Breast cancer MRI radiomics: An overview of algorithmic features and impact of inter-reader variability in annotating tumors

Identifying radiogenomic associations of breast cancer based on DCE-MRI by using Siamese Neural Network with manufacturer bias normalization

BACKGROUND AND PURPOSE

The immunohistochemical test (IHC) for Human Epidermal Growth Factor Receptor 2 (HER2) and hormone receptors (HR) provides prognostic information and guides treatment for patients with invasive breast cancer. The objective of this paper is to establish a non-invasive system for identifying HER2 and HR in breast cancer using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI).

METHODS

In light of the absence of high-performance algorithms and external validation in previously published methods, this study utilizes 3D deep features and radiomics features to represent the information of the Region of Interest (ROI). A Siamese Neural Network was employed as the classifier, with 3D deep features and radiomics features serving as the network input. To neutralize manufacturer bias, a batch effect normalization method, ComBat, was introduced. To enhance the reliability of the study, two datasets, Predict Your Therapeutic Response with Imaging and moLecular Analysis (I-SPY 1) and I-SPY 2, were incorporated. I-SPY 2 was utilized for model training and validation, while I-SPY 1 was exclusively employed for external validation. Additionally, a breast tumor segmentation network was trained to improve radiomic feature extraction.

RESULTS

The results indicate that our approach achieved an average Area Under the Curve (AUC) of 0.632, with a Standard Error of the Mean (SEM) of 0.042 for HER2 prediction in the I-SPY 2 dataset. For HR prediction, our method attained an AUC of 0.635 (SEM 0.041), surpassing other published methods in the AUC metric. Moreover, the proposed method yielded competitive results in other metrics. In external validation using the I-SPY 1 dataset, our approach achieved an AUC of 0.567 (SEM 0.032) for HR prediction and 0.563 (SEM 0.033) for HER2 prediction.

CONCLUSION

This study proposes a non-invasive system for identifying HER2 and HR in breast cancer. Although the results do not conclusively demonstrate superiority in both tasks, they indicate that the proposed method achieved good performance and is a competitive classifier compared to other reference methods. Ablation studies demonstrate that both radiomics features and deep features for the Siamese Neural Network are beneficial for the model. The introduced manufacturer bias normalization method has been shown to enhance the method's performance. Furthermore, the external validation of the method enhances the reliability of this research. Source code, pre-trained segmentation network, Radiomics and deep features, data for statistical analysis, and Supporting Information of this article are online at: https://github.com/FORRESTHUACHEN/Siamese_Neural_Network_based_Brest_cancer_Radiogenomic.

Prediction of High-Risk Neuroblastoma Among Neuroblastic Tumors Using Radiomics Features Derived from Magnetic Resonance Imaging: A Pilot Study

PURPOSE

This study aimed to predict high-risk neuroblastoma among neuroblastic tumors using radiomics features extracted from MRI.

MATERIALS AND METHODS

Pediatric patients (age≤18 years) diagnosed with neuroblastic tumors who had pre-treatment MR images available were enrolled from institution A from January 2010 to November 2019 (training set) and institution B from January 2016 to January 2022 (test set). Segmentation was performed with regions of interest manually drawn along tumor margins on the slice with the widest tumor area by two radiologists. First-order and texture features were extracted and intraclass correlation coefficients (ICCs) were calculated. Multivariate logistic regression (MLR) and random forest (RF) models from 10-fold cross-validation were built using these features. The trained MLR and RF models were tested in an external test set.

RESULTS

Thirty-two patients (M:F=23:9, 26.0±26.7 months) were in the training set and 14 patients (M:F=10:4, 33.4±20.4 months) were in the test set with radiomics features (n=930) being extracted. For 10 of the most relevant features selected, intra- and inter-observer variability was moderate to excellent (ICCs 0.633-0.911, 0.695-0.985, respectively). The area under the receiver operating characteristic curve (AUC) was 0.94 (sensitivity 67%, specificity 91%, and accuracy 84%) for the MLR model and the average AUC was 0.83 (sensitivity 44%, specificity 87%, and accuracy 75%) for the RF model from 10-fold cross-validation. In the test set, AUCs of the MLR and RF models were 0.94 and 0.91, respectively.

CONCLUSION

An MRI-based radiomics model can help predict high-risk neuroblastoma among neuroblastic tumors.

Artificial Intelligence-Enhanced Breast MRI: Applications in Breast Cancer Primary Treatment Response Assessment and Prediction

ABSTRACT

Primary systemic therapy (PST) is the treatment of choice in patients with locally advanced breast cancer and is nowadays also often used in patients with early-stage breast cancer. Although imaging remains pivotal to assess response to PST accurately, the use of imaging to predict response to PST has the potential to not only better prognostication but also allow the de-escalation or omission of potentially toxic treatment with undesirable adverse effects, the accelerated implementation of new targeted therapies, and the mitigation of surgical delays in selected patients. In response to the limited ability of radiologists to predict response to PST via qualitative, subjective assessments of tumors on magnetic resonance imaging (MRI), artificial intelligence-enhanced MRI with classical machine learning, and in more recent times, deep learning, have been used with promising results to predict response, both before the start of PST and in the early stages of treatment. This review provides an overview of the current applications of artificial intelligence to MRI in assessing and predicting response to PST, and discusses the challenges and limitations of their clinical implementation.

Comparing effectiveness of image perturbation and test retest imaging in improving radiomic model reliability

Image perturbation is a promising technique to assess radiomic feature repeatability, but whether it can achieve the same effect as test-retest imaging on model reliability is unknown. This study aimed to compare radiomic model reliability based on repeatable features determined by the two methods using four different classifiers. A 191-patient public breast cancer dataset with 71 test-retest scans was used with pre-determined 117 training and 74 testing samples. We collected apparent diffusion coefficient images and manual tumor segmentations for radiomic feature extraction. Random translations, rotations, and contour randomizations were performed on the training images, and intra-class correlation coefficient (ICC) was used to filter high repeatable features. We evaluated model reliability in both internal generalizability and robustness, which were quantified by training and testing AUC and prediction ICC. Higher testing performance was found at higher feature ICC thresholds, but it dropped significantly at ICC = 0.95 for the test-retest model. Similar optimal reliability can be achieved with testing AUC = 0.7-0.8 and prediction ICC > 0.9 at the ICC threshold of 0.9. It is recommended to include feature repeatability analysis using image perturbation in any radiomic study when test-retest is not feasible, but care should be taken when deciding the optimal feature repeatability criteria.

Stability of Multi-Parametric Prostate MRI Radiomic Features to Variations in Segmentation

Stability analysis remains a fundamental step in developing a successful imaging biomarker to personalize oncological strategies. This study proposes an in silico contour generation method for simulating segmentation variations to identify stable radiomic features. Ground-truth annotation provided for the whole prostate gland on the multi-parametric MRI sequences (T2w, ADC, and SUB-DCE) were perturbed to mimic segmentation differences observed among human annotators. In total, we generated 15 synthetic contours for a given image-segmentation pair. One thousand two hundred twenty-four unfiltered/filtered radiomic features were extracted applying Pyradiomics, followed by stability assessment using ICC(1,1). Stable features identified in the internal population were then compared with an external population to discover and report robust features. Finally, we also investigated the impact of a wide range of filtering strategies on the stability of features. The percentage of unfiltered (filtered) features that remained robust subjected to segmentation variations were T2w-36% (81%), ADC-36% (94%), and SUB-43% (93%). Our findings suggest that segmentation variations can significantly impact radiomic feature stability but can be mitigated by including pre-filtering strategies as part of the feature extraction pipeline.

Influence of Image Processing on Radiomic Features From Magnetic Resonance Imaging

OBJECTIVE

Before implementing radiomics in routine clinical practice, comprehensive knowledge about the repeatability and reproducibility of radiomic features is required. The aim of this study was to systematically investigate the influence of image processing parameters on radiomic features from magnetic resonance imaging (MRI) in terms of feature values as well as test-retest repeatability.

MATERIALS AND METHODS

Utilizing a phantom consisting of 4 onions, 4 limes, 4 kiwifruits, and 4 apples, we acquired a test-retest dataset featuring 3 of the most commonly used MRI sequences on a 3 T scanner, namely, a T1-weighted, a T2-weighted, and a fluid-attenuated inversion recovery sequence, each at high and low resolution. After semiautomatic image segmentation, image processing with systematic variation of image processing parameters was performed, including spatial resampling, intensity discretization, and intensity rescaling. For each respective image processing setting, a total of 45 radiomic features were extracted, corresponding to the following 7 matrices/feature classes: conventional indices, histogram matrix, shape matrix, gray-level zone length matrix, gray-level run length matrix, neighboring gray-level dependence matrix, and gray-level cooccurrence matrix. Systematic differences of individual features between different resampling steps were assessed using 1-way analysis of variance with Tukey-type post hoc comparisons to adjust for multiple testing. Test-retest repeatability of radiomic features was measured using the concordance correlation coefficient, dynamic range, and intraclass correlation coefficient.

RESULTS

Image processing influenced radiological feature values. Regardless of the acquired sequence and feature class, significant differences ( P < 0.05) in feature values were found when the size of the resampled voxels was too large, that is, bigger than 3 mm. Almost all higher-order features depended strongly on intensity discretization. The effects of intensity rescaling were negligible except for some features derived from T1-weighted sequences. For all sequences, the percentage of repeatable features (concordance correlation coefficient and dynamic range ≥ 0.9) varied considerably depending on the image processing settings. The optimal image processing setting to achieve the highest percentage of stable features varied per sequence. Irrespective of image processing, the fluid-attenuated inversion recovery sequence in high-resolution overall yielded the highest number of stable features in comparison with the other sequences (89% vs 64%-78% for the respective optimal image processing settings). Across all sequences, the most repeatable features were generally obtained for a spatial resampling close to the originally acquired voxel size and an intensity discretization to at least 32 bins.

CONCLUSION

Variation of image processing parameters has a significant impact on the values of radiomic features as well as their repeatability. Furthermore, the optimal image processing parameters differ for each MRI sequence. Therefore, it is recommended that these processing parameters be determined in corresponding test-retest scans before clinical application. Extensive repeatability, reproducibility, and validation studies as well as standardization are required before quantitative image analysis and radiomics can be reliably translated into routine clinical care.

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.

Robustness of radiomics to variations in segmentation methods in multimodal brain MRI

Radiomics in neuroimaging uses fully automatic segmentation to delineate the anatomical areas for which radiomic features are computed. However, differences among these segmentation methods affect radiomic features to an unknown extent. A scan-rescan dataset (n = 46) of T1-weighted and diffusion tensor images was used. Subjects were split into a sleep-deprivation and a control group. Scans were segmented using four segmentation methods from which radiomic features were computed. First, we measured segmentation agreement using the Dice-coefficient. Second, robustness and reproducibility of radiomic features were measured using the intraclass correlation coefficient (ICC). Last, difference in predictive power was assessed using the Friedman-test on performance in a radiomics-based sleep deprivation classification application. Segmentation agreement was generally high (interquartile range = 0.77–0.90) and median feature robustness to segmentation method variation was higher (ICC > 0.7) than scan-rescan reproducibility (ICC 0.3–0.8). However, classification performance differed significantly among segmentation methods (p < 0.001) ranging from 77 to 84%. Accuracy was higher for more recent deep learning-based segmentation methods. Despite high agreement among segmentation methods, subtle differences significantly affected radiomic features and their predictive power. Consequently, the effect of differences in segmentation methods should be taken into account when designing and evaluating radiomics-based research methods.

Impact of image quality on radiomics applications

Radiomics features extracted from medical images have been widely reported to be useful in the patient specific outcome modeling for variety of assessment and prediction purposes. Successful application of radiomics features as imaging biomarkers, however, is dependent on the robustness of the approach to the variation in each step of the modeling workflow. Variation in the input image quality is one of the main sources that impacts the reproducibility of radiomics analysis when a model is applied to broader range of medical imaging data. The quality of medical image is generally affected by both the scanner related factors such as image acquisition/reconstruction settings and the patient related factors such as patient motion. This article aimed to review the published literatures in this field that reported the impact of various imaging factors on the radiomics features through the change in image quality. The literatures were categorized by different imaging modalities and also tabulated based on the imaging parameters and the class of radiomics features included in the study. Strategies for image quality standardization were discussed based on the relevant literatures and recommendations for reducing the impact of image quality variation on the radiomics in multi-institutional clinical trial were summarized at the end of this article.

The stability of oncologic MRI radiomic features and the potential role of deep learning: a review

The use of MRI radiomic models for the diagnosis, prognosis and treatment response prediction of tumors has been increasingly reported in literature. However, its widespread adoption in clinics is hampered by issues related to features stability. In the MRI radiomic workflow, the main factors that affect radiomic features computation can be found in the image acquisition and reconstruction phase, in the image pre-processing steps, and in the segmentation of the region of interest on which radiomic indices are extracted. Deep Neural Networks (DNNs), having shown their potentiality in the medical image processing and analysis field, can be seen as an attractive strategy to partially overcome the issues related to radiomic stability and mitigate their impact. In fact, DNN approaches can be prospectively integrated in the MRI radiomic workflow to improve image quality, obtain accurate and reproducible segmentations and generate standardized images. In this review, DNN methods that can be included in the image processing steps of the radiomic workflow are described and discussed, in the light of a detailed analysis of the literature in the context of MRI radiomic reliability.

Challenges in ensuring the generalizability of image quantitation methods for MRI

Image quantitation methods including quantitative MRI, multiparametric MRI, and radiomics offer great promise for clinical use. However, many of these methods have limited clinical adoption, in part due to issues of generalizability, that is, the ability to translate methods and models across institutions. Researchers can assess generalizability through measurement of repeatability and reproducibility, thus quantifying different aspects of measurement variance. In this article, we review the challenges to ensuring repeatability and reproducibility of image quantitation methods as well as present strategies to minimize their variance to enable wider clinical implementation. We present possible solutions for achieving clinically acceptable performance of image quantitation methods and briefly discuss the impact of minimizing variance and achieving generalizability towards clinical implementation and adoption.

Precision of MRI radiomics features in the liver and hepatocellular carcinoma

OBJECTIVES

To assess the precision of MRI radiomics features in hepatocellular carcinoma (HCC) tumors and liver parenchyma.

METHODS

The study population consisted of 55 patients, including 16 with untreated HCCs, who underwent two repeat contrast-enhanced abdominal MRI exams within 1 month to evaluate: (1) test-retest repeatability using the same MRI system (n = 28, 10 HCCs); (2) inter-platform reproducibility between different MRI systems (n = 27, 6 HCCs); (3) inter-observer reproducibility (n = 16, 16 HCCs). Shape and 1st- and 2nd-order radiomics features were quantified on pre-contrast T1-weighted imaging (WI), T1WI portal venous phase (pvp), T2WI, and ADC (apparent diffusion coefficient), on liver regions of interest (ROIs) and HCC volumes of interest (VOIs). Precision was assessed by calculating intraclass correlation coefficient (ICC), concordance correlation coefficient (CCC), and coefficient of variation (CV).

RESULTS

There was moderate to excellent test-retest repeatability of shape and 1st- and 2nd-order features for all sequences in HCCs (ICC: 0.53-0.99; CV: 3-29%), and moderate to good test-retest repeatability of 1st- and 2nd-order features for T1WI sequences, and 2nd-order features for T2WI in the liver (ICC: 0.53-0.73; CV: 12-19%). There was poor inter-platform reproducibility for all features and sequences, except for shape and 1st-order features on T1WI in HCCs (CCC: 0.58-0.99; CV: 3-15%). Good to excellent inter-observer reproducibility was found for all features and sequences in HCCs (CCC: 0.80-0.99; CV: 4-15%) and moderate to good for liver (CCC: 0.45-0.86; CV: 6-25%).

CONCLUSIONS

MRI radiomics features have acceptable repeatability in the liver and HCC when using the same MRI system and across readers but have low reproducibility across MR systems, except for shape and 1st-order features on T1WI. Data must be interpreted with caution when performing multiplatform radiomics studies.

KEY POINTS

• MRI radiomics features have acceptable repeatability when using the same MRI system but less reproducible when using different MRI platforms. • MRI radiomics features extracted from T1 weighted-imaging show greater stability across exams than T2 weighted-imaging and ADC. • Inter-observer reproducibility of MRI radiomics features was found to be good in HCC tumors and acceptable in liver parenchyma.

Radiomics feature reliability assessed by intraclass correlation coefficient: a systematic review

Radiomics research is rapidly growing in recent years, but more concerns on radiomics reliability are also raised. This review attempts to update and overview the current status of radiomics reliability research in the ever expanding medical literature from the perspective of a single reliability metric of intraclass correlation coefficient (ICC). To conduct this systematic review, Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed. After literature search and selection, a total of 481 radiomics studies using CT, PET, or MRI, covering a wide range of subject and disease types, were included for review. In these highly heterogeneous studies, feature reliability to image segmentation was much more investigated than reliability to other factors, such as image acquisition, reconstruction, post-processing, and feature quantification. The reported ICCs also suggested high radiomics feature reliability to image segmentation. Image acquisition was found to introduce much more feature variability than image segmentation, in particular for MRI, based on the reported ICC values. Image post-processing and feature quantification yielded different levels of radiomics reliability and might be used to mitigate image acquisition-induced variability. Some common flaws and pitfalls in ICC use were identified, and suggestions on better ICC use were given. Due to the extremely high study heterogeneities and possible risks of bias, the degree of radiomics feature reliability that has been achieved could not yet be safely synthesized or derived in this review. More future researches on radiomics reliability are warranted.

Improved value of whole-lesion histogram analysis on DCE parametric maps for diagnosing small breast cancer (≤ 1 cm)

OBJECTIVES

To determine if whole-lesion histogram analysis on dynamic contrast-enhanced (DCE) parametric maps help to improve the diagnostic accuracy of small suspicious breast lesions (≤ 1 cm).

METHODS

This retrospective study included 99 female patients with 114 lesions (40 malignant and 74 benign lesions) suspicious on magnetic resonance imaging (MRI).Two radiologists reviewed all lesions and descripted the morphologic and kinetic characteristics according to BI-RADS by consensus. Whole lesions were segmented on DCE parametric maps (washin and washout), and quantitative histogram features were extracted. Univariate analysis and multivariate logistic regression analysis with forward stepwise covariate selection were performed to identify significant variables. Diagnostic performance was assessed and compared with that of qualitative BI-RADS assessment and quantitative histogram analysis by ROC analysis.

RESULTS

For malignancy defined as a washout or plateau pattern, the qualitative kinetic pattern showed a significant difference between the two groups (p = 0.023), yielding an AUC of 0.603 (95% confidence interval [CI]: 0.507, 0.694). The mean and median of washout were independent quantitative predictors of malignancy (p = 0.002, 0.010), achieving an AUC of 0.796 (95% CI: 0. 709, 0.865). The AUC of the quantitative model was better than that of the qualitative model (p < 0.001).

CONCLUSIONS

Compared with the qualitative BI-RADS assessment, quantitative whole-lesion histogram analysis on DCE parametric maps was better to discriminate between small benign and malignant breast lesions (≤ 1 cm) initially defined as suspicious on DCE-MRI.

KEY POINTS

• For malignancy defined as a washout or plateau, the kinetic pattern may provide information to diagnose small breast cancer. • The mean and median of washout map were significantly lower for small malignant breast lesions than for benign lesions. • Quantitative histogram analysis on MRI parametric maps improves diagnostic accuracy for small breast cancer, which may obviate unnecessary biopsy.

Radiomics feature stability of open-source software evaluated on apparent diffusion coefficient maps in head and neck cancer

Radiomics is a promising technique for discovering image based biomarkers of therapy response in cancer. Reproducibility of radiomics features is a known issue that is addressed by the image biomarker standardisation initiative (IBSI), but it remains challenging to interpret previously published radiomics signatures. This study investigates the reproducibility of radiomics features calculated with two widely used radiomics software packages (IBEX, MaZda) in comparison to an IBSI compliant software package (PyRadiomics). Intensity histogram, shape and textural features were extracted from 334 diffusion weighted magnetic resonance images of 59 head and neck cancer (HNC) patients from the PREDICT-HN observational radiotherapy study. Based on name and linear correlation, PyRadiomics shares 83 features with IBEX and 49 features with MaZda, a sub-set of well correlated features are considered reproducible (IBEX: 15 features, MaZda: 18 features). We explore the impact of including non-reproducible radiomics features in a HNC radiotherapy response model. It is possible to classify equivalent patient groups using radiomic features from either software, but only when restricting the model to reliable features using a correlation threshold method. This is relevant for clinical biomarker validation trials as it provides a framework to assess the reproducibility of reported radiomic signatures from existing trials.

Machine Learning Algorithm Validation: From Essentials to Advanced Applications and Implications for Regulatory Certification and Deployment

The deployment of machine learning (ML) models in the health care domain can increase the speed and accuracy of diagnosis and improve treatment planning and patient care. Translating academic research to applications that are deployable in clinical settings requires the ability to generalize and high reproducibility, which are contingent on a rigorous and sound methodology for the development and evaluation of ML models. This article describes the fundamental concepts and processes for ML model evaluation and highlights common workflows. It concludes with a discussion of the requirements for the deployment of ML models in clinical settings.

Contrast-Enhanced Mammography and Radiomics Analysis for Noninvasive Breast Cancer Characterization: Initial Results

PURPOSE

To investigate the potential of contrast-enhanced mammography (CEM) and radiomics analysis for the noninvasive differentiation of breast cancer invasiveness, hormone receptor status, and tumor grade.

PROCEDURES

This retrospective study included 100 patients with 103 breast cancers who underwent pretreatment CEM. Radiomics analysis was performed using MAZDA software. Lesions were manually segmented. Radiomic features were derived from first-order histogram (HIS), co-occurrence matrix (COM), run length matrix (RLM), absolute gradient, autoregressive model, the discrete Haar wavelet transform (WAV), and lesion geometry. Fisher, probability of error and average correlation (POE+ACC), and mutual information (MI) coefficients informed feature selection. Linear discriminant analysis followed by k-nearest neighbor classification (with leave-one-out cross-validation) was used for pairwise texture-based separation of tumor invasiveness and hormone receptor status using histopathology as the standard of reference.

RESULTS

Radiomics analysis achieved the highest accuracies of 87.4 % for differentiating invasive from noninvasive cancers based on COM+HIS/MI, 78.4 % for differentiating HR positive from HR negative cancers based on COM+HIS/Fisher, 97.2 % for differentiating human epidermal growth factor receptor 2 (HER2)-positive/HR-negative from HER2-negative/HR-positive cancers based on RLM+WAV/MI, 100 % for differentiating triple-negative from triple-positive breast cancers mainly based on COM+WAV+HIS/POE+ACC, and 82.1 % for differentiating triple-negative from HR-positive cancers mainly based on WAV+HIS/Fisher. Accuracies for differentiating grade 1 vs. grades 2 and 3 cancers were 90 % for invasive cancers (based on COM/MI) and 100 % for noninvasive cancers (almost entirely based on COM/MI).

CONCLUSIONS

Radiomics analysis with CEM has potential for noninvasive differentiation of tumors with different degrees of invasiveness, hormone receptor status, and tumor grade.

Imaging features of gadoxetic acid-enhanced MR imaging for evaluation of tumor-infiltrating CD8 cells and PD-L1 expression in hepatocellular carcinoma

BACKGROUND

Tumor-infiltrating CD8 cells and expression of programmed cell death ligand 1 (PD-L1) are immune checkpoint markers in patients with hepatocellular carcinoma (HCC). We aimed to determine the ability of preoperative gadoxetic acid-enhanced magnetic resonance imaging (MRI) findings to predict CD8 cell density and PD-L1 expression in HCC.

METHODS

A total of 120 patients with HCC who underwent 3.0-T gadoxetic acid-enhanced MRI before curative resection from January 2016 to June 2020 were enrolled and divided into a training set (n = 84) and a testing set (n = 36). Thirty-four patients with advanced stage HCC who received anti-PD-1 inhibitor between January 2017 and April 2020 and underwent pretreated gadoxetic acid-enhanced MRI scans were enrolled in an independent validation set. PD-L1 expression and CD8 cell infiltration were assessed with immunohistochemical staining, respectively. Two radiologists blinded to pathology results evaluated the pretreated MR features in consensus. Logistic regression and the receiver operating characteristic curve (ROC) analyses were used to determine the value of image features to predict high CD8 cell density, PD-L1 positivity and the combination of high CD8 cell density and PD-L1 positivity in HCC in the training set and validated the findings in the testing set. The associations of MRI predictors with the objective response to immunotherapy were assessed in the independent validation.

RESULTS

In the training set, the independent MRI predictors were irregular tumor margin (ITM, P = 0.008) and peritumoral low signal intensity (PLSI) on hepatobiliary phase (HBP) images (P < 0.001) for PD-L1 positivity, absence of an enhancing capsule (AEC, P = 0.001) and PLSI on HBP images (P = 0.025) for high CD8 cell density, and PLSI on HBP images (P = 0.001) and ITM (P = 0.023) for the both. The area under the curves (AUCs) of the predictive models for evaluating PD-L1 positivity, high CD8 cell density and the combination of high CD8 cell density and PD-L1 positivity were 0.810 and 0.809, 0.740 and 0.728, and 0.809 and 0.874 in the training and testing set, respectively. The objective response was demonstrated to be associated with the combination of PLSI on HBP images and ITM (PHI, P = 0.004), and the combination of PLSI on HBP images and AEC (PHA, P = 0.012) in the independent validation set.

CONCLUSIONS

Pretreated MRI features have the potential to identify patients with HCC in an immune-activated state and predict outcomes of immunotherapy. Trial registration The study was retrospectively registered on March 5, 2020 with registration no. [2020] 02-012-01.

Pre-operative MRI Radiomics for the Prediction of Progression and Recurrence in Meningiomas

Objectives: A subset of meningiomas may show progression/recurrence (P/R) after surgical resection. This study applied pre-operative MR radiomics based on support vector machine (SVM) to predict P/R in meningiomas.

Methods: From January 2007 to January 2018, 128 patients with pathologically confirmed WHO grade I meningiomas were included. Only patients who had undergone pre-operative MRIs and post-operative follow-up MRIs for more than 1 year were studied. Pre-operative T2WI and contrast-enhanced T1WI were analyzed. On each set of images, 32 first-order features and 75 textural features were extracted. The SVM classifier was utilized to evaluate the significance of extracted features, and the most significant four features were selected to calculate SVM score for each patient.

Results: Gross total resection (Simpson grades I–III) was performed in 93 (93/128, 72.7%) patients, and 19 (19/128, 14.8%) patients had P/R after surgery. Subtotal tumor resection, bone invasion, low apparent diffusion coefficient (ADC) value, and high SVM score were more frequently encountered in the P/R group (p < 0.05). In multivariate Cox hazards analysis, bone invasion, ADC value, and SVM score were high-risk factors for P/R (p < 0.05) with hazard ratios of 7.31, 4.67, and 8.13, respectively. Using the SVM score, an AUC of 0.80 with optimal cutoff value of 0.224 was obtained for predicting P/R. Patients with higher SVM scores were associated with shorter progression-free survival (p = 0.003).

Conclusions: Our preliminary results showed that pre-operative MR radiomic features may have the potential to offer valuable information in treatment planning for meningiomas.

Reproducibility of radiomics features derived from intravoxel incoherent motion diffusion-weighted MRI of cervical cancer

BACKGROUND

The reproducibility of intravoxel incoherent motion (IVIM)-based radiomics studies in humans has not been reported.

PURPOSE

To determine the inter- and intra-observer variability on the reproducibility of IVIM-based radiomics features in cervical cancer (CC).

MATERIAL AND METHODS

The IVIM images of 25 patients with CC were retrospectively collected. Based on the high-resolution T2-weighted images, the regions of interest (ROIs) were independently delineated twice in diffusion-weighted images at a b value of 1000 s/mm² (interval time was one month) by two radiologists. This was done at the largest transversal cross-sections of the tumors. The ROI was subsequently used in apparent diffusion coefficient (ADC), true diffusion coefficient (D), pseudo-diffusion coefficient (D*), and perfusion fraction (f) maps derived from IVIM images. In total, 105 radiomics features were then finally extracted from the IVIM-derived maps. The inter- and intra-observer reproducibility of IVIM-derived features was then evaluated using the intraclass correlation coefficient.

RESULTS

Inter- and intra-observer variability affected the reproducibility of radiomics features. D* map had 100% and 95% reproducible features, ADC map had 89% and 93%, D map had 97% and 86%, while f map had 54% and 62% reproducible features with good to excellent reliability in the intra-observer analysis. Similarly, D* map had 90% and 94%, ADC map had 85% and 70%, D map had 81% and 78%, while f map had 41% and 93% reproducible features with good to excellent reliability in the inter-observer analysis.

CONCLUSION

Inter- and intra-observer variability can affect radiomics analysis. Cognizant to this, multicenter studies should pay more attention to intra- and inter-observer variability.

Distinguishing granulomas from adenocarcinomas by integrating stable and discriminating radiomic features on non-contrast computed tomography scans

OBJECTIVE

To identify stable and discriminating radiomic features on non-contrast CT scans to develop more generalisable radiomic classifiers for distinguishing granulomas from adenocarcinomas.

METHODS

In total, 412 patients with adenocarcinomas and granulomas from three institutions were retrospectively included. Segmentations of the lung nodules were performed manually by an expert radiologist in a 2D axial view. Radiomic features were extracted from intra- and perinodular regions. A total of 145 patients were used as part of the training set (S_tr), whereas 205 patients were used as part of test set I (S_te¹) and 62 patients were used as part of independent test set II (S_te²). To mitigate the variation of CT acquisition parameters, we defined 'stable' radiomic features as those for which the feature expression remains relatively unchanged between different sites, as assessed using a Wilcoxon rank-sum test. These stable features were used to develop more generalisable radiomic classifiers that were more resilient to variations in lung CT scans. Features were ranked based on two criteria, firstly based on discriminability (i.e. maximising AUC) alone and subsequently based on maximising both feature stability and discriminability. Different machine-learning classifiers (Linear discriminant analysis, Quadratic discriminant analysis, Support vector machines and random forest) were trained with features selected using the two different criteria and then compared on the two independent test sets for distinguishing granulomas from adenocarcinomas, in terms of area under the receiver operating characteristic curve.

RESULTS

In the test sets, classifiers constructed using the criteria involving maximising feature stability and discriminability simultaneously achieved higher AUC compared with the discriminating alone criteria (S_te¹ [n = 205]: maximum AUCs of 0.85versus . 0.80; p-value = 0.047 and S_te² [n = 62]: maximum AUCs of 0.87 versus. 0.79; p-value = 0.021). These differences held for features extracted from scans with <3 mm slice thickness (AUC = 0.88 versus. 0.80; p-value = 0.039, n = 100) and for the ≥3 mm cases (AUC = 0.81 versus. 0.76; p-value = 0.034, n = 105). In both experiments, shape and peritumoural texture features had a higher stability compared with intratumoural texture features.

CONCLUSIONS

Our study suggests that explicitly accounting for both stability and discriminability results in more generalisable radiomic classifiers to distinguish adenocarcinomas from granulomas on non-contrast CT scans. Our results also showed that peritumoural texture and shape features were less affected by the scanner parameters compared with intratumoural texture features; however, they were also less discriminating compared with intratumoural features.

Radiomics- Quantitative Biomarker Analysis for Breast Cancer Diagnosis and Prediction: A Review

BACKGROUND

Cancer of the breast has become a global problem for women's health. Though concerns regarding early detection and accurate diagnosis were raised, an effort is required for precision medicine as well as personalized treatment. In the past years, the area of medicinal imaging has seen an unprecedented growth that leads to an advancement of radiomics, which provides countless quantitative biomarkers extracted from modern diagnostic images, including a detailed tumor characterization of breast malignancy.

DISCUSSION

In this research, we presented the methodology and implementation of radiomics, together with its future trends and challenges by the basis of published papers. Radiomics could distinguish between malignant from benign tumors, predict prognostic factors, molecular subtypes of breast carcinoma, treatment response to neoadjuvant chemotherapy (NAC), and recurrence survival. The incorporation of quantitative knowledge with clinical, histopathological and genomic information will enable physicians to afford customized care of treatment for patients with breast cancer.

CONCLUSION

Our research was intended to help physicians and radiologists learn fundamental knowledge about radiomics and also to work collaboratively with researchers to explore evidence for further usage in clinical practice.

Machine Learning Based on Multi-Parametric MRI to Predict Risk of Breast Cancer

Purpose

Machine learning (ML) can extract high-throughput features of images to predict disease. This study aimed to develop nomogram of multi-parametric MRI (mpMRI) ML model to predict the risk of breast cancer.

Methods

The mpMRI included non-enhanced and enhanced T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), apparent diffusion coefficient (ADC), K ^trans, K _ep, V _e, and V _p. Regions of interest were annotated in an enhanced T1WI map and mapped to other maps in every slice. 1,132 features and top-10 principal components were extracted from every parameter map. Single-parametric and multi-parametric ML models were constructed via 10 rounds of five-fold cross-validation. The model with the highest area under the curve (AUC) was considered as the optimal model and validated by calibration curve and decision curve. Nomogram was built with the optimal ML model and patients' characteristics.

Results

This study involved 144 malignant lesions and 66 benign lesions. The average age of patients with benign and malignant lesions was 42.5 years old and 50.8 years old, respectively, which were statistically different. The sixth and fourth principal components of K ^trans had more importance than others. The AUCs of K ^trans, K _ep, V _e and V _p, non-enhanced T1WI, enhanced T1WI, T2WI, and ADC models were 0.86, 0.81, 0.81, 0.83, 0.79, 0.81, 0.84, and 0.83 respectively. The model with an AUC of 0.90 was considered as the optimal model which was validated by calibration curve and decision curve. Nomogram for the prediction of breast cancer was built with the optimal ML models and patient age.

Conclusion

Nomogram could improve the ability of breast cancer prediction preoperatively.

Radiomics Approach for Prediction of Recurrence in Non-Functioning Pituitary Macroadenomas

Objectives

A subset of non-functioning pituitary macroadenomas (NFPAs) may exhibit early progression/recurrence (P/R) after surgical resection. The purpose of this study was to apply radiomics in predicting P/R in NFPAs.

Methods

Only patients who had undergone preoperative MRI and postoperative MRI follow-ups for more than 1 year were included in this study. From September 2010 to December 2017, 50 eligible patients diagnosed with pathologically confirmed NFPAs were identified. Preoperative coronal T2WI and contrast-enhanced (CE) T1WI imaging were analyzed by computer algorithms. For each imaging sequence, 32 first-order features and 75 texture features were extracted. Support vector machine (SVM) classifier was utilized to evaluate the importance of extracted parameters, and the most significant three parameters were used to build the prediction model. The SVM score was calculated based on the three selected features.

Results

Twenty-eight patients exhibited P/R (28/50, 56%) after surgery. The median follow-up time was 38 months, and the median time to P/R was 20 months. Visual disturbance, hypopituitarism, extrasellar extension, compression of the third ventricle, large tumor height and volume, failed optic chiasmatic decompression, and high SVM score were more frequently encountered in the P/R group (p < 0.05). In multivariate Cox hazards analysis, symptoms of sex hormones, hypopituitarism, and SVM score were high risk factors for P/R (p < 0.05) with hazard ratios of 10.71, 2.68, and 6.88. The three selected radiomics features were T1 surface-to-volume radio, T1 GLCM-informational measure of correlation, and T2 NGTDM-coarseness. The radiomics predictive model shows 25 true positive, 16 true negative, 6 false positive, and 3 false negative cases, with an accuracy of 82% and AUC of 0.78 in differentiating P/R from non-P/R NFPAs. For SVM score, optimal cut-off value of 0.537 and AUC of 0.87 were obtained for differentiation of P/R. Higher SVM scores were associated with shorter progression-free survival (p < 0.001).

Conclusions

Our preliminary results showed that objective and quantitative MR radiomic features can be extracted from NFPAs. Pending more studies and evidence to support the findings, radiomics analysis of preoperative MRI may have the potential to offer valuable information in treatment planning for NFPAs.

Multi-parametric MRI lesion heterogeneity biomarkers for breast cancer diagnosis

PURPOSE

To identify intra-lesion imaging heterogeneity biomarkers in multi-parametric Magnetic Resonance Imaging (mpMRI) for breast lesion diagnosis.

METHODS

Dynamic Contrast Enhanced (DCE) and Diffusion Weighted Imaging (DWI) of 73 female patients, with 85 histologically verified breast lesions were acquired. Non-rigid multi-resolution registration was utilized to spatially align sequences. Four (4) DCE (2^nd post-contrast frame, Initial-Enhancement, Post-Initial-Enhancement and Signal-Enhancement-Ratio) and one (1) DWI (Apparent-Diffusion-Coefficient) representations were analyzed, considering a representative lesion slice. 11 1^st-order-statistics and 16 texture features (Gray-Level-Co-occurrence-Matrix (GLCM) and Gray-Level-Run-Length-Matrix (GLRLM) based) were derived from lesion segments, provided by Fuzzy C-Means segmentation, across the 5 representations, resulting in 135 features. Least-Absolute-Shrinkage and Selection-Operator (LASSO) regression was utilized to select optimal feature subsets, subsequently fed into 3 classification schemes: Logistic-Regression (LR), Random-Forest (RF), Support-Vector-Machine-Sequential-Minimal-Optimization (SVM-SMO), assessed with Receiver-Operating-Characteristic (ROC) analysis.

RESULTS

LASSO regression resulted in 7, 6 and 7 features subsets from DCE, DWI and mpMRI, respectively. Best classification performance was obtained by the RF multi-parametric scheme (Area-Under-ROC-Curve, (AUC) ± Standard-Error (SE), AUC ± SE = 0.984 ± 0.025), as compared to DCE (AUC ± SE = 0.961 ± 0.030) and DWI (AUC ± SE = 0.938 ± 0.032) and statistically significantly higher as compared to DWI. The selected mpMRI feature subset highlights the significance of entropy (1^st-order-statistics and 2^nd-order-statistics (GLCM)) and percentile features extracted from 2^nd post-contrast frame, PIE, SER maps and ADC map.

CONCLUSION

Capturing breast intra-lesion heterogeneity, across mpMRI lesion segments with 1^st-order-statistics and texture features (GLCM and GLRLM based), offers a valuable diagnostic tool for breast cancer.

Contribution of Magnetic Resonance Imaging in Determining Lumpectomy Cavity in Breast Radiotherapy

BACKGROUND

Accurate localization of the lumpectomy cavity is important for breast cancer radiotherapy after breast-conserving surgery (BCS), but the LC localization based on CT is often difficult to delineate accurately. The study aimed to compare CT-defined LC planning to MRI-defined findings in the supine position for higher soft-tissue resolution of MRI.

METHODS

Fifty-nine breast cancer patients underwent radiotherapy CT planning in supine position followed by MR imaging on the same day. LC was contoured by the radiologist and radiation oncologist together by CT and MRI separately. T2 weighted MR images and tomography findings were combined and the LC volume, mean diameter and the longest axis length were measured after contouring. Subsequently, patients were divided into two groups according to seroma in LC and the above-mentioned parameters were compared.

RESULTS

We did not find any statistically significant difference in the LC volume, mean diameter and length at the longest axis between CT and MRI but based on the presence or absence of seroma, statistically significant differences were found in the LC volumes and the length at the longest axis of LC volumes.

CONCLUSION

We believe that the supine MRI in the same position with CT will be more effective for radiotherapy planning, particularly in patients without a seroma in the surgical cavity.

Artificial Intelligence and Texture Analysis in Cardiac Imaging

PURPOSE OF REVIEW

The aim of this structured review is to summarize the current research applications and opportunities arising from artificial intelligence (AI) and texture analysis with regard to cardiac imaging.

RECENT FINDINGS

Current research findings suggest tremendous potential for AI in cardiac imaging, especially with regard to objective image analyses, overcoming the limitations of an observer-dependent subjective image interpretation. Researchers have used this technique across multiple imaging modalities, for instance to detect myocardial scars in cardiac MR imaging, to predict contrast enhancement in non-contrast studies, and to improve image acquisition and reconstruction. AI in medical imaging has the potential to provide novel, much-needed applications for improving patient care pertaining to the cardiovascular system. While several shortcomings are still present in the current methodology, AI may serve as a resourceful assistant to radiologists and clinicians alike.

Radiomics at a Glance: A Few Lessons Learned from Learning Approaches

Simple Summary

Radiomics has become a prominent component of medical imaging research and many studies show its specific value as a support tool for clinical decision-making processes. Radiomic data are typically analyzed with statistical and machine learning methods, which change depending on the disease context and the imaging modality. We found a certain bias in the literature towards the use of such methods and believe that this limitation may influence the capacity of producing accurate and reliable decisions. Therefore, in view of the relevance of various types of learning methods, we report their significance and discuss their unrevealed potential.

Abstract

Processing and modeling medical images have traditionally represented complex tasks requiring multidisciplinary collaboration. The advent of radiomics has assigned a central role to quantitative data analytics targeting medical image features algorithmically extracted from large volumes of images. Apart from the ultimate goal of supporting diagnostic, prognostic, and therapeutic decisions, radiomics is computationally attractive due to specific strengths: scalability, efficiency, and precision. Optimization is achieved by highly sophisticated statistical and machine learning algorithms, but it is especially deep learning that stands out as the leading inference approach. Various types of hybrid learning can be considered when building complex integrative approaches aimed to deliver gains in accuracy for both classification and prediction tasks. This perspective reviews some selected learning methods by focusing on both their significance for radiomics and their unveiled potential.

MRI-based radiomics in breast cancer: feature robustness with respect to inter-observer segmentation variability

Radiomics is an emerging field using the extraction of quantitative features from medical images for tissue characterization. While MRI-based radiomics is still at an early stage, it showed some promising results in studies focusing on breast cancer patients in improving diagnoses and therapy response assessment. Nevertheless, the use of radiomics raises a number of issues regarding feature quantification and robustness. Therefore, our study aim was to determine the robustness of radiomics features extracted by two commonly used radiomics software with respect to variability in manual breast tumor segmentation on MRI. A total of 129 histologically confirmed breast tumors were segmented manually in three dimensions on the first post-contrast T1-weighted MR exam by four observers: a dedicated breast radiologist, a resident, a Ph.D. candidate, and a medical student. Robust features were assessed using the intraclass correlation coefficient (ICC > 0.9). The inter-observer variability was evaluated by the volumetric Dice Similarity Coefficient (DSC). The mean DSC for all tumors was 0.81 (range 0.19–0.96), indicating a good spatial overlap of the segmentations based on observers of varying expertise. In total, 41.6% (552/1328) and 32.8% (273/833) of all RadiomiX and Pyradiomics features, respectively, were identified as robust and were independent of inter-observer manual segmentation variability.

Radiomics in medical imaging-"how-to" guide and critical reflection

Radiomics is a quantitative approach to medical imaging, which aims at enhancing the existing data available to clinicians by means of advanced mathematical analysis. Through mathematical extraction of the spatial distribution of signal intensities and pixel interrelationships, radiomics quantifies textural information by using analysis methods from the field of artificial intelligence. Various studies from different fields in imaging have been published so far, highlighting the potential of radiomics to enhance clinical decision-making. However, the field faces several important challenges, which are mainly caused by the various technical factors influencing the extracted radiomic features.The aim of the present review is twofold: first, we present the typical workflow of a radiomics analysis and deliver a practical "how-to" guide for a typical radiomics analysis. Second, we discuss the current limitations of radiomics, suggest potential improvements, and summarize relevant literature on the subject.

Radiomics in diffusion data: a test-retest, inter- and intra-reader DWI phantom study

AIM

The aim of this study was to evaluate the robustness of radiomics features of a MRI (magnetic resonance imaging) phantom in quantitative diffusion-weighted imaging (DWI) and depending on the image resolution.

MATERIALS AND METHODS

Scanning of an in-house developed DWI phantom was performed at a 1.5 T MRI scanner (Magnetom AERA, Siemens, Erlangen, Germany) using an echo planar imaging (EPI) DWI sequence (b=0,500,1,000 s/mm²) with low (3×3 mm²) and high (2×2 mm²) image resolutions. Scans were repeated after phantom repositioning to evaluate retest reliability. Radiomics features were extracted after semi-automatic segmentation and standardised pre-processing. Intra-/interobserver reproducibility and test-retest robustness were assessed using intraclass correlation coefficients (ICC). Differences were tested with non-parametric Wilcoxon's signed-rank and Friedman's test (p < 0.05) with Dunn's post-hoc analysis.

RESULTS

Test-retest ICC was overall high with >0.90 for 39/46 radiomics features in all sequences/resolutions. Decreased test-retest ICCs were pronounced for conventional Min-value (overall ICC=0.817), and grey-level zone length matrix (GLZLM) features Short-Zone Emphasis (SZE) and Short-Zone Low Grey-level Emphasis (SZLGE) (for both overall ICC=0.927). Test-retest reproducibility was significantly different between b=500, 1,000 and apparent diffusion coefficient (ADC) (mean 0.975±0.050, 0.974±0.051 and 0.966±0.063), which remained significant after post-hoc analysis between b=1,000 and ADC (p = 0.022). ICCs were not significantly different between resolutions of 2×2 and 3×3 mm² regarding b=500 (mean: 0.977±0.052 and 0.974±0.049, p = 0.612), b=1,000 (mean: 0.973±0.059 and 0.974±0.054, p = 0.516), and ADC (mean: 0.972±0.049 and 0.955±0.101, p = 0.851). Inter- and intra-observer reliability was consistently high for all sequences (overall mean 0.992±0.021 and 0.990±0.028).

CONCLUSION

Under ex-vivo conditions, DWI provided robust radiomics features with those from ADC being slightly less robust than from raw DWI (b=500, 1,000 s/mm²). No significant difference was detected for different resolutions. Although, ex-vivo reliability of DWI radiomics features was high, no implications can be made regarding in-vivo analyses.

Radiomics for Tumor Characterization in Breast Cancer Patients: A Feasibility Study Comparing Contrast-Enhanced Mammography and Magnetic Resonance Imaging

The aim of our intra-individual comparison study was to investigate and compare the potential of radiomics analysis of contrast-enhanced mammography (CEM) and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) of the breast for the non-invasive assessment of tumor invasiveness, hormone receptor status, and tumor grade in patients with primary breast cancer. This retrospective study included 48 female patients with 49 biopsy-proven breast cancers who underwent pretreatment breast CEM and MRI. Radiomics analysis was performed by using MaZda software. Radiomics parameters were correlated with tumor histology (invasive vs. non-invasive), hormonal status (HR+ vs. HR-), and grading (low grade G1 + G2 vs. high grade G3). CEM radiomics analysis yielded classification accuracies of up to 92% for invasive vs. non-invasive breast cancers, 95.6% for HR+ vs. HR- breast cancers, and 77.8% for G1 + G2 vs. G3 invasive cancers. MRI radiomics analysis yielded classification accuracies of up to 90% for invasive vs. non-invasive breast cancers, 82.6% for HR+ vs. HR- breast cancers, and 77.8% for G1+G2 vs. G3 cancers. Preliminary results indicate a potential of both radiomics analysis of DCE-MRI and CEM for non-invasive assessment of tumor-invasiveness, hormone receptor status, and tumor grade. CEM may serve as an alternative to MRI if MRI is not available or contraindicated.

A rapid volume of interest-based approach of radiomics analysis of breast MRI for tumor decoding and phenotyping of breast cancer

BACKGROUND

Recently, radiomics has emerged as a non-invasive, imaging-based tissue characterization method in multiple cancer types. One limitation for robust and reproducible analysis lies in the inter-reader variability of the tumor annotations, which can potentially cause differences in the extracted feature sets and results. In this study, the diagnostic potential of a rapid and clinically feasible VOI (Volume of Interest)-based approach to radiomics is investigated to assess MR-derived parameters for predicting molecular subtype, hormonal receptor status, Ki67- and HER2-Expression, metastasis of lymph nodes and lymph vessel involvement as well as grading in patients with breast cancer.

METHODS

A total of 98 treatment-naïve patients (mean 59.7 years, range 28.0-89.4) with BI-RADS 5 and 6 lesions who underwent a dedicated breast MRI prior to therapy were retrospectively included in this study. The imaging protocol comprised dynamic contrast-enhanced T1-weighted imaging and T2-weighted imaging. Tumor annotations were obtained by drawing VOIs around the primary tumor lesions followed by thresholding. From each segmentation, 13.118 quantitative imaging features were extracted and analyzed with machine learning methods. Validation was performed by 5-fold cross-validation with 25 repeats.

RESULTS

Predictions for molecular subtypes obtained AUCs of 0.75 (HER2-enriched), 0.73 (triple-negative), 0.65 (luminal A) and 0.69 (luminal B). Differentiating subtypes from one another was highest for HER2-enriched vs triple-negative (AUC 0.97), followed by luminal B vs triple-negative (0.86). Receptor status predictions for Estrogen Receptor (ER), Progesterone Receptor (PR) and Hormone receptor positivity yielded AUCs of 0.67, 0.69 and 0.69, while Ki67 and HER2 Expressions achieved 0.81 and 0.62. Involvement of the lymph vessels could be predicted with an AUC of 0.8, while lymph node metastasis yielded an AUC of 0.71. Models for grading performed similar with an AUC of 0.71 for Elston-Ellis grading and 0.74 for the histological grading.

CONCLUSION

Our preliminary results of a rapid approach to VOI-based tumor-annotations for radiomics provides comparable results to current publications with the perks of clinical suitability, enabling a comprehensive non-invasive platform for breast tumor decoding and phenotyping.

Machine learning applications in imaging analysis for patients with pituitary tumors: a review of the current literature and future directions

PURPOSE

To provide an overview of fundamental concepts in machine learning (ML), review the literature on ML applications in imaging analysis of pituitary tumors for the last 10 years, and highlight the future directions on potential applications of ML for pituitary tumor patients.

METHOD

We presented an overview of the fundamental concepts in ML, its various stages used in healthcare, and highlighted the key components typically present in an imaging-based tumor analysis pipeline. A search was conducted across four databases (PubMed, Ovid, Embase, and Google Scholar) to gather research articles from the past 10 years (2009-2019) involving imaging related to pituitary tumor and ML. We grouped the studies by imaging modalities and analyzed the ML tasks in terms of the data inputs, reference standards, methodologies, and limitations.

RESULTS

Of the 16 studies included in our analysis, 10 appeared in 2018-2019. Most of the studies utilized retrospective data and followed a semi-automatic ML pipeline. The studies included use of magnetic resonance imaging (MRI), facial photographs, surgical microscopic video, spectrometry, and spectroscopy imaging. The objectives of the studies covered 14 distinct applications and majority of the studies addressed a binary classification problem. Only five of the 11 MRI-based studies had an external validation or a holdout set to test the performance of a final trained model.

CONCLUSION

Through our concise evaluation and comparison of the studies using the concepts presented, we highlight future directions so that potential ML applications using different imaging modalities can be developed to benefit the clinical care of pituitary tumor patients.

Multicenter evaluation of MRI-based radiomic features: A phantom study

INTRODUCTION

This work describes the development of a novel radiomics phantom designed for magnetic resonance imaging (MRI) that can be used in a multicenter setting. The purpose of this study is to assess the stability and reproducibility of MRI-based radiomic features using this phantom across different MRI scanners.

METHODS & MATERIALS

A set of phantoms were three-dimensional (3D) printed using MRI visible materials. One set of phantoms were imaged on seven MRI scanners and one was imaged on one MRI scanner. Radiomics analysis of the phantoms, which included first-order features, shape and texture features was performed. Intraclass correlation coefficient (ICC) was used to assess the stability of radiomic features across eight scanners and the reproducibility of two printed models on one scanner. Coefficient of variation (COV) was used to assess the reproducibility of radiomics measurements in the phantom on a single scanner.

RESULTS

The phantom models provide sufficient signal-to-noise and contrast in all the tumor models permitting robust automatic segmentation. During a 12-month period of monitoring, the phantom material was stable with T1 and T2 of 150.7 ± 6.7 ms and 56.1 ± 3.9 ms, respectively. Of all the radiomic features computed, 34 of 69 had COV < 10%. Features from first-order statistics were the most robust in stability across the eight scanners with eight of 12 (67%) having high stability. About 29 of 50 (58%) texture features had high stability and no shape features had high stability features across the eight scanners.

CONCLUSION

A novel MRI radiomics phantom has been developed to assess the reproducibility and stability of MRI-based radiomic features across multiple institutions. The variation in radiomic feature stability demonstrates the need for caution when interpreting these features for clinical studies.

Image-Based Cardiac Diagnosis With Machine Learning: A Review

Cardiac imaging plays an important role in the diagnosis of cardiovascular disease (CVD). Until now, its role has been limited to visual and quantitative assessment of cardiac structure and function. However, with the advent of big data and machine learning, new opportunities are emerging to build artificial intelligence tools that will directly assist the clinician in the diagnosis of CVDs. This paper presents a thorough review of recent works in this field and provide the reader with a detailed presentation of the machine learning methods that can be further exploited to enable more automated, precise and early diagnosis of most CVDs.

Optimal Statistical Incorporation of Independent Feature Stability Information into Radiomics Studies

Conducting side experiments termed robustness experiments, to identify features that are stable with respect to rescans, annotation, or other confounding effects is an important element in radiomics research. However, the matter of how to include the finding of these experiments into the model building process still needs to be explored. Three different methods for incorporating prior knowledge into a radiomics modelling process were evaluated: the naïve approach (ignoring feature quality), the most common approach consisting of removing unstable features, and a novel approach using data augmentation for information transfer (DAFIT). Multiple experiments were conducted using both synthetic and publicly available real lung imaging patient data. Ignoring additional information from side experiments resulted in significantly overestimated model performances meaning the estimated mean area under the curve achieved with a model was increased. Removing unstable features improved the performance estimation, while slightly decreasing the model performance, i.e. decreasing the area under curve achieved with the model. The proposed approach was superior both in terms of the estimation of the model performance and the actual model performance. Our experiments show that data augmentation can prevent biases in performance estimation and has several advantages over the plain omission of the unstable feature. The actual gain that can be obtained depends on the quality and applicability of the prior information on the features in the given domain. This will be an important topic of future research.

Breast Cancer Radiogenomics: Current Status and Future Directions

Radiogenomics is an area of research that aims to identify associations between imaging phenotypes ("radio-") and tumor genome ("-genomics"). Breast cancer radiogenomics research in particular has been an especially prolific area of investigation in recent years as evidenced by the wide number and variety of publications and conferences presentations. To date, research has primarily been focused on dynamic contrast enhanced pre-operative breast MRI and breast cancer molecular subtypes, but investigations have extended to all breast imaging modalities as well as multiple additional genetic markers including those that are commercially available. Furthermore, both human and computer-extracted features as well as deep learning techniques have been explored. This review will summarize the specific imaging modalities used in radiogenomics analysis, describe the methods of extracting imaging features, and present the types of genomics, molecular, and related information used for analysis. Finally, the limitations and future directions of breast cancer radiogenomics research will be discussed.

Harmonization of radiomic features of breast lesions across international DCE-MRI datasets

Purpose: Radiomic features extracted from medical images acquired in different countries may demonstrate a batch effect. Thus, we investigated the effect of harmonization on a database of radiomic features extracted from dynamic contrast-enhanced magnetic resonance (DCE-MR) breast imaging studies of 3150 benign lesions and cancers collected from international datasets, as well as the potential of harmonization to improve classification of malignancy. Approach: Eligible features were harmonized by category using the ComBat method. Harmonization effect on features was evaluated using the Davies-Bouldin index for degree of clustering between populations for both benign lesions and cancers. Performance in distinguishing between cancers and benign lesions was evaluated for each dataset using 10-fold cross validation with the area under the receiver operating characteristic curve (AUC) determined on the pre- and postharmonization sets of radiomic features in each dataset and a combined one. Differences in AUCs were evaluated for statistical significance. Results: The Davies-Bouldin index increased by 27% for benign lesions and by 43% for cancers, indicating that the postharmonization features were more similar. Classification performance using postharmonization features performed better than that using preharmonization features ( p < 0.001 for all three). Conclusion: Harmonization of radiomic features may enable combining databases from different populations for more comprehensive computer-aided diagnosis models of breast cancer.

Robustness and Reproducibility of Radiomics in Magnetic Resonance Imaging: A Phantom Study

OBJECTIVES

The aim of this study was to investigate the robustness and reproducibility of radiomic features in different magnetic resonance imaging sequences.

MATERIALS AND METHODS

A phantom was scanned on a clinical 3 T system using fluid-attenuated inversion recovery (FLAIR), T1-weighted (T1w), and T2-weighted (T2w) sequences with low and high matrix size. For retest data, scans were repeated after repositioning of the phantom. Test and retest datasets were segmented using a semiautomated approach. Intraobserver and interobserver comparison was performed. Radiomic features were extracted after standardized preprocessing of images. Test-retest robustness was assessed using concordance correlation coefficients, dynamic range, and Bland-Altman analyses. Reproducibility was assessed by intraclass correlation coefficients.

RESULTS

The number of robust features (concordance correlation coefficient and dynamic range ≥ 0.90) was higher for features calculated from FLAIR than from T1w and T2w images. High-resolution FLAIR images provided the highest percentage of robust features (n = 37/45, 81%). No considerable difference in the number of robust features was observed between low- and high-resolution T1w and T2w images (T1w low: n = 26/45, 56%; T1w high: n = 25/45, 54%; T2 low: n = 21/45, 46%; T2 high: n = 24/45, 52%). A total of 15 (33%) of 45 features showed excellent robustness across all sequences and demonstrated excellent intraobserver and interobserver reproducibility (intraclass correlation coefficient ≥ 0.75).

CONCLUSIONS

FLAIR delivers the most robust substrate for radiomic analyses. Only 15 of 45 features showed excellent robustness and reproducibility across all sequences. Care must be taken in the interpretation of clinical studies using nonrobust features.

Robustness of radiomic features in magnetic resonance imaging: review and a phantom study

Radiomic analysis has exponentially increased the amount of quantitative data that can be extracted from a single image. These imaging biomarkers can aid in the generation of prediction models aimed to further personalized medicine. However, the generalizability of the model is dependent on the robustness of these features. The purpose of this study is to review the current literature regarding robustness of radiomic features on magnetic resonance imaging. Additionally, a phantom study is performed to systematically evaluate the behavior of radiomic features under various conditions (signal to noise ratio, region of interest delineation, voxel size change and normalization methods) using intraclass correlation coefficients. The features extracted in this phantom study include first order, shape, gray level cooccurrence matrix and gray level run length matrix. Many features are found to be non-robust to changing parameters. Feature robustness assessment prior to feature selection, especially in the case of combining multi-institutional data, may be warranted. Further investigation is needed in this area of research.

Lymph Node Imaging in Patients with Primary Breast Cancer: Concurrent Diagnostic Tools

The detection of lymph node metastasis affects the management of patients with primary breast cancer significantly in terms of staging, treatment, and prognosis. The main goal for the radiologist is to determine and detect the presence of metastatic disease in nonpalpable axillary lymph nodes with a positive predictive value that is high enough to initially select patients for upfront axillary lymph node dissection. Features that are suggestive of axillary adenopathy may be seen with different imaging modalities, but ultrasound is the method of choice for evaluating axillary lymph nodes and for performing image-guided lymph node interventions. This review aims to provide a comprehensive overview of the available imaging modalities for lymph node assessment in patients diagnosed with primary breast cancer. IMPLICATIONS FOR PRACTICE: The detection of lymph node metastasis affects the management of patients with primary breast cancer. The main goal for the radiologist is to detect lymph node metastasis in patients to allow for the selection of patients who should undergo upfront axillary lymph node dissection. Features that are suggestive of axillary adenopathy may be seen with mammography, computed tomography, and magnetic resonance imaging, but ultrasonography is the imaging modality of choice for evaluating axillary lymph nodes. A normal axillary lymph node is characterized by a reniform shape, a maximal cortical thickness of 3 mm without focal bulging, smooth margins, and, depending on size, a discernable central fatty hilum.

Machine learning in breast MRI

Machine-learning techniques have led to remarkable advances in data extraction and analysis of medical imaging. Applications of machine learning to breast MRI continue to expand rapidly as increasingly accurate 3D breast and lesion segmentation allows the combination of radiologist-level interpretation (eg, BI-RADS lexicon), data from advanced multiparametric imaging techniques, and patient-level data such as genetic risk markers. Advances in breast MRI feature extraction have led to rapid dataset analysis, which offers promise in large pooled multiinstitutional data analysis. The object of this review is to provide an overview of machine-learning and deep-learning techniques for breast MRI, including supervised and unsupervised methods, anatomic breast segmentation, and lesion segmentation. Finally, it explores the role of machine learning, current limitations, and future applications to texture analysis, radiomics, and radiogenomics. Level of Evidence: 3 Technical Efficacy Stage: 2 J. Magn. Reson. Imaging 2019. J. Magn. Reson. Imaging 2020;52:998-1018.

Machine learning-based prediction of future breast cancer using algorithmically measured background parenchymal enhancement on high-risk screening MRI

BACKGROUND

Preliminary work has demonstrated that background parenchymal enhancement (BPE) assessed by radiologists is predictive of future breast cancer in women undergoing high-risk screening MRI. Algorithmically assessed measures of BPE offer a more precise and reproducible means of measuring BPE than human readers and thus might improve the predictive performance of future cancer development.

PURPOSE

To determine if algorithmically extracted imaging features of BPE on screening breast MRI in high-risk women are associated with subsequent development of cancer.

STUDY TYPE

Case-control study.

POPULATION

In all, 133 women at high risk for developing breast cancer; 46 of these patients developed breast cancer subsequently over a follow-up period of 2 years.

FIELD STRENGTH/SEQUENCE

5 T or 3.0 T T₁ -weighted precontrast fat-saturated and nonfat-saturated sequences and postcontrast nonfat-saturated sequences.

ASSESSMENT

Automatic features of BPE were extracted with a computer algorithm. Subjective BPE scores from five breast radiologists (blinded to clinical outcomes) were also available.

STATISTICAL TESTS

Leave-one-out crossvalidation for a multivariate logistic regression model developed using the automatic features and receiver operating characteristic (ROC) analysis were performed to calculate the area under the curve (AUC). Comparison of automatic features and subjective features was performed using a generalized regression model and the P-value was obtained. Odds ratios for automatic and subjective features were compared.

RESULTS

The multivariate model discriminated patients who developed cancer from the patients who did not, with an AUC of 0.70 (95% confidence interval: 0.60-0.79, P < 0.001). The imaging features remained independently predictive of subsequent development of cancer (P < 0.003) when compared with the subjective BPE assessment of the readers.

DATA CONCLUSION

Automatically extracted BPE measurements may potentially be used to further stratify risk in patients undergoing high-risk screening MRI.

LEVEL OF EVIDENCE

3 Technical Efficacy: Stage 5 J. Magn. Reson. Imaging 2019;50:456-464.

Application of Radiomics and Decision Support Systems for Breast MR Differential Diagnosis

Over the years, MR systems have evolved from imaging modalities to advanced computational systems producing a variety of numerical parameters that can be used for the noninvasive preoperative assessment of breast pathology. Furthermore, the combination with state-of-the-art image analysis methods provides a plethora of quantifiable imaging features, termed radiomics that increases diagnostic accuracy towards individualized therapy planning. More importantly, radiomics can now be complemented by the emerging deep learning techniques for further process automation and correlation with other clinical data which facilitate the monitoring of treatment response, as well as the prediction of patient's outcome, by means of unravelling of the complex underlying pathophysiological mechanisms which are reflected in tissue phenotype. The scope of this review is to provide applications and limitations of radiomics towards the development of clinical decision support systems for breast cancer diagnosis and prognosis.