Computer-aided diagnosis of breast DCE-MRI images using bilateral asymmetry of contrast enhancement between two breasts

A multi-stage fusion framework to classify breast lesions using deep learning and radiomics features computed from four-view mammograms

BACKGROUND

Developing computer aided diagnosis (CAD) schemes of mammograms to classify between malignant and benign breast lesions has attracted a lot of research attention over the last several decades. However, unlike radiologists who make diagnostic decisions based on the fusion of image features extracted from multi-view mammograms, most CAD schemes are single-view-based schemes, which limit CAD performance and clinical utility.

PURPOSE

This study aims to develop and test a novel CAD framework that optimally fuses information extracted from ipsilateral views of bilateral mammograms using both deep transfer learning (DTL) and radiomics feature extraction methods.

METHODS

An image dataset containing 353 benign and 611 malignant cases is assembled. Each case contains four images: the craniocaudal (CC) and mediolateral oblique (MLO) view of the left and right breast. First, we extract four matching regions of interest (ROIs) from images that surround centers of two suspicious lesion regions seen in CC and MLO views, as well as matching ROIs in the contralateral breasts. Next, the handcrafted radiomics (HCRs) features and VGG16 model-generated automated features are extracted from each ROI resulting in eight feature vectors. Then, after reducing feature dimensionality and quantifying the bilateral and ipsilateral asymmetry of four ROIs to yield four new feature vectors, we test four fusion methods to build three support vector machine (SVM) classifiers by an optimal fusion of asymmetrical image features extracted from four view images.

RESULTS

Using a 10-fold cross-validation method, results show that a SVM classifier trained using an optimal fusion of four view images yields the highest classification performance (AUC = 0.876 ± 0.031), which significantly outperforms SVM classifiers trained using one projection view alone, AUC = 0.817 ± 0.026 and 0.792 ± 0.026 for the CC and MLO view of bilateral mammograms, respectively (p < 0.001).

CONCLUSIONS

The study demonstrates that the shift from single-view CAD to four-view CAD and the inclusion of both DTL and radiomics features significantly increases CAD performance in distinguishing between malignant and benign breast lesions.

Differences Between Ipsilateral and Contralateral Early Parenchymal Enhancement Kinetics Predict Response of Breast Cancer to Neoadjuvant Therapy

RATIONALE AND OBJECTIVES

To determine whether kinetics measured with ultrafast dynamic contrast-enhanced magnetic resonance imaging in tumor and normal parenchyma pre- and post-neoadjuvant therapy (NAT) can predict the response of breast cancer to NAT.

MATERIALS AND METHODS

Twenty-four patients with histologically confirmed invasive breast cancer were enrolled. They were scanned with ultrafast dynamic contrast-enhanced magnetic resonance imaging (3-7 seconds/frame) pre- and post-NAT. Four kinetic parameters were calculated in the segmented tumors, and ipsi- and contra-lateral normal parenchyma: (1) tumor (tSE30) or background parenchymal relative enhancement at 30 seconds (BPE30), (2) maximum relative enhancement slope (MaxSlope), (3) bolus arrival time (BAT), and (4) area under relative signal enhancement curve for the initial 30 seconds (AUC30). The tumor kinetics and the differences between ipsi- and contra-lateral parenchymal kinetics were compared for patients achieving pathologic complete response (pCR) vs those who had residual disease after NAT. The chi-squared test and two-sided t-test were used for baseline demographics. The Wilcoxon rank sum test and one-way analysis of variance were used for differential responses to therapy.

RESULTS

Patients with similar pre-NAT mean BPE30, median BAT and mean AUC30 in the ipsi- and contralateral normal parenchyma were more likely to achieve pCR following NAT (p < 0.02). Patients classified as having residual cancer burden (RCB) II after NAT showed higher post-NAT tSE30 and tumor AUC30 and higher post-NAT MaxSlope in ipsilateral normal parenchyma compared to those classified as RCB I or pCR (p < 0.05).

CONCLUSION

Bilateral asymmetry in normal parenchyma could predict treatment outcome prior to NAT. Post-NAT tumor kinetics could evaluate the aggressiveness of residual tumor.

Real-time mental stress detection using multimodality expressions with a deep learning framework

Mental stress is becoming increasingly widespread and gradually severe in modern society, threatening people’s physical and mental health. To avoid the adverse effects of stress on people, it is imperative to detect stress in time. Many studies have demonstrated the effectiveness of using objective indicators to detect stress. Over the past few years, a growing number of researchers have been trying to use deep learning technology to detect stress. However, these works usually use single-modality for stress detection and rarely combine stress-related information from multimodality. In this paper, a real-time deep learning framework is proposed to fuse ECG, voice, and facial expressions for acute stress detection. The framework extracts the stress-related information of the corresponding input through ResNet50 and I3D with the temporal attention module (TAM), where TAM can highlight the distinguishing temporal representation for facial expressions about stress. The matrix eigenvector-based approach is then used to fuse the multimodality information about stress. To validate the effectiveness of the framework, a well-established psychological experiment, the Montreal imaging stress task (MIST), was applied in this work. We collected multimodality data from 20 participants during MIST. The results demonstrate that the framework can combine stress-related information from multimodality to achieve 85.1% accuracy in distinguishing acute stress. It can serve as a tool for computer-aided stress detection.

A deep matrix factorization framework for identifying underlying tissue-specific patterns of DCE-MRI: applications for molecular subtype classification in breast cancer

Objective.Breast cancer is heterogeneous in that different angiogenesis and blood flow characteristics could be present within a tumor. The pixel kinetics of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) can assume several distinct signal patterns related to specific tissue characteristics. Identification of the latent, tissue-specific dynamic patterns of intratumor heterogeneity can shed light on the biological mechanisms underlying the heterogeneity of tumors.Approach.To mine this information, we propose a deep matrix factorization-based dynamic decomposition (DMFDE) model specifically designed according to DCE-MRI characteristics. The time-series imaging data were decomposed into tissue-specific dynamic patterns and their corresponding proportion maps. The image pixel matrix and the reference matrix of population-level kinetics obtained by clustering the dynamic signals were used as the inputs. Two multilayer neural network branches were designed to collaboratively project the input matrix into a latent dynamic pattern and a dynamic proportion matrix, which was justified using simulated data. Clinical implications of DMFDE were assessed by radiomics analysis of proportion maps obtained from the tumor/parenchyma region for classifying the luminal A subtype.Main results.The decomposition performance of DMFDE was evaluated by the root mean square error and was shown to be better than that of the conventional convex analysis of mixtures (CAM) method. The predictive model withK = 3, 4, and 5 dynamic proportion maps generated AUC values of 0.780, 0.786 and 0.790, respectively, in distinguishing between luminal A and nonluminal A tumors, which are better than the CAM method (AUC = 0.726). The combination of statistical features from images with different proportion maps has the highest prediction value (AUC = 0.813), which is significantly higher than that based on CAM.Conclusion.This proposed method identified the latent dynamic patterns associated with different molecular subtypes, and radiomics analysis based on the pixel compositions of the uncovered dynamic patterns was able to determine molecular subtypes of breast cancer.

A deep matrix completion method for imputing missing histological data in breast cancer by integrating DCE-MRI radiomics

PURPOSE

Clinical indicators of histological information are important for breast cancer treatment and operational decision making, but these histological data suffer from frequent missing values due to various experimental/clinical reasons. The limited amount of histological information from breast cancer samples impedes the accuracy of data imputation. The purpose of this study was to impute missing histological data, including Ki-67 expression level, luminal A subtype, and histological grade, by integrating tumor radiomics.

METHODS

To this end, a deep matrix completion (DMC) method was proposed for imputing missing histological data using nonmissing features composed of histological and tumor radiomics (termed radiohistological features). DMC finds a latent nonlinear association between radiohistological features across all samples and samples for all the features. Radiomic features of morphologic, statistical, and texture were extracted from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) inside the tumor. Experiments on missing histological data imputation were performed with a variable number of features and missing data rates. The performance of the DMC method was compared with those of the nonnegative matrix factorization (NMF) and collaborative filtering (MCF)-based data imputation methods. The area under the curve (AUC) was used to assess the performance of missing histological data imputation.

RESULTS

By integrating radiomics from DCE-MRI, the DMC method showed significantly better performance in terms of AUC than that using only histological data. Additionally, DMC using 120 radiomic features showed an optimal prediction performance (AUC = 0.793), which was better than the NMF (AUC = 0.756) and MCF methods (AUC = 0.706; corrected p = 0.001). The DMC method consistently performed better than the NMF and MCF methods with a variable number of radiomic features and missing data rates.

CONCLUSIONS

DMC improves imputation performance by integrating tumor histological and radiomics data. This study transforms latent imaging-scale patterns for interactions with molecular-scale histological information and is promising in the tumor characterization and management of patients.

Artificial intelligence in tumor subregion analysis based on medical imaging: A review

Medical imaging is widely used in the diagnosis and treatment of cancer, and artificial intelligence (AI) has achieved tremendous success in medical image analysis. This paper reviews AI-based tumor subregion analysis in medical imaging. We summarize the latest AI-based methods for tumor subregion analysis and their applications. Specifically, we categorize the AI-based methods by training strategy: supervised and unsupervised. A detailed review of each category is presented, highlighting important contributions and achievements. Specific challenges and potential applications of AI in tumor subregion analysis are discussed.

Radiomics of Tumor Heterogeneity in Longitudinal Dynamic Contrast-Enhanced Magnetic Resonance Imaging for Predicting Response to Neoadjuvant Chemotherapy in Breast Cancer

Breast tumor morphological and vascular characteristics can be changed during neoadjuvant chemotherapy (NACT). The early changes in tumor heterogeneity can be quantitatively modeled by longitudinal dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), which is useful in predicting responses to NACT in breast cancer. In this retrospective analysis, 114 female patients with unilateral unifocal primary breast cancer who received NACT were included in a development (n = 61) dataset and a testing dataset (n = 53). DCE-MRI was performed for each patient before and after treatment (two cycles of NACT) to generate baseline and early follow-up images, respectively. Feature-level changes (delta) of the entire tumor were evaluated by calculating the relative net feature change (deltaRAD) between baseline and follow-up images. The voxel-level change inside the tumor was evaluated, which yielded a Jacobian map by registering the follow-up image to the baseline image. Clinical information and the radiomic features were fused to enhance the predictive performance. The area under the curve (AUC) values were assessed to evaluate the prediction performance. Predictive models using radiomics based on pre- and post-treatment images, Jacobian maps and deltaRAD showed AUC values of 0.568, 0.767, 0.630 and 0.726, respectively. When features from these images were fused, the predictive model generated an AUC value of 0.771. After adding the molecular subtype information in the fused model, the performance was increased to an AUC of 0.809 (sensitivity of 0.826 and specificity of 0.800), which is significantly higher than that of the baseline imaging- and Jacobian map-based predictive models (p = 0.028 and 0.019, respectively). The level of tumor heterogeneity reduction (evaluated by texture feature) is higher in the NACT responders than in the nonresponders. The results suggested that changes in DCE-MRI features that reflect a reduction in tumor heterogeneity following NACT could provide early prediction of breast tumor response. The prediction was improved when the molecular subtype information was combined into the model.

Pattern Classification Approaches for Breast Cancer Identification via MRI: State-Of-The-Art and Vision for the Future

Mining algorithms for Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI) of breast tissue are discussed. The algorithms are based on recent advances in multi-dimensional signal processing and aim to advance current state-of-the-art computer-aided detection and analysis of breast tumours when these are observed at various states of development. The topics discussed include image feature extraction, information fusion using radiomics, multi-parametric computer-aided classification and diagnosis using information fusion of tensorial datasets as well as Clifford algebra based classification approaches and convolutional neural network deep learning methodologies. The discussion also extends to semi-supervised deep learning and self-supervised strategies as well as generative adversarial networks and algorithms using generated confrontational learning approaches. In order to address the problem of weakly labelled tumour images, generative adversarial deep learning strategies are considered for the classification of different tumour types. The proposed data fusion approaches provide a novel Artificial Intelligence (AI) based framework for more robust image registration that can potentially advance the early identification of heterogeneous tumour types, even when the associated imaged organs are registered as separate entities embedded in more complex geometric spaces. Finally, the general structure of a high-dimensional medical imaging analysis platform that is based on multi-task detection and learning is proposed as a way forward. The proposed algorithm makes use of novel loss functions that form the building blocks for a generated confrontation learning methodology that can be used for tensorial DCE-MRI. Since some of the approaches discussed are also based on time-lapse imaging, conclusions on the rate of proliferation of the disease can be made possible. The proposed framework can potentially reduce the costs associated with the interpretation of medical images by providing automated, faster and more consistent diagnosis.

Detecting Asymmetric Patterns and Localizing Cancers on Mammograms

One in eight women develops invasive breast cancer in her lifetime. The frontline protection against this disease is mammography. While computer-assisted diagnosis algorithms have made great progress in generating reliable global predictions, few focus on simultaneously producing regions of interest (ROIs) for biopsy. Can we combine ROI-oriented algorithms with global classification of cancer status, which simultaneously highlight suspicious regions and optimize classification performance? Can the asymmetry of breasts be adopted in deep learning for finding lesions and classifying cancers? We answer the above questions by building deep-learning networks that identify masses and microcalcifications in paired mammograms, exclude false positives, and stepwisely improve performance of the model with asymmetric information regarding the breasts. This method achieved a co-leading place in the Digital Mammography DREAM Challenge for predicting breast cancer. We highlight here the importance of this dual-purpose process that simultaneously provides the locations of potential lesions in mammograms.

•

A top-performing algorithm in the International DREAM Digital Mammography Challenge

•

Shows efficacy of asymmetric information from opposite breasts in identifying cancers

•

Integrated pixel-level localization and overall classification into the same software

Breast cancer affects one out of eight women in their lifetime. Given the importance of the need, in this work we present a region-of-interest-oriented deep-learning pipeline for detecting and locating breast cancers based on digital mammograms. It is a leading algorithm in the well-received Digital Mammography DREAM Challenge, in which computational methods were evaluated on large-scale, held-out testing sets of digital mammograms. This algorithm connects two aims: (1) determining whether a breast has cancer and (2) determining cancer-associated regions of interest. Particularly, we addressed the challenge of variation of mammogram images across different patients by pairing up the two opposite breasts to examine asymmetry, which substantially improved global classification as well as local lesion detection. We have dockerized this code, envisioning that it will be widely used in practice and as a future reference for digital mammography analysis.

Radiogenomic signatures reveal multiscale intratumour heterogeneity associated with biological functions and survival in breast cancer

Advanced tumours are often heterogeneous, consisting of subclones with various genetic alterations and functional roles. The precise molecular features that characterize the contributions of multiscale intratumour heterogeneity to malignant progression, metastasis, and poor survival are largely unknown. Here, we address these challenges in breast cancer by defining the landscape of heterogeneous tumour subclones and their biological functions using radiogenomic signatures. Molecular heterogeneity is identified by a fully unsupervised deconvolution of gene expression data. Relative prevalence of two subclones associated with cell cycle and primary immunodeficiency pathways identifies patients with significantly different survival outcomes. Radiogenomic signatures of imaging scale heterogeneity are extracted and used to classify patients into groups with distinct subclone compositions. Prognostic value is confirmed by survival analysis accounting for clinical variables. These findings provide insight into how a radiogenomic analysis can identify the biological activities of specific subclones that predict prognosis in a noninvasive and clinically relevant manner.

Tumours are made up of heterogeneous subclones. Here, the authors show using breast cancer imaging and gene expression datasets that these subclones can be inferred by the deconvolution of gene expression data, mapped to MRI derived radiogenomic signatures and used to estimate prognosis.

Strengths, Weaknesses, Opportunities, and Threats Analysis of Artificial Intelligence and Machine Learning Applications in Radiology

Currently, the use of artificial intelligence (AI) in radiology, particularly machine learning (ML), has become a reality in clinical practice. Since the end of the last century, several ML algorithms have been introduced for a wide range of common imaging tasks, not only for diagnostic purposes but also for image acquisition and postprocessing. AI is now recognized to be a driving initiative in every aspect of radiology. There is growing evidence of the advantages of AI in radiology creating seamless imaging workflows for radiologists or even replacing radiologists. Most of the current AI methods have some internal and external disadvantages that are impeding their ultimate implementation in the clinical arena. As such, AI can be considered a portion of a business trying to be introduced in the health care market. For this reason, this review analyzes the current status of AI, and specifically ML, applied to radiology from the scope of strengths, weaknesses, opportunities, and threats (SWOT) analysis.

Generative adversarial network-based super-resolution of diffusion-weighted imaging: Application to tumour radiomics in breast cancer

Diffusion-weighted imaging (DWI) is increasingly used to guide the clinical management of patients with breast tumours. However, accurate tumour characterization with DWI and the corresponding apparent diffusion coefficient (ADC) maps are challenging due to their limited resolution. This study aimed to produce super-resolution (SR) ADC images and to assess the clinical utility of these SR images by performing a radiomic analysis for predicting the histologic grade and Ki-67 expression status of breast cancer. To this end, 322 samples of dynamic enhanced magnetic resonance imaging (DCE-MRI) and the corresponding DWI data were collected. A SR generative adversarial (SRGAN) and an enhanced deep SR (EDSR) network along with the bicubic interpolation were utilized to generate SR-ADC images from which radiomic features were extracted. The dataset was randomly separated into a development dataset (n = 222) to establish a deep SR model using DCE-MRI and a validation dataset (n = 100) to improve the resolution of ADC images. This random separation of datasets was performed 10 times, and the results were averaged. The EDSR method was significantly better than the SRGAN and bicubic methods in terms of objective quality criteria. Univariate and multivariate predictive models of radiomic features were established to determine the area under the receiver operating characteristic curve (AUC). Individual features from the tumour SR-ADC images showed a higher performance with the EDSR and SRGAN methods than with the bicubic method and the original images. Multivariate analysis of the collective radiomics showed that the EDSR- and SRGAN-based SR-ADC images performed better than the bicubic method and original images in predicting either Ki-67 expression levels (AUCs of 0.818 and 0.801, respectively) or the tumour grade (AUCs of 0.826 and 0.828, respectively). This work demonstrates that in addition to improving the resolution of ADC images, deep SR networks can also improve tumour image-based diagnosis in breast cancer.

Decision support system for breast lesions via dynamic contrast enhanced magnetic resonance imaging

The presented study aims to design a computer-aided detection and diagnosis system for breast dynamic contrast enhanced magnetic resonance imaging. In the proposed system, the segmentation task is performed in two stages. The first stage is called breast region segmentation in which adaptive noise filtering, local adaptive thresholding, connected component analysis, integral of horizontal projection, and breast region of interest detection algorithms are applied to the breast images consecutively. The second stage of segmentation is breast lesion detection that consists of 32-class Otsu thresholding and Markov random field techniques. Histogram, gray level co-occurrence matrix and neighboring gray tone difference matrix based feature extraction, Fisher score based feature selection and, tenfold and leave-one-out cross-validation steps are carried out after segmentation to increase the reliability of the designed system while decreasing the computational time. Finally, support vector machines, k- nearest neighbor, and artificial neural network classifiers are performed to separate the breast lesions as benign and malignant. The average accuracy, sensitivity, specificity, and positive predictive values of each classifier are calculated and the best results are compared with the existing similar studies. According to the achieved results, the proposed decision support system for breast lesion segmentation distinguishes the breast lesions with 86%, 100%, 67%, and 85% accuracy, sensitivity, specificity, and positive predictive values, respectively. These results show that the proposed system can be used to support the radiologists during a breast cancer diagnosis.

Joint Prediction of Breast Cancer Histological Grade and Ki-67 Expression Level Based on DCE-MRI and DWI Radiomics

OBJECTIVE

Histologic grade and Ki-67 proliferation status are important clinical indictors for breast cancer prognosis and treatment. The purpose of this study is to improve prediction accuracy of these clinical indicators based on tumor radiomic analysis.

METHODS

We jointly predicted Ki-67 and tumor grade with a multitask learning framework by separately utilizing radiomics from tumor MRI series. Additionally, we showed how multitask learning models (MTLs) could be extended to combined radiomics from the MRI series for a better prediction based on the assumption that features from different sources of images share common patterns while providing complementary information. Tumor radiomic analysis was performed with morphological, statistical and textural features extracted on the DWI and dynamic contrast-enhanced MRI (DCE-MRI) series of the precontrast and subtraction images, respectively.

RESULTS

Joint prediction of Ki-67 status and tumor grade on MR images using the MTL achieved performance improvements over that of single-task-based predictive models. Similarly, for the prediction tasks of Ki-67 and tumor grade, the MTL for combined precontrast and apparent diffusion coefficient (ADC) images achieved AUCs of 0.811 and 0.816, which were significantly better than that of the single-task- based model with p values of 0.005 and 0.017, respectively.

CONCLUSION

Mapping MRI radiomics to two related clinical indicators improves prediction performance for both Ki-67 expression level and tumor grade.

SIGNIFICANCE

Joint prediction of indicators by multitask learning that combines correlations of MRI radiomics is important for optimal tumor therapy and treatment because clinical decisions are made by integrating multiple clinical indicators.

Molecular Subtypes Recognition of Breast Cancer in Dynamic Contrast-Enhanced Breast Magnetic Resonance Imaging Phenotypes from Radiomics Data

Background and Objective

Breast cancer is a major cause of mortality among women if not treated in early stages. Recognizing molecular markers from DCE-MRI directly to distinguish the four molecular subtypes without invasive biopsy is helpful for guiding treatment plans for breast cancer, which provides a fast way to consequential treatment plan decision in early time and best opportunity for patients.

Methods

This study presents an approach of molecular subtypes recognition from breast cancer image phenotypes by radiomics. An improved region growth algorithm with dynamic threshold without user interaction is proposed for cancer lesion segmentation, which gives the precise border of lesion other than area with background. The lesions are extracted automatically based on radiologists' annotation which guarantees the lesion is segmented correctly. Various features are extracted on lesions data including texture, morphology, dynamic kinetics, and statistics features carried out on a large patient cohort, which are used to validate the relationship between image phenotypes and the molecular subtypes. A new algorithm of multimodel-based recursive feature elimination is applied on the radiomics data generated by the feature extraction process. This method obtains the feature subset with stable performance for different classification models, and the gradient boosting decision tree model gets the best results of both classification performance and imbalance performance on molecular subtypes.

Result

From the experimental results, 69 optimal features from 143 original features are found by the multimodel-based recursive feature elimination algorithms and the gradient boosting decision tree classifier obtains a good performance with accuracy 0.87, precise 0.88, recall 0.87, and F1-score 0.87. The dataset with 637 patients in this paper has serious imbalance problem on different molecular subtypes, and the the robust features that are generated by multimodel-based recursive feature eliminiation algorithm make the gradient boosting decision tree classifier have good behaviors. The recognition precision for the four molecular subtypes of luminal A, luminal B, HER-2, and basal-like are 0.91, 0.89, 0.83, and 0.87, respectively.

Conclusions

The improved lesion segmentation method gives more precise lesion edge, which not only saves the time of automatic extraction of lesion region of interest without threshold setting for each case, but also prevents the segmentation error by manual and prejudice from different radiologists. The feature selection algorithm of multimodel-based recursive feature elimination has the ability to find robust and optimal features that distinguish the four molecular subtypes from image phenotypes. The gradient boosting decision tree classifier rather plays a main role in recognition than other models used in this paper.

Integration of dynamic contrast-enhanced magnetic resonance imaging and T2-weighted imaging radiomic features by a canonical correlation analysis-based feature fusion method to predict histological grade in ductal breast carcinoma

Tumour histological grade has prognostic implications in breast cancer. Tumour features in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and T2-weighted (T2W) imaging can provide related and complementary information in the analysis of breast lesions to improve MRI-based histological status prediction in breast cancer. A dataset of 167 patients with invasive ductal carcinoma (IDC) was assembled, consisting of 72 low/intermediate-grade and 95 high-grade cases with preoperative DCE-MRI and T2W images. The data cohort was separated into development (n  =  111) and validation (n  =  56) cohorts. Each tumour was segmented in the precontrast and the intermediate and last postcontrast DCE-MR images and was mapped to the tumour in the T2W images. Radiomic features, including texture, morphology, and histogram distribution features in the tumour image, were extracted for those image series. Features from the DCE-MR and T2W images were fused by a canonical correlation analysis (CCA)-based method. The support vector machine (SVM) classifiers were trained and tested on the development and validation cohorts, respectively. SVM-based recursive feature elimination (SVM-RFE) was adopted to identify the optimal features for prediction. The areas under the ROC curves (AUCs) for the T2W images and the DCE-MRI series of precontrast, intermediate and last postcontrast images were 0.750  ±  0.047, 0.749  ±  0.047, and 0.788  ±  0.045, respectively, for the development cohort and 0.715  ±  0.068, 0.704  ±  0.073, and 0.744  ±  0.067, respectively, for the validation cohort. After the CCA-based fusion of features from the DCE-MRI series and T2W images, the AUCs increased to 0.751  ±  0.065, 0.803  ±  0.0600 and 794  ±  0.060 in the validation cohort. Moreover, the method of fusing features between DCE-MRI and T2W images using CCA achieved better performance than the concatenation-based feature fusion or classifier fusion methods. Our results demonstrated that anatomical and functional MR images yield complementary information, and feature fusion of radiomic features by matrix transformation to optimize their correlations produced a classifier with improved performance for predicting the histological grade of IDC.

Tumour heterogeneity revealed by unsupervised decomposition of dynamic contrast-enhanced magnetic resonance imaging is associated with underlying gene expression patterns and poor survival in breast cancer patients

BACKGROUND

Heterogeneity is a common finding within tumours. We evaluated the imaging features of tumours based on the decomposition of tumoural dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) data to identify their prognostic value for breast cancer survival and to explore their biological importance.

METHODS

Imaging features (n = 14), such as texture, histogram distribution and morphological features, were extracted to determine their associations with recurrence-free survival (RFS) in patients in the training cohort (n = 61) from The Cancer Imaging Archive (TCIA). The prognostic value of the features was evaluated in an independent dataset of 173 patients (i.e. the reproducibility cohort) from the TCIA I-SPY 1 TRIAL dataset. Radiogenomic analysis was performed in an additional cohort, the radiogenomic cohort (n = 87), using DCE-MRI from TCGA-BRCA and corresponding gene expression data from The Cancer Genome Atlas (TCGA). The MRI tumour area was decomposed by convex analysis of mixtures (CAM), resulting in 3 components that represent plasma input, fast-flow kinetics and slow-flow kinetics. The prognostic MRI features were associated with the gene expression module in which the pathway was analysed. Furthermore, a multigene signature for each prognostic imaging feature was built, and the prognostic value for RFS and overall survival (OS) was confirmed in an additional cohort from TCGA.

RESULTS

Three image features (i.e. the maximum probability from the precontrast MR series, the median value from the second postcontrast series and the overall tumour volume) were independently correlated with RFS (p values of 0.0018, 0.0036 and 0.0032, respectively). The maximum probability feature from the fast-flow kinetics subregion was also significantly associated with RFS and OS in the reproducibility cohort. Additionally, this feature had a high correlation with the gene expression module (r = 0.59), and the pathway analysis showed that Ras signalling, a breast cancer-related pathway, was significantly enriched (corrected p value = 0.0044). Gene signatures (n = 43) associated with the maximum probability feature were assessed for associations with RFS (p = 0.035) and OS (p = 0.027) in an independent dataset containing 1010 gene expression samples. Among the 43 gene signatures, Ras signalling was also significantly enriched.

CONCLUSIONS

Dynamic pattern deconvolution revealed that tumour heterogeneity was associated with poor survival and cancer-related pathways in breast cancer.

On the potential use of dynamic contrast-enhanced (DCE) MRI parameters as radiomic features of cervical cancer

PURPOSE

To evaluate whether the analysis of high-temporal resolution DCE-MRI by various tracer kinetic models could yield useful radiomic features in discriminating cervix carcinoma and normal cervix tissue.

METHODS

Forty-three patients (median age 51 yr; range 26-78 yr) diagnosed with cervical cancer based on postoperative pathology were enrolled in this study with informed consent. DCE-MRI data with temporal resolution of 2 s were acquired and analyzed using the Tofts (TOFTS), extended Tofts (EXTOFTS), conventional two-compartment (CC), adiabatic tissue homogeneity (ATH), and distributed parameter (DP) models. Ability of all kinetic parameters in distinguishing tumor from normal tissue was assessed using Mann-Whitney U test and receiver operating characteristic (ROC) curves. Repeatability of parameter estimates due to sampling of arterial input functions (AIFs) was also studied using intraclass correlation (ICC) analysis.

RESULTS

Fractional extravascular, extracellular volume (Ve) of all models were significantly smaller in cervix carcinoma than normal cervix tissue, and were associated with large values of area under ROC curve (AUC 0.884-0.961). Capillary permeability PS derived from the ATH, CC, and DP models also yielded large AUC values (0.730, 0.860, and 0.797). Transfer constant Ktrans derived from TOFTS and EXTOFTS models yielded smaller AUC (0.587 and 0.701). Repeatability of parameters derived from all models was robust to AIF sampling, with ICC coefficients typically larger than 0.80.

CONCLUSIONS

With the use of high-temporal resolution DCE-MRI, all tracer kinetic models could reflect pathophysiological differences between cervix carcinoma and normal tissue (with significant differences in Ve and PS) and potentially yield radiomic features with diagnostic value.

Background parenchymal enhancement on breast MRI: A comprehensive review

The degree of normal fibroglandular tissue that enhances on breast MRI, known as background parenchymal enhancement (BPE), was initially described as an incidental finding that could affect interpretation performance. While BPE is now established to be a physiologic phenomenon that is affected by both endogenous and exogenous hormone levels, evidence supporting the notion that BPE frequently masks breast cancers is limited. However, compelling data have emerged to suggest BPE is an independent marker of breast cancer risk and breast cancer treatment outcomes. Specifically, multiple studies have shown that elevated BPE levels, measured qualitatively or quantitatively, are associated with a greater risk of developing breast cancer. Evidence also suggests that BPE could be a predictor of neoadjuvant breast cancer treatment response and overall breast cancer treatment outcomes. These discoveries come at a time when breast cancer screening and treatment have moved toward an increased emphasis on targeted and individualized approaches, of which the identification of imaging features that can predict cancer diagnosis and treatment response is an increasingly recognized component. Historically, researchers have primarily studied quantitative tumor imaging features in pursuit of clinically useful biomarkers. However, the need to segment less well-defined areas of normal tissue for quantitative BPE measurements presents its own unique challenges. Furthermore, there is no consensus on the optimal timing on dynamic contrast-enhanced MRI for BPE quantitation. This article comprehensively reviews BPE with a particular focus on its potential to increase precision approaches to breast cancer risk assessment, diagnosis, and treatment. It also describes areas of needed future research, such as the applicability of BPE to women at average risk, the biological underpinnings of BPE, and the standardization of BPE characterization. Level of Evidence: 3 Technical Efficacy Stage: 5 J. Magn. Reson. Imaging 2020;51:43-61.

Radiomic analysis of imaging heterogeneity in tumours and the surrounding parenchyma based on unsupervised decomposition of DCE-MRI for predicting molecular subtypes of breast cancer

OBJECTIVES

This study aimed to predict the molecular subtypes of breast cancer via intratumoural and peritumoural radiomic analysis with subregion identification based on the decomposition of contrast-enhanced magnetic resonance imaging (DCE-MRI).

METHODS

The study included 211 women with histopathologically confirmed breast cancer. We utilised a completely unsupervised convex analysis of mixtures (CAM) method by unmixing dynamic imaging series from heterogeneous tissues. Each tumour and the surrounding parenchyma were thus decomposed into multiple subregions, representing different vascular characterisations, from which radiomic features were extracted. A random forest model was trained and tested using a leave-one-out cross-validation (LOOCV) method to predict breast cancer subtypes. The predictive models from tumoural and peritumoural subregions were fused for classification.

RESULTS

Tumour and peritumour DCE-MR images were decomposed into three compartments, representing plasma input, fast-flow kinetics, and slow-flow kinetics. The tumour subregion related to fast-flow kinetics showed the best performance among the subregions for differentiating between patients with four molecular subtypes (area under the receiver operating characteristic curve (AUC) = 0.832), exhibiting an AUC value significantly (p < 0.0001) higher than that obtained with the entire tumour (AUC = 0.719). When the tumour- and parenchyma-based predictive models were fused, the performance, measured as the AUC, increased to 0.897; this value was significantly higher than that obtained with other tumour partition methods.

CONCLUSIONS

Radiomic analysis of intratumoural and peritumoural heterogeneity based on the decomposition of image time-series signals has the potential to more accurately identify tumour kinetic features and serve as a valuable clinical marker to enhance the prediction of breast cancer subtypes.

KEY POINTS

• Decomposition of image time-series signals has the potential to more accurately identify tumour kinetic features. • Fusion of intratumoural- and peritumoural-based predictive models improves the prediction of breast cancer subtypes.

Automatic and fast segmentation of breast region-of-interest (ROI) and density in MRIs

Accurate segmentation of the breast region of interest (BROI) and breast density (BD) is a significant challenge during the analysis of breast MR images. Most of the existing methods for breast segmentation are semi-automatic and limited in their ability to achieve accurate results. This is because of difficulties in removing landmarks from noisy magnetic resonance images (MRI) due to similar intensity levels and the close connection to BROI. This study proposes an innovative, fully automatic and fast segmentation approach to identify and remove landmarks such as the heart and pectoral muscles. The BROI segmentation is carried out with a framework consisting of three major steps. Firstly, we use adaptive wiener filtering and k-means clustering to minimize the influence of noises, preserve edges and remove unwanted artefacts. The second step systematically excludes the heart area by utilizing active contour based level sets where initial contour points are determined by the maximum entropy thresholding and convolution method. Finally, a pectoral muscle is removed by using morphological operations and local adaptive thresholding on MR images. Prior to the elimination of the pectoral muscle, the MR image is sub divided into three sections: left, right, and central based on the geometrical information. Subsequently, a BD segmentation is achieved with 4 level fuzzy c-means (FCM) thresholding on the denoised BROI segmentation. The proposed method is validated using the 1350 breast images from 15 female subjects. The pixel-based quantitative analysis showed excellent segmentation results when compared with manually drawn BROI and BD. Furthermore, the presented results in terms of evaluation matrices: Acc, Sp, AUC, MR, P, Se and DSC demonstrate the high quality of segmentations using the proposed method. The average computational time for the segmentation of BROI and BD is 1 minute and 50 seconds.

Computer-aided diagnosis based on enhancement of degraded fundus photographs

PURPOSE

Retinal imaging is an important and effective tool for detecting retinal diseases. However, degraded images caused by the aberrations of the eye can disguise lesions, so that a diseased eye can be mistakenly diagnosed as normal. In this work, we propose a new image enhancement method to improve the quality of degraded images.

METHODS

A new method is used to enhance degraded-quality fundus images. In this method, the image is converted from the input RGB colour space to LAB colour space and then each normalized component is enhanced using contrast-limited adaptive histogram equalization. Human visual system (HVS)-based fundus image quality assessment, combined with diagnosis by experts, is used to evaluate the enhancement.

RESULTS

The study included 191 degraded-quality fundus photographs of 143 subjects with optic media opacity. Objective quality assessment of image enhancement (range: 0-1) indicated that our method improved colour retinal image quality from an average of 0.0773 (variance 0.0801) to an average of 0.3973 (variance 0.0756). Following enhancement, area under curves (AUC) were 0.996 for the glaucoma classifier, 0.989 for the diabetic retinopathy (DR) classifier, 0.975 for the age-related macular degeneration (AMD) classifier and 0.979 for the other retinal diseases classifier.

CONCLUSION

The relatively simple method for enhancing degraded-quality fundus images achieves superior image enhancement, as demonstrated in a qualitative HVS-based image quality assessment. This retinal image enhancement may, therefore, be employed to assist ophthalmologists in more efficient screening of retinal diseases and the development of computer-aided diagnosis.

Computer-Aided Diagnosis Scheme for Distinguishing Between Benign and Malignant Masses in Breast DCE-MRI

Our purpose in this study was to develop a computer-aided diagnosis (CAD) scheme for distinguishing between benign and malignant breast masses in dynamic contrast material-enhanced magnetic resonance imaging (DCE-MRI). Our database consisted 90 DCE-MRI examinations, each of which contained four sequential phase images; this database included 28 benign masses and 62 malignant masses. In our CAD scheme, we first determined 11 objective features of masses by taking into account the image features and the dynamic changes in signal intensity that experienced radiologists commonly use for describing masses in DCE-MRI. Quadratic discriminant analysis (QDA) was employed to distinguish between benign and malignant masses. As the input of the QDA, a combination of four objective features was determined among the 11 objective features according to a stepwise method. These objective features were as follows: (i) the change in signal intensity from 2 to 5 min; (ii) the change in signal intensity from 0 to 2 min; (iii) the irregularity of the shape; and (iv) the smoothness of the margin. Using this approach, the classification accuracy, sensitivity, and specificity were shown to be 85.6 % (77 of 90), 87.1 % (54 of 62), and 82.1 % (23 of 28), respectively. Furthermore, the positive and negative predictive values were 91.5 % (54 of 59) and 74.2 % (23 of 31), respectively. Our CAD scheme therefore exhibits high classification accuracy and is useful in the differential diagnosis of masses in DCE-MRI images.

DCE-MRI texture analysis with tumor subregion partitioning for predicting Ki-67 status of estrogen receptor-positive breast cancers

BACKGROUND

Breast tumor heterogeneity is related to risk factors that lead to worse prognosis, yet such heterogeneity has not been well studied.

PURPOSE

To predict the Ki-67 status of estrogen receptor (ER)-positive breast cancer patients via analysis of tumor heterogeneity with subgroup identification based on patterns of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI).

STUDY TYPE

Retrospective study.

POPULATION

Seventy-seven breast cancer patients with ER-positive breast cancer were investigated, of whom 51 had low Ki-67 expression.

FIELD STRENGTH/SEQUENCE

T₁ -weighted 3.0T DCE-MR images.

ASSESSMENT

Each tumor was partitioned into multiple subregions using three methods based on patterns of dynamic enhancement: 1) time to peak (TTP), 2) peak enhancement rate (PER), and 3) kinetic pattern clustering (KPC). In each tumor subregion, 18 texture features were computed.

STATISTICAL TESTING

Univariate and multivariate logistic regression analyses were performed using a leave-one-out-based cross-validation (LOOCV) method. The partitioning results were compared with the same feature extraction methods across the whole tumor.

RESULTS

In the univariate analysis, the best-performing feature was the texture statistic of sum variance in the tumor subregion with early TTP for differentiating between patients with high and low Ki-67 expression (area under the receiver operating characteristic curves, AUC = 0.748). Multivariate analysis showed that features from the tumor subregion associated with early TTP yielded the highest performance (AUC = 0.807) among the subregions for predicting the Ki-67 status. Among all regions, the tumor area with high PER at a precontrast MR image achieved the highest performance (AUC = 0.722), while the subregion that exhibited the highest overall enhancement rate based on KPC had an AUC of 0.731. These three models based on intratumoral texture analysis significantly (P < 0.01) outperformed the model using features from the whole tumor (AUC = 0.59).

DATA CONCLUSION

Texture analysis of intratumoral heterogeneity has the potential to serve as a valuable clinical marker to enhance the prediction of breast cancer prognosis.

LEVEL OF EVIDENCE

4 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2017.

Radiomic analysis reveals DCE-MRI features for prediction of molecular subtypes of breast cancer

The purpose of this study was to investigate the role of features derived from breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) and to incorporated clinical information to predict the molecular subtypes of breast cancer. In particular, 60 breast cancers with the following four molecular subtypes were analyzed: luminal A, luminal B, human epidermal growth factor receptor-2 (HER2)-over-expressing and basal-like. The breast region was segmented and the suspicious tumor was depicted on sequentially scanned MR images from each case. In total, 90 features were obtained, including 88 imaging features related to morphology and texture as well as dynamic features from tumor and background parenchymal enhancement (BPE) and 2 clinical information-based parameters, namely, age and menopausal status. An evolutionary algorithm was used to select an optimal subset of features for classification. Using these features, we trained a multi-class logistic regression classifier that calculated the area under the receiver operating characteristic curve (AUC). The results of a prediction model using 24 selected features showed high overall classification performance, with an AUC value of 0.869. The predictive model discriminated among the luminal A, luminal B, HER2 and basal-like subtypes, with AUC values of 0.867, 0.786, 0.888 and 0.923, respectively. An additional independent dataset with 36 patients was utilized to validate the results. A similar classification analysis of the validation dataset showed an AUC of 0.872 using 15 image features, 10 of which were identical to those from the first cohort. We identified clinical information and 3D imaging features from DCE-MRI as candidate biomarkers for discriminating among four molecular subtypes of breast cancer.

Role of pharmacokinetic parameters derived with high temporal resolution DCE MRI using simultaneous PET/MRI system in breast cancer: A feasibility study

PURPOSE

To evaluate the reliability of pharmacokinetic parameters like K^trans, Kep and v_e derived through DCE MRI breast protocol using 3T Simultaneous PET/MRI (3Tesla Positron Emission Tomography/Magnetic Resonance Imaging) system in distinguishing benign and malignant lesions.

MATERIALS AND METHODS

High temporal resolution DCE (Dynamic Contrast Enhancement) MRI performed as routine breast MRI for diagnosis or as a part of PET/MRI for cancer staging using a 3T simultaneous PET/MRI system in 98 women having 109 breast lesions were analyzed for calculation of pharmacokinetic parameters (K^trans, v_e, and Kep) at 60s time point using an in-house developed computation scheme.

RESULTS

Receiver operating characteristic (ROC) curve analysis revealed a cut off value for K^trans, Kep, v_e as 0.50, 2.59, 0.15 respectively which reliably distinguished benign and malignant breast lesions. Data analysis revealed an overall accuracy of 94.50%, 79.82% and 87.16% for K^trans, Kep, v_e respectively. Introduction of native T1 normalization with an externally placed phantom showed a higher accuracy (94.50%) than without native T1 normalization (93.50%) with an increase in specificity of 87% vs 84%.

CONCLUSION

Overall the results indicate that reliable measurement of pharmacokinetic parameters with reduced acquisition time is feasible in a 3TMRI embedded PET/MRI system with reasonable accuracy and application may be extended to exploit the potential of simultaneous PET/MRI in further work on breast cancer.

Computer-aided breast MR image feature analysis for prediction of tumor response to chemotherapy

PURPOSE

To identify a new clinical marker based on quantitative kinetic image features analysis and assess its feasibility to predict tumor response to neoadjuvant chemotherapy.

METHODS

The authors assembled a dataset involving breast MR images acquired from 68 cancer patients before undergoing neoadjuvant chemotherapy. Among them, 25 patients had complete response (CR) and 43 had partial and nonresponse (NR) to chemotherapy based on the response evaluation criteria in solid tumors. The authors developed a computer-aided detection scheme to segment breast areas and tumors depicted on the breast MR images and computed a total of 39 kinetic image features from both tumor and background parenchymal enhancement regions. The authors then applied and tested two approaches to classify between CR and NR cases. The first one analyzed each individual feature and applied a simple feature fusion method that combines classification results from multiple features. The second approach tested an attribute selected classifier that integrates an artificial neural network (ANN) with a wrapper subset evaluator, which was optimized using a leave-one-case-out validation method.

RESULTS

In the pool of 39 features, 10 yielded relatively higher classification performance with the areas under receiver operating characteristic curves (AUCs) ranging from 0.61 to 0.78 to classify between CR and NR cases. Using a feature fusion method, the maximum AUC=0.85±0.05. Using the ANN-based classifier, AUC value significantly increased to 0.96±0.03 (p<0.01).

CONCLUSIONS

This study demonstrated that quantitative analysis of kinetic image features computed from breast MR images acquired prechemotherapy has potential to generate a useful clinical marker in predicting tumor response to chemotherapy.

A new quantitative image analysis method for improving breast cancer diagnosis using DCE-MRI examinations

PURPOSE

To investigate the feasibility of applying a new quantitative image analysis method to improve breast cancer diagnosis performance using dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) by integrating background parenchymal enhancement (BPE) features into the decision making process.

METHODS

A dataset involving 115 DCE-MRI examinations was used in this study. Each examination depicts one identified suspicious breast tumor. Among them, 75 cases were verified as malignant and 40 were benign by the biopsy results. A computer-aided detection scheme was applied to segment breast regions and the suspicious tumor depicted on the sequentially scanned MR images of each case. We then computed 18 kinetic features in which 6 were computed from the segmented breast tumor and 12 were BPE features from the background parenchymal regions (excluding the tumor). Support vector machine (SVM) based statistical learning classifiers were trained and optimized using different combinations of features that were computed either from tumor only or from both tumor and BPE. Each SVM was tested using a leave-one-case-out validation method and assessed using an area under the receiver operating characteristic curve (AUC).

RESULTS

When using kinetic features computed from tumors only, the maximum AUC is 0.865 ± 0.035. After fusing with the BPE features, AUC increased to 0.919 ± 0.029. At 90% specificity, the tumor classification sensitivity increased by 13.2%.

CONCLUSIONS

The proposed quantitative BPE features provide valuable supplementary information to the kinetic features of breast tumors in DCE-MRI. Their addition to computer-aided diagnosis methodologies could improve breast cancer diagnosis based on DCE-MRI examinations.