Search

Rationale and Objectives Breast segmentation using the U-net architecture was implemented and tested in independent validation datasets to quantify fibroglandular tissue volume in breast MRI. Materials and Methods Two datasets were used. The training set was MRI of 286 patients with unilateral breast cancer. The segmentation was done on the contralateral normal breasts. The ground truth for the breast and fibroglandular tissue (FGT) was obtained by using a template-based segmentation method. The U-net deep learning algorithm was implemented to analyze the training set, and the final model was obtained using 10-fold cross-validation. The independent validation set was MRI of 28 normal volunteers acquired using four different MR scanners. Dice Similarity Coefficient (DSC), voxel-based accuracy, and Pearson's correlation were used to evaluate the performance. Results For the 10-fold cross-validation in the initial training set of 286 patients, the DSC range was 0.83–0.98 (mean 0.95 ± 0.02) for breast and 0.73–0.97 (mean 0.91 ± 0.03) for FGT; and the accuracy range was 0.92–0.99 (mean 0.98 ± 0.01) for breast and 0.87–0.99 (mean 0.97 ± 0.01) for FGT. For the entire 224 testing breasts of the 28 normal volunteers in the validation datasets, the mean DSC was 0.86 ± 0.05 for breast, 0.83 ± 0.06 for FGT; and the mean accuracy was 0.94 ± 0.03 for breast and 0.93 ± 0.04 for FGT. The testing results for MRI acquired using four different scanners were comparable. Conclusion Deep learning based on the U-net algorithm can achieve accurate segmentation results for the breast and FGT on MRI. It may provide a reliable and efficient method to process large number of MR images for quantitative analysis of breast density.

ObjectiveTo build radiomics models using features extracted from DCE-MRI and mammography for diagnosis of breast cancer.Materials and Methods266 patients receiving MRI and mammography, who had well-enhanced lesions on MRI and histologically confirmed diagnosis were analyzed. Training dataset had 146 malignant and 56 benign, and testing dataset had 48 malignant and 18 benign lesions. Fuzzy-C-means clustering algorithm was used to segment the enhanced lesion on subtraction MRI maps. Two radiologists manually outlined the corresponding lesion on mammography by consensus, with the guidance of MRI maximum intensity projection. Features were extracted using PyRadiomics from three DCE-MRI parametric maps, and from the lesion and a 2-cm bandshell margin on mammography. The support vector machine (SVM) was applied for feature selection and model building, using 5 datasets: DCE-MRI, mammography lesion-ROI, mammography margin-ROI, mammography lesion+margin, and all combined.ResultsIn the training dataset evaluated using 10-fold cross-validation, the diagnostic accuracy of the individual model was 83.2% for DCE-MRI, 75.7% for mammography lesion, 64.4% for mammography margin, and 77.2% for lesion+margin. When all features were combined, the accuracy was improved to 89.6%. By adding mammography features to MRI, the specificity was significantly improved from 69.6% (39/56) to 82.1% (46/56), pConclusionThe radiomics model built from the combined MRI and mammography has the potential to provide a machine learning-based diagnostic tool and decrease the false positive diagnosis of contrast-enhanced benign lesions on MRI.

Since the development of phase-contrast magnetic resonance imaging (PC-MRI), quantification of cerebrospinal fluid (CSF) flow across the cerebral aqueduct has been utilized for diagnosis of conditions such as normal pressure hydrocephalus (NPH). This study aims to develop an automated method of aqueduct CSF flow analysis using convolution neural networks (CNNs), which can replace the current standard involving manual segmentation of aqueduct region of interest (ROI). Retrospective analysis was performed on 333 patients who underwent PC-MRI, totaling 353 imaging studies. Aqueduct flow measurements using manual ROI placement was performed independently by two radiologists. Two types of CNNs, MultiResUNet and UNet, were trained using ROI data from the senior radiologist, with PC-MRI studies being randomly divided into training (80%) and validation (20%) datasets. Segmentation performance was assessed using Dice similarity coefficient (DSC), and CSF flow parameters were calculated from both manual and CNN-derived ROIs. MultiResUNet, UNet and second radiologist (Rater 2) had DSCs of 0.933, 0.928, and 0.867, respectively, with p 0.001 between CNNs and Rater 2. Comparison of CSF flow parameters showed excellent intraclass correlation coefficients (ICCs) for MultiResUNet, with lowest correlation being 0.67. For UNet, lower ICCs of -0.01 to 0.56 were observed. Only 3/353 (0.8%) studies failed to have appropriate ROIs placed by MultiResUNet, compared to 12/353 (3.4%) failed cases for UNet. In conclusion, CNNs were able to measure aqueductal CSF flow with similar performance to a senior neuroradiologist. MultiResUNet demonstrated fewer cases of segmentation failure and more consistent flow measurements compared to the widely adopted UNet.

Objectives: A subset of meningiomas may show progression/recurrence (P/R) after surgical resection. This study applied pre-operative MR radiomics based on support vector machine (SVM) to predict P/R in meningiomas.Methods: From January 2007 to January 2018, 128 patients with pathologically confirmed WHO grade I meningiomas were included. Only patients who had undergone pre-operative MRIs and post-operative follow-up MRIs for more than 1 year were studied. Pre-operative T2WI and contrast-enhanced T1WI were analyzed. On each set of images, 32 first-order features and 75 textural features were extracted. The SVM classifier was utilized to evaluate the significance of extracted features, and the most significant four features were selected to calculate SVM score for each patient.Results: Gross total resection (Simpson grades I–III) was performed in 93 (93/128, 72.7%) patients, and 19 (19/128, 14.8%) patients had P/R after surgery. Subtotal tumor resection, bone invasion, low apparent diffusion coefficient (ADC) value, and high SVM score were more frequently encountered in the P/R group (p < 0.05). In multivariate Cox hazards analysis, bone invasion, ADC value, and SVM score were high-risk factors for P/R (p < 0.05) with hazard ratios of 7.31, 4.67, and 8.13, respectively. Using the SVM score, an AUC of 0.80 with optimal cutoff value of 0.224 was obtained for predicting P/R. Patients with higher SVM scores were associated with shorter progression-free survival (p = 0.003).Conclusions: Our preliminary results showed that pre-operative MR radiomic features may have the potential to offer valuable information in treatment planning for meningiomas.

Rationale and Objectives Computer-aided methods have been widely applied to diagnose lesions on breast magnetic resonance imaging (MRI). The first step was to identify abnormal areas. A deep learning Mask Regional Convolutional Neural Network (R-CNN) was implemented to search the entire set of images and detect suspicious lesions. Materials and Methods Two DCE-MRI datasets were used, 241 patients acquired using non–fat-sat sequence for training, and 98 patients acquired using fat-sat sequence for testing. All patients have confirmed unilateral mass cancers. The tumor was segmented using fuzzy c-means clustering algorithm to serve as the ground truth. Mask R-CNN was implemented with ResNet-101 as the backbone. The neural network output the bounding boxes and the segmented tumor for evaluation using the Dice Similarity Coefficient (DSC). The detection performance, and the trade-off between sensitivity and specificity, was analyzed using free response receiver operating characteristic. Results When the precontrast and subtraction image of both breasts were used as input, the false positive from the heart and normal parenchymal enhancements could be minimized. The training set had 1469 positive slices (containing lesion) and 9135 negative slices. In 10-fold cross-validation, the mean accuracy = 0.86 and DSC = 0.82. The testing dataset had 1568 positive and 7264 negative slices, with accuracy = 0.75 and DSC = 0.79. When the obtained per-slice results were combined, 240 of 241 (99.5%) lesions in the training and 98 of 98 (100%) lesions in the testing datasets were identified. Conclusion Deep learning using Mask R-CNN provided a feasible method to search breast MRI, localize, and segment lesions. This may be integrated with other artificial intelligence algorithms to develop a fully automatic breast MRI diagnostic system.

Using transmission ultrasound (TU) tomography for quantification of fibroglandular tissue in the breast is a relatively new mechanism to determine breast density. In this research determine breast density from both TU images and the respective magnetic resonance images (MRI) of whole breasts. The MRI-based breast density is used as ground-truth to validate TU-based breast density, termed as quantitative breast density (QBD). The comparison between the two breast density assessments was done by calculating the Pearson correlation coefficient and results showed a strong correlation of 0.90, indicating that TU-based measurements provide a valid way to assess breast density.

Background The purpose of this study was to clarify the effect of asymmetric COW variants on carotid flow changes, and proposed an easy estimate of the representative carotid flow volume for accurate numerical simulation. Methods A total of 210 healthy adults receiving magnetic resonance angiography and carotid duplex sonography were included. Three anterior cerebral artery asymmetry (AA) groups were defined based on the diameter ratio difference (DRD) of bilateral A1 segments: AA1 group, one-side A1 aplasia; AA2, A1 DRD ≥ 50%; AA3, A1 DRD between 10 and 50%. Similarly, 3 posterior communicating artery (PcomA) asymmetry (PA) groups were defined: PA1 group, one fetal-origin posterior cerebral artery and absent contralateral PcomA; PA2, PcomA DRD ≥ 50%; PA3, PcomA DRD between 10 and 50%. Results With A1 asymmetry, the ICA diameter of the dominant A1 is significantly greater than the contralateral side. Significant differences of bilateral ICA flow were present in the AA1 and AA2 groups (mean flow difference 42.9 and 30.7%, respectively). Significant bilateral ICA diameter and flow differences were only found in the PA1 group. Linear regression analysis of ICA diameter and flow found a moderately positive correlation between ICA diameter and flow in all AA groups, with a 1 mm increment in vessel diameter corresponding to a 62.6 ml increment of flow volume. The product of bilateral ICA diameter and flow volume difference (ICA-PDF) could be a potential discriminator with a cutoff of 4.31 to predict A1 asymmetry ≥50% with a sensitivity of 0.81 and specificity of 0.76. Conclusions The study verifies that A1 asymmetry causes unequal bilateral carotid inflow, and consequently different bilateral ICA diameters. Adjustment of the inflow boundary conditions according to the COW variants would be necessary to improve the accuracy of numerical simulation.

Background To investigate the discrepancy between two-dimensional digital subtraction angiography and three-dimensional rotational angiography for small (Materials and methods Eight small (Results In all eight cases, the neck images via three-dimensional rotational angiography were larger than two-dimensional-digital subtraction angiography with a mean difference of 0.95 mm. All eight cases analyzed with three-dimensional rotational angiography, but only one case with two-dimensional-digital subtraction angiography were classified as wide-neck aneurysms with dome-to-neck ratio Conclusions Aneurysm neck overestimation with three-dimensional rotational angiography predisposed neuro-interventionalists to more complex treatment techniques. Additional two-dimensional information is crucial for endovascular treatment planning for small cerebral aneurysms.

BACKGROUND Spontaneous intracranial hypotension (SIH) is often misdiagnosed, and can lead to severe complications. Conventional MR sequences show a limited ability to aid in this diagnosis. MR-based intracranial pressure (MR-ICP) may be able to detect changes of intracranial elastance and pressure. PURPOSE To determine whether MR-ICP is able to differentiate SIH patients from normal subjects, improve diagnostic sensitivity, and provide an insight into the pathophysiology. STUDY TYPE Prospective. SUBJECTS Twenty-eight SIH cases with orthostatic headache and 20 healthy volunteers. FIELD STRENGTH/SEQUENCE Cine phase-contrast MRI on a 1.5T scanner. ASSESSMENT Intracranial elastance (IE) was derived from the ratio of the peak-to-peak cerebrospinal fluid (CSF) pressure gradient (PGcsf-pp ) and intracranial volume change, obtained by summing all flows before each sequential cardiac frame. STATISTICAL TESTS Student's t-test was used to compare the MR-ICP indexes and flow parameters between SIH patients and healthy volunteers (P

Rationale and Objectives Breast cancer occurs more frequently in the upper outer (UO) quadrant, but whether this higher cancer incidence is related to the greater amount of dense tissue is not known. Magnetic resonance imaging acquires three-dimensional volumetric images and is the most suitable among all breast imaging modalities for regional quantification of density. This study applied a magnetic resonance imaging-based method to measure quadrant percent density (QPD), and evaluated its association with the quadrant location of the developed breast cancer. Materials and Methods A total of 126 cases with pathologically confirmed breast cancer were reviewed. Only women who had unilateral breast cancer located in a clear quadrant were selected for analysis. A total of 84 women, including 47 Asian women and 37 western women, were included. An established computer-aided method was used to segment the diseased breast and the contralateral normal breast, and to separate the dense and fatty tissues. Then, a breast was further separated into four quadrants using the nipple and the centroid as anatomic landmarks. The tumor was segmented using a computer-aided method to determine its quadrant location. The distribution of cancer quadrant location, the quadrant with the highest QPD, and the proportion of cancers occurring in the highest QPD were analyzed. Results The highest incidence of cancer occurred in the UO quadrant (36 out of 84, 42.9%). The highest QPD was also noted most frequently in the UO quadrant (31 out of 84, 36.9%). When correlating the highest QPD with the quadrant location of breast cancer, only 17 women out of 84 (20.2%) had breast cancer occurring in the quadrant with the highest QPD. Conclusions The results showed that the development of breast cancer in a specific quadrant could not be explained by the density in that quadrant, and further studies are needed to find the biological reasons accounting for the higher breast cancer incidence in the UO quadrant.

Background The computed tomography angiography (CTA) spot sign represents active contrast extravasation within acute primary intracerebral hemorrhage (ICH) and is an independent predictor of hematoma expansion (HE) and poor clinical outcomes. The spot sign could be detected on first-pass CTA (fpCTA) or delayed CTA (dCTA). Purpose To investigate the additional benefits of dCTA spot sign in primary ICH and hematoma size for predicting spot sign. Material and Methods This is a retrospective study of 100 patients who underwent non-contrast CT (NCCT) and CTA within 24 h of onset of primary ICH. The presence of spot sign on fpCTA or dCTA, and hematoma size on NCCT were recorded. The spot sign on fpCTA or dCTA for predicting significant HE, in-hospital mortality, and poor clinical outcomes (mRS ≥ 4) are calculated. The hematoma size for prediction of CTA spot sign was also analyzed. Results Only the spot sign on dCTA could predict high risk of significant HE and poor clinical outcomes as on fpCTA ( P Conclusion This study clarifies that dCTA imaging could improve predictive performance of CTA in primary ICH. Furthermore, the XY value is the best predictor for CTA spot sign.

Background: Diagnosis of spontaneous intracranial hypotension (SIH) relies on the ability of medical staff to recognize cerebrospinal fluid (CSF) leakage at the spine. However, difficulties with interobserver discrepancy sometimes occurred while reading magnetic resonance myelography (MRM) because clear image definition was lacking. In this study, we tried to determine which pattern of CSF distribution is more reliable for diagnosis of CSF leakage by using MRM. Methods: From January 2012 to August 2014, 19 SIH patients and 27 healthy controls (HC) were recruited into our study; 10 of the 19 patients were recovered (SIH-R) after treatment. Whole spine MRM was performed using the 3D-SPACE (three-dimensional sampling perfection with application-optimized contrasts using different flip-angle evolutions) sequence, and interpreted by two experienced neuroradiologists. Two 4-point classification systems of CSF distribution were used to evaluate the three-dimensional maximum intensity projection (3D MIP) and the thin-slice axial multiplanar reconstruction (MPR) images, respectively. Results: The interobserver agreement between the two readers interpreting the 3D MIP and thin-slice axial MPR MRM were moderate to good (κ=0.60–0.78). Grade 3 of 3D MIP and Type D of axial MPR MRM were only noticed in the SIH. Overall, Grade 3 of MIP and Type D of MPR showed significant difference (p 70%. Conclusion: Grade 3 on 3D MIP and Type D on axial MPR MRM were definite criteria of MRM for localizing CSF leakage, and Type C in the T-spine was a probable leakage sign with high sensitivity and NPV.

Background This study evaluated breast tissue stiffness measured by ultrasound elastography and the percent breast density measured by magnetic resonance imaging to understand their relationship. Methods Magnetic resonance imaging and whole breast ultrasound were performed in 20 patients with suspicious lesions. Only the contralateral normal breasts were analyzed. Breast tissue stiffness was measured from the echogenic homogeneous fibroglandular tissues in the central breast area underneath the nipple. An automatic, computer algorithm-based, segmentation method was used to segment the whole breast and fibroglandular tissues on three dimensional magnetic resonanceimaging. A finite element model was applied to deform the prone magnetic resonance imaging to match the supine ultrasound images, by using the inversed gravity loaded transformation. After deformation, the tissue level used in ultrasound elastography measurement could be estimated on the deformed supine magnetic resonance imaging to measure the breast density in the corresponding tissue region. Results The mean breast tissue stiffness was 2.3 ± 0.8 m/s. The stiffness was not correlated with age (r = 0.29). Overall, there was no positive correlation between breast stiffness and breast volume (r = − 0.14), or the whole breast percent density (r = − 0.09). There was also no correlation between breast stiffness and the local percent density measured from the corresponding region (r = − 0.12). Conclusions The lack of correlation between breast stiffness measured by ultrasound and the whole breast or local percent density measured by magnetic resonance imaging suggests that breast stiffness is not solely related to the amount of fibroglandular tissue. Further studies are needed to investigate whether they are dependent or independent cancer risk factors.

Rationale and Objectives Low-dose chest computed tomography (LDCT), increasingly being used for screening of lung cancer, may also be used to measure breast density, which is proven as a risk factor for breast cancer. In this study, we developed a segmentation method to measure quantitative breast density on CT images and correlated with magnetic resonance density. Materials and Methods Forty healthy women receiving both LDCT and breast magnetic resonance imaging (MRI) were studied. A semiautomatic method was applied to quantify the breast density on LDCT images. The intra- and interoperator reproducibility was evaluated. The volumetric density on MRI was obtained by using a well-established automatic template-based segmentation method. The breast volume (BV), fibroglandular tissue volume (FV), and percent breast density (PD) measured on LDCT and MRI were compared. Results The measurements of BV, FV, and PD on LDCT images yield highly consistent results, with the intraclass correlation coefficient of 0.999 for BV, 0.977 for FV, and 0.966 for PD for intraoperator reproducibility, and intraclass correlation coefficient of 0.953 for BV, 0.974 for FV, and 0.973 for PD for interoperator reproducibility. The BV, FV, and PD measured on LDCT and MRI were well correlated (all r ≥ 0.90). Bland-Altman plots showed that a larger BV and FV were measured on LDCT than on MRI. Conclusions The preliminary results showed that quantitative breast density can be measured from LDCT, and that our segmentation method could yield a high reproducibility on the measured volume and PD. The results measured on LDCT and MRI were highly correlated. Our results showed that LDCT may provide valuable information about breast density for evaluating breast cancer risk.

© 2015 The Authors. Published by Elsevier Inc. Mammographic density has been proven as an independent risk factor for breast cancer. Women with dense breast tissue visible on a mammogram have a much higher cancer risk than women with little density. A great research effort has been devoted to incorporate breast density into risk prediction models to better estimate each individual’s cancer risk. In recent years, the passage of breast density notification legislation in many states in USA requires that every mammography report should provide information regarding the patient’s breast density. Accurate definition and measurement of breast density are thus important, which may allow all the potential clinical applications of breast density to be implemented. Because the two-dimensional mammography-based measurement is subject to tissue overlapping and thus not able to provide volumetric information, there is an urgent need to develop reliable quantitative measurements of breast density. Various new imaging technologies are being developed. Among these new modalities, volumetric mammographic density methods and threedimensional magnetic resonance imaging are the most well studied. Besides, emerging modalities, including different x-ray–based, optical imaging, and ultrasound-based methods, have also been investigated. All these modalities may either overcome some fundamental problems related to mammographic density or provide additional density and/or compositional information. The present review article aimed to summarize the current established and emerging imaging techniques for the measurement of breast density and the evidence of the clinical use of these density methods from the literature.

Parasagittal and parafalcine (PSPF) meningiomas recur more frequently than other intracranial meningiomas owing to the difficulty in achieving gross total resection. The present study investigated the preoperative magnetic resonance imaging (MRI) features for the prediction of progression/recurrence (P/R) in benign PSPF meningiomas with an emphasis on the apparent diffusion coefficient (ADC) values.We retrospectively investigated the preoperative MRI features for the prediction of P/R in benign (World Health Organization grade I) PSPF meningiomas. Only patients who had undergone preoperative and postoperative MRI follow-up studies for ≥1 year were included. From October 2006 to December 2015, 48 patients with a diagnosis of benign PSPF meningioma were included (median follow-up period, 42.5 months). Of these 48 patients, 12 (25%) developed P/R (median time to P/R, 23 months).PSPF meningiomas in male patients, subtotal resection, large tumor diameter, high diffusion-weighted imaging signal, and lower ADC values or ratios were significantly associated with P/R (P0.05). The cutoff points of the ADC value and ADC ratio for the prediction of P/R were 0.83 × 10The preoperative ADC values and ratios for the prediction of P/R offer additional valuable information for the treatment planning for PSPF meningiomas.

Magnetic resonance imaging (MRI) has been a prevalence technique for breast cancer diagnosis. Computer-aided detection and segmentation of lesions from MRIs plays a vital role for the MRI-based disease analysis. There are two main issues of the existing breast lesion segmentation techniques: requiring manual delineation of Regions of Interests (ROIs) as a step of initialization; and requiring a large amount of labeled images for model construction or parameter learning, while in real clinical or experimental settings, it is highly challenging to get sufficient labeled MRIs. To resolve these issues, this work proposes a semi-supervised method for breast tumor segmentation based on super voxel strategies. After image segmentation with advanced cluster techniques, we take a supervised learning step to classify the tumor and nontumor patches in order to automatically locate the tumor regions in an MRI. To obtain the optimal performance of tumor extraction, we take extensive experiments to learn parameters for tumor segmentation and classification, and design 225 classifiers corresponding to different parameter settings. We call the proposed method as Semi-supervised Tumor Segmentation (SSTS), and apply it to both mass and nonmass lesions. Experimental results show better performance of SSTS compared with five state-of-the-art methods.

© 2015 The Authors. PURPOSE: This study presented a three-dimensional magnetic resonance (MR)–based method to separate a breast into four quadrants for quantitative measurements of the quadrant breast volume (BV) and density. METHODS: Breast MR images from 58 healthy women were studied. The breast and the fibroglandular tissue were segmented by using a computer-based algorithm. A breast was divided into four quadrants using two perpendicular planes intersecting at the nipple or the nipple-centroid line. After the separation, the BV, the fibroglandular tissue volume, and the percent density (PD) were calculated. The symmetry of the quadrant BV in the left and right breasts separated by using the nipple alone, or the nipple-centroid line, was compared. RESULTS: The quadrant separation made on the basis of the nipple-centroid line showed closer BVs in four quadrants than using the nipple alone. The correlation and agreement for the BV in corresponding quadrants of the left and the right breasts were improved after the nipple-centroid reorientation. Among the four quadrants, PD was the highest in the lower outer and the lowest in the upper outer (significant than the other three) quadrants (P

BACKGROUND: C-arm cone-beam computed tomography (CBCT) is a comparatively novel modality for guiding percutaneous transthoracic lung biopsies (PTLBs), and despite its potential advantages over conventional computed tomography (CCT), a head-to-head comparison of the two techniques has yet to be reported in the literature. This study aims to evaluate the diagnostic value and safety of CBCT-guided PTLB compared to CCT-guided biopsy, with cases performed in a single hospital. METHODS: A total of 104 PTLB patients were retrospectively analyzed in this study. 35 PTLBs were performed under CBCT guidance, and 69 PTLBs were performed under CCT guidance. Diagnostic accuracy, sensitivity, and specificity for malignancy as well as procedure time, radiation dose of patients, and complication rate in the two groups were compared. RESULTS: Total procedure time was significantly lower in the CBCT group (32 ± 11 minutes) compared to the CCT group (38 ± 9.7 minutes; P = .009), especially among patients ≥70 years of age (CBCT: 33 ± 12 minutes, CCT: 42 ± 13, P = .022). For lesions in the lower lobes, the CBCT-guided group received significantly reduced effective radiation dose (2.9 ± 1.6 mSv) than CCT-guided patients (3.7 ± 0.80; P = .042). Diagnostic accuracy, sensitivity, and specificity for malignancy were comparable between the two groups, as were post-biopsy complication rates. CONCLUSION: CBCT guidance significantly reduces the procedure time and radiation exposure for PTLBs compared with CCT, and should be considered in clinical settings that may be difficult or time-consuming to perform under CCT.

Purpose: Breast tissue composition is considered to be associated with breast cancer risk. This study aimed to develop a computer-aided classification (CAC) system to automatically classify echotexture patterns as heterogeneous or homogeneous using automated breast ultrasound (ABUS) images. Methods: A CAC system was proposed that can recognize breast echotexture patterns in ABUS images. For each case, the echotexture pattern was assessed by two expert radiologists and classified as heterogeneous or homogeneous. After neutrosophic image transformation and fuzzy c-mean clusterings, the lower and upper boundaries of the fibroglandular tissues were defined. Then, the number of hypoechoic regions and histogram features were extracted from the fibroglandular tissues, and the support vector machine model with the leave-one-out cross-validation method was utilized as the classifier. The authors’ database included a total of 208 ABUS images of the breasts of 104 females. Results: The accuracies of the proposed system for the classification of heterogeneous and homogeneous echotexture patterns were 93.48% (43/46) and 92.59% (150/162), respectively, with an overall Az (area under the receiver operating characteristic curve) of 0.9786. The agreement between the radiologists and the proposed system was almost perfect, with a kappa value of 0.814. Conclusions: The use of ABUS and the proposed method can provide quantitative information on the echotexture patterns of the breast and can be used to evaluate whether breast echotexture patterns are associated with breast cancer risk in the future.

Adequately selecting a therapeutic approach for bladder cancer depends on accurate grading and staging. Substantial inaccuracy of clinical staging with bimanual examination, cystoscopy, and transurethral resection of bladder tumor has facilitated the increasing utility of magnetic resonance imaging to evaluate bladder cancer. Diffusion-weighted imaging (DWI) is a noninvasive functional magnetic resonance imaging technique. The high tissue contrast between cancers and surrounding tissues on DWI is derived from the difference of water molecules motion. DWI is potentially a useful tool for the detection, characterization, and staging of bladder cancers; it can also monitor posttreatment response and provide information on predicting tumor biophysical behaviors. Despite advancements in DWI techniques and the use of quantitative analysis to evaluate the apparent diffusion coefficient values, there are some inherent limitations in DWI interpretation related to relatively poor spatial resolution, lack of cancer specificity, and lack of standardized image acquisition protocols and data analysis procedures that restrict the application of DWI and reproducibility of apparent diffusion coefficient values. In addition, inadequate bladder distension, artifacts, thinness of bladder wall, cancerous mimickers of normal bladder wall and benign lesions, and variations in the manifestation of bladder cancer may interfere with diagnosis and monitoring of treatment. Recognition of these pitfalls and limitations can minimize their impact on image interpretation, and carefully applying the analyzed results and combining with pathologic grading and staging to clinical practice can contribute to the selection of an adequate treatment method to improve patient care.

Purpose: Triple-negative breast cancer (TNBC), an aggressive subtype, is frequently misclassified as fibroadenoma due to benign morphologic features on breast ultrasound (US). This study aims to develop a computer-aided diagnosis (CAD) system based on texture features for distinguishing between TNBC and benign fibroadenomas in US images. Methods: US images of 169 pathology-proven tumors (mean size, 1.65 cm; range, 0.7–3.0 cm) composed of 84 benign fibroadenomas and 85 TNBC tumors are used in this study. After a tumor is segmented out using the level-set method, morphological, conventional texture, and multiresolution gray-scale invariant texture feature sets are computed using a best-fitting ellipse, gray-level co-occurrence matrices, and the ranklet transform, respectively. The linear support vector machine with leave-one-out cross-validation schema is used as a classifier, and the diagnostic performance is assessed with receiver operating characteristic curve analysis. Results: The Az values of the morphology, conventional texture, and multiresolution gray-scale invariant texture feature sets are 0.8470 [95% confidence intervals (CIs), 0.7826–0.8973], 0.8542 (95% CI, 0.7911–0.9030), and 0.9695 (95% CI, 0.9376–0.9865), respectively. The Az of the CAD system based on the combined feature sets is 0.9702 (95% CI, 0.9334–0.9882). Conclusions: The CAD system based on texture features extracted via the ranklet transform may be useful for improving the ability to discriminate between TNBC and benign fibroadenomas.

To facilitate rapid and accurate assessment, this study proposed a novel fully automatic method to detect and identify focal tumor breast lesions using both kinetic and morphologic features from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). After motion registration of all phases of the DCE-MRI study, three automatically generated lines were used to segment the whole breast region of each slice. The kinetic features extracted from the pixel-based time-signal intensity curve (TIC) by a two-stage detection algorithm was first used, and then three-dimensional (3-D) morphologic characteristics of the detected regions were applied to differentiate between tumor and non-tumor regions. In this study, 95 biopsy-confirmed lesions (28 benign and 67 malignant lesions) in 54 women were used to evaluate the detection efficacy of the proposed system. The detection performance was analyzed using the free-response operating characteristics (FROC) curve and detection rate. The proposed computer-aided detection (CADe) system had a detection rate of 92.63% (88/95) of all tumor lesions, with 6.15 false positives per case. Based on the results, kinetic features extracted by TIC can be used to detect tumor lesions and 3-D morphology can effectively reduce the false positives.

This study aimed to investigate a computer-aided system for detecting breast masses using dynamic contrast-enhanced magnetic resonance imaging for clinical use. Detection performance of the system was analyzed on 61 biopsy-confirmed lesions (21 benign and 40 malignant lesions) in 34 women. The breast region was determined using the demons deformable algorithm. After the suspicious tissues were identified by kinetic feature (area under the curve) and the fuzzy c-means clustering method, all breast masses were detected based on the rotation-invariant and multi-scale blob characteristics. Subsequently, the masses were further distinguished from other detected non-tumor regions (false positives). Free-response operating characteristics (FROC) curve and detection rate were used to evaluate the detection performance. Using the combined features, including blob, enhancement, morphologic, and texture features with 10-fold cross validation, the mass detection rate was 100 % (61/61) with 15.15 false positives per case and 91.80 % (56/61) with 4.56 false positives per case. In conclusion, the proposed computer-aided detection system can help radiologists reduce inter-observer variability and the cost associated with detection of suspicious lesions from a large number of images. Our results illustrated that breast masses can be efficiently detected and that enhancement and morphologic characteristics were useful for reducing non-tumor regions.

Background and Purpose Posterior reversible encephalopathy syndrome (PRES) is a clinicoradiologic entity with several causes, characterized by rapid onset of symptoms and typical neuroimaging features, which usually resolve if promptly recognized and treated. Brainstem variant of PRES presents with vasogenic edema in brainstem regions on magnetic resonance (MR) images and there is sparing of the supratentorial regions. Because PRES is usually caused by a hypertensive crisis, which would likely have a systemic effect and global manifestations on the brain tissue, we thus proposed that some microscopic abnormalities of the supratentorial regions could be detected with diffusion-weighted imaging (DWI) using apparent diffusion coefficient (ADC) analysis in brainstem variant of PRES and hypothesized that “normal-looking” supratentorial regions will increase water diffusion. Methods We retrospectively identified patients with PRES who underwent brain magnetic resonance imaging studies. We identified 11 brainstem variants of PRES patients, who formed the study cohort, and 11 typical PRES patients and 20 normal control subjects as the comparison cohorts for this study. Nineteen regions of interest were drawn and systematically placed. The mean ADC values were measured and compared among these 3 groups. Results ADC values of the typical PRES group were consistently elevated compared with those in normal control subjects. ADC values of the brainstem variant group were consistently elevated compared with those in normal control subjects. ADC values of the typical PRES group and brainstem variant group did not differ significantly, except for the pons area. Conclusions Quantitative MR DWI may aid in the evaluation of supratentorial microscopic abnormalities in brainstem variant of PRES patients.

This study aimed to evaluate the value of using 3-D breast MRI morphologic features to differentiate benign and malignant breast lesions. The 3-D morphological features extracted from breast MRI were used to analyze the malignant likelihood of tumor from ninety-five solid breast masses (44 benign and 51 malignant) of 82 patients. Each mass-like lesion was examined with regards to three categories of morphologic features, including texture-based gray-level co-occurrence matrix (GLCM) feature, shape, and ellipsoid fitting features. For obtaining a robust combination of features from different categories, the biserial correlation coefficient (|r(pb)|)≧0.4 was used as the feature selection criterion. Receiver operating characteristic (ROC) curve was used to evaluate performance and Student's t-test to verify the classification accuracy. The combination of the selected 3-D morphological features, including conventional compactness, radius, spiculation, surface ratio, volume covering ratio, number of inside angular regions, sum of number of inside and outside angular regions, showed an accuracy of 88.42% (84/95), sensitivity of 88.24% (45/51), and specificity of 88.64% (39/44), respectively. The AZ value was 0.8926 for these seven combined morphological features. In conclusion, 3-D MR morphological features specified by GLCM, tumor shape and ellipsoid fitting were useful for differentiating benign and malignant breast masses.

Author(s): Chen, Jeon-Hor; Bahri, Shadfar; Mehta, Rita S; Carpenter, Philip M; McLaren, Christine E; Chen, Wen-Pin; Fwu, Peter T; Hsiang, David JB; Lane, Karen T; Butler, John A; Su, Min-Ying | Abstract: Background and objectivesTo investigate accuracy of magnetic resonance imaging (MRI) for measuring residual tumor size in breast cancer patients receiving neoadjuvant chemotherapy (NAC).MethodsNinety-eight patients were studied. Several MRI were performed during NAC for response monitoring, and the residual tumor size was measured on last MRI after completing NAC. Covariates, including age, tumor characteristics, biomarkers, NAC regimens, MRI scanners, and time from last MRI to operation, were analyzed. Univariate and Multivariate linear regression models were used to determine the predictive value of these covariates for MRI-pathology size discrepancy as the outcome measure.ResultsThe mean (±SD) of the absolute difference between MRI and pathological residual tumor size was 1.0 ± 2.0 cm (range, 0-14 cm). Univariate regression analysis showed tumor type, morphology, HR status, HER2 status, and MRI scanner (1.5 T or 3.0 T) were significantly associated with MRI-pathology size discrepancy (all P l 0.05). Multivariate regression analyses demonstrated that only tumor type, tumor morphology, and biomarker status considering both HR and HER-2 were independent predictors (P = 0.0014, 0.0032, and 0.0286, respectively).ConclusionThe accuracy of MRI in evaluating residual tumor size depends on tumor type, morphology, and biomarker status. The information may be considered in surgical planning for NAC patients.

Rapid volume density analysis (RVDA) for automated breast ultrasound (ABUS) has been proposed as a more efficient method for estimating breast density. In the current experiment, ABUS images were obtained for 67 breasts from 40 patients. For each case, three rectangular volumes of interest (VOIs) were extracted, including the VOIs located at the 6 and 12 o’clock positions relative to the nipple in the anterior to posterior pass and the lateral position relative to the nipple in the lateral pass. The centers of these VOIs were defined to align with the center of nipple, and the depths reached the retromammary fat boundary. The fuzzy c-means classifier was applied to differentiate the fibroglandular and fat tissues to estimate the density. The classification results of the three VOIs were averaged to obtain the breast density. The density correlations between the RVDA and the ABUS methods were 0.98 and 0.96 using Pearson’s correlation and linear regression coefficients, respectively. The average computation times for RVDA and ABUS were 4.2 and 17.8 seconds, respectively, using an Intel® Core™2 2.66 GHz computer with 3.25 GB memory. In conclusion, the RVDA method offers a quantitative and efficient breast density estimation for ABUS.

Background: We measured breast density (BD) on MRI and correlated with endogenous hormonal levels. Patients and methods: Twenty-four premenopausal women received four weekly breast MRI. A blood sample was collected on the same day of MRI. BD was measured using a computer-based algorithm. The generalized estimation equation method was applied to model mean fibroglandular tissue volume (FV) and mean percent density (PD) from predictor variables including estradiol, progesterone, and week during a cycle. Results: In week 3, a borderline significant correlation between estradiol and PD (r = 0.43, P = 0.04), estradiol and FV (r = 0.40, P = 0.05) and between progesterone and FV (r = 0.42, P = 0.04) was noted. The FV and PD measured in weeks 4 and 1 were higher than in weeks 2 and 3, adjusted for variation in endogenous estradiol and progesterone, indicating that the hormone change could not account for the changes in density. No lag effect of endogenous hormone on the change of FV or PD was noted (all P-values > 0.05). Conclusions: Our results showed that BD is not strongly associated with the endogenous hormone. Their association with breast cancer risk was likely coming from different mechanisms, and they should be considered as independent risk factors. © The Author 2013. Published by Oxford University Press on behalf of the European Society for Medical Oncology. All rights reserved.

The aim of this study was to evaluate the change of breast density in the normal breast of patients receiving neoadjuvant chemotherapy (NAC). Forty-four breast cancer patients were studied. MRI acquisition was performed before treatment (baseline), and 4 and 12 weeks after treatment. A computer-algorithm-based program was used to segment breast tissue and calculate breast volume (BV), fibroglandular tissue volume (FV), and percent density (PD) (the ratio of FV over BV × 100%). The reduction of FV and PD after treatment was compared with baseline using paired t-tests with a Bonferroni-Holm correction. The association of density reduction with age was analyzed. FV and PD after NAC showed significant decreases compared with the baseline. FV was 110.0 ml (67.2, 189.8) (geometric mean (interquartile range)) at baseline, 104.3 ml (66.6, 164.4) after 4 weeks (p < 0.0001), and 94.7 ml (60.2, 144.4) after 12 weeks (comparison with baseline, p < 0.0001; comparison with 4 weeks, p = 0.016). PD was 11.2% (6.4, 22.4) at baseline, 10.6% (6.6, 20.3) after 4 weeks (p < 0.0001), and 9.7% (6.2, 17.9) after 12 weeks (comparison with baseline, p = 0.0001; comparison with 4 weeks, p = 0.018). Younger patients tended to show a higher density reduction, but overall correlation with age was only moderate (r = 0.28 for FV, p = 0.07, and r = 0.52 for PD, p = 0.0003). Our study showed that breast density measured from MR images acquired at 3T MR can be accurately quantified using a robust computer-aided algorithm based on non-parametric non-uniformity normalization (N3) and an adaptive fuzzy C-means algorithm. Similar to doxorubicin and cyclophosphamide regimens, the taxane-based NAC regimen also caused density atrophy in the normal breast and showed reduction in FV and PD. The effect of breast density reduction was age related and duration related.

The normal breast tissue responds to the fluctuation of endogenous hormones during a menstrual cycle (MC) and shows changes in breast density. The changes between left and right breasts of the same women were compared to evaluate the symmetrical response. Twenty-four healthy women were recruited in this study. Four weekly magnetic resonance imaging (MRI) studies were performed during one MC. A computer algorithm was used to segment the breast and the fibroglandular tissue to measure the fibroglandular tissue volume (FV) and three morphological parameters: circularity, convexity and irregularity. The coefficient of variation (CV) for each parameter measured among four MRI studies was calculated; also, the maximal percent change between two MRI studies that show the highest and the lowest FV was calculated. These parameters measured from left and right breasts were compared using Pearson correlation. For the FV, the CV measured between left and right breasts of 24 subjects was highly correlated, with r=0.91; the maximal percent difference was also highly correlated, with r=0.93. Overall, the mean left-to-right difference in the measured FV was small: 1.2%±1.1% for CV and 2.6%±2.3% for the maximal percent difference. For the three morphological parameters, the mean left-to-right percentage difference was similar to the differences seen in FV; however, these morphological parameters do not reveal a high functional symmetry between left and right breasts. The results showed that the measured FV from left and right breasts of the same woman revealed a high functional symmetry. Since endogenous hormone plays an important role in the development of breast cancer, it would be interesting to investigate whether the functional asymmetry of response in some patients is associated with the risk of developing unilateral breast cancer.

Breast density is an independent risk factor for breast cancer, where women with denser breasts are more likely to develop cancer. By identifying women at higher risk, healthcare providers can suggest screening at a younger age to effectively diagnose and treat breast cancer in its earlier stages. Clinical risk assessment models currently do not incorporate breast density, despite its strong correlation with breast cancer. Current methods to measure breast density rely on mammography and MRI, both of which may be difficult to use as a routine risk assessment tool. We propose to use diffuse optical tomography with structured-light to measure the dense, fibroglandular (FGT) tissue volume, which has a different chromophore signature than the surrounding adipose tissue. To test the ability of this technique, we performed simulations by creating numerical breast phantoms from segmented breast MR images. We looked at two different cases, one with a centralized FGT distribution and one with a dispersed distribution. As expected, the water and lipid volumes segmented at half-maximum were overestimated for the dispersed case. However, it was noticed that the recovered water and lipid concentrations were lower and higher, respectively, than the centralized case. This information may provide insight into the morphological distribution of the FGT and can be a correction in estimating the breast density.

To correlate parameters of Ultrasonography-guided Diffuse optical tomography (US-DOT) with pharmacokinetic features of Dynamic contrast-enhanced (DCE)-MRI and pathologic markers of breast cancer. Our institutional review board approved this retrospective study and waived the requirement for informed consent. Thirty seven breast cancer patients received US-DOT and DCE-MRI with less than two weeks in between imaging sessions. The maximal total hemoglobin concentration (THC) measured by US-DOT was correlated with DCE-MRI pharmacokinetic parameters, which included K trans , k ep and signal enhancement ratio (SER). These imaging parameters were also correlated with the pathologic biomarkers of breast cancer. The parameters THC and SER showed marginal positive correlation (r = 0.303, p = 0.058). Tumors with high histological grade, negative ER, and higher Ki-67 expression ≥20 % showed statistically higher THC values compared to their counterparts (p = 0.019, 0.041, and 0.023 respectively). Triple-negative (TN) breast cancers showed statistically higher K trans values than non-TN cancers (p = 0.048). THC obtained from US-DOT and K trans obtained from DCE-MRI were associated with biomarkers indicative of a higher aggressiveness in breast cancer. Although US-DOT and DCE-MRI both measured the vascular properties of breast cancer, parameters from the two imaging modalities showed a weak association presumably due to their different contrast mechanisms and depth sensitivities.

Purpose: To develop an ultrasoundcomputer-aided diagnosis(CAD) system using speckle features of automated breast ultrasound (ABUS) images. Methods: The ABUS images of 147 pathologically proven breast masses (76 benign and 71 malignant cases) were used. For each mass, a volume of interest (VOI) was cropped to define the tumor area, and the average number of speckle pixels within a VOI was calculated. In addition, first-order and second-order statistical analyses of the speckle pixels were used to quantify the information of gray-level distributions and the spatial relations among the pixels. Receiver operating characteristic curve analysis was used to evaluate the performance. Results: The proposed CAD system based on speckle patterns achieved an accuracy of 84.4% (124/147), a sensitivity of 83.1% (59/71), a specificity of 85.5% (65/76), and an Az of 0.91. The performance indices of the speckle features were comparable to the performance indices of the morphological features, which include shape and ellipse-fitting features (p-value > 0.05). Furthermore, combining speckle and morphological features yielded an Az that was significantly better than the Az of the morphological features alone (0.96 vs 0.91, p-value = 0.0154). Conclusions: The results suggest that the proposed speckle features, while combined with morphological features, are promising for the classification of breast masses detected using ABUS.

Purpose: To compare the breast volume (BV), fibroglandular tissue volume (FV), and percent density (PD) measured from breast MRI of the same women using four different MR scanners. Methods: The study was performed in 34 healthy Asian volunteers using two 1.5T (GE and Siemens) and two 3T (GE and Philips) MR scanners. The BV, FV, and PD were measured on nonfat-suppressed T1-weighted images using a comprehensive computer algorithm-based segmentation method. The scanner-to-scanner measurement difference, and the coefficient of variation (CV) among the four scanners were calculated. The measurement variation between two density morphological patterns presenting as the central type and the intermingled type was separately analyzed and compared. Results: All four scanners provided satisfactory image quality allowing for successful completion of the segmentation processes. The measured parameters between each pair of MR scanners were highly correlated, with R2 ≥ 0.95 for BV, R2 ≥ 0.99 for FV, and R2 ≥ 0.97 for PD in all comparisons. The mean percent differences between each pair of scanners were 5.9%–7.8% for BV, 5.3%–6.5% for FV, 4.3%–7.3% for PD; with the overall CV of 5.8% for BV, 4.8% for FV, and 4.9% for PD. The variation of FV was smaller in the central type than in the intermingled type (p = 0.04). Conclusions: The results showed that the variation of FV and PD measured from four different MR scanners is around 5%, suggesting the parameters measured using different scanners can be used for a combined analysis in a multicenter study.

This study aimed to evaluate the influence of hormone receptor (HR) and Ki-67 proliferation markers in predicting the accuracy of magnetic resonance imaging (MRI) for measuring residual tumor size in patients with HER2-negative (HER2(-)) breast cancer receiving neoadjuvant chemotherapy (NAC).Fifty-four women were studied. Patients received AC (doxorubicin (Adriamycin)/cyclophosphamide) and/or taxane-based regimens. The accuracy of MR-determined clinical complete response (CCR) was compared to pathological complete response (pCR). The size of detectable residual tumor on MRI was correlated with pathologically diagnosed tumor size using the Pearson correlation.MRI correctly diagnosed 16 of the 17 cases of pCR. There were 8 false-negative diagnoses: 7 HR(+) and 1 HR(-). The overall sensitivity, specificity, and accuracy of MRI were 78%, 94%, and 83%, respectively. The positive predictive value was 97% and the negative predictive value was 67%. For MRI vs. pathologically determined tumor size correlation, HR(-) cancers showed a higher correlation (R = 0.79) than did HR(+) cancers (R = 0.58). A worse MRI/pathology size discrepancy was found in HR(+) cancer than in HR(-)cancer (1.6 ± 2.8 cm vs. 0.56 ± 0.9 cm; P = .05). Tumors with low Ki-67 proliferation (40%) showed a larger size discrepancy than did those with high Ki-67 proliferation (≥ 40%) (1.2 ± 2.0 cm vs. 0.4 ± 0.8 cm; P = .05).The results showed that the diagnostic performance of MRI for patients with breast cancer undergoing NAC is associated with a molecular biomarker profile. Among HER2(-)tumors, the accuracy of MRI was worse in HR(+)cancers than in HR(-)cancers and was also worse in low-proliferation tumors than in high-proliferation tumors. These findings may help in surgical planning.

Background: This study investigated one-stop breast screening combining magnetic resonance imaging (MRI) and ultrasound (US) in asymptomatic Asian women. Methods: 3,586 asymptomatic women (mean age, 45.3 years) were retrospectively analyzed by breast MRI followed by US. US-guided biopsy was performed when the MRI-detected lesion was confirmed by US. When the lesion was not detected on the initial US, a second-look US guided by MRI findings was performed. Then biopsy was done. MRI-positive and US-negative patients were followed up according to MRI lesion size, MRI lesion morphology, and mammographic diagnosis. Results: In total, 115 subjects had suspicious malignant lesions and received US-guided biopsy, and 47 malignant lesions, including 35 invasive cancers and 12 carcinoma in situ (CIS) lesions, were diagnosed. More than half (22/35, 63%) of the women with invasive cancer were Conclusions: The results from the one-stop breast screening in this study showed that combining MRI and US is an efficient multimodality tool for screening asymptomatic Asian women in a metropolitan area of Taiwan who had concerns about the diagnosis and radiation of mammography.

To assess how the molecular biomarker status of a breast cancer, including human epidermal growth factor receptor 2 (HER2), hormone receptors, and the proliferation marker Ki-67 status, affects the diagnosis at 3.0-T magnetic resonance (MR) imaging.This study was approved by the institutional review board and was HIPAA compliant. Fifty patients (age range, 28-82 years; mean age, 49 years) receiving neoadjuvant chemotherapy were monitored with 3.0-T MR imaging. The longest dimension of the residual cancer was measured at MR imaging and correlated with pathologic findings. Patients were further divided into subgroups on the basis of HER2, hormone receptor, and Ki-67 status. Pathologic complete response (pCR) was defined as when there were no residual invasive cancer cells. The Pearson correlation was used to correlate MR imaging-determined and pathologic tumor size, and the unpaired t test was used to compare MR imaging-pathologic size discrepancies.Of the 50 women, 14 achieved pCR. There were seven false-negative diagnoses at MR imaging. The overall sensitivity, specificity, and accuracy for diagnosing invasive residual disease at MR imaging were 81%, 93%, and 84%, respectively. The mean MR imaging-pathologic size discrepancy was 0.5 cm ± 0.9 (standard deviation) for HER2-positive cancer and 2.3 cm ± 3.5 for HER2-negative cancer (P = .009). In the HER2-negative group, the size discrepancy was smaller for hormone receptor-negative than for hormone receptor-positive cancers (1.0 cm ± 1.1 vs 3.0 cm ± 4.0, P = .04). The size discrepancy was smaller in patients with 40% or greater Ki-67 expression (0.8 cm ± 1.1) than in patients with 10% or less Ki-67 expression (3.9 cm ± 5.1, P = .06).The diagnostic accuracy of breast MR imaging is better in more aggressive than in less aggressive cancers. When MR imaging is used for surgical planning, caution should be taken with HER2-negative hormone receptor-positive cancers.

Purpose: To investigate the difference of MR percent breast density measured from fat-suppressed versus nonfat-suppressed imaging sequences. Methods: Breast magnetic resonance imaging (MRI) with and without fat suppression was acquired from 38 subjects. Breasts were divided into subgroups of different morphological patterns (“central” and “intermingled” types). Breast volume, fibroglandular tissue volume, and percent density were measured. The results were compared using nonparametric statistical tests and regarded as significant at p

Purpose: The purpose of this study is to compare the measurements of breast density using three-dimensional (3-D) automated whole breast ultrasound (ABUS) and magnetic resonance imaging (MRI). Methods: In this study, 3-D ABUS and MRI breast images were obtained from 40 patients—bilaterally in 27 patients and unilaterally (due to operation in the contralateral breast) in 13 patients. To differentiate the fibroglandular and fatty tissues in ABUS and MRI images, the fuzzy C-mean classifier was used. Calculated values for percent density and breast volume from the two modalities were compared to and correlated with linear regression analysis. Intraoperator and interoperator variations among eight cases were evaluated to verify the consistency of the density analysis. Results: Mean percent density and breast volume derived from ABUS (17.63±11.87% and 418.30±132.97 cm3, respectively) and MRI images (23.79±16.62% and 544.90±207.41 cm3) demonstrated good correlation (R=0.917 and R=0.884). Intraoperator and interoperator analyses yielded slightly larger coefficients of variation for percent density and breast volume in ABUS compared to MRI. However, the differences were not statistically significant. Conclusions: ABUS and MRI showed high correlation for breast density and breast volume quantification. Both modalities could provide useful breast density information to physicians.

Purpose: Quantitative breast density is known as a strong risk factor associated with the development of breast cancer.Measurement of breast density based on three-dimensional breast MRI may provide very useful information. One important step for quantitative analysis of breast density on MRI is the correction of field inhomogeneity to allow an accurate segmentation of the fibroglandular tissue (dense tissue). A new bias field correction method by combining the nonparametric nonuniformity normalization (N3) algorithm and fuzzy-C-means (FCM)-based inhomogeneity correction algorithm is developed in this work. Methods: The analysis is performed on non-fat-sat T1-weighted images acquired using a 1.5 T MRI scanner. A total of 60 breasts from 30 healthy volunteers was analyzed. N3 is known as a robust correction method, but it cannot correct a strong bias field on a large area. FCM-based algorithm can correct the bias field on a large area, but it may change the tissuecontrast and affect the segmentation quality. The proposed algorithm applies N3 first, followed by FCM, and then the generated bias field is smoothed using Gaussian kernal and B-spline surface fitting to minimize the problem of mistakenly changed tissuecontrast. The segmentation results based on the N 3 + FCM corrected images were compared to the N3 and FCM alone corrected images and another method, coherent local intensity clustering (CLIC), corrected images. The segmentation quality based on different correction methods were evaluated by a radiologist and ranked. Results: The authors demonstrated that the iterative N 3 + FCM correction method brightens the signal intensity of fatty tissues and that separates the histogram peaks between the fibroglandular and fatty tissues to allow an accurate segmentation between them. In the first reading session, the radiologist found ( N 3 + FCM > N 3 > FCM ) ranking in 17 breasts, ( N 3 + FCM > N 3 = FCM ) ranking in 7 breasts, ( N 3 + FCM = N 3 > FCM ) in 32 breasts, ( N 3 + FCM = N 3 = FCM ) in 2 breasts, and ( N 3 > N 3 + FCM > FCM ) in 2 breasts. The results of the second reading session were similar. The performance in each pairwise Wilcoxon signed-rank test is significant, showing N 3 + FCM superior to both N3 and FCM, and N3 superior to FCM. The performance of the new N 3 + FCM algorithm was comparable to that of CLIC, showing equivalent quality in 57/60 breasts. Conclusions: Choosing an appropriate bias field correction method is a very important preprocessing step to allow an accurate segmentation of fibroglandular tissues based on breast MRI for quantitative measurement of breast density. The proposed algorithm combining N 3 + FCM and CLIC both yield satisfactory results.

Purpose: Breast ultrasound(US) is recently becoming more and more popular for detecting breast lesions. However, screening results in hundreds of USimages for each subject. This magnitude of images can lead to fatigue in radiologist, causing failure in the detection of lesions of a subtle nature. In this study, an image stitching technique is proposed for combining multipass images of the whole breast into a series of full-view images, and a fully automatic screening system that works off these images is also presented. Methods: Using the registration technique based on the simple sum of absolute block-mean difference (SBMD) measure, three-pass images were merged into full-view USimages. An automatic screening system was then developed for detecting tumors from these full-view images. The preprocessing step was used to reduce the tumor detection time of the system and to improve image quality. The gray-level slicing method was then used to divide images into numerous regions. Finally, seven computerized features—darkness, uniformity, width-height ratio, area size, nonpersistence, coronal area size, and region continuity—were defined and used to determine whether or not each region was a part of a tumor. Results: In the experiment, there was a total of 25 experimental cases with 26 lesions, and each case was composed of 252 images (three passes, 84 images/pass). The processing time of the proposed stitching procedure for each case was within 30 s with a Pentium IV 2.0 processor, and the detection sensitivity of the proposed CADsystem was 92.3% with 1.76 false positives per case. Conclusions: The proposed automatic screening system can be applied to the whole breast images stitched together via SBMD-based registration in order to detect tumors.

Purpose: Mammographic density and breast parenchymal patterns (the relative distribution of fatty and fibroglandular tissue) have been shown to be associated with the risk of developing breast cancer. Percent breast density as determined by mammography is a well-established risk factor, but on the other hand, studies on parenchymal pattern have been scarce, possibly due to the lack of reliable quantitative parameters that can be used to analyze parenchymal tissue distribution. In this study the morphology of fibroglandular tissue distribution was analyzed using three-dimensional breast MRI, which is not subject to the tissue overlapping problem. Methods: Four parameters, circularity, convexity, irregularity, and compactness, which are sensitive to the shape and margin of segmented fibroglandular tissue, were analyzed for 230 patients. Cases were assigned to one of two distinct parenchymal breast patterns: Intermingled pattern with intermixed fatty and fibroglandular tissue (Type I, N=141), and central pattern with confined fibroglandular tissue inside surrounded by fatty tissue outside (Type C, N=89). For each analyzed parameter, the differentiation between these two patterns was analyzed using a two-tailed t-test based on transformed parameters to normal distribution, as well as distribution histograms and ROC analysis. Results: These two groups of patients were well matched both in age (50±11 vs 50±11) and in fibroglandular tissue volume (Type I: 104±62 cm3 vs Type C: 112±73 cm3). Between Type I and Type C breasts, all four morphological parameters showed significant differences that could be used to differentiate between the two breast types. In the ROC analysis, among all four parameters, the “compactness” could achieve the highest area under the curve of 0.84, and when all four parameters were combined, the AUC could be further increased to 0.94. Conclusions: The results suggest that these morphological parameters analyzed from 3D MRI can be used to distinguish between intermingled and central dense tissue distribution patterns, and hence may be used to characterize breast parenchymal pattern quantitatively. The availability of these quantitative morphological parameters may facilitate the investigation of the relationship between parenchymal pattern and breast cancer risk.

Purpose: In breast MRI, skin and fibroglandular tissue commonly possess similar signal intensities, and as such, the inclusion of skin as dense tissue leads to an overestimation in the measured density. This study investigated the impact of skin to the quantitative measurement of breast density using MRI. Methods: The analysis was performed on the normal breasts of 50 women using nonfat-saturated (nonfat-sat) T1 weighted MR images. The skin was segmented by using a dynamic searching algorithm, which was based on the change in signal intensities from the background air (dark), to the skin (moderate), and then to the fatty tissue (bright). Tissue with moderate intensities that fell between the two boundaries determined based on the intensity gradients (from air to skin, and from skin to fat) was categorized as skin. The percent breast density measured with and without skin exclusion was compared. Also the relationship between the skin volume and the breast volume was investigated. Then, this relationship was used to estimate the skin volume from the breast volume for skin correction. Results: The percentage of the skin volume normalized to the breast volume ranged from 5.0% to 15.2% (median 8.6%, mean±STD 8.8±2.6%) among 50 women. The percent breast densities measured with skin (y) and without skin (x) were highly correlated, y=1.23x+7% (r=0.94, p

Breast density has been established as an independent risk factor associated with the development of breast cancer. The terms mammographic density and breast density are often used interchangeably, since most breast density studies are performed with projection mammography. It is known that increase in mammographic density is associated with an increased cancer risk. A sensitive method that allows for the measurement of small changes in breast density may provide useful information for risk management. Despite the efforts to develop quantitative breast density measurements from projection mammograms, the measurements show large variability as a result of projection imaging, differing body position, differing levels of compression, and variation of the x-ray beam characteristics. This study used two separate computer-aided methods, threshold-based and proportion-based evaluations, to analyze breast density on whole breast ultrasound(US)imaging and to compare with the grading results of three radiologists using projection mammography. Thirty-two female subjects with 252 images per case were included in this study. Whole breast USimages were obtained from an Aloka SSD-5500 ultrasound machine with an ASU-1004 transducer (Aloka, Japan). Before analyzing breast density, an adaptive speckle reduction filter was used for removing speckle noise, and a robust thresholding algorithm was used to divide breast tissue into fatty or fibroglandular classifications. Then, the proposed approaches were applied for analysis. In the threshold-based method, a statistical model was employed to determine whether each pixel in the breast region belonged to fibroglandular or fatty tissue. The proportion-based method was based on three-dimensional information to calculate the volumetric proportion of fibroglandular tissue to the total breast tissue. The experimental cases were graded by the proposed analysis methods and compared with the ground standard density classification assigned by a majority voting of three experienced breast radiologists. For the threshold-based method, 28 of 32 US test cases and for the proportion-based density classifier, 27 of 32 US test cases were found to be in agreement with the radiologist “ground standard” mammographic interpretations, resulting in overall accuracies of 87.5% and 84.4%, respectively. Moreover, the concordance values of the proposed methods were between 0.0938 and 0.1563, which were less than the average interobserver concordance of 0.3958. The experiment result showed that the proposed methods could be a reference opinion and offer concordant and reliable quantification of breast density for the radiologist.

To develop a computer-based algorithm for detecting blood vessels that appear in breast dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI), and to evaluate the improvement in reducing the number of vascular pixels that are labeled by computer-aided diagnosis (CAD) systems as being suspicious of malignancy.The analysis was performed in 34 cases. The algorithm applied a filter bank based on wavelet transform and the Hessian matrix to detect linear structures as blood vessels on a two-dimensional maximum intensity projection (MIP). The vessels running perpendicular to the MIP plane were then detected based on the connectivity of enhanced pixels above a threshold. The nonvessel enhancements were determined and excluded based on their morphological properties, including those showing scattered small segment enhancements or nodular or planar clusters. The detected vessels were first converted to a vasculature skeleton by thinning and subsequently compared to the vascular track manually drawn by a radiologist.When evaluating the performance of the algorithm in identifying vascular tissue, the correct-detection rate refers to pixels identified by both the algorithm and radiologist, while the incorrect-detection rate refers to pixels identified by only the algorithm, and the missed-detection rate refers to pixels identified only by the radiologist. From 34 analyzed cases the median correct-detection rate was 85.6% (mean 84.9% +/- 7.8%), the incorrect-detection rate was 13.1% (mean 15.1% +/- 7.8%), and the missed-detection rate was 19.2% (mean 21.3% +/- 12.8%). When detected vessels were excluded in the hot-spot color-coding of the CAD system, they could reduce the labeling of vascular vessels in 2.6%-68.6% of hot-spot pixels (mean 16.6% +/- 15.9%).The computer algorithm-based method can detect most large vessels and provide an effective means in reducing the labeling of vascular pixels as suspicious on a DCE-MRI CAD system. This algorithm may improve the workflow of radiologists using CAD for image display, but will be particularly useful for development of automated CAD that gives diagnostic impression.

To investigate methods developed for the characterisation of the morphology and enhancement kinetic features of both mass and non-mass lesions, and to determine their diagnostic performance to differentiate between malignant and benign lesions that present as mass versus non-mass types. Quantitative analysis of morphological features and enhancement kinetic parameters of breast lesions were used to differentiate among four groups of lesions: 88 malignant (43 mass, 45 non-mass) and 28 benign (19 mass, 9 non-mass). The enhancement kinetics was measured and analysed to obtain transfer constant (K trans) and rate constant (k ep). For each mass eight shape/margin parameters and 10 enhancement texture features were obtained. For the lesions presenting as nonmass-like enhancement, only the texture parameters were obtained. An artificial neural network (ANN) was used to build the diagnostic model. For lesions presenting as mass, the four selected morphological features could reach an area under the ROC curve (AUC) of 0.87 in differentiating between malignant and benign lesions. The kinetic parameter (k ep) analysed from the hot spot of the tumour reached a comparable AUC of 0.88. The combined morphological and kinetic features improved the AUC to 0.93, with a sensitivity of 0.97 and a specificity of 0.80. For lesions presenting as non-mass-like enhancement, four texture features were selected by the ANN and achieved an AUC of 0.76. The kinetic parameter k ep from the hot spot only achieved an AUC of 0.59, with a low added diagnostic value. The results suggest that the quantitative diagnostic features can be used for developing automated breast CAD (computer-aided diagnosis) for mass lesions to achieve a high diagnostic performance, but more advanced algorithms are needed for diagnosis of lesions presenting as non-mass-like enhancement.

Purpose Studies specifically reporting MRI of fibrocystic change (FCC) of the breast are very few and its MRI features are not clearly known. The purpose of this study was to analyze the MRI features of FCC of the breast. Materials and Methods Thirty-one patients with pathologically proven FCC of the breast were retrospectively reviewed. The MRI study was performed using a 1.5-T MR scanner with standard bilateral breast coil. The imaging protocol consisted of pre-contrast T1-weighed imaging and dynamic contrast-enhanced axial T1-weighed imaging. The MRI features were interpreted based on the morphologic and enhancement kinetic descriptors defined on ACR BIRADS-MRI lexicon. Results FCC of the breast had a wide spectrum of morphologic and kinetic features on MRI. Two types of FCC were found, including a more diffuse type of nonmass lesion (12/31, 39%) showing benign enhancement kinetic pattern with medium wash-in in early phase (9/10, 90%) and a focal mass-type lesion (11/31, 35%) with enhancement kinetic usually showing rapid up-slope mimicking a breast cancer (8/11, 73%). Conclusion MRI is able to elaborate the diverse imaging features of FCC of the breast. Our result showed that FCC presenting as a focal mass-type lesion was usually overdiagnosed as malignancy. Understanding MRI of FCC is important to determine which cohort of patients should be followed up alone or receive aggressive management.

Proton magnetic resonance spectroscopy (1H MRS) and dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) provide functional information, including vascular volume, vascular permeability and choline (Cho) metabolism. In this study, we applied these two imaging modalities to quantitatively characterize 36 malignant breast lesions in 32 patients and analyzed the correlation between them. Cho concentration was quantified by single-voxel 1H MRS using water as an internal reference. The measured Cho levels ranged from 0.32 to 10.47 mmol/kg, consistent with previously reported values. In 25 mass-type lesions, the Cho concentration was significantly correlated with tumor size (r=.69, P

Splenic preservation is currently the trend for treatment of patients with splenic trauma to avoid complications of splenectomy. This study aimed to evaluate the feasibility of emergent transcatheter arterial embolization (TAE) for hemodynamically unstable patients with blunt splenic injury.In a period of 2 years, 65 patients of blunt splenic trauma were studied. Patients with initial systolic blood pressure90 mmHg and showed initial response including rapid response and transient response to the emergent fluid resuscitation were included. Angiography and TAE was undertaken if contrast medium extravasation or pseudoaneurysm formation was noted in the computed tomography (CT) images, according to the criteria of American Association for the Surgery of Trauma. All patients who underwent TAE were admitted for observation of the possibility of delayed rupture.Thirteen hemodynamically unstable patients who were responsive to initial fluid resuscitation received angiography due to abnormal CT findings including contrast agent extravasation in 12 patients, 2 patients with arteriovenous fistula, and 8 patients with pseudoaneurysm formation. TAE was successfully performed in all of these 13 patients, including 2 patients with associated left renal injuries and 1 patient associated with bilateral internal mammary arteries injuries, without complications.TAE is a safe and effective procedure for treating blunt splenic injury even in hemodynamically unstable patients who responded to initial fluid resuscitation.