Fully automatic lesion segmentation in breast MRI using mean-shift and graph-cuts on a region adjacency graph.

PURPOSE: To present and evaluate a fully automatic method for segmentation (i.e., detection and delineation) of suspicious tissue in breast MRI. MATERIALS AND METHODS: The method, based on mean-shift clustering and graph-cuts on a region adjacency graph, was developed and its parameters tuned using multimodal (T1, T2, DCE-MRI) clinical breast MRI data from 35 subjects (training data). It was then tested using two data sets. Test set 1 comprises data for 85 subjects (93 lesions) acquired using the same protocol and scanner system used to acquire the training data. Test set 2 comprises data for eight subjects (nine lesions) acquired using a similar protocol but a different vendor's scanner system. Each lesion was manually delineated in three-dimensions by an experienced breast radiographer to establish segmentation ground truth. The regions of interest identified by the method were compared with the ground truth and the detection and delineation accuracies quantitatively evaluated. RESULTS: One hundred percent of the lesions were detected with a mean of 4.5 ± 1.2 false positives per subject. This false-positive rate is nearly 50% better than previously reported for a fully automatic breast lesion detection system. The median Dice coefficient for Test set 1 was 0.76 (interquartile range, 0.17), and 0.75 (interquartile range, 0.16) for Test set 2. CONCLUSION: The results demonstrate the efficacy and accuracy of the proposed method as well as its potential for direct application across different MRI systems. It is (to the authors' knowledge) the first fully automatic method for breast lesion detection and delineation in breast MRI.

New spatiotemporal features for improved discrimination of benign and malignant lesions in dynamic contrast-enhanced-magnetic resonance imaging of the breast.

OBJECTIVES: The objective of this study was to measure the efficacy of 7 new spatiotemporal features for discriminating between benign and malignant lesions in dynamic contrast-enhanced-magnetic resonance imaging (MRI) of the breast. METHODS: A total of 48 breast lesions from 39 patients were used: 25 malignant and 23 benign. Lesions were acquired using 1.5-T MRI machines in 3 different protocols. Two experiments were performed: (i) selection of the most discriminatory subset of features drawn from the new features and features from the literature and (ii) validation of classification performance of the selected subset of features. RESULTS: Results of the feature selection experiment show that the subset comprising 2 of the new features is the most useful for automatic classification of suspicious lesions in the breast: (i) gradient correlation of maximum intensity and (ii) mean wash-in rate. Results of the validation experiment show that using these 2 features, unseen data can be classified with an area under the receiver operating characteristic curve of 0.91 ± 0.06. CONCLUSIONS: Results of the experiments suggest that suspicious lesions in dynamic contrast-enhanced-MRI of the breast can be classified, with high accuracy, using only 2 of the proposed spatiotemporal features. The selected features indicate heterogeneity of enhancement and speed of enhancement in a tissue. High values of these indicators are likely to be correlated with malignancy.

A new diagnostic approach to popliteal artery entrapment syndrome.

A new method of diagnosing and defining functional popliteal artery entrapment syndrome is described. By combining ultrasonography and magnetic resonance imaging techniques with dynamic plantarflexion of the ankle against resistance, functional entrapment can be demonstrated and the location of the arterial occlusion identified. This combination of imaging modalities will also define muscular anatomy for guiding intervention such as surgery or Botox injection.

Functional Popliteal Artery Entrapment Syndrome: Poorly Understood and Frequently Missed? A Review of Clinical Features, Appropriate Investigations, and Treatment Options.

Functional popliteal artery entrapment syndrome (PAES) is an important and possibly underrecognized cause of exertional leg pain (ELP). As it is poorly understood, it is at risk of misdiagnosis and mismanagement. The features indicative of PAES are outlined, as it can share features with other causes of ELP. Investigating functional PAES is also fraught with potential problems and if it is performed incorrectly, it can result in false negative and false positive findings. A review of the current vascular investigations is provided, highlighting some of the limitations standard tests have in determining functional PAES. Once a clinical suspicion for PAES is satisfied, it is necessary to further distinguish the subcategories of anatomical and functional entrapment and the group of asymptomatic occluders. When definitive entrapment is confirmed, it is important to identify the level of entrapment so that precise intervention can be performed. Treatment strategies for functional PAES are discussed, including the possibility of a new, less invasive intervention of guided Botulinum toxin injection at the level of entrapment as an alternative to vascular surgery.

Rapid determination of vertebral fat fraction over a large range of vertebral bodies.

INTRODUCTION: Vertebral body fat fraction (FF) has been found to vary between lumbar vertebrae using magnetic resonance spectroscopy (MRS). We aim to more quickly assess a larger number of adjacent vertebrae using a single T2-weighted iterative decomposition of water and fat with echo asymmetry and least-squares estimation (IDEAL) sequence. METHODS: Five men had dual-energy X-ray absorptometry (DEXA) and 1.5-T MR scans performed. MRS was performed at L3, and a sagittal IDEAL sequence was also performed, resulting in separate fat-only and water-only readings from T10 to S2. For the IDEAL measurements, two independent observers followed a set reading protocol, with five observations each per vertebra. Intra- and interobserver variability were assessed as deviations from the mean within and between observers, respectively. RESULTS: For FF measurements there was limited intra-observer variation, with observers being on average within 3.4% of the pooled mean value. Similarly, there was good interobserver agreement, with an average variation of 2.1%. All men showed a reduction in FF of 1.6-7% between L5 and S1. Otherwise, there was a trend of increasing FF moving inferiorly from T10 to S2. This averaged 2.7% per vertebra (range 1.1-3.8%) and may not have been dependent on MRS-measured FF at the L3 level. There was poor correlation between MRS-measured FF at L2-4 and bone mineral density measured using DEXA (R(2) = 0.06). CONCLUSION: IDEAL measurements are generally reproducible between observers following a set protocol. There appears to be a gradient in FF moving from T10 to S2, with S1 showing a consistent decrease. This variation may better describe overall marrow function than a single-vertebra reading.

Association of imaging markers of myocardial fibrosis with metabolic and functional disturbances in early diabetic cardiomyopathy.

BACKGROUND: Metabolic and vascular disturbances contribute to diabetic cardiomyopathy, but the role of interstitial fibrosis in early disease is unproven. We sought to assess the relationship between imaging markers of diffuse fibrosis and myocardial dysfunction and to link this to possible causes of early diabetic cardiomyopathy. METHODS AND RESULTS: Hemodynamic and metabolic data were measured in 67 subjects with type 2 diabetes mellitus (age 60±10 years) with no cardiac symptoms. Myocardial function was evaluated with standard echocardiography and myocardial deformation; ischemia was excluded by exercise echocardiography. Calibrated integrated backscatter was calculated from parasternal long-axis views. T1 mapping was performed after contrast with a modified Look-Locker technique using saturation recovery images. Amino-terminal propeptides of procollagens type I and III, as well as the carboxy-terminal propeptide of procollagen type I, were assayed to determine collagen turnover. Subjects with abnormal early diastolic tissue velocity (E(m)) had shorter postcontrast T1 values (P=0.042) and higher calibrated integrated backscatter (P=0.007). They were heavier (P=0.003) and had worse exercise capacity (P<0.001), lower insulin sensitivity (P=0.003), and blunted systolic tissue velocity (P=0.05). Postcontrast T1 was associated with diastolic dysfunction (E(m) r=0.28, P=0.020; E/E(m) r=-0.24, P=0.049), impaired exercise capacity (r=0.30, P=0.016), central adiposity (r=-0.26, P=0.046), blood pressure (systolic r=-0.30, P=0.012; diastolic r=-0.49, P<0.001), and insulin sensitivity (r=0.30, P=0.037). The association of T1 with E/E(m) (ß=-0.31, P=0.017) was independent of blood pressure and metabolic disturbance. Amino-terminal propeptide of procollagens type III was linked to diastolic dysfunction (E(m) r=-0.32, P=0.008) and calibrated integrated backscatter (r=0.30, P=0.015) but not T1 values. CONCLUSIONS: The association between myocardial diastolic dysfunction, postcontrast T1 values, and metabolic disturbance supports that diffuse myocardial fibrosis is an underlying contributor to early diabetic cardiomyopathy.

Denoising of dynamic contrast-enhanced MR images using dynamic nonlocal means.

This paper presents a new algorithm for denoising dynamic contrast-enhanced (DCE) MR images. It is a novel variation on the nonlocal means (NLM) algorithm. The algorithm, called dynamic nonlocal means (DNLM), exploits the redundancy of information in the temporal sequence of images. Empirical evaluations of the performance of the DNLM algorithm relative to seven other denoising methods-simple Gaussian filtering, the original NLM algorithm, a trivial extension of NLM to include the temporal dimension, bilateral filtering, anisotropic diffusion filtering, wavelet adaptive multiscale products threshold, and traditional wavelet thresholding-are presented. The evaluations include quantitative evaluations using simulated data and real data (20 DCE-MRI data sets from routine clinical breast MRI examinations) as well as qualitative evaluations using the same real data (24 observers: 14 image/signal-processing specialists, 10 clinical breast MRI radiographers). The results of the quantitative evaluation using the simulated data show that the DNLM algorithm consistently yields the smallest MSE between the denoised image and its corresponding original noiseless version. The results of the quantitative evaluation using the real data provide evidence, at the alpha = 0.05 level of significance, that the DNLM algorithm yields the smallest MSE between the denoised image and its corresponding original noiseless version. The results of the qualitative evaluation provide evidence, at the alpha = 0.05 level of significance, that the DNLM algorithm performs visually better than all of the other algorithms. Collectively the qualitative and quantitative results suggest that the DNLM algorithm more effectively attenuates noise in DCE MR images than any of the other algorithms.

A new denoising method for dynamic contrast-enhanced MRI.

This paper presents a new algorithm for denoising dynamic contrast-enhanced (DCE) MR images. The algorithm is called Dynamic Non-Local Means and is a novel variation on the Non-Local Means (NL-Means) algorithm. It exploits the redundancy of information in the DCE-MRI sequence of images. An evaluation of the performance of the algorithm relative to six other denoising algorithms-Gaussian filtering, the original NL-Means algorithm, bilateral filtering, anisotropic diffusion filtering, the wavelets adaptive multiscale products threshold method, and the traditional wavelet thresholding method-is also presented. The evaluation was performed by two groups of expert observers-18 signal/image processing experts, and 9 clinicians (8 radiographers and 1 radiologist)-using real DCE-MRI data. The results of the evaluation provide evidence, at the alpha=0.05 level of significance, that both groups of observers deem the DNLM algorithm to perform visually better than all of the other algorithms.

Dynamic breast MRI: image registration and its impact on enhancement curve estimation.

A novel algorithm for performing registration of dynamic contrast-enhanced (DCE) MRI data of the breast is presented. It is based on an algorithm known as iterated dynamic programming originally devised to solve the stereo matching problem. Using artificially distorted DCE-MRI breast images it is shown that the proposed algorithm is able to correct for movement and distortions over a larger range than is likely to occur during routine clinical examination. In addition, using a clinical DCE-MRI data set with an expertly labeled suspicious region, it is shown that the proposed algorithm significantly reduces the variability of the enhancement curves at the pixel level yielding more pronounced uptake and washout phases.