Effects of k-space orders on the time-intensity curves in dynamic contrast-enhanced magnetic resonance imaging of the breast based on simulation study

PurposeThis study aims to investigate the influence of time-intensity curves (TICs) on the shapes using a dynamic contrast-enhanced magnetic resonance imaging (MRI) study depending on the Cartesian and radial orders for benign and cancerous breast tumors.MethodsBased on kinetic curve parameters, the signal intensities of six concentration gradients comprising two benign and four cancer models were used. The study aimed to construct a dynamic simulated image by creating a digital phantom image according to the following steps: (1) creating a simple numerical phantom, (2) setting the signal intensity in the contrast area, (3) creating the k-space in each time phase, (4) extracting data from k-space in each time phase, (5) filling in the k-space and adding data to the k-space assembly, and (6) creating a magnitude image. The TICs of Cartesian (centric and sequential) and radial (full-length [RFL] and half-length [RHL]) orders were created and sigmoid curve fitting was performed to compare these curves. Maximum slope (MS, s⁻¹), width of the response (WOR, s), and primary signal response (PSR) were then calculated. Phase encode steps were set for 512 and 256.ResultsMS was significantly decreased by radial order in the cancer model. No change was observed in WOR in Cartesian order, whereas RFL and RHL orders increased in the cancer models. PSR increased remarkably in the radial orders of cancer models.The difference in the fill slope in radial orders was remarkable when the TIC was steeper compared with when it was gentle, especially RHL. In WOR, both radial RFL and RHL were well matched except for the one benign model, and the shape of radial TIC was similar to sequential order as compared to centric order in 256 steps.ConclusionThe effects of Cartesian and radial orders on the patterns of TICs in a dynamic contrast-enhanced MRI study of benign and cancerous breast tumors were revealed. Interestingly, the TIC gradient of radial orders became gentler, particularly in the breast cancer MRI.     

Intravoxel incoherent motion diffusion-weighted imaging as an adjunct to dynamic contrast-enhanced MRI to improve accuracy of the differential diagnosis of benign and malignant breast lesions

PurposeTo investigate the value of use of intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) as an adjunct to dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) to distinguish benign from malignant breast lesions.Materials and methodsRetrospective analysis of data pertaining to 117 patients with breast lesions who underwent DCE-MRI and IVIM-DWI examination with 3.0 T MRI was conducted. A total of 128 lesions were pathologically confirmed (47 benign and 81 malignant). Between-group differences in DCE-MRI parameters (Morphology, enhancement pattern, maximum slope of increase (MSI) and time–signal curve (TIC) type) and IVIM-DWI parameters (f value, D value and D* value) were assessed. Multivariate logistic regression was performed to identify variables that distinguished benign from malignant breast lesions. The diagnostic performance of DCE-MRI and DCE-MRI plus IVIM-DWI, to distinguish benign from malignant breast lesions, was evaluated using pathology results as the gold standard.ResultsLesion morphology, MSI, and TIC type (P < 0.05), but not the enhancement pattern (P > 0.05), were significantly different between the benign and malignant groups. The f (8.53 ± 2.14) and D* (7.64 ± 2.07) values in the malignant group were significantly higher than those in the benign group (7.68 ± 1.97 and 6.83 ± 2.13, respectively), while the D value (0.99 ± 0.22) was significantly lower than that (1.34 ± 0.17) in the benign group (P < 0.05 for all). On logistic regression analysis, the sensitivity, specificity and accuracy of DCE-MRI were 90.1%, 70.2% and 82.8% respectively; the corresponding figures for the combination of IVIM-DWI and DCE-MRI were 88.8%, 85.1%, and 87.5%respectively.ConclusionIVIM-DWI method as an adjunct to DCE-MRI can improve the specificity and accuracy in differential diagnosis of benign and malignant lesions of breast.     

Evaluation of lung tumor perfusion by dynamic contrast-enhanced MRI

The characterization of solid pulmonary lesions with imaging methods remains a diagnostic challenge. The aim of this study was to correlate kinetic parameters of dynamic perfusion magnetic resonance imaging (MRI) with histological tumor classification. Dynamic contrast-enhanced MRI of 31 patients with pulmonary masses (five benign lesions, 26 malignant tumors) was acquired in the tumor areas every 20 s for a mean duration of 124 s. Contrast uptake (CU) was measured by signal analysis in regions of interest (ROIs). The beginning and duration of CU, maximum CU (MCU, % of baseline), maximum contrast upslope (%/s) and the delay to the maximum contrast upslope (s) were calculated. All lesions were classified histologically. The beginning of CU correlated significantly with the MCU delay in all lesions (P=.033). The frequency of a plateau phase was higher in malignant tumors compared to benign lesions (P=.031). Masses with a high MCU showed more frequently a washout of contrast medium after a plateau phase (P=.006) and a higher maximum contrast upslope (P<.001). The MCU delay time was shorter in adenocarcinoma than in squamous cell carcinoma (P=.004). These results indicate that dynamic contrast enhanced MRI might become instrumental in differentiating benign from malignant intrapulmonary tumors and distinguishing adenocarcinoma from squamous cell carcinoma.     

基于MRI影像组学的BI-RADS 3-5类乳腺病变三分类

医生根据磁共振影像征象对患者的乳腺病变程度进行BI-RADS分类评估时存在一定的主观性,且 BI-RADS 3-5类病变的良恶性存在交叉,在临床诊断时极易发生因诊断类别较高而造成不必要的有创治疗．针对这些问题,本文应用影像组学技术对乳腺的T₁加权（T1W）和动态对比增强（DCE）磁共振图像进行特征提取和融合,采用最小绝对收缩和选择算子（LASSO）算法筛选出各特征集的最优特征集,并分别使用支持向量机（SVM）、随机森林（RF）、K最近邻（KNN）及逻辑回归（LR）算法进行BI-RADS 3-5类乳腺病变三分类,并且在此基础上实现乳腺良恶性分类．结果显示基于特征融合的四个影像组学模型对乳腺病变BI-RADS 3-5类的分类准确率分别为81.25%、87.50%、78.38%、81.25%;对乳腺病变良恶性鉴别的准确率分别为90.91%、93.55%、92.73%、94.55%. 这表明MRI影像组学结合机器学习的算法对乳腺病变BI-RADS分类效果及良恶性鉴别效果均较好,且特征融合可进一步提高分类预测的准确率．     

Should abbreviated breast MRI be compliant with American College of Radiology requirements for MRI accreditation?

ObjectiveTo evaluate non-inferiority and diagnostic performance of an American College of Radiology compliant abbreviated MRI protocol (AB-MRI) compared with standard-of-care breast MRI (SOC-BMRI) in patients with increased breast cancer risk.Material and methodsWomen with increased lifetime breast cancer risk by American Cancer Society guidelines underwent breast MRI at a single institution between October 2015 and February 2018. AB-MRI was acquired at 3.0 T with T2-weighted extended fast spin echo triple-echo Dixon and pre- and post-contrast 3D dual-echo fast spoiled gradient echo two-point Dixon sequences with an 8-channel breast coil 1–7 days after SOC-BMRI. Three readers independently reviewed AB-MRI and assigned BI-RADS categories for maximum intensity projection images (AB1), dynamic contrast-enhanced (DCE) images (AB2), and DCE and non-contrast T2 and fat-only images (AB3). These scores were compared to those from SOC-BMRI.ResultsCancer yield was 14 per 1000 (women-years) in 73 women aged 26–75 years (mean 53.5 years). AB-MRI acquisition times (mean 9.63 min) and table times (mean 15.07 min) were significantly shorter than those of SOC-BMRI (means 19.46 and 36.3 min, respectively) (p < .001). Accuracy, sensitivity, specificity, and positive and negative predictive values were identical for AB3 and SOC-BMRI (93%, 100%, 93%, 16.7%, and 100%, respectively). AB-MRI with AB1 and AB2 had significantly lower specificity (AB1 = 73.6%, AB2 = 77.8%), positive predictive values (AB1 = 5%, AB2 = 5.9%), and accuracy (AB1 = 74%, AB2 = 78%) than those of SOC-BMRI (p = .002 for AB1, p = .01 for AB2).ConclusionAB-MRI was acquired significantly faster than SOC-BMRI and its diagnostic performance was non-inferior. Inclusion of T2 and fat-only images was necessary to achieve non-inferiority by multireader evaluation.     

Choice of contrast enhancement index for dynamic magnetic resonance mammography

Indices are often used in dynamic MRI of the breast to quantitate signal enhancement within suspicious lesions. Two indices are commonly used: one calculates the difference in pre- and postcontrast signal intensity, normalised to a base-line signal intensity such as that of fat (which does not enhance) whilst the other calculates the ratio of pre- to postcontrast signal intensity. The results of a computational simulation are presented which demonstrate the superiority of the normalised signal difference index, based on the criterion that the best index is that which is least influenced by initial tissue T₁. This hypothesis was tested by comparing the two indices in a group of patients with clinical or mammographic suspicion of recurrent breast carcinoma. Of 37 patient examinations using Gadolinium enhanced MRI of the breast, 11 patients showed 13 lesions with some degree of enhancement, which were subsequently diagnosed histologically as either benign or malignant. The normalised signal difference index showed no overlap between the benign and malignant groups, whereas some overlap was observed with the signal ratio index. The clinical findings are therefore consistent with the results of the computational simulation.     

A knowledge-driven feature learning and integration method for breast cancer diagnosis on multi-sequence MRI

BackgroundThe classification of benign versus malignant breast lesions on multi-sequence Magnetic Resonance Imaging (MRI) is a challenging task since breast lesions are heterogeneous and complex. Recently, deep learning methods have been used for breast lesion diagnosis with raw image input. However, without the guidance of domain knowledge, these data-driven methods cannot ensure that the features extracted from images are comprehensive for breast cancer diagnosis. Specifically, these features are difficult to relate to clinically relevant phenomena.PurposeInspired by the cognition process of radiologists, we propose a Knowledge-driven Feature Learning and Integration (KFLI) framework, to discriminate between benign and malignant breast lesions using Multi-sequences MRI.MethodsStarting from sequence division based on characteristics, we use domain knowledge to guide the feature learning process so that the feature vectors of sub-sequence are constrained to lie in characteristic-related semantic space. Then, different deep networks are designed to extract various sub-sequence features. Furthermore, a weighting module is employed for the integration of the features extracted from different sub-sequence images adaptively.ResultsThe KFLI is a domain knowledge and deep network ensemble, which can extract sufficient and effective features from each sub-sequence for a comprehensive diagnosis of breast cancer. Experiments on 100 MRI studies have demonstrated that the KFLI achieves sensitivity, specificity, and accuracy of 84.6%, 85.7% and 85.0%, respectively, which outperforms other state-of-the-art algorithms.     

Computer-aided diagnosis of breast DCE-MRI using pharmacokinetic model and 3-D morphology analysis

Three-dimensional (3-D) dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) consists of a large number of images in different enhancement phases which are used to identify and characterize breast lesions. The purpose of this study was to develop a computer-assisted algorithm for tumor segmentation and characterization using both kinetic information and morphological features of 3-D breast DCE-MRI. An integrated color map created by intersecting kinetic and area under the curve (AUC) color maps was used to detect potential breast lesions, followed by the application of a region growing algorithm to segment the tumor. Modified fuzzy c-means clustering was used to identify the most representative kinetic curve of the whole segmented tumor, which was then characterized by using conventional curve analysis or pharmacokinetic model. The 3-D morphological features including shape features (compactness, margin, and ellipsoid fitting) and texture features (based on the grey level co-occurrence matrix) of the segmented tumor were obtained to characterize the lesion. One hundred and thirty-two biopsy-proven lesions (63 benign and 69 malignant) were used to evaluate the performance of the proposed computer-aided system for breast MRI. Five combined features including rate constant (k_ep), volume of plasma (v_p), energy (G₁), entropy (G₂), and compactness (C₁), had the best performance with an accuracy of 91.67% (121/132), sensitivity of 91.30% (63/69), specificity of 92.06% (58/63), and A_z value of 0.9427. Combining the kinetic and morphological features of 3-D breast MRI is a potentially useful and robust algorithm when attempting to differentiate benign and malignant lesions.     

A novel CNN algorithm for pathological complete response prediction using an I-SPY TRIAL breast MRI database

PurposeTo apply our convolutional neural network (CNN) algorithm to predict neoadjuvant chemotherapy (NAC) response using the I-SPY TRIAL breast MRI dataset.MethodsFrom the I-SPY TRIAL breast MRI database, 131 patients from 9 institutions were successfully downloaded for analysis. First post-contrast MRI images were used for 3D segmentation using 3D slicer. Our CNN was implemented entirely of 3 × 3 convolutional kernels and linear layers. The convolutional kernels consisted of 6 residual layers, totaling 12 convolutional layers. Dropout with a 0.5 keep probability and L2 normalization was utilized. Training was implemented by using the Adam optimizer. A 5-fold cross validation was used for performance evaluation. Software code was written in Python using the TensorFlow module on a Linux workstation with one NVidia Titan X GPU.ResultsOf 131 patients, 40 patients achieved pCR following NAC (group 1) and 91 patients did not achieve pCR following NAC (group 2). Diagnostic accuracy of our CNN two classification model distinguishing patients with pCR vs non-pCR was 72.5 (SD ± 8.4), with sensitivity 65.5% (SD ± 28.1) and specificity of 78.9% (SD ± 15.2). The area under a ROC Curve (AUC) was 0.72 (SD ± 0.08).ConclusionIt is feasible to use our CNN algorithm to predict NAC response in patients using a multi-institution dataset.     

Evaluation of solitary pulmonary nodules with dynamic contrast-enhanced MR imaging—a promising technique?

The evaluation of a solitary pulmonary nodule (SPN) is one of the most frequently encountered challenges in thoracic radiology. In addition to a “state-of-the-art” evaluation of SPNs with CT and biopsy techniques, recently the assessment of the enhancement characteristics with iodinized contrast agents has shown its potential to improve the characterization of SPNs. We investigated whether dynamic contrast-enhanced MRI is suitable to assess the degree and kinetics of MR contrast enhancement and whether this technique could help in the noninvasive specification of SPNs. We studied prospectively 21 patients with SPNs. T₁-weighted and proton density-weighted spoiled gradient-echo breath-hold images (2D-FLASH) were obtained before and after the administration of Gd-DTPA in a standard dosage of 0.1 mmol/kg body weight. The maximum enhancement and the initial velocity of contrast uptake were assessed and correlated with pathohistological findings. To quantify contrast enhancement, we used the relative signal intensity increase (S_rel) and the recently introduced enhancement factor (EF) and contrast uptake equivalent (CE). Dynamic contrast-enhanced MRI proved to be well suited for the assessment of the contrast enhancement characteristics of SPNs. Significant differences were found in the degree and kinetics of contrast enhancement for specific types of nodules. Malignant neoplastic SPNs enhanced stronger and faster than benign neoplastic SPNs. The strongest and fastest enhancement, however, was found in a benign type of nodules where histology revealed inflammatory/fibrous lesions. These differences in contrast enhancement between the different pathohistological groups were more significant when EF and CE rather than S_rel was used for the quantification of contrast enhancement. The results of this study indicate a potential role for dynamic contrast-enhanced MRI in the preoperative noninvasive evaluation of SPNs using EF and CE as contrast uptake assessment parameters.     

MRI-guided breast vacuum biopsy: Localization of the lesion without contrast-agent application using diffusion-weighted imaging

ObjectiveIn magnetic resonance-guided breast vacuum biopsies, the contrast agent for targeting suspicious lesions can typically be applied only once during an intervention, due to the slow elimination of the gadolinium chelate from the extracellular fluid space. This study evaluated the feasibility of diffusion-weighted imaging (DWI) for lesion targeting in vacuum assisted magnetic resonance imaging (MRI) biopsies.ConclusionDWI may be used as an alternative to dynamic contrast-enhanced MRI with the advantage of reproducibility. However, the targeted lesion requires the characteristics of a mass-like lesion, substantial diffusion restriction, and a minimum size of approximately 1 cm.     

Triple-negative breast cancer: Pretreatment magnetic resonance imaging features and clinicopathological factors associated with recurrence

PurposeWe aimed to investigate the magnetic resonance imaging (MRI) features and clinicopathologic factors with recurrence of triple-negative breast cancer (TNBC).Patients and methodsWe identified 281 patients with 288 surgically confirmed TNBC lesions who underwent pretreatment MRI between 2009 and 2015. The presence of intratumoral high signal on T2-weighted images, high-signal rim on diffusion-weighted images (DWI), and rim enhancement on the dynamic contrast-enhanced MRI and clinicopathological data were collected. Cox proportional analysis was performed.ResultsOf the 288 lesions, 36 (12.5%) recurred after a median follow-up of 18 months (range, 3.6–68.3 months). Rim enhancement (hazard ratio [HR] = 3.15; 95% confidence interval [CI] = 1.01, 9.88; p = .048), and lymphovascular invasion (HR = 2.73, 95% CI = 1.20, 6.23; p = .016) were independently associated with disease recurrence. While fibroglandular volume, background parenchymal enhancement, intratumoral T2 high signal, and high-signal rim on DWI, were not found to be risk factors for recurrence.ConclusionPretreatment MRI features may help predict a high risk of recurrence in patients with TNBC.     

Relationship between lesion size and signal enhancement on subtraction fat-suppressed MR imaging of the breast

OBJECTIVE: To investigate the relationship between size and whole lesion enhancement of breast neoplasms. MATERIALS AND METHODS: Fat-suppressed subtraction MRI was performed in 94 breast lesions (44 malignant, 50 benign) with pathologically confirmed diagnoses. Of these, all malignant lesions and 31 of the 50 benign lesions showed enhancement. The degree of enhancement was quantified by using an ROI tracing around the whole lesion and calculated as the percentage increase in signal intensity between the corresponding precontrast and postcontrast images. RESULTS: The 44 malignant lesions showed enhancement percentage of 38.3% to 186.4% (mean 109.9%), and the 31 benign lesions showed enhancement percentage of 12.8% to 180.2% (mean 79.5%). The difference is statistically significant (P = .002). In 54 small lesions (28 malignant, 26 benign) with enhancing pixel areas of <300 mm(2) corresponding to a diameter of approximately 19.5 mm, an enhancement exceeding 75% of baseline separated malignant lesions (mean enhancement 116.7%) from benign ones (mean enhancement 72.8%) (P = .0001). This gave a sensitivity of 100% and a specificity of 69%, a positive predictive value of 78%, negative predictive value of 100% and an accuracy of 85% in using >75% enhancement increase in detecting malignancy in small (<300 mm(2)) enhancing lesions. CONCLUSION: The high sensitivity in the detection of small malignant lesions suggests a potential for the method to be used in assessment of small enhancing breast lesions.     

Diffusion weighted imaging for evaluation of breast lesions: Comparison between high b-value single-shot and routine readout-segmented sequences at 3 T

PurposeIn this study, we compare readout-segmented echo-planar imaging (rs-EPI) Diffusion Weighted Imaging (DWI) to a work-in-progress single-shot EPI with modified Inversion Recovery Background Suppression (ss-EPI-mIRBS) sequence at 3 T using a b-value of 2000 s/mm² on image quality, lesion visibility and evaluation time.MethodFrom September 2017 to December 2018, 23 women (one case used for training) with known breast cancer were included in this study, after providing signed informed consent. Women were scanned with the conventional rs-EPI sequence and the work-in-progress ss-EPI-mIRBS during the same examination. Four breast radiologists (4–13 years of experience) independently scored both series for overall image quality (1: extremely poor to 9: excellent). All lesions (47 in total, 36 malignant, and 11 benign and high-risk) were evaluated for visibility (1: not visible, 2: visible if location is given, 3: visible) and probability of malignancy (BI-RADS 1 to 5). ADC values were determined by measuring signal intensity in the lesions using dynamic contrast-enhanced (DCE) images for reference. Evaluation times for all assessments were automatically recorded. Results were analyzed using the visual grading characteristics (VGC) and the resulting area under the curve (AUC_VGC) method. Statistical analysis was performed in SPSS, with McNemar tests, and paired t-tests used for comparison.ResultsNo significant differences were detected between the two sequences in image quality (AUC_VGC: 0.398, p = 0.087) and lesion visibility (AUC_VGC: 0.534, p = 0.336) scores. Lesion characteristics (e.g benign and high-risk, versus malignant; small (≤10 mm) vs. larger (>10 mm)) did not result in different image quality or lesion visibility between sequences. Sensitivity (rs-EPI: 72.2% vs. ss-EPImIRBS: 78.5%, p = 0.108) and specificity (70.5% vs. 56.8%, p = 0.210, respectively) were comparable. In both sequences the mean ADC value was higher for benign and high-risk lesions than for malignant lesions (ss-EPI-mIRBS: p = 0.022 and rs-EPI: p = 0.055). On average, ss-EPI-mIRBS resulted in decreased overall reading time by 7.7 s/case (p = 0.067); a reduction of 17%. For malignant lesions, average reading time was significantly shorter using ss-EPI-mIRBS compared to rs-EPI (64.0 s/lesion vs. 75.9 s/lesion, respectively, p = 0.039).ConclusionBased on this study, the ss-EPI sequence using a b-value of 2000 s/mm² enables for a mIRBS acquisition with quality and lesion conspicuity that is comparable to conventional rs-EPI, but with a decreased reading time.     

Dynamic sequential 3D gadolinium-enhanced MRI of the whole breast

Dynamic contrast-enhanced 2D MR imaging of the breast has shown high sensitivity and specificity for the detection and characterization of breast lesions. We investigated the ability of a dynamic fast 3D MR imaging technique that repeatedly scans the whole breast in 44-s intervals without an interscan delay time to obtain similar sensitivity and specificity as 2D imaging. Fifty-six patients scheduled for breast biopsy were entered into the study, and 83 lesions detected by 3D dynamic scanning were biopsied. Dynamic 3D contrast-enhanced breast imaging with subtraction detected and correctly classified all 23 cancers, and 44 of the 60 benign lesions yielding a sensitivity of 100%, a specificity of 73%, and a 100% predictive negative value. The enhancement profiles of metastatic lymph nodes were similar to those of primary cancer. This technique allowed detection of multifocal and multicentric lesions and did not require a priori knowledge of lesion location. These results indicate that dynamic contrast-enhanced 3D MRI of the whole breast is a useful and economically feasible method for staging breast cancer, providing a comprehensive noninvasive method for total evaluation of the breast and axilla in patients considering breast conservation surgery or lumpectomy.     

Diagnostic performance of apparent diffusion coefficient and quantitative kinetic parameters for predicting additional malignancy in patients with newly diagnosed breast cancer

Purpose

To evaluate the diagnostic performance of an apparent diffusion coefficient (ADC) and quantitative kinetic parameters in patients with newly diagnosed breast cancer.

Materials and Methods

We enrolled 169 lesions in 89 patients with breast cancer who underwent dynamic contrast-enhanced MRI (DCE-MRI) and diffusion-weighted imaging (DWI). Comparisons between benign and malignant lesions were performed for lesion type (mass or nonmass-like enhancement), size (≥ 1 cm or < 1 cm), ADC, kinetic parameters and the presence of a US correlate.

Results

There were 63 benign and 106 malignant lesions. The mean size and initial peak enhancement of the benign lesions were significantly lower than those of malignant lesions (P < 0.001 for both). The ADC of the benign lesions was significantly higher than that of malignant lesions (1.42 × 10^− 3 mm²/sec vs. 1.04 × 10^− 3 mm²/sec; P < 0.001). The area under the receiver operating characteristic curve (AUC) for predicting malignancy was 0.87 for the combined parameters of size, ADC, and initial peak enhancement, which was higher than those of each parameter.

Conclusions

Combination of quantitative kinetic parameters and ADC showed higher diagnostic performance for predicting malignancy than each parameter alone for the evaluation of patients with breast cancer.     

Research and progress in magnetic resonance imaging of triple-negative breast cancer

Triple-negative breast cancer (TNBC), which characterized by distinct biological and clinical pathological features, has a worse prognosis because the lack of effective therapeutic targets. Breast MR is the most accurate imaging modality for diagnosis of breast cancer currently. MR imaging recognition could assist in diagnosis, pretreatment planning and prognosis evaluation of TNBC. MR findings of a larger solitary lesion, mass with smooth mass margin, high signal intensity on T₂-weighted images and rim enhancement are typical MRI features associated with TNBC. Further work is necessary about the clinical application of dynamic contrast-enhanced MR imaging (DCE-MRI), DWI and MRS.     

Classification of breast mass lesions using model-based analysis of the characteristic kinetic curve derived from fuzzy c-means clustering

The purpose of this study is to evaluate the diagnostic efficacy of the representative characteristic kinetic curve of dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) extracted by fuzzy c-means (FCM) clustering for the discrimination of benign and malignant breast tumors using a novel computer-aided diagnosis (CAD) system. About the research data set, DCE-MRIs of 132 solid breast masses with definite histopathologic diagnosis (63 benign and 69 malignant) were used in this study. At first, the tumor region was automatically segmented using the region growing method based on the integrated color map formed by the combination of kinetic and area under curve color map. Then, the FCM clustering was used to identify the time-signal curve with the larger initial enhancement inside the segmented region as the representative kinetic curve, and then the parameters of the Tofts pharmacokinetic model for the representative kinetic curve were compared with conventional curve analysis (maximal enhancement, time to peak, uptake rate and washout rate) for each mass. The results were analyzed with a receiver operating characteristic curve and Student's t test to evaluate the classification performance. Accuracy, sensitivity, specificity, positive predictive value and negative predictive value of the combined model-based parameters of the extracted kinetic curve from FCM clustering were 86.36% (114/132), 85.51% (59/69), 87.30% (55/63), 88.06% (59/67) and 84.62% (55/65), better than those from a conventional curve analysis. The A(Z) value was 0.9154 for Tofts model-based parametric features, better than that for conventional curve analysis (0.8673), for discriminating malignant and benign lesions. In conclusion, model-based analysis of the characteristic kinetic curve of breast mass derived from FCM clustering provides effective lesion classification. This approach has potential in the development of a CAD system for DCE breast MRI.