Current Issue : October - December Volume : 2016 Issue Number : 4 Articles : 5 Articles
Background: Spine magnetic resonance image (MRI) plays a very important role\nin the diagnosis of various spinal diseases, such as disc degeneration, scoliosis, and\nosteoporosis. Accurate localization and segmentation of the intervertebral disc (IVD)\nin spine MRI can help accelerate the diagnosis time and assist in the treatment by\nproviding quantitative parameters. In this paper, a method based on Gabor filter bank\nis proposed for IVD localization and segmentation.\nMethods: First, the structural features of IVDs are extracted using a Gabor filter bank.\nSecond, the Gabor features of spine are calculated and spinal curves are detected.\nThird, the Gabor feature images (GFI) of IVDs are calculated and adjusted according\nto the spinal curves. Fourth, the IVDs are localized by clustering analysis with GFI.\nFinally, an optimum grayscale-based algorithm with self-adaptive threshold, combined\nwith the localization results and Gabor features of the spine, is performed for IVDs\nsegmentation.\nResults: The proposed method is verified by an MRI dataset consisting of 278 IVDs\nfrom 37 patients. The accuracy of localization is 98.23 % and the dice similarity index for\nsegmentation evaluation is 0.9237.\nConclusions: The proposed Gabor filter based method is effective for IVD localization\nand segmentation. It would be useful in computer-aided diagnosis of IVD diseases and\ncomputer-assisted spine surgery....
Architectural distortion is an important ultrasonographic indicator of breast cancer. However, it is\ndifficult for clinicians to determine whether a given lesion is malignant because such distortions\ncan be subtle in ultra sonographic images. In this paper, we report on a study to develop a computerized\nscheme for the histological classification of masses with architectural distortions as a differential\ndiagnosis aid. Our database consisted of 72 ultra sonographic images obtained from 47\npatients whose masses had architectural distortions. This included 51 malignant (35 invasive and\n16 noninvasive carcinomas) and 21 benign masses. In the proposed method, the location of the\nmasses and the area occupied by them were first determined by an experienced clinician. Fourteen\nobjective features concerning masses with architectural distortions were then extracted automatically\nby taking into account subjective features commonly used by experienced clinicians to\ndescribe such masses. The k-nearest neighbors (k-NN) rule was finally used to distinguish three\nhistological classifications. The proposed method yielded classification accuracy values of 91.4%\n(32/35) for invasive carcinoma, 75.0% (12/16) for noninvasive carcinoma, and 85.7% (18/21) for\nbenign mass, respectively. The sensitivity and specificity values were 92.2% (47/51) and 85.7%\n(18/21), respectively. The positive predictive values (PPV) were 88.9% (32/36) for invasive carcinoma\nand 85.7% (12/14) for noninvasive carcinoma whereas the negative predictive values\n(NPV) were 81.8% (18/22) for benign mass. Thus, the proposed method can help the differential\ndiagnosis of masses with architectural distortions in ultrasonographic images....
Objective. To demonstrate a novel approach of compensating overexposure artifacts in CT scans of the knees without attaching\nany supporting appliances to the patient. C-Arm CT systems offer the opportunity to perform weight-bearing knee scans on\nstanding patients to diagnose diseases like osteoarthritis. However, one serious issue is overexposure of the detector in regions\nclose to the patella, which can not be tackled with common techniques. Methods. A Kinect camera is used to algorithmically\nremove overexposure artifacts close to the knee surface. Overexposed near-surface knee regions are corrected by extrapolating\nthe absorption values from more reliable projection data. To achieve this, we develop a cross-calibration procedure to transform\nsurface points from the Kinect to CT voxel coordinates. Results. Artifacts at both knee phantoms are reduced significantly in\nthe reconstructed data and a major part of the truncated regions is restored. Conclusion. The results emphasize the feasibility of\nthe proposed approach. The accuracy of the cross-calibration procedure can be increased to further improve correction results.\nSignificance. The correction method can be extended to a multi-Kinect setup for use in real-world scenarios. Using depth cameras\ndoes not require prior scans and offers the possibility of a temporally synchronized correction of overexposure artifacts. To achieve\nthis, we develop a cross-calibration procedure to transform surface points from the Kinect to CT voxel coordinates....
Background: The hemodynamic balloon model describes the change in coupling\nfrom underlying neural activity to observed blood oxygen level dependent (BOLD)\nresponse. It plays an increasing important role in brain research using magnetic resonance\nimaging (MRI) techniques. However, changes in the BOLD signal are sensitive\nto the resting blood volume fraction (i.e., V0) associated with the regional vasculature.\nIn previous studies the value was arbitrarily set to a physiologically plausible value to\ncircumvent the ill-posedness of the inverse problem. These approaches fail to explore\nactual V0 value and could yield inaccurate model estimation.\nMethods: The present study represents the first empiric attempt to derive the actual\nV0 from data obtained using cerebral blood volume imaging, with the aim of augmenting\nthe existing estimation schemes. Bimanual finger tapping experiments were\nperformed to determine how V0 influences the model estimation of BOLD signals\nwithin a single-region and multiple-regions (i.e., dynamic causal modeling). In order to\nshow the significance of applying the true V0, we have presented the different results\nobtained when using the real V0 and assumed V0 in terms of single-region model estimation\nand dynamic causal modeling.\nResults: The results show that V0 significantly influences the estimation results within\na single-region and multiple-regions. Using the actual V0 might yield more realistic and\nphysiologically meaningful model estimation results.\nConclusion: Incorporating regional venous information in the analysis of the hemodynamic\nmodel can provide more reliable and accurate parameter estimations and\nmodel predictions, and improve the inference about brain connectivity based on fMRI\ndata....
Background: Magneto-acoustic tomography with current injection involves using\nelectrical impedance imaging technology. To explore the potential applications\nin imaging biological tissue and enhance image quality, a new scan mode for the\ntransducer is proposed that is based on translational and circular scanning to record\nacoustic signals from sources.\nMethods: An imaging algorithm to analyze these signals is developed in respect to\nthis alternative scanning scheme. Numerical simulations and physical experiments\nwere conducted to evaluate the effectiveness of this scheme. An experiment using\na graphite sheet as a tissue-mimicking phantom medium was conducted to verify\nsimulation results. A pulsed voltage signal was applied across the sample, and acoustic\nsignals were recorded as the transducer performed stepped translational or circular\nscans. The imaging algorithm was used to obtain an acoustic-source image based on\nthe signals.\nResults: In simulations, the acoustic-source image is correlated with the conductivity\nat the sample boundaries of the sample, but image results change depending\non distance and angular aspect of the transducer. In general, as angle and distance\ndecreases, the image quality improves. Moreover, experimental data confirmed the\ncorrelation.\nConclusion: The acoustic-source images resulting from the alternative scanning\nmode has yielded the outline of a phantom medium. This scan mode enables improvements\nto be made in the sensitivity of the detecting unit and a change to a transducer\narray that would improve the efficiency and accuracy of acoustic-source images....
Loading....