Effects of MRI scanner parameters on breast cancer radiomics

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

BACKGROUND

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

PURPOSE

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

STUDY TYPE

Retrospective.

POPULATION

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

FIELD STRENGTH/SEQUENCE

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

ASSESSMENT

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

STATISTICAL TESTS

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

RESULTS

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

DATA CONCLUSION

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

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY: Stage 2.

MRI-based radiomics approach for the prediction of recurrence-free survival in triple-negative breast cancer after breast-conserving surgery or mastectomy

To explore the value of a radiomics signature and develop a nomogram combined with a radiomics signature and clinical factors for predicting recurrence-free survival in triple-negative breast cancer patients. We enrolled 151 patients from the cancer imaging archive who underwent preoperative contrast-enhanced magnetic resonance imaging. They were assigned to training, validation and external validation cohorts. Image features with coefficients not equal to zero in the 10-fold cross-validation were selected to generate a radiomics signature. Based on the optimal cutoff value of the radiomics signature determined by maximally selected log-rank statistics, patients were stratified into high- and low-risk groups in the training and validation cohorts. Kaplan-Meier survival analysis was performed for both groups. Kaplan-Meier survival distributions in these groups were compared using log-rank tests. Univariate and multivariate Cox regression analyses were used to construct clinical and combined models. Concordance index was used to assess the predictive performance of the 3 models. Calibration of the combined model was assessed using calibration curves. Four image features were selected to generate the radiomics signature. The Kaplan-Meier survival distributions of patients in the 2 groups were significantly different in the training (P < .001) and validation cohorts (P = .001). The C-indices of the radiomics model, clinical model, and combined model in the training and validation cohorts were 0.772, 0.700, 0.878, and 0.744, 0.574, 0.777, respectively. The C-indices of the radiomics model, clinical model, and combined model in the external validation cohort were 0.778, 0.733, 0.822, respectively. The calibration curves of the combined model showed good calibration. The radiomics signature can predict recurrence-free survival of patients with triple-negative breast cancer and improve the predictive performance of the clinical model.

Effects of MRI scanner manufacturers in classification tasks with deep learning models

Deep learning has become a leading subset of machine learning and has been successfully employed in diverse areas, ranging from natural language processing to medical image analysis. In medical imaging, researchers have progressively turned towards multi-center neuroimaging studies to address complex questions in neuroscience, leveraging larger sample sizes and aiming to enhance the accuracy of deep learning models. However, variations in image pixel/voxel characteristics can arise between centers due to factors including differences in magnetic resonance imaging scanners. Such variations create challenges, particularly inconsistent performance in machine learning-based approaches, often referred to as domain shift, where the trained models fail to achieve satisfactory or improved results when confronted with dissimilar test data. This study analyzes the performance of multiple disease classification tasks using multi-center MRI data obtained from three widely used scanner manufacturers (GE, Philips, and Siemens) across several deep learning-based networks. Furthermore, we investigate the efficacy of mitigating scanner vendor effects using ComBat-based harmonization techniques when applied to multi-center datasets of 3D structural MR images. Our experimental results reveal a substantial decline in classification performance when models trained on one type of scanner manufacturer are tested with data from different manufacturers. Moreover, despite applying ComBat-based harmonization, the harmonized images do not demonstrate any noticeable performance enhancement for disease classification tasks.

Radiomics in the evaluation of ovarian masses - a systematic review

OBJECTIVES

The study aim was to conduct a systematic review of the literature reporting the application of radiomics to imaging techniques in patients with ovarian lesions.

METHODS

MEDLINE/PubMed, Web of Science, Scopus, EMBASE, Ovid and ClinicalTrials.gov were searched for relevant articles. Using PRISMA criteria, data were extracted from short-listed studies. Validity and bias were assessed independently by 2 researchers in consensus using the Quality in Prognosis Studies (QUIPS) tool. Radiomic Quality Score (RQS) was utilised to assess radiomic methodology.

RESULTS

After duplicate removal, 63 articles were identified, of which 33 were eligible. Fifteen assessed lesion classifications, 10 treatment outcomes, 5 outcome predictions, 2 metastatic disease predictions and 1 classification/outcome prediction. The sample size ranged from 28 to 501 patients. Twelve studies investigated CT, 11 MRI, 4 ultrasound and 1 FDG PET-CT. Twenty-three studies (70%) incorporated 3D segmentation. Various modelling methods were used, most commonly LASSO (least absolute shrinkage and selection operator) (10/33). Five studies (15%) compared radiomic models to radiologist interpretation, all demonstrating superior performance. Only 6 studies (18%) included external validation. Five studies (15%) had a low overall risk of bias, 9 (27%) moderate, and 19 (58%) high risk of bias. The highest RQS achieved was 61.1%, and the lowest was - 16.7%.

CONCLUSION

Radiomics has the potential as a clinical diagnostic tool in patients with ovarian masses and may allow better lesion stratification, guiding more personalised patient care in the future. Standardisation of the feature extraction methodology, larger and more diverse patient cohorts and real-world evaluation is required before clinical translation.

CLINICAL RELEVANCE STATEMENT

Radiomics shows promising results in improving lesion stratification, treatment selection and outcome prediction. Modelling with larger cohorts and real-world evaluation is required before clinical translation.

KEY POINTS

• Radiomics is emerging as a tool for enhancing clinical decisions in patients with ovarian masses. • Radiomics shows promising results in improving lesion stratification, treatment selection and outcome prediction. • Modelling with larger cohorts and real-world evaluation is required before clinical translation.

An MRI-based Radiomics Approach to Improve Breast Cancer Histological Grading

RATIONALE AND OBJECTIVES

Nottingham histological grade (NHG) 2 breast cancer has an intermediate risk of recurrence, which is not informative for therapeutic decision-making. We sought to develop and independently validate an MRI-based radiomics signature (Rad-Grade) to improve prognostic re-stratification of NHG 2 tumors.

MATERIALS AND METHODS

Nine hundred-eight subjects with invasive breast cancer and preoperative MRI scans were retrospectively obtained. The NHG 1 and 3 tumors were randomly split into training and independent test cohort, with the NHG 2 as the prognostic validation set. From MRI image features, a radiomics-based signature predictive of the histological grade was built by use of the LASSO logistic regression algorithm. The model was developed for identifying NHG 1 and 3 radiological patterns, followed with re-stratification of NHG 2 tumors into Rad-Grade (RG)2-low (NHG 1-like) and RG2-high (NHG 3-like) subtypes using the learned patterns, and the prognostic value was assessed in terms of recurrence-free survival (RFS).

RESULTS

The Rad-Grade showed independent prognostic value for re-stratification of NHG 2 tumors, where RG2-high had an increased risk for recurrence (HR 2.20, 1.10-4.40, p = 0.026) compared with RG2-low after adjusting for established risk factors. RG2-low shared similar phenotypic characteristics and RFS outcomes with NHG 1, and RG2-high with NHG 3, revealing that the model captures radiomic features in NHG 2 that are associated with different aggressiveness. The prognostic value of Rad-Grade was further validated in the NHG2 ER+ (HR 2.53, 1.13-5.56, p = 0.023) and NHG 2 ER+LN- (HR 5.72, 1.24-26.44, p = 0.025) subgroups, and in specific treatment contexts.

CONCLUSION

The radiomics-based re-stratification of NHG 2 tumors offers a cost-effective promising alternative to gene expression profiling for tumor grading and thus may improve clinical decisions.

Radiomics-based aortic flow profile characterization with 4D phase-contrast MRI

4D PC MRI of the aorta has become a routinely available examination, and a multitude of single parameters have been suggested for the quantitative assessment of relevant flow features for clinical studies and diagnosis. However, clinically applicable assessment of complex flow patterns is still challenging. We present a concept for applying radiomics for the quantitative characterization of flow patterns in the aorta. To this end, we derive cross-sectional scalar parameter maps related to parameters suggested in literature such as throughflow, flow direction, vorticity, and normalized helicity. Derived radiomics features are selected with regard to their inter-scanner and inter-observer reproducibility, as well as their performance in the differentiation of sex-, age- and disease-related flow properties. The reproducible features were tested on user-selected examples with respect to their suitability for characterizing flow profile types. In future work, such signatures could be applied for quantitative flow assessment in clinical studies or disease phenotyping.

MRI radiomics and potential applications to glioblastoma

MRI plays an important role in the evaluation of glioblastoma, both at initial diagnosis and follow up after treatment. Quantitative analysis via radiomics can augment the interpretation of MRI in terms of providing insights regarding the differential diagnosis, genotype, treatment response, and prognosis. The various MRI radiomic features of glioblastoma are reviewed in this article.

Four-Dimensional Machine Learning Radiomics for the Pretreatment Assessment of Breast Cancer Pathologic Complete Response to Neoadjuvant Chemotherapy in Dynamic Contrast-Enhanced MRI

BACKGROUND

Breast cancer response to neoadjuvant chemotherapy (NAC) is typically evaluated through the assessment of tumor size reduction after a few cycles of NAC. In case of treatment ineffectiveness, this results in the patient suffering potentially severe secondary effects without achieving any actual benefit.

PURPOSE

To identify patients achieving pathologic complete response (pCR) after NAC by spatio-temporal radiomic analysis of dynamic contrast-enhanced (DCE) MRI images acquired before treatment.

STUDY TYPE

Single-center, retrospective.

POPULATION

A total of 251 DCE-MRI pretreatment images of breast cancer patients.

FIELD STRENGTH/SEQUENCE

1.5 T/3 T, T1-weighted DCE-MRI.

ASSESSMENT

Tumor and peritumoral regions were segmented, and 348 radiomic features that quantify texture temporal variation, enhancement kinetics heterogeneity, and morphology were extracted. Based on subsets of features identified through forward selection, machine learning (ML) logistic regression models were trained separately with all images and stratifying on cancer molecular subtype and validated with leave-one-out cross-validation.

STATISTICAL TESTS

Feature significance was assessed using the Mann-Whitney U-test. Significance of the area under the receiver operating characteristics (ROC) curve (AUC) of the ML models was assessed using the associated 95% confidence interval (CI). Significance threshold was set to 0.05, adjusted with Bonferroni correction.

RESULTS

Nine features related to texture temporal variation and enhancement kinetics heterogeneity were significant in the discrimination of cases achieving pCR vs. non-pCR. The ML models achieved significant AUC of 0.707 (all cancers, n = 251, 59 pCR), 0.824 (luminal A, n = 107, 14 pCR), 0.823 (luminal B, n = 47, 15 pCR), 0.844 (HER2 enriched, n = 25, 11 pCR), 0.803 (triple negative, n = 72, 19 pCR).

DATA CONCLUSIONS

Differences in imaging phenotypes were found between complete and noncomplete responders. Furthermore, ML models trained per cancer subtype achieved high performance in classifying pCR vs. non-pCR cases. They may, therefore, have potential to help stratify patients according to the level of response predicted before treatment, pending further validation with larger prospective cohorts.

EVIDENCE LEVEL

4 TECHNICAL EFFICACY: Stage 4.

Reproducibility assessment of radiomics features in various ultrasound scan settings and different scanner vendors

INTRODUCTION

Radiomics in Ultrasound (US) imaging has been investigated for the prediction and prognosis of cancers. However, inter-scanner and intra-scanner variations may affect the reproducibility of radiomics results. This study aims to evaluate the reproducibility of US textural radiomics features across various scan settings and scanner vendors.

MATERIALS AND METHODS

US images in quality control (QC) phantom were obtained by three scanners (Philips, Samsung, and Siemens) with different scan settings and parameters. Circular regions of interest (ROIs) inside isoechoic, hypoechoic, and hyperechoic objects were manually delineated. Forty textural radiomics features were extracted from each ROI, and then the robust features that could distinguish different echogenic objects were obtained by the Mann-Whitney U test. Reproducibility of the robust radiomics features was assessed by the intraclass correlation coefficient (ICC) and coefficient of variation (CV); ICC>0.90 and %CV<20 were considered reproducible.

RESULTS

According to the Mann-Whitney U test results, ten robust features could differentiate the hypoechoic, and 15 robust features could differentiate the hyperechoic objects from the isoechoic objects (P<0.001). The total ICC of the robust features for each echogenic object was >0.95 in different scanners and scan settings. Four and seven features were individually reproducible (%CV < 20, ICC>0.90) in hypoechoic and hyperechoic objects, respectively. Also, four features seem reproducible by changing the ROI location across the horizontal and vertical lines for both convex and linear array transducers.

CONCLUSIONS

Most of the US textural radiomics features in this study were not reproducible. However, several features showed high reproducibility at different scan settings and scanners. These features may also be reproducible when ROI size and location change slightly.

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.

Assessing the robustness of radiomics/deep learning approach in the identification of efficacy of anti–PD-1 treatment in advanced or metastatic non-small cell lung carcinoma patients

Administration of anti–PD-1 is now a standard therapy in advanced non-small cell lung carcinoma (NSCLC) patients. The clinical application of biomarkers reflecting tumor immune microenvironment is hurdled by the invasiveness of obtaining tissues despite its importance in immunotherapy. This study aimed to develop a robust and non-invasive radiomics/deep learning machine biomarker for predicting the response to immunotherapy in NSCLC patients. Radiomics/deep learning features were exacted from computed tomography (CT) images of NSCLC patients treated with Nivolumab or Pembrolizumab. The robustness of radiomics/deep learning features was assessed against various perturbations, then robust features were selected based on the Intraclass Correlation Coefficient (ICC). Radiomics/deep learning machine-learning classifiers were constructed by combining seven feature exactors, 13 feature selection methods, and 12 classifiers. The optimal model was selected using the mean area under the curve (AUC) and relative standard deviation (RSD). The consistency of image features against various perturbations was high (the range of median ICC: 0.78–0.97), but the consistency was poor in test–retest testing (the range of median ICC: 0.42–0.67). The optimal model, InceptionV3_RELF_Nearest Neighbors classifiers, had the highest prediction efficacy (AUC: 0.96 and RSD: 0.50) for anti–PD-1/PD-L1 treatment. Accuracy (ACC), sensitivity, specificity, precision, and F1 score were 95.24%, 95.00%, 95.50%, 91.67%, and 95.30%, respectively. For successful model robustification, tailoring perturbations for robustness testing to the target dataset is key. Robust radiomics/deep learning features, when paired with machine-learning methodologies, will work on the exactness and the repeatability of anticipating immunotherapy adequacy.

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.

Prediction of the degree of pathological differentiation in tongue squamous cell carcinoma based on radiomics analysis of magnetic resonance images

Background

Tongue squamous cell carcinoma (TSCC) is one of the most difficult malignancies to control. It displays particular and aggressive behaviour even at an early stage. The purpose of this paper is to explore the value of radiomics based on magnetic resonance fat-suppressed T2-weighted images in predicting the degree of pathological differentiation of TSCC.

Methods

Retrospective analysis of 127 patients with TSCC who were randomly divided into a primary cohort and a test cohort, including well-differentiated, moderately differentiated and poorly differentiated. The tumour regions were manually labelled in fat-suppressed T2-weighted imaging (FS-T2WI), and PyRadiomics was used to extract radiomics features. The radiomics features were then selected by the least absolute shrinkage and selection operator (LASSO) method. The model was established by the logistic regression classifier using a 5-fold cross-validation method, applied to all data and evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity and specificity.

Results

In total, 1132 features were extracted, and seven features were selected for modelling. The AUC in the logistic regression model for well-differentiated TSCC was 0.90 with specificity and precision values of 0.92 and 0.78, respectively, and the sensitivity for poorly differentiated TSCC was 0.74.

Conclusions

The MRI-based radiomics signature could discriminate between well-differentiated, moderately differentiated and poorly differentiated TSCC and might be used as a biomarker for preoperative grading.

Progress of MRI Radiomics in Hepatocellular Carcinoma

Background

Hepatocellular carcinoma (HCC) is the sixth most common cancer in the world and the third leading cause of cancer-related death. Although the diagnostic scheme of HCC is currently undergoing refinement, the prognosis of HCC is still not satisfactory. In addition to certain factors, such as tumor size and number and vascular invasion displayed on traditional imaging, some histopathological features and gene expression parameters are also important for the prognosis of HCC patients. However, most parameters are based on postoperative pathological examinations, which cannot help with preoperative decision-making. As a new field, radiomics extracts high-throughput imaging data from different types of images to build models and predict clinical outcomes noninvasively before surgery, rendering it a powerful aid for making personalized treatment decisions preoperatively.

Objective

This study reviewed the workflow of radiomics and the research progress on magnetic resonance imaging (MRI) radiomics in the diagnosis and treatment of HCC.

Methods

A literature review was conducted by searching PubMed for search of relevant peer-reviewed articles published from May 2017 to June 2021.The search keywords included HCC, MRI, radiomics, deep learning, artificial intelligence, machine learning, neural network, texture analysis, diagnosis, histopathology, microvascular invasion, surgical resection, radiofrequency, recurrence, relapse, transarterial chemoembolization, targeted therapy, immunotherapy, therapeutic response, and prognosis.

Results

Radiomics features on MRI can be used as biomarkers to determine the differential diagnosis, histological grade, microvascular invasion status, gene expression status, local and systemic therapeutic responses, and prognosis of HCC patients.

Conclusion

Radiomics is a promising new imaging method. MRI radiomics has high application value in the diagnosis and treatment of HCC.

Robustness of radiomic features of benign breast lesions and hormone receptor positive/HER2-negative cancers across DCE-MR magnet strengths

Radiomic features extracted from breast lesion images have shown potential in diagnosis and prognosis of breast cancer. As medical centers transition from 1.5 T to 3.0 T magnetic resonance (MR) imaging, it is beneficial to identify potentially robust radiomic features across field strengths because images acquired at different field strengths could be used in machine learning models. Dynamic contrast-enhanced MR images of benign breast lesions and hormone receptor positive/HER2-negative (HR+/HER2-) breast cancers were acquired retrospectively, yielding 612 unique cases: 150 and 99 benign lesions imaged at 1.5 T and 3.0 T, and 223 and 140 HR+/HER2- cancerous lesions imaged at 1.5 T and 3.0 T, respectively. In addition, an independent set of seven lesions imaged at both field strengths, three benign lesions and four HR+/HER2- cancers, was analyzed separately. Lesions were automatically segmented using a 4D fuzzy c-means method; thirty-eight radiomic features were extracted. Feature value distributions were compared by cancer status and imaging field strength using the Kolmogorov-Smirnov test. Features that did not demonstrate a statistically significant difference were considered to be potentially robust. The area under the receiver operating characteristic curve (AUC), for the task of classifying lesions as benign or HR+/HER2- cancer, was determined for each feature at each field strength. Three features were found to be both potentially robust across field strength and of high classification performance, i.e., AUCs statistically greater than 0.5 in the classification task: one shape feature (irregularity), one texture feature (sum average) and one enhancement variance kinetics features (enhancement variance increasing rate). In the demonstration set of lesions imaged at both field strengths, two of the three potentially robust features showed qualitative agreement across field strength. These findings may contribute to the development of computer-aided diagnosis models that are robust across field strength for this classification task.

AI-Enhanced Diagnosis of Challenging Lesions in Breast MRI: A Methodology and Application Primer

Computer-aided diagnosis (CAD) systems have become an important tool in the assessment of breast tumors with magnetic resonance imaging (MRI). CAD systems can be used for the detection and diagnosis of breast tumors as a "second opinion" review complementing the radiologist's review. CAD systems have many common parts, such as image preprocessing, tumor feature extraction, and data classification that are mostly based on machine-learning (ML) techniques. In this review article, we describe applications of ML-based CAD systems in MRI covering the detection of diagnostically challenging lesions of the breast such as nonmass enhancing (NME) lesions, and furthermore discuss how multiparametric MRI and radiomics can be applied to the study of NME, including prediction of response to neoadjuvant chemotherapy (NAC). Since ML has been widely used in the medical imaging community, we provide an overview about the state-of-the-art and novel techniques applied as classifiers to CAD systems. The differences in the CAD systems in MRI of the breast for several standard and novel applications for NME are explained in detail to provide important examples, illustrating: 1) CAD for detection and diagnosis, 2) CAD in multiparametric imaging, 3) CAD in NAC, and 4) breast cancer radiomics. We aim to provide a comparison between these CAD applications and to illustrate a global view on intelligent CAD systems based on machine and deep learning in MRI of the breast. LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY STAGE: 2.

Normalization of breast MRIs using cycle-consistent generative adversarial networks

OBJECTIVES

Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI) is widely used to complement ultrasound examinations and x-ray mammography for early detection and diagnosis of breast cancer. However, images generated by various MRI scanners (e.g., GE Healthcare, and Siemens) differ both in intensity and noise distribution, preventing algorithms trained on MRIs from one scanner to generalize to data from other scanners. In this work, we propose a method to solve this problem by normalizing images between various scanners.

METHODS

MRI normalization is challenging because it requires normalizing intensity values and mapping noise distributions between scanners. We utilize a cycle-consistent generative adversarial network to learn a bidirectional mapping and perform normalization between MRIs produced by GE Healthcare and Siemens scanners in an unpaired setting. Initial experiments demonstrate that the traditional CycleGAN architecture struggles to preserve the anatomical structures of the breast during normalization. Thus, we propose two technical innovations in order to preserve both the shape of the breast as well as the tissue structures within the breast. First, we incorporate mutual information loss during training in order to ensure anatomical consistency. Second, we propose a modified discriminator architecture that utilizes a smaller field-of-view to ensure the preservation of finer details in the breast tissue.

RESULTS

Quantitative and qualitative evaluations show that the second innovation consistently preserves the breast shape and tissue structures while also performing the proper intensity normalization and noise distribution mapping.

CONCLUSION

Our results demonstrate that the proposed model can successfully learn a bidirectional mapping and perform normalization between MRIs produced by different vendors, potentially enabling improved diagnosis and detection of breast cancer. All the data used in this study are publicly available at https://wiki.cancerimagingarchive.net/pages/viewpage.action?pageId=70226903.

Deep learning radiomics-based prediction of distant metastasis in patients with locally advanced rectal cancer after neoadjuvant chemoradiotherapy: A multicentre study

BACKGROUND

Accurate predictions of distant metastasis (DM) in locally advanced rectal cancer (LARC) patients receiving neoadjuvant chemoradiotherapy (nCRT) are helpful in developing appropriate treatment plans. This study aimed to perform DM prediction through deep learning radiomics.

METHODS

We retrospectively sampled 235 patients receiving nCRT with the minimum 36 months' postoperative follow-up from three hospitals. Through transfer learning, a deep learning radiomic signature (DLRS) based on multiparametric magnetic resonance imaging (MRI) was constructed. A nomogram was established integrating deep MRI information and clinicopathologic factors for better prediction. Harrell's concordance index (C-index) and time-dependent receiver operating characteristic (ROC) were used as performance metrics. Furthermore, the risk of DM in patients with different response to nCRT was evaluated with the nomogram.

FINDINGS

DLRS performed well in DM prediction, with a C-index of 0·747 and an area under curve (AUC) at three years of 0·894 in the validation cohort. The performance of nomogram was better, with a C-index of 0·775. In addition, the nomogram could stratify patients with different responses to nCRT into high- and low-risk groups of DM (P < 0·05).

INTERPRETATION

MRI-based deep learning radiomics had potential in predicting the DM of LARC patients receiving nCRT and could help evaluate the risk of DM in patients who have different responses to nCRT.

FUNDING

The funding bodies that contributed to this study are listed in the Acknowledgements section.

Radiomic Features of Multiparametric MRI Present Stable Associations With Analogous Histological Features in Patients With Brain Cancer

Magnetic resonance (MR)-derived radiomic features have shown substantial predictive utility in modeling different prognostic factors of glioblastoma and other brain cancers. However, the biological relationship underpinning these predictive models has been largely unstudied, and the generalizability of these models had been called into question. Here, we examine the localized relationship between MR-derived radiomic features and histology-derived “histomic” features using a data set of 16 patients with brain cancer. Tile-based radiomic features were collected on T1, post-contrast T1, FLAIR, and diffusion-weighted imaging (DWI)-derived apparent diffusion coefficient (ADC) images acquired before patient death, with analogous histomic features collected for autopsy samples coregistered to the magnetic resonance imaging. Features were collected for each original image, as well as a 3D wavelet decomposition of each image, resulting in 837 features per MR and histology image. Correlative analyses were used to assess the degree of association between radiomic–histomic pairs for each magnetic resonance imaging. The influence of several confounds was also assessed using linear mixed-effect models for the normalized radiomic–histomic distance, testing for main effects of different acquisition field strengths. Results as a whole were largely heterogeneous, but several features showed substantial associations with their histomic analogs, particularly those derived from the FLAIR and postcontrast T1W images. These features with the strongest association typically presented as stable across field strengths as well. These data suggest that a subset of radiomic features can consistently capture texture information on underlying tissue histology.

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.

Cross-modality image feature fusion diagnosis in breast cancer

Considering the complementarity of mammography and breast MRI, the research of feature fusion diagnosis based on cross-modality images was explored to improve the accuracy of breast cancer diagnosis. 201 patients with both mammography and breast MRI were collected retrospectively, including 117 cases of benign lesions and 84 cases of malignant ones. Two feature optimization strategies of sequential floating forward selection (SFFS), SFFS-1 and SFFS-2, were defined based on the sequential floating forward selection method. Each strategy was used to analyze the diagnostic performance of single-modality images and then to study the feature fusion diagnosis of cross-modality images. Three feature fusion approaches were compared: optimizing MRI features and then fusing those of mammography; optimizing mammography features and then fusing those of MRI; selecting the effective features from the whole feature set (mammography and MRI). Support vector machine, Naive Bayes, and K-nearest neighbor were employed as the classifiers and were finally integrated to get better performance. The average accuracy and area under the ROC curve (AUC) of MRI (88.56%, 0.9 for SFFS-1, 88.39%, 0.89 for SFFS-2) were better than mammography (84.25%, 0.84 for SFFS-1, 80.43%, 0.80 for SFFS-2). Furthermore, compared with a single modality, the average accuracy and AUC of cross-modality feature fusion can improve from 85.40% and 0.86 to 89.66% and 0.91. Classifier integration improved the accuracy and AUC from 90.49%, 0.92 to 92.37%, and 0.97. Cross-modality image feature fusion can achieve better diagnosis performance than a single modality. Feature selection strategy SFFS-1 has better efficiency than SFFS-2. Classifier integration can further improve diagnostic accuracy.

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.

MIL normalization -- prerequisites for accurate MRI radiomics analysis

The quality of magnetic resonance (MR) images obtained with different instruments and imaging parameters varies greatly. A large number of heterogeneous images are collected, and they suffer from acquisition variation. Such imaging quality differences will have a great impact on the radiomics analysis. The main differences in MR images include modality mismatch (M), intensity distribution variance (I), and layer-spacing differences (L), which are referred to as MIL differences in this paper for convenience. An MIL normalization system is proposed to reconstruct uneven MR images into high-quality data with complete modality, a uniform intensity distribution and consistent layer spacing. Three radiomics tasks, including tumor segmentation, pathological grading and genetic diagnosis of glioma, were used to verify the effect of MIL normalization on radiomics analysis. Three retrospective glioma datasets were analyzed in this study: BraTs (285 cases), TCGA (112 cases) and HuaShan (403 cases). They were used to test the effect of MIL on three different radiomics tasks, including tumor segmentation, pathological grading and genetic diagnosis. MIL normalization included three components: multimodal synthesis based on an encoder-decoder network, intensity normalization based on CycleGAN, and layer-spacing unification based on Statistical Parametric Mapping (SPM). The Dice similarity coefficient, areas under the curve (AUC) and six other indicators were calculated and compared after different normalization steps. The MIL normalization system can improved the Dice coefficient of segmentation by 9% (P < .001), the AUC of pathological grading by 32% (P < .001), and IDH1 status prediction by 25% (P < .001) when compared to non-normalization. The proposed MIL normalization system provides high-quality standardized data, which is a prerequisite for accurate radiomics analysis.

Radiomics feature robustness as measured using an MRI phantom

Radiomics involves high-throughput extraction of large numbers of quantitative features from medical images and analysis of these features to predict patients’ outcome and support clinical decision-making. However, radiomics features are sensitive to several factors, including scanning protocols. The purpose of this study was to investigate the robustness of magnetic resonance imaging (MRI) radiomics features with various MRI scanning protocol parameters and scanners using an MRI radiomics phantom. The variability of the radiomics features with different scanning parameters and repeatability measured using a test–retest scheme were evaluated using the coefficient of variation and intraclass correlation coefficient (ICC) for both T1- and T2-weighted images. For variability measures, the features were categorized into three groups: large, intermediate, and small variation. For repeatability measures, the average T1- and T2-weighted image ICCs for the phantom (0.963 and 0.959, respectively) were higher than those for a healthy volunteer (0.856 and 0.849, respectively). Our results demonstrated that various radiomics features are dependent on different scanning parameters and scanners. The radiomics features with a low coefficient of variation and high ICC for both the phantom and volunteer can be considered good candidates for MRI radiomics studies. The results of this study will assist current and future MRI radiomics studies.

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

OBJECTIVE

Quantitative analysis in MRI is challenging due to variabilities in intensity distributions across patients, acquisitions and scanners and suffers from bias field inhomogeneity. Radiomic studies are impacted by these effects that affect radiomic feature values. This paper describes a dedicated pipeline to increase reproducibility in breast MRI radiomic studies.

MATERIALS AND METHODS

T1, T2, and T1-DCE MR images of two breast phantoms were acquired using two scanners and three dual breast coils. Images were retrospectively corrected for bias field inhomogeneity and further normalised using Z score or histogram matching. Extracted radiomic features were harmonised between coils by the ComBat method. The whole pipeline was assessed qualitatively and quantitatively using statistical comparisons on two series of radiomic feature values computed in the gel mimicking the normal breast tissue or in dense lesions.

RESULTS

Intra and inter-acquisition variabilities were strongly reduced by the standardisation pipeline. Harmonisation by ComBat lowered the percentage of radiomic features significantly different between the three coils from 87% after bias field correction and MR normalisation to 3% in the gel, while preserving or improving performance of lesion classification in the phantoms.

DISCUSSION

A dedicated standardisation pipeline was developed to reduce variabilities in breast MRI, which paves the way for robust multi-scanner radiomic studies but needs to be assessed on patient data.

Radiomics for glioblastoma survival analysis in pre-operative MRI: exploring feature robustness, class boundaries, and machine learning techniques

Background

This study aims to identify robust radiomic features for Magnetic Resonance Imaging (MRI), assess feature selection and machine learning methods for overall survival classification of Glioblastoma multiforme patients, and to robustify models trained on single-center data when applied to multi-center data.

Methods

Tumor regions were automatically segmented on MRI data, and 8327 radiomic features extracted from these regions. Single-center data was perturbed to assess radiomic feature robustness, with over 16 million tests of typical perturbations. Robust features were selected based on the Intraclass Correlation Coefficient to measure agreement across perturbations. Feature selectors and machine learning methods were compared to classify overall survival. Models trained on single-center data (63 patients) were tested on multi-center data (76 patients). Priors using feature robustness and clinical knowledge were evaluated.

Results

We observed a very large performance drop when applying models trained on single-center on unseen multi-center data, e.g. a decrease of the area under the receiver operating curve (AUC) of 0.56 for the overall survival classification boundary at 1 year. By using robust features alongside priors for two overall survival classes, the AUC drop could be reduced by 21.2%. In contrast, sensitivity was 12.19% lower when applying a prior.

Conclusions

Our experiments show that it is possible to attain improved levels of robustness and accuracy when models need to be applied to unseen multi-center data. The performance on multi-center data of models trained on single-center data can be increased by using robust features and introducing prior knowledge. For successful model robustification, tailoring perturbations for robustness testing to the target dataset is key.

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.

Impact of different b-value combinations on radiomics features of apparent diffusion coefficient in cervical cancer

Background

The impact of variable b-value combinations on apparent diffusion coefficient (ADC)-based radiomics features has not been fully addressed in literature.

Purpose

To investigate the correlation between radiomics features extracted from ADC maps and various b-value combinations in cervical cancer.

Material and Methods

Diffusion-weighted images (b-values: 0, 600, 800, and 1000 s/mm2) of 20 patients with cervical cancer were included. Tumors were identified with the largest transversal cross-section and manually segmented by radiologist. For each b-value combination, 92 radiomics features were extracted and coefficient of variance (CV) was used to evaluate the robustness of radiomics features with different b-value combinations. Features with CV > 5% were normalized by the mean feature variation across the group.

Results

Out of a total of 92 radiomics features, 18 were classified as robust features with CV ≤5%. Among the rest (CV > 5%), 11, 23, and 40 features demonstrated 5%< CV ≤10%, 10%< CV ≤20%, and CV > 20%, respectively. A subset of features in each category (CV > 5%) showed strong correlation with the b-value combination variation, including 44% (7/16) features in gray level co-occurrence matrix, 62% (8/13) features in gray level dependence matrix, 64% (9/14) features in first order, 50% (8/16) features in gray level run length matrix, 57% (8/14) features in gray level size matrix, and 20% (1/5) features in neighborhood gray-tone difference matrix.

Conclusions

Variations in b-value combinations demonstrated impact on radiomics features extracted from ADC maps for cervical cancer. The radiomics features with CV <5% can be considered as robust features and are recommended to be used in multicenter radiomics studies.

Automated volumetric radiomic analysis of breast cancer vascularization improves survival prediction in primary breast cancer

To investigate whether automated volumetric radiomic analysis of breast cancer vascularization (VAV) can improve survival prediction in primary breast cancer. 314 consecutive patients with primary invasive breast cancer received standard clinical MRI before the initiation of treatment according to international recommendations. Diagnostic work-up, treatment, and follow-up was done at one tertiary care, academic breast-center (outcome: disease specific survival/DSS vs. disease specific death/DSD). The Nottingham Prognostic Index (NPI) was used as the reference method with which to predict survival of breast cancer. Based on the MRI scans, VAV was accomplished by commercially available, FDA-cleared software. DSD served as endpoint. Integration of VAV into the NPI gave NPI_VAV. Prediction of DSD by NPI_VAV compared to standard NPI alone was investigated (Cox regression, likelihood-test, predictive accuracy: Harrell's C, Kaplan Meier statistics and corresponding hazard ratios/HR, confidence intervals/CI). DSD occurred in 35 and DSS in 279 patients. Prognostication of the survival outcome by NPI (Harrell's C = 75.3%) was enhanced by VAV (NPI_VAV: Harrell's C = 81.0%). Most of all, the NPI_VAV identified patients with unfavourable outcome more reliably than NPI alone (hazard ratio/HR = 4.5; confidence interval/CI = 2.14-9.58; P = 0.0001). Automated volumetric radiomic analysis of breast cancer vascularization improved survival prediction in primary breast cancer. Most of all, it optimized the identification of patients at higher risk of an unfavorable outcome. Future studies should integrate MRI as a "gate keeper" in the management of breast cancer patients. Such a "gate keeper" could assist in selecting patients benefitting from more advanced diagnostic procedures (genetic profiling etc.) in order to decide whether are a more aggressive therapy (chemotherapy) is warranted.

Three-dimensional radiomics of triple-negative breast cancer: Prediction of systemic recurrence

This paper evaluated 3-dimensional radiomics features of breast magnetic resonance imaging (MRI) as prognostic factors for predicting systemic recurrence in triple-negative breast cancer (TNBC) and validated the results with a different MRI scanner. The Rad score was generated from 3-dimensional radiomic features of MRI for 231 TNBCs (training set (GE scanner), n = 182; validation set (Philips scanner), n = 49). The Clinical and Rad models to predict systemic recurrence were built up and the models were externally validated. In the training set, the Rad score was significantly higher in the group with systemic recurrence (median, −8.430) than the group without (median, −9.873, P < 0.001). The C-index of the Rad model to predict systemic recurrence in the training set was 0.97, which was significantly higher than in the Clinical model (0.879; P = 0.009). When the models were externally validated, the C-index of the Rad model was 0.848, lower than the 0.939 of the Clinical model, although the difference was not statistically significant (P = 0.100). The Rad model for predicting systemic recurrence in TNBC showed a significantly higher C-index than the Clinical model. However, external validation with a different MRI scanner did not show the Rad model to be superior over the Clinical model.

Application and Analysis of Biomedical Imaging Technology in Early Diagnosis of Breast Cancer

Breast cancer is the primary malignant tumor that endangers women's health. The incidence of breast cancer is increasing rapidly in recent years. Accurate disease evaluation before treatment is the key to the selection of treatment options. Biomedical imaging technology plays an irreplaceable role in the diagnosis and staging of tumors. Various imaging methods can provide excellent temporal and spatial resolution from multiple levels and perspectives and have become one of the most commonly used means of breast cancer early detection. With the development of radiomics, it has been found that early imaging diagnosis of breast cancer plays an important guiding role in clinical decision-making. The purpose of this study is to explore the characteristics of various breast cancer imaging technologies, promote the development of individualized accurate diagnosis and treatment of imaging, and improve the clinical application value of radiomics in the early diagnosis of breast cancer.

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.

Measurement Variability in Treatment Response Determination for Non-Small Cell Lung Cancer: Improvements Using Radiomics

Multimodality imaging measurements of treatment response are critical for clinical practice, oncology trials, and the evaluation of new treatment modalities. The current standard for determining treatment response in non-small cell lung cancer (NSCLC) is based on tumor size using the RECIST criteria. Molecular targeted agents and immunotherapies often cause morphological change without reduction of tumor size. Therefore, it is difficult to evaluate therapeutic response by conventional methods. Radiomics is the study of cancer imaging features that are extracted using machine learning and other semantic features. This method can provide comprehensive information on tumor phenotypes and can be used to assess therapeutic response in this new age of immunotherapy. Delta radiomics, which evaluates the longitudinal changes in radiomics features, shows potential in gauging treatment response in NSCLC. It is well known that quantitative measurement methods may be subject to substantial variability due to differences in technical factors and require standardization. In this review, we describe measurement variability in the evaluation of NSCLC and the emerging role of radiomics.

Prediction of malignant glioma grades using contrast-enhanced T1-weighted and T2-weighted magnetic resonance images based on a radiomic analysis

We conducted a feasibility study to predict malignant glioma grades via radiomic analysis using contrast-enhanced T1-weighted magnetic resonance images (CE-T1WIs) and T2-weighted magnetic resonance images (T2WIs). We proposed a framework and applied it to CE-T1WIs and T2WIs (with tumor region data) acquired preoperatively from 157 patients with malignant glioma (grade III: 55, grade IV: 102) as the primary dataset and 67 patients with malignant glioma (grade III: 22, grade IV: 45) as the validation dataset. Radiomic features such as size/shape, intensity, histogram, and texture features were extracted from the tumor regions on the CE-T1WIs and T2WIs. The Wilcoxon-Mann-Whitney (WMW) test and least absolute shrinkage and selection operator logistic regression (LASSO-LR) were employed to select the radiomic features. Various machine learning (ML) algorithms were used to construct prediction models for the malignant glioma grades using the selected radiomic features. Leave-one-out cross-validation (LOOCV) was implemented to evaluate the performance of the prediction models in the primary dataset. The selected radiomic features for all folds in the LOOCV of the primary dataset were used to perform an independent validation. As evaluation indices, accuracies, sensitivities, specificities, and values for the area under receiver operating characteristic curve (or simply the area under the curve (AUC)) for all prediction models were calculated. The mean AUC value for all prediction models constructed by the ML algorithms in the LOOCV of the primary dataset was 0.902 ± 0.024 (95% CI (confidence interval), 0.873-0.932). In the independent validation, the mean AUC value for all prediction models was 0.747 ± 0.034 (95% CI, 0.705-0.790). The results of this study suggest that the malignant glioma grades could be sufficiently and easily predicted by preparing the CE-T1WIs, T2WIs, and tumor delineations for each patient. Our proposed framework may be an effective tool for preoperatively grading malignant gliomas.

Myocardial Radiomics in Cardiac MRI

OBJECTIVE. The purpose of this article is to review the nascent field of radiomics in cardiac MRI. CONCLUSION. Cardiac MRI produces a large number of images in a fairly inefficient manner with sometimes limited clinical application. In the era of precision medicine, there is increasing need for imaging to account for a broader array of diseases in an efficient and objective manner. Radiomics, the extraction and analysis of quantitative imaging features from medical imaging, may offer potential solutions to this need.

Deep learning for identifying radiogenomic associations in breast cancer

RATIONALE AND OBJECTIVES

To determine whether deep learning models can distinguish between breast cancer molecular subtypes based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI).

MATERIALS AND METHODS

In this institutional review board-approved single-center study, we analyzed DCE-MR images of 270 patients at our institution. Lesions of interest were identified by radiologists. The task was to automatically determine whether the tumor is of the Luminal A subtype or of another subtype based on the MR image patches representing the tumor. Three different deep learning approaches were used to classify the tumor according to their molecular subtypes: learning from scratch where only tumor patches were used for training, transfer learning where networks pre-trained on natural images were fine-tuned using tumor patches, and off-the-shelf deep features where the features extracted by neural networks trained on natural images were used for classification with a support vector machine. Network architectures utilized in our experiments were GoogleNet, VGG, and CIFAR. We used 10-fold crossvalidation method for validation and area under the receiver operating characteristic (AUC) as the measure of performance.

RESULTS

The best AUC performance for distinguishing molecular subtypes was 0.65 (95% CI:[0.57,0.71]) and was achieved by the off-the-shelf deep features approach. The highest AUC performance for training from scratch was 0.58 (95% CI:[0.51,0.64]) and the best AUC performance for transfer learning was 0.60 (95% CI:[0.52,0.65]) respectively. For the off-the-shelf approach, the features extracted from the fully connected layer performed the best.

CONCLUSION

Deep learning may play a role in discovering radiogenomic associations in breast cancer.

Radiomic Feature Robustness and Reproducibility in Quantitative Bone Radiography: A Study on Radiologic Parameter Changes

The purpose of this study was to investigate the robustness of different radiography radiomic features over different radiologic parameters including kV, mAs, filtration, tube angles, and source skin distance (SSD). A tibia bone phantom was prepared and all imaging studies was conducted on this phantom. Different radiologic parameters including kV, mAs, filtration, tube angles, and SSD were studied. A region of interest was drawn on the images and many features from different feature sets including histogram, gradient, run-length matrix, co-occurrence matrix, autoregressive model, and wavelet derived parameters were extracted. All radiomic features were categorized based on coefficient of variation (COV). Bland-Altman analysis also was used to evaluate the mean, standard deviation, and upper/lower reproducibility limits for radiomic features in response to variation in each testing parameters. Results on COV in all features showed that 22%, 34%, and 45% of features were most robust (COV ≤ 5%) against kV, mAs, and SSD respectively and there was no robust features against filtration and tube angle. Also, all features (100%) and 76% of which showed large variations (COV > 20%) against filtrations and tube angle respectively. Autoregressive model feature set has no robust features against all radiologic parameters. Features including sum-average, sum-entropy, correlation, mean, and percentile (50, 90, and 99) belong to co-occurrence matrix and histogram feature sets were found as most robust features. Bland-Altman analysis showed the high reproducibity of some feature sets against radiologic parameter changes. The results presented here indicated that radiologic parameters have great impacts on radiomic feature values and caution should be taken into account when work with these features. In quantitative bone studies, robust features with low COV can be selected for clinical or research applications. Reproducible features also can be obtained using Bland-Altman analysis.

Association of distant recurrence-free survival with algorithmically extracted MRI characteristics in breast cancer

BACKGROUND

While important in diagnosis of breast cancer, the scientific assessment of the role of imaging in prognosis of outcomes and treatment planning is limited.

PURPOSE

To evaluate the potential of using quantitative imaging variables for stratifying risk of distant recurrence in breast cancer patients.

STUDY TYPE

Retrospective.

POPULATION

In all, 892 female invasive breast cancer patients.

SEQUENCE

Dynamic contrast-enhanced MRI with field strength 1.5 T and 3 T.

ASSESSMENT

Computer vision algorithms were applied to extract a comprehensive set of 529 imaging features quantifying size, shape, enhancement patterns, and heterogeneity of the tumors and the surrounding tissue. Using a development set with 446 cases, we selected 20 imaging features with high prognostic value.

STATISTICAL TESTS

We evaluated the imaging features using an independent test set with 446 cases. The principal statistical measure was a concordance index between individual imaging features and patient distant recurrence-free survival (DRFS).

RESULTS

The strongest association with DRFS that persisted after controlling for known prognostic clinical and pathology variables was found for signal enhancement ratio (SER) partial tumor volume (concordance index [C] = 0.768, 95% confidence interval [CI]: 0.679-0.856), tumor major axis length (C = 0.742, 95% CI: 0.650-0.834), kurtosis of the SER map within tumor (C = 0.640, 95% CI: 0.521-0.760), tumor cluster shade (C = 0.313, 95% CI: 0.216-0.410), and washin rate information measure of correlation (C = 0.702, 95% CI: 0.601-0.803).

DATA CONCLUSION

Quantitative assessment of breast cancer features seen in a routine breast MRI might be able to be used for assessment of risk of distant recurrence.

LEVEL OF EVIDENCE

4 Technical Efficacy: Stage 6 J. Magn. Reson. Imaging 2019.

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.

Quantitative variations in texture analysis features dependent on MRI scanning parameters: A phantom model

Objectives

To evaluate the influence of MRI scanning parameters on texture analysis features.

Methods

Publicly available data from the Reference Image Database to Evaluate Therapy Response (RIDER) project sponsored by The Cancer Imaging Archive included MRIs on a phantom comprised of 18 25‐mm doped, gel‐filled tubes, and 1 20‐mm tube containing 0.25 mM Gd‐DTPA (EuroSpinII Test Object5, Diagnostic Sonar, Ltd, West Lothian, Scotland). MRIs performed on a 1.5 T GE HD, 1.5 T Siemens Espree (VB13), or 3.0 T GE HD with TwinSpeed gradients with an eight‐channel head coil included T1WIs with multiple flip angles (flip‐angle = 2,5,10,15,20,25,30), TR/TE = 4.09–5.47/0.90–1.35 ms, NEX = 1 and DCE with 30° flip‐angle, TR/TE=4.09–5.47/0.90–1.35, and NEX = 1,4. DICOM data were imported into an in‐house developed texture analysis program which extracted 41‐texture features including histogram, gray‐level co‐occurrence matrix (GLCM), and gray‐level run‐length (GLRL). Two‐tailed t tests, corrected for multiple comparisons (Q values) were calculated to compare changes in texture features with variations in MRI scanning parameters (magnet strength, flip‐angle, number of excitations (NEX), scanner platform).

Results

Significant differences were seen in histogram features (mean, median, standard deviation, range) with variations in NEX (Q = 0.003–0.045) and scanner platform (Q < 0.0001), GLCM features (entropy, contrast, energy, and homogeneity) with NEX (Q = 0.001–0.018) and scanner platform (Q < 0.0001), GLRL features (long‐run emphasis, high gray‐level run emphasis, high gray‐level emphasis) with magnet strength (Q = 0.0003), NEX (Q = 0.003–0.022) and scanner platform (Q < 0.0001).

Conclusion

Significant differences were seen in many texture features with variations in MRI acquisition emphasizing the need for standardized MRI technique.

Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set

PURPOSE

To determine whether a multivariate machine learning-based model using computer-extracted features of pre-treatment dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) can predict pathologic complete response (pCR) to neoadjuvant therapy (NAT) in breast cancer patients.

METHODS

Institutional review board approval was obtained for this retrospective study of 288 breast cancer patients at our institution who received NAT and had a pre-treatment breast MRI. A comprehensive set of 529 radiomic features was extracted from each patient's pre-treatment MRI. The patients were divided into equal groups to form a training set and an independent test set. Two multivariate machine learning models (logistic regression and a support vector machine) based on imaging features were trained to predict pCR in (a) all patients with NAT, (b) patients with neoadjuvant chemotherapy (NACT), and (c) triple-negative or human epidermal growth factor receptor 2-positive (TN/HER2+) patients who had NAT. The multivariate models were tested using the independent test set, and the area under the receiver operating characteristics (ROC) curve (AUC) was calculated.

RESULTS

Out of the 288 patients, 64 achieved pCR. The AUC values for predicting pCR in TN/HER+ patients who received NAT were significant (0.707, 95% CI 0.582-0.833, p < 0.002).

CONCLUSIONS

The multivariate models based on pre-treatment MRI features were able to predict pCR in TN/HER2+ patients.

A machine learning approach to radiogenomics of breast cancer: a study of 922 subjects and 529 DCE-MRI features

BACKGROUND

Recent studies showed preliminary data on associations of MRI-based imaging phenotypes of breast tumours with breast cancer molecular, genomic, and related characteristics. In this study, we present a comprehensive analysis of this relationship.

METHODS

We analysed a set of 922 patients with invasive breast cancer and pre-operative MRI. The MRIs were analysed by a computer algorithm to extract 529 features of the tumour and the surrounding tissue. Machine-learning-based models based on the imaging features were trained using a portion of the data (461 patients) to predict the following molecular, genomic, and proliferation characteristics: tumour surrogate molecular subtype, oestrogen receptor, progesterone receptor and human epidermal growth factor status, as well as a tumour proliferation marker (Ki-67). Trained models were evaluated on the set of the remaining 461 patients.

RESULTS

Multivariate models were predictive of Luminal A subtype with AUC = 0.697 (95% CI: 0.647-0.746, p < .0001), triple negative breast cancer with AUC = 0.654 (95% CI: 0.589-0.727, p < .0001), ER status with AUC = 0.649 (95% CI: 0.591-0.705, p < .001), and PR status with AUC = 0.622 (95% CI: 0.569-0.674, p < .0001). Associations between individual features and subtypes we also found.

CONCLUSIONS

There is a moderate association between tumour molecular biomarkers and algorithmically assessed imaging features.

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

PURPOSE

To review features used in MRI radiomics of breast cancer and study the inter-reader stability of the features.

METHODS

We implemented 529 algorithmic features that can be extracted from tumor and fibroglandular tissue (FGT) in breast MRIs. The features were identified based on a review of the existing literature with consideration of their usage, prognostic ability, and uniqueness. The set was then extended so that it comprehensively describes breast cancer imaging characteristics. The features were classified into 10 groups based on the type of data used to extract them and the type of calculation being performed. For the assessment of inter-reader variability, four fellowship-trained readers annotated tumors on preoperative dynamic contrast-enhanced MRIs for 50 breast cancer patients. Based on the annotations, an algorithm automatically segmented the image and extracted all features resulting in one set of features for each reader. For a given feature, the inter-reader stability was defined as the intraclass correlation coefficient (ICC) computed using the feature values obtained through all readers for all cases.

RESULTS

The average inter-reader stability for all features was 0.8474 (95% CI: 0.8068-0.8858). The mean inter-reader stability was lower for tumor-based features (0.6348, 95% CI: 0.5391-0.7257) than FGT-based features (0.9984, 95% CI: 0.9970-0.9992). The feature group with the highest inter-reader stability quantifies breast and FGT volume. The feature group with the lowest inter-reader stability quantifies variations in tumor enhancement.

CONCLUSIONS

Breast MRI radiomics features widely vary in terms of their stability in the presence of inter-reader variability. Appropriate measures need to be taken for reducing this variability in tumor-based radiomics.

A study of association of Oncotype DX recurrence score with DCE-MRI characteristics using multivariate machine learning models

PURPOSE

To determine whether multivariate machine learning models of algorithmically assessed magnetic resonance imaging (MRI) features from breast cancer patients are associated with Oncotype DX (ODX) test recurrence scores.

METHODS

A set of 261 female patients with invasive breast cancer, pre-operative dynamic contrast enhanced magnetic resonance (DCE-MR) images and available ODX score at our institution was identified. A computer algorithm extracted a comprehensive set of 529 features from the DCE-MR images of these patients. The set of patients was divided into a training set and a test set. Using the training set we developed two machine learning-based models to discriminate (1) high ODX scores from intermediate and low ODX scores, and (2) high and intermediate ODX scores from low ODX scores. The performance of these models was evaluated on the independent test set.

RESULTS

High against low and intermediate ODX scores were predicted by the multivariate model with AUC 0.77 (95% CI 0.56-0.98, p < 0.003). Low against intermediate and high ODX score was predicted with AUC 0.51 (95% CI 0.41-0.61, p = 0.75).

CONCLUSION

A moderate association between imaging and ODX score was identified. The evaluated models currently do not warrant replacement of ODX with imaging alone.