area of knowledge that studies features extracted from different imaging techniques and subsequently transformed into high-dimensional data that can be associated with biological events. Diffuse midline gliomas (DMG) are one of the most devastating types of cancer, with a median survival of approximately 11 months after diagnosis and 4-5 months after radiological and clinical progression.

METHODS

A retrospective study. From a database of 91 patients with DMG, only 12 had the H3.3K27M mutation and brain MRI DICOM files available. Radiomic features were extracted from MRI T1 and T2 sequences using LIFEx software. Statistical analysis included normal distribution tests and the Mann-Whitney U test, ROC analysis, and calculation of cut-off values.

RESULTS

A total of 5760 radiomic values were included in the analyses. AUROC demonstrated 13 radiomics with statistical significance for progression-free survival (PFS) and overall survival (OS). Diagnostic performance tests showed nine radiomics with specificity for PFS above 90% and one with a sensitivity of 97.2%. For OS, 3 out of 4 radiomics demonstrated between 80 and 90% sensitivity.

CONCLUSIONS

Several radiomic features demonstrated statistical significance and have the potential to further aid DMG diagnostic assessment non-invasively. The most significant radiomics were first- and second-order features with GLCM texture profile, GLZLM_GLNU, and NGLDM_Contrast.

Multimodal MRI radiomic models to predict genomic mutations in diffuse intrinsic pontine glioma with missing imaging modalities

Purpose

Predicting H3.1, TP53, and ACVR1 mutations in DIPG could aid in the selection of therapeutic options. The contribution of clinical data and multi-modal MRI were studied for these three predictive tasks. To keep the maximum number of subjects, which is essential for a rare disease, missing data were considered. A multi-modal model was proposed, collecting all available data for each patient, without performing any imputation.

Methods

A retrospective cohort of 80 patients with confirmed DIPG and at least one of the four MR modalities (T1w, T1c, T2w, and FLAIR), acquired with two different MR scanners was built. A pipeline including standardization of MR data and extraction of radiomic features within the tumor was applied. The values of radiomic features between the two MR scanners were realigned using the ComBat method. For each prediction task, the most robust features were selected based on a recursive feature elimination with cross-validation. Five different models, one based on clinical data and one per MR modality, were developed using logistic regression classifiers. The prediction of the multi-modal model was defined as the average of all possible prediction results among five for each patient. The performances of the models were compared using a leave-one-out approach.

Results

The percentage of missing modalities ranged from 6 to 11% across modalities and tasks. The performance of each individual model was dependent on each specific task, with an AUC of the ROC curve ranging from 0.63 to 0.80. The multi-modal model outperformed the clinical model for each prediction tasks, thus demonstrating the added value of MRI. Furthermore, regardless of performance criteria, the multi-modal model came in the first place or second place (very close to first). In the leave-one-out approach, the prediction of H3.1 (resp. ACVR1 and TP53) mutations achieved a balanced accuracy of 87.8% (resp. 82.1 and 78.3%).

Conclusion

Compared with a single modality approach, the multi-modal model combining multiple MRI modalities and clinical features was the most powerful to predict H3.1, ACVR1, and TP53 mutations and provided prediction, even in the case of missing modality. It could be proposed in the absence of a conclusive biopsy.

Visual ensemble selection of deep convolutional neural networks for 3D segmentation of breast tumors on dynamic contrast enhanced MRI

OBJECTIVES

To develop a visual ensemble selection of deep convolutional neural networks (CNN) for 3D segmentation of breast tumors using T1-weighted dynamic contrast-enhanced (T1-DCE) MRI.

METHODS

Multi-center 3D T1-DCE MRI (n = 141) were acquired for a cohort of patients diagnosed with locally advanced or aggressive breast cancer. Tumor lesions of 111 scans were equally divided between two radiologists and segmented for training. The additional 30 scans were segmented independently by both radiologists for testing. Three 3D U-Net models were trained using either post-contrast images or a combination of post-contrast and subtraction images fused at either the image or the feature level. Segmentation accuracy was evaluated quantitatively using the Dice similarity coefficient (DSC) and the Hausdorff distance (HD95) and scored qualitatively by a radiologist as excellent, useful, helpful, or unacceptable. Based on this score, a visual ensemble approach selecting the best segmentation among these three models was proposed.

RESULTS

The mean and standard deviation of DSC and HD95 between the two radiologists were equal to 77.8 ± 10.0% and 5.2 ± 5.9 mm. Using the visual ensemble selection, a DSC and HD95 equal to 78.1 ± 16.2% and 14.1 ± 40.8 mm was reached. The qualitative assessment was excellent (resp. excellent or useful) in 50% (resp. 77%).

CONCLUSION

Using subtraction images in addition to post-contrast images provided complementary information for 3D segmentation of breast lesions by CNN. A visual ensemble selection allowing the radiologist to select the most optimal segmentation obtained by the three 3D U-Net models achieved comparable results to inter-radiologist agreement, yielding 77% segmented volumes considered excellent or useful.

KEY POINTS

• Deep convolutional neural networks were developed using T1-weighted post-contrast and subtraction MRI to perform automated 3D segmentation of breast tumors. • A visual ensemble selection allowing the radiologist to choose the best segmentation among the three 3D U-Net models outperformed each of the three models. • The visual ensemble selection provided clinically useful segmentations in 77% of cases, potentially allowing for a valuable reduction of the manual 3D segmentation workload for the radiologist and greatly facilitating quantitative studies on non-invasive biomarker in breast MRI.

Radiomics in clinical trials: perspectives on standardization

The term biomarker is used to describe a biological measure of the disease behavior. The existing imaging biomarkers are associated with the known tissue biological characteristics and follow a well-established roadmap to be implemented in routine clinical practice. Recently, a new quantitative imaging analysis approach named radiomics has emerged. It refers to the extraction of a large number of advanced imaging features with high-throughput computing. Extensive research has demonstrated its value in predicting disease behavior, progression, and response to therapeutic options. However, there are numerous challenges to establishing it as a clinically viable solution, including lack of reproducibility and transparency. The data-driven nature also does not offer insights into the underpinning biology of the observed relationships. As such, additional effort is needed to establish it as a qualified biomarker to inform clinical decisions. Here we review the technical difficulties encountered in the clinical applications of radiomics and current effort in addressing some of these challenges in clinical trial designs. By addressing these challenges, the true potential of radiomics can be unleashed.

Harmonization Strategies in Multicenter MRI-Based Radiomics

Radiomics analysis is a powerful tool aiming to provide diagnostic and prognostic patient information directly from images that are decoded into handcrafted features, comprising descriptors of shape, size and textural patterns. Although radiomics is gaining momentum since it holds great promise for accelerating digital diagnostics, it is susceptible to bias and variation due to numerous inter-patient factors (e.g., patient age and gender) as well as inter-scanner ones (different protocol acquisition depending on the scanner center). A variety of image and feature based harmonization methods has been developed to compensate for these effects; however, to the best of our knowledge, none of these techniques has been established as the most effective in the analysis pipeline so far. To this end, this review provides an overview of the challenges in optimizing radiomics analysis, and a concise summary of the most relevant harmonization techniques, aiming to provide a thorough guide to the radiomics harmonization process.

Radiomics software comparison using digital phantom and patient data: IBSI-compliance does not guarantee concordance of feature values

Introduction Radiomics is a promising imaging-based tool which could enhance clinical observation and identify representative features. To avoid different interpretations, the Image Biomarker Standardisation Initiative (IBSI) imposed conditions for harmonisation. This study evaluates IBSI-compliant radiomics applications against a known benchmark and clinical datasets for agreements. Materials and methods The applications compared were RadiomiX Research Toolbox, LIFEx v7.0.0, and syngo.via Frontier Radiomics v1.2.5 (based on PyRadiomics v2.1). Basic assessment included comparing feature names and their formulas. The IBSI digital phantom was used for evaluation against reference values. For agreement evaluation (including same software but different versions), two clinical datasets were used: 27 contrast-enhanced computed tomography (CECT) of colorectal liver metastases and 39 magnetic resonance imaging (MRI) of breast cancer, including intravoxel incoherent motion and dynamic contrast-enhanced (DCE) MRI. The lower 95% confidence interval of intraclass correlation coefficient was used to define excellent agreement (>0.9). Results The three radiomics applications share 41 (3 shape, 8 intensity, 30 texture) out of 172, 84 and 110 features for RadiomiX, LIFEx and syngo.via, respectively, as well as wavelet filtering. The naming convention is, however, different between them. Syngo.via had excellent agreement with the IBSI benchmark, while LIFEx and RadiomiX showed slightly worse agreement. Excellent reproducibility was achieved for shape features only, while intensity and texture features varied considerably with the imaging type. For intensity, excellent agreement ranged from 46% for the DCE maps to 100% for CECT, while this lowered to 44% and 73% for texture features, respectively. Wavelet features produced the greatest variation between applications, with an excellent agreement for only 3% to 11% features. Conclusion Even with IBSI-compliance, the reproducibility of features between radiomics applications is not guaranteed. To evaluate variation, quality assurance of radiomics applications should be performed and repeated when updating to a new version or adding a new modality.

Expert tumor annotations and radiomics for locally advanced breast cancer in DCE-MRI for ACRIN 6657/I-SPY1

Breast cancer is one of the most pervasive forms of cancer and its inherent intra- and inter-tumor heterogeneity contributes towards its poor prognosis. Multiple studies have reported results from either private institutional data or publicly available datasets. However, current public datasets are limited in terms of having consistency in: a) data quality, b) quality of expert annotation of pathology, and c) availability of baseline results from computational algorithms. To address these limitations, here we propose the enhancement of the I-SPY1 data collection, with uniformly curated data, tumor annotations, and quantitative imaging features. Specifically, the proposed dataset includes a) uniformly processed scans that are harmonized to match intensity and spatial characteristics, facilitating immediate use in computational studies, b) computationally-generated and manually-revised expert annotations of tumor regions, as well as c) a comprehensive set of quantitative imaging (also known as radiomic) features corresponding to the tumor regions. This collection describes our contribution towards repeatable, reproducible, and comparative quantitative studies leading to new predictive, prognostic, and diagnostic assessments.

Test-Retest Data for the Assessment of Breast MRI Radiomic Feature Repeatability

Background

Radiomic features extracted from breast MRI have potential for diagnostic, prognostic, and predictive purposes. However, before they can be used as biomarkers in clinical decision support systems, features need to be repeatable and reproducible.

Objective

Identify repeatable radiomics features within breast tissue on prospectively collected MRI exams through multiple test–retest measurements.

Study Type

Prospective.

Population

11 healthy female volunteers.

Field Strength/Sequence

1.5 T; MRI exams, comprising T2‐weighted turbo spin‐echo (T2W) sequence, native T1‐weighted turbo gradient‐echo (T1W) sequence, diffusion‐weighted imaging (DWI) sequence using b‐values 0/150/800, and corresponding derived ADC maps.

Assessment

18 MRI exams (three test–retest settings, repeated on 2 days) per healthy volunteer were examined on an identical scanner using a fixed clinical breast protocol. For each scan, 91 features were extracted from the 3D manually segmented right breast using Pyradiomics, before and after image preprocessing. Image preprocessing consisted of 1) bias field correction (BFC); 2) z‐score normalization with and without BFC; 3) grayscale discretization using 32 and 64 bins with and without BFC; and 4) z‐score normalization + grayscale discretization using 32 and 64 bins with and without BFC.

Statistical Tests

Features' repeatability was assessed using concordance correlation coefficient(CCC) for each pair, i.e. each MRI was compared to each of the remaining 17 MRI with a cut‐off value of CCC > 0.90.

Results

Images without preprocessing produced the highest number of repeatable features for both T1W sequence and ADC maps with 15 of 91 (16.5%) and 8 of 91 (8.8%) repeatable features, respectively. Preprocessed images produced between 4 of 91 (4.4%) and 14 of 91 (15.4%), and 6 of 91 (6.6%) and 7 of 91 (7.7%) repeatable features, respectively for T1W and ADC maps. Z‐score normalization produced highest number of repeatable features, 26 of 91 (28.6%) in T2W sequences, in these images, no preprocessing produced 11 of 91 (12.1%) repeatable features.

Data Conclusion

Radiomic features extracted from T1W, T2W sequences and ADC maps from breast MRI exams showed a varying number of repeatable features, depending on the sequence. Effects of different preprocessing procedures on repeatability of features were different for each sequence.

Level of Evidence

2

Technical Efficacy Stage

1

Impact of Preprocessing and Harmonization Methods on the Removal of Scanner Effects in Brain MRI Radiomic Features

Simple Summary

As a rapid-development research field, radiomics-based analysis has been applied to many clinical problems. However, the reproducibility of the radiomics studies remain challenging especially when data suffers from scanner effects, a kind of non-biological variations introduced by different image acquiring settings. This study aims to investigate how the image preprocessing methods (N4 bias field correction and image resampling) and the harmonization methods (intensity normalization methods working on images and ComBat method working on radiomic features) help to remove the scanner effects and improve the radiomics reproducibility in brain MRI radiomics.

Abstract

In brain MRI radiomics studies, the non-biological variations introduced by different image acquisition settings, namely scanner effects, affect the reliability and reproducibility of the radiomics results. This paper assesses how the preprocessing methods (including N4 bias field correction and image resampling) and the harmonization methods (either the six intensity normalization methods working on brain MRI images or the ComBat method working on radiomic features) help to remove the scanner effects and improve the radiomic feature reproducibility in brain MRI radiomics. The analyses were based on in vitro datasets (homogeneous and heterogeneous phantom data) and in vivo datasets (brain MRI images collected from healthy volunteers and clinical patients with brain tumors). The results show that the ComBat method is essential and vital to remove scanner effects in brain MRI radiomic studies. Moreover, the intensity normalization methods, while not able to remove scanner effects at the radiomic feature level, still yield more comparable MRI images and improve the robustness of the harmonized features to the choice among ComBat implementations.

Radiomics: A Primer for Breast Radiologists

Radiomics has a long-standing history in breast imaging with computer-aided detection (CAD) for screening mammography developed in the late 20th century. Although conventional CAD had widespread adoption, the clinical benefits for experienced breast radiologists were debatable due to high false-positive marks and subsequent increased recall rates. The dramatic growth in recent years of artificial intelligence-based analysis, including machine learning and deep learning, has provided numerous opportunities for improved modern radiomics work in breast imaging. There has been extensive radiomics work in mammography, digital breast tomosynthesis, MRI, ultrasound, PET-CT, and combined multimodality imaging. Specific radiomics outcomes of interest have been diverse, including CAD, prediction of response to neoadjuvant therapy, lesion classification, and survival, among other outcomes. Additionally, the radiogenomics subfield that correlates radiomics features with genetics has been very proliferative, in parallel with the clinical validation of breast cancer molecular subtypes and gene expression assays. Despite the promise of radiomics, there are important challenges related to image normalization, limited large unbiased data sets, and lack of external validation. Much of the radiomics work to date has been exploratory using single-institution retrospective series for analysis, but several promising lines of investigation have made the leap to clinical practice with commercially available products. As a result, breast radiologists will increasingly be incorporating radiomics-based tools into their daily practice in the near future. Therefore, breast radiologists must have a broad understanding of the scope, applications, and limitations of radiomics work.