Yun Sub Jung

Multilevel analysis of spatiotemporal association features for differentiation of tumor enhancement patterns in breast DCE-MRI

PURPOSE Analyzing spatiotemporal enhancement patterns is an important task for the differential diagnosis of breast tumors in dynamic contrast-enhanced MRI (DCE-MRI), and yet remains challenging because of complexities in analyzing the time-series of three-dimensional image data. The authors propose a novel approach to breast MRI computer-aided diagnosis (CAD) using a multilevel analysis of spatiotemporal association features for tumor enhancement patterns in DCE-MRI. METHODS A database of 171 cases consisting of 111 malignant and 60 benign tumors was used. Time-series contrast-enhanced MR images were obtained from two different types of MR scanners and protocols. The images were first registered for motion compensation, and then tumor regions were segmented using a fuzzy c-means clustering-based method. Spatiotemporal associations of tumor enhancement patterns were analyzed at three levels: Mapping of pixelwise kinetic features within a tumor, extraction of spatial association features from kinetic feature maps, and extraction of kinetic association features at the spatial feature level. A total of 84 initial features were extracted. Predictable values of these features were evaluated with an area under the ROC curve, and were compared between the spatiotemporal association features and a subset of simple form features which do not reflect spatiotemporal association. Several optimized feature sets were identified among the spatiotemporal association feature group or among the simple feature group based on a feature ranking criterion using a support vector machine based recursive feature elimination algorithm. A least-squares support vector machine (LS-SVM) classifier was used for tumor differentiation and the performances were evaluated using a leave-one-out testing. RESULTS Predictable values of the extracted single features ranged in 0.52-0.75. By applying multilevel analysis strategy, the spatiotemporal association features became more informative in predicting tumor malignancy, which was shown by a statistical testing in ten spatiotemporal association features. By using a LS-SVM classifier with the optimized second and third level feature set, the CAD scheme showed Az of 0.88 in classification of malignant and benign tumors. When this performance was compared to the same LS-SVM classifier with simple form features which do not reflect spatiotemporal association, there was a statistically significant difference (0.88 vs 0.79, p <0.05), suggesting that the multilevel analysis strategy yields a significant performance improvement. CONCLUSIONS The results suggest that the multilevel analysis strategy characterizes the complex tumor enhancement patterns effectively with the spatiotemporal association features, which in turn leads to an improved tumor differentiation. The proposed CAD scheme has a potential for improving diagnostic performance in breast DCE-MRI.

Alterations in hepatic metabolism of sulfur-containing amino acids induced by ethanol in rats

Summary. Alterations in hepatic metabolism of S-amino acids were monitored over one week in male rats treated with a single dose of ethanol (3 g/kg, ip). Methionine and S-adenosylhomocysteine concentrations were increased rapidly, but S-adenosylmethionine, cysteine, and glutathione (GSH) decreased following ethanol administration. Activities of methionine adenosyltransferase, cystathionine γ-lyase and cystathionine β-synthase were all inhibited. γ-Glutamylcysteine synthetase activity was increased from t = 8 hr, but GSH level did not return to control for 24 hr. Hepatic hypotaurine and taurine levels were elevated immediately, but reduced below control in 18 hr. Changes in serum and urinary taurine levels were consistent with results observed in liver. Cysteine dioxygenase activity was increased rapidly, but declined from t = 24 hr. The results show that a single dose of ethanol induces profound changes in hepatic S-amino acid metabolism, some of which persist for several days. Ethanol not only inhibits the cysteine synthesis but suppresses the cysteine availability further by enhancing its irreversible catabolism to taurine, which would play a significant role in the depletion of hepatic GSH.

Speckle reduction in multimode fiber with a piezoelectric transducer in radial vibration for fiber laser marking and display applications

We propose and experimentally demonstrate an effective method to reduce far-field speckle noise in multimode fiber with a short cylindrical piezoelectric transducer (PZT) vibrating in radial direction. In this study, the fiber was coiled as tightly as possible around the mandrel of the PZT and periodic stretching effect was caused by the radial oscillations of the actuator. This technique can be adapted at a high modulation frequency, so the speckle patterns can be time-averaged. The output of the optical fiber was intensively observed by a CCD camera. By counting all the pixels corresponding to relative intensity graded 256 levels in selected area and by calculating the mean value and standard deviation of the intensity, we can measure the speckle contrast and vibration effect in quantitative measurands. It was clearly observed that the characteristics of the speckle pattern in vibration-ON-state were signinficantly reduced than that of vibration-OFF-state by comparing the proposed measurands as well as direct CCD images. We expect that the proposed speckle reduction technology would find viable applications in realization of fiber laser, laser marking, optical trapping and projection display systems.

Characterizing time-intensity curves for spectral morphometric analysis of intratumoral enhancement patterns in breast DCE-MRI: Comparison between differentiation performance of temporal model parameters based on DFT and SVD

This study was designed to characterize the spatio-temporal properties of intratumoral enhancement patterns by using voxel-wise temporal enhancement spectra and morphometry of their spatial distributions in dynamic contrast-enhanced (DCE) breast MRI. Discrete Fourier transformation (DFT) and singular value decomposition (SVD) were used to extract the temporal enhancement features for comparison, generating 4D spectral maps. The spatial variations of DFT and SVD-based eigen spectra within tumor were captured by 3D moment descriptors, respectively. Differentiation between benign and malignant tumors was carried out using least squares support vector machine (LS-SVM) with a radial basis function (RBF) kernel and leave-one-out cross validation was used for performance evaluation. Using DFT, the sensitivity, specificity and area under ROC curve were 84.8%, 64.4% and 0.728. Using SVD, the corresponding values were 100%, 86.7% and 0.935. Combination of SVD and 3D moments yields higher performance in tumor differentiation than that of DFT and 3D moments.

Automatic Patient-Adaptive Bleeding Detection in a Capsule Endoscopy

We present a method for patient-adaptive detection of bleeding region for a Capsule Endoscopy (CE) images. The CE system has 320x320 resolution and transmits 3 images per second to receiver during around 10-hour. We have developed a technique to detect the bleeding automatically utilizing color spectrum transformation (CST) method. However, because of irregular conditions like organ difference, patient difference and illumination condition, detection performance is not uniform. To solve this problem, the detection method in this paper include parameter compensation step which compensate irregular image condition using color balance index (CBI). We have investigated color balance through sequential 2 millions images. Based on this pre-experimental result, we defined ΔCBI to represent deviate of color balance compared with standard small bowel color balance. The ΔCBI feature value is extracted from each image and used in CST method as parameter compensation constant. After candidate pixels were detected using CST method, they were labeled and examined with a bleeding character. We tested our method with 4,800 images in 12 patient data set (9 abnormal, 3 normal). Our experimental results show the proposed method achieves (before patient adaptive method : 80.87% and 74.25%, after patient adaptive method : 94.87% and 96.12%) of sensitivity and specificity.

Tumor classification using perfusion volume fractions in breast DCE-MRI

This study was designed to classify contrast enhancement curves using both three-time-points (3TP) method and clustering approach at full-time points, and to introduce a novel evaluation method using perfusion volume fractions for differentiation of malignant and benign lesions. DCE-MRI was applied to 24 lesions (12 malignant, 12 benign). After region growing segmentation for each lesion, hole-filling and 3D morphological erosion and dilation were performed for extracting final lesion volume. 3TP method and k-means clustering at full-time points were applied for classifying kinetic curves into six classes. Intratumoral volume fraction for each class was calculated. ROC and linear discriminant analyses were performed with distributions of the volume fractions for each class, pairwise and whole classes, respectively. The best performance in each class showed accuracy (ACC), 84.7% (sensitivity (SE), 100%; specificity (SP), 66.7% to a single class) to 3TP method, whereas ACC, 73.6% (SE, 41.7%; SP, 100% to a single class) to k-means clustering. The best performance in pairwise classes showed ACC, 75% (SE, 83.3%; SP, 66.7% to four class pairs and SE, 58.3%; SP, 91.7% to a single class pair) to 3TP method and ACC, 75% (SE, 75%; SP, 75% to a single class pair and SE, 66.7%; SP, 83.3% to three class pairs) to k-means clustering. The performance in whole classes showed ACC, 75% (SE, 83.3%; SP, 66.7%) to 3TP method and ACC, 75% (SE, 91.7%; 58.3%) to k-means clustering. The results indicate that tumor classification using perfusion volume fractions is helpful in selecting meaningful kinetic patterns for differentiation of malignant and benign lesions, and that two different classification methods are complementary to each other.