Multimodality computer-aided breast cancer diagnosis with FFDM and DCE-MRI

A coarse-to-fine and automatic algorithm for breast diagnosis on multi-series MRI images

Introduction

Early breast carcinomas can be effectively diagnosed and controlled. However, it demands extra work and radiologist in China often suffer from overtime working due to too many patients, even experienced ones could make mistakes after overloaded work. To improve the efficiency and reduce the rate of misdiagnosis, automatic breast diagnosis on Magnetic Resonance Imaging (MRI) images is vital yet challenging for breast disease screening and successful treatment planning. There are some obstacles that hinder the development of automatic approaches, such as class-imbalance of samples, hard mimics of lesions, etc. In this paper, we propose a coarse-to-fine algorithm to address those problems of automatic breast diagnosis on multi-series MRI images. The algorithm utilizes deep learning techniques to provide breast segmentation, tumor segmentation and tumor classification functions, thus supporting doctors' decisions in clinical practice.

Methods

In proposed algorithm, a DenseUNet is firstly employed to extract breast-related regions by removing irrelevant parts in the thoracic cavity. Then, by taking advantage of the attention mechanism and the focal loss, a novel network named Attention Dense UNet (ADUNet) is designed for the tumor segmentation. Particularly, the focal loss in ADUNet addresses class-imbalance and model overwhelmed problems. Finally, a customized network is developed for the tumor classification. Besides, while most approaches only consider one or two series, the proposed algorithm takes in account multiple series of MRI images.

Results

Extensive experiments are carried out to evaluate its performance on 435 multi-series MRI volumes from 87 patients collected from Tongji Hospital. In the dataset, all cases are with benign, malignant, or both type of tumors, the category of which covers carcinoma, fibroadenoma, cyst and abscess. The ground truths of tumors are labeled by two radiologists with 3 years of experience on breast MRI reporting by drawing contours of tumor slice by slice. ADUNet is compared with other prevalent deep-learning methods on the tumor segmentation and quantitative results, and achieves the best performance on both Case Dice Score and Global Dice Score by 0.748 and 0.801 respectively. Moreover, the customized classification network outperforms two CNN-M based models and achieves tumor-level and case-level AUC by 0.831 and 0.918 respectively.

Discussion

All data in this paper are collected from the same MRI device, thus it is reasonable to assume that they are from the same domain and independent identically distributed. Whether the proposed algorithm is robust enough in a multi-source case still remains an open question. Each stage of the proposed algorithm is trained separately, which makes each stage more robust and converge faster. Such training strategy considers each stage as a separate task and does not take into account the relationships between tasks.

Multi-modality relation attention network for breast tumor classification

Automatic breast image classification plays an important role in breast cancer diagnosis, and multi-modality image fusion may improve classification performance. However, existing fusion methods ignore relevant multi-modality information in favor of improving the discriminative ability of single-modality features. To improve classification performance, this paper proposes a multi-modality relation attention network with consistent regularization for breast tumor classification using diffusion-weighted imaging (DWI) and apparent dispersion coefficient (ADC) images. Within the proposed network, a novel multi-modality relation attention module improves the discriminative ability of single-modality features by exploring the correlation information between two modalities. In addition, a module ensures the classification consistency of ADC and DWI modality, thus improving robustness to noise. Experimental results on our database demonstrate that the proposed method is effective for breast tumor classification, and outperforms existing multi-modality fusion methods. The AUC, accuracy, specificity, and sensitivity are 85.1%, 86.7%, 83.3%, and 88.9% respectively.

Effectiveness of MRI in screening women for breast cancer: a systematic review

Artificial intelligence techniques for the diagnosis of disease continue to develop with rapid pace. This review article systematically determines incremental accuracy and other parameters of current methods, including sensitivity, specificity, positive predictive value and negative predictive value with regard to breast MRI as a screening tool for women under 50 years. Articles were included from the databases of health technology assessment agencies from 2000 to 2019, using various medical subject heading terms. A total of 23 eligible studies were included incorporating a total of 11,688 patients out of which two were multicentered, four were accuracy studies, seven were prospective studies and four were retrospective studies. MRI screening showed an adequate detection of invasive cancers, premalignant lesions and pre-invasive cancers, suggesting that MRI is a powerful surveillance tool to detect cancer in high-risk populations. These findings have indicated that MRI has particular sensitivity and specificity for the diagnosis of breast cancer.

PROSPERO Registration Number: CRD42020158372.

Harnessing multimodal data integration to advance precision oncology

Advances in quantitative biomarker development have accelerated new forms of data-driven insights for patients with cancer. However, most approaches are limited to a single mode of data, leaving integrated approaches across modalities relatively underdeveloped. Multimodal integration of advanced molecular diagnostics, radiological and histological imaging, and codified clinical data presents opportunities to advance precision oncology beyond genomics and standard molecular techniques. However, most medical datasets are still too sparse to be useful for the training of modern machine learning techniques, and significant challenges remain before this is remedied. Combined efforts of data engineering, computational methods for analysis of heterogeneous data and instantiation of synergistic data models in biomedical research are required for success. In this Perspective, we offer our opinions on synthesizing complementary modalities of data with emerging multimodal artificial intelligence methods. Advancing along this direction will result in a reimagined class of multimodal biomarkers to propel the field of precision oncology in the coming decade.

Artificial Intelligence: reshaping the practice of radiological sciences in the 21st century

Advances in computing hardware and software platforms have led to the recent resurgence in artificial intelligence (AI) touching almost every aspect of our daily lives by its capability for automating complex tasks or providing superior predictive analytics. AI applications are currently spanning many diverse fields from economics to entertainment, to manufacturing, as well as medicine. Since modern AI's inception decades ago, practitioners in radiological sciences have been pioneering its development and implementation in medicine, particularly in areas related to diagnostic imaging and therapy. In this anniversary article, we embark on a journey to reflect on the learned lessons from past AI's chequered history. We further summarize the current status of AI in radiological sciences, highlighting, with examples, its impressive achievements and effect on re-shaping the practice of medical imaging and radiotherapy in the areas of computer-aided detection, diagnosis, prognosis, and decision support. Moving beyond the commercial hype of AI into reality, we discuss the current challenges to overcome, for AI to achieve its promised hope of providing better precision healthcare for each patient while reducing cost burden on their families and the society at large.

A New Application of Multimodality Radiomics Improves Diagnostic Accuracy of Nonpalpable Breast Lesions in Patients with Microcalcifications-Only in Mammography

Background

The aim of this study was to assess a radiomic scheme that combines image features from digital mammography and dynamic contrast-enhanced MRI to improve classification accuracy of nonpalpable breast lesion (NBL) with Breast Imaging-Reporting and Data System (BI-RADS) 3–5 microcalcifications-only in mammography.

Material/Methods

This retrospective study was approved by the Internal Research Review and Ethical Committee of our hospital. We included 81 patients who underwent a three-dimensional digital breast X-ray wire positioning for local resection between October 2012 and November 2016. All patients underwent breast MRI and mammography before the treatment, and all obtained pathological confirmation. According to the pathological results, 41 patients with benign lesions were assigned to the benign group and 40 patients with malignant lesions were assigned to the malignant group. We used the random forest algorithm to select significant features and to test the single and multimodal classifiers using the Leave-One-Out-Cross-Validation method. An area under the receiver operating characteristic curve was also used to evaluate its discriminating performance.

Results

The multimodal classifier achieved AUC of 0.903, with a sensitivity of 82.5% and a specificity of 80.48%, which was better than any single modality.

Conclusions

Multimodal radiomics classification shows promising power in discriminating malignant lesions from benign lesions in NBL patients with BI-RADS 3–5 microcalcifications-only in mammography.

Identification of Triple-Negative Breast Cancer Genes and a Novel High-Risk Breast Cancer Prediction Model Development Based on PPI Data and Support Vector Machines

Triple-negative breast cancer (TNBC) is a special subtype of breast cancer that is difficult to treat. It is crucial to identify breast cancer-related genes that could provide new biomarkers for breast cancer diagnosis and potential treatment goals. In the development of our new high-risk breast cancer prediction model, seven raw gene expression datasets from the NCBI gene expression omnibus (GEO) database (GSE31519, GSE9574, GSE20194, GSE20271, GSE32646, GSE45255, and GSE15852) were used. Using the maximum relevance minimum redundancy (mRMR) method, we selected significant genes. Then, we mapped transcripts of the genes on the protein-protein interaction (PPI) network from the Search Tool for the Retrieval of Interacting Genes (STRING) database, as well as traced the shortest path between each pair of proteins. Genes with higher betweenness values were selected from the shortest path proteins. In order to ensure validity and precision, a permutation test was performed. We randomly selected 248 proteins from the PPI network for shortest path tracing and repeated the procedure 100 times. We also removed genes that appeared more frequently in randomized results. As a result, 54 genes were selected as potential TNBC-related genes. Using 14 out the 54 genes, which are potential TNBC associated genes, as input features into a support vector machine (SVM), a novel model was trained to predict high-risk breast cancer. The prediction accuracy of normal tissues and TNBC tissues reached 95.394%, and the predictions of Stage II and Stage III TNBC reached 86.598%, indicating that such genes play important roles in distinguishing breast cancers, and that the method could be promising in practical use. According to reports, some of the 54 genes we identified from the PPI network are associated with breast cancer in the literature. Several other genes have not yet been reported but have functional resemblance with known cancer genes. These may be novel breast cancer-related genes and need further experimental validation. Gene ontology (GO) enrichment and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses were performed to appraise the 54 genes. It was indicated that cellular response to organic cyclic compounds has an influence in breast cancer, and most genes may be related with viral carcinogenesis.

Artificial Intelligence for Breast MRI in 2008-2018: A Systematic Mapping Review

OBJECTIVE

The purpose of this study is to review literature from the past decade on applications of artificial intelligence (AI) to breast MRI.

MATERIALS AND METHODS

In June 2018, a systematic search of the literature was performed to identify articles on the use of AI in breast MRI. For each article identified, the surname of the first author, year of publication, journal of publication, Web of Science Core Collection journal category, country of affiliation of the first author, study design, dataset, study aim(s), AI methods used, and, when available, diagnostic performance were recorded.

RESULTS

Sixty-seven studies, 58 (87%) of which had a retrospective design, were analyzed. When journal categories were considered, 36% of articles were identified as being included in the radiology and imaging journal category. Contrast-enhanced sequences were used for most AI applications (n = 50; 75%) and, on occasion, were combined with other MRI sequences (n = 8; 12%). Four main clinical aims were addressed: breast lesion classification (n = 36; 54%), image processing (n = 14; 21%), prognostic imaging (n = 9; 13%), and response to neoadjuvant therapy (n = 8; 12%). Artificial neural networks, support vector machines, and clustering were the most frequently used algorithms, accounting for 66%. The performance achieved and the most frequently used techniques were then analyzed according to specific clinical aims. Supervised learning algorithms were primarily used for lesion characterization, with the AUC value from ROC analysis ranging from 0.74 to 0.98 (median, 0.87) and with that from prognostic imaging ranging from 0.62 to 0.88 (median, 0.80), whereas unsupervised learning was mainly used for image processing purposes.

CONCLUSION

Interest in the application of advanced AI methods to breast MRI is growing worldwide. Although this growth is encouraging, the current performance of AI applications in breast MRI means that such applications are still far from being incorporated into clinical practice.

Combined Benefit of Quantitative Three-Compartment Breast Image Analysis and Mammography Radiomics in the Classification of Breast Masses in a Clinical Data Set

Purpose To investigate the combination of mammography radiomics and quantitative three-compartment breast (3CB) image analysis of dual-energy mammography to limit unnecessary benign breast biopsies. Materials and Methods For this prospective study, dual-energy craniocaudal and mediolateral oblique mammograms were obtained immediately before biopsy in 109 women (mean age, 51 years; range, 31-85 years) with Breast Imaging Reporting and Data System category 4 or 5 breast masses (35 invasive cancers, 74 benign) from 2013 through 2017. The three quantitative compartments of water, lipid, and protein thickness at each pixel were calculated from the attenuation at high and low energy by using a within-image phantom. Masses were automatically segmented and features were extracted from the low-energy mammograms and the quantitative compartment images. Tenfold cross-validations using a linear discriminant classifier with predefined feature signatures helped differentiate between malignant and benign masses by means of (a) water-lipid-protein composition images alone, (b) mammography radiomics alone, and (c) a combined image analysis of both. Positive predictive value of biopsy performed (PPV₃) at maximum sensitivity was the primary performance metric, and results were compared with those for conventional diagnostic digital mammography. Results The PPV₃ for conventional diagnostic digital mammography in our data set was 32.1% (35 of 109; 95% confidence interval [CI]: 23.9%, 41.3%), with a sensitivity of 100%. In comparison, combined mammography radiomics plus quantitative 3CB image analysis had PPV₃ of 49% (34 of 70; 95% CI: 36.5%, 58.9%; P < .001), with a sensitivity of 97% (34 of 35; 95% CI: 90.3%, 100%; P < .001) and 35.8% (39 of 109) fewer total biopsies (P < .001). Conclusion Quantitative three-compartment breast image analysis of breast masses combined with mammography radiomics has the potential to reduce unnecessary breast biopsies. © RSNA, 2018 Online supplemental material is available for this article.

The correlation between mammographic densities and molecular pathology in breast cancer

This study aimed to analyze the correlation between mammographic density obtained by density analysis software (DAS)/radiologists visual (RV) classification with molecular subtype, and the expression levels of estrogen receptor (ER), progesterone receptor (PR), Ki67 antigen (Ki-67), p53 gene (p53), and human epidermal growth factor receptor-2 (HER2). A total of 688 breast cancer patients with digital mammography and complete molecular pathological results in Tianjin Medical University Cancer Institute and Hospital between February 2015 and February 2016 were collected. The DAS-density grade (DASD) and the radiologists visually classified density grade (RVD) were evaluated by 3 radiologists. The correlation between density grade and the expression levels of ER, PR, Ki-67, p53, HER2 and breast cancer molecular subtype (PMS) were analyzed. The agreement between DASD and RVD was explored. ER, PR and HER-2 positive rate were significantly different among patients with different RVD grades (P< 0.05). HER2 positive rates showed an increasing trend following RVD upgrading (P𝑡𝑟𝑒𝑛𝑑< 0.05). HER-2 positive rate in RVD D1 + D2 was 7.69%, which was higher than that in D3 + D4 (P< 0.05). The ER and Ki-67 expressions in patients were markedly different among DASD (P= 0.009 and 0.002) and RVD (P= 0.012 and 0.036) with different grades. The kappa value of each DASD to RVD was 0.31 (P< 0.01). The RVD 3 proportion was 14.58% (63/432) in HER2 Over-expressing subtype, which was apparently higher than RVD1 (2.43%, 1/41) (P< 0.05). Breast density may be partial correlated with molecular pathology in breast cancer.

Logistic regression model for diagnosis of transition zone prostate cancer on multi-parametric MRI

OBJECTIVES

We aimed to develop logistic regression (LR) models for classifying prostate cancer within the transition zone on multi-parametric magnetic resonance imaging (mp-MRI).

METHODS

One hundred and fifty-five patients (training cohort, 70 patients; temporal validation cohort, 85 patients) underwent mp-MRI and transperineal-template-prostate-mapping (TPM) biopsy. Positive cores were classified by cancer definitions: (1) any-cancer; (2) definition-1 [≥Gleason 4 + 3 or ≥ 6 mm cancer core length (CCL)] [high risk significant]; and (3) definition-2 (≥Gleason 3 + 4 or ≥ 4 mm CCL) cancer [intermediate-high risk significant]. For each, logistic-regression mp-MRI models were derived from the training cohort and validated internally and with the temporal cohort. Sensitivity/specificity and the area under the receiver operating characteristic (ROC-AUC) curve were calculated. LR model performance was compared to radiologists' performance.

RESULTS

Twenty-eight of 70 patients from the training cohort, and 25/85 patients from the temporal validation cohort had significant cancer on TPM. The ROC-AUC of the LR model for classification of cancer was 0.73/0.67 at internal/temporal validation. The radiologist A/B ROC-AUC was 0.65/0.74 (temporal cohort). For patients scored by radiologists as Prostate Imaging Reporting and Data System (Pi-RADS) score 3, sensitivity/specificity of radiologist A 'best guess' and LR model was 0.14/0.54 and 0.71/0.61, respectively; and radiologist B 'best guess' and LR model was 0.40/0.34 and 0.50/0.76, respectively.

CONCLUSIONS

LR models can improve classification of Pi-RADS score 3 lesions similar to experienced radiologists.

KEY POINTS

• MRI helps find prostate cancer in the anterior of the gland • Logistic regression models based on mp-MRI can classify prostate cancer • Computers can help confirm cancer in areas doctors are uncertain about.

Review of treatment assessment using DCE-MRI in breast cancer radiation therapy

As a noninvasive functional imaging technique, dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is being used in oncology to measure properties of tumor microvascular structure and permeability. Studies have shown that parameters derived from certain pharmacokinetic models can be used as imaging biomarkers for tumor treatment response. The use of DCE-MRI for quantitative and objective assessment of radiation therapy has been explored in a variety of methods and tumor types. However, due to the complexity in imaging technology and divergent outcomes from different pharmacokinetic approaches, the method of using DCE-MRI in treatment assessment has yet to be standardized, especially for breast cancer. This article reviews the basic principles of breast DCE-MRI and recent studies using DCE-MRI in treatment assessment. Technical and clinical considerations are emphasized with specific attention to assessment of radiation treatment response.

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

Dynamic contrast material-enhanced magnetic resonance imaging (DCE-MRI) of breasts is an important imaging modality in breast cancer diagnosis with higher sensitivity but relatively lower specificity. The objective of this study is to investigate a new approach to help improve diagnostic performance of DCE-MRI examinations based on the automated detection and analysis of bilateral asymmetry of characteristic kinetic features between the left and right breast. An image dataset involving 130 DCE-MRI examinations was assembled and used in which 80 were biopsy-proved malignant and 50 were benign. A computer-aided diagnosis (CAD) scheme was developed to segment breast areas depicted on each MR image, register images acquired from the sequential MR image scan series, compute average contrast enhancement of all pixels in one breast, and a set of kinetic features related to the difference of contrast enhancement between the left and right breast, and then use a multi-feature based Bayesian belief network to classify between malignant and benign cases. A leave-one-case-out validation method was applied to test CAD performance. The computed area under a receiver operating characteristic (ROC) curve is 0.78 ± 0.04. The positive and negative predictive values are 0.77 and 0.64, respectively. The study indicates that bilateral asymmetry of kinetic features between the left and right breasts is a potentially useful image biomarker to enhance the detection of angiogenesis associated with malignancy. It also demonstrates the feasibility of applying a simple CAD approach to classify between malignant and benign DCE-MRI examinations based on this new image biomarker.

Mixtures of receiver operating characteristic curves

RATIONALE AND OBJECTIVES

Receiver operating characteristic (ROC) curves are ubiquitous in the analysis of imaging metrics as markers of both diagnosis and prognosis. While empirical estimation of ROC curves remains the most popular method, there are several reasons to consider smooth estimates based on a parametric model.

MATERIALS AND METHODS

A mixture model is considered for modeling the distribution of the marker in the diseased population motivated by the biological observation that there is more heterogeneity in the diseased population than there is in the normal one. It is shown that this model results in an analytically tractable ROC curve which is itself a mixture of ROC curves.

RESULTS

The use of creatine kinase-BB isoenzyme in diagnosis of severe head trauma is used as an example. ROC curves are fit using the direct binormal method, ROCKIT software, and the Box-Cox transformation as well as the proposed mixture model. The mixture model generates an ROC curve that is much closer to the empirical one than the other methods considered.

CONCLUSIONS

Mixtures of ROC curves can be helpful in fitting smooth ROC curves in datasets where the diseased population has higher variability than can be explained by a single distribution.

Breast image analysis for risk assessment, detection, diagnosis, and treatment of cancer

The role of breast image analysis in radiologists' interpretation tasks in cancer risk assessment, detection, diagnosis, and treatment continues to expand. Breast image analysis methods include segmentation, feature extraction techniques, classifier design, biomechanical modeling, image registration, motion correction, and rigorous methods of evaluation. We present a review of the current status of these task-based image analysis methods, which are being developed for the various image acquisition modalities of mammography, tomosynthesis, computed tomography, ultrasound, and magnetic resonance imaging. Depending on the task, image-based biomarkers from such quantitative image analysis may include morphological, textural, and kinetic characteristics and may depend on accurate modeling and registration of the breast images. We conclude with a discussion of future directions.

Applications of ROC analysis in medical research: recent developments and future directions

With the growing focus on comparative effectiveness research and personalized medicine, receiver-operating characteristic analysis can continue to play an important role in health care decision making. Specific applications of receiver-operating characteristic analysis include predictive model assessment and validation, biomarker diagnostics, responder analysis in patient-reported outcomes, and comparison of alternative treatment options. The authors present a survey of the potential applications of the method and briefly review several relevant extensions. Given the level of attention paid to biomarker validation, personalized medicine and comparative effectiveness research, it is highly likely that the receiver-operating characteristic analysis will remain an important visual and analytic tool for medical research and evidence-based medicine in the foreseeable future.

Breast imaging: understanding how accuracy is measured when lesions are the unit of analysis

Medical imaging tests of breast cancer patients can be used to detect and provide information on the location of multiple malignant lesions within a patient. Within this context, it is often the case that one needs to evaluate the accuracy of an imaging test for finding the multiple lesions in a patient rather than simply detecting that a patient has disease. A natural way to approach this task is to estimate the accuracy of the test using a lesion-level analysis. Sensitivity, specificity, and receiver operating characteristic (ROC) curves are analytic measures that are frequently used to quantify the accuracy of medical tests. When the test or radiologist must first locate the lesions, however, it is not possible to directly estimate the specificity or an ROC curve keeping the individual lesions as the unit of analysis. The goal of this study is to demonstrate to clinicians conducting or reviewing studies evaluating breast imaging tests what measures of accuracy can and cannot be calculated in different types of studies and to describe in detail the difficulty with calculating specificity and ROC curves in a lesion-level analysis.