IEEE transactions on medical imaging
-
IEEE Trans Med Imaging · Oct 2005
Chirp imaging vibro-acoustography for removing the ultrasound standing wave artifact.
Vibro-acoustography (VA) is an imaging technique that uses the dynamic (oscillatory) radiation force of two continuous-wave (CW) ultrasound to image objects at low frequency (within the kHz range). In this technique, the dynamic radiation force is created by means of a confocused transducer emitting two ultrasound beams at slightly-shifted frequencies f1 and f2 = f1 + deltaf. It has been demonstrated previously that high-resolution images of various types of inclusions and tissues can be obtained using this technique. ⋯ The chirp image is produced by averaging the amplitude of the acoustic emission produced during the sweep. Vibro-acoustography chirp imaging experiments are performed on a stainless-steel sphere attached to a latex sheet in a tank of degassed water. The resulting chirp images demonstrate remarkable reduction of the standing wave artifact compared to the "fixed frequency" VA images.
-
IEEE Trans Med Imaging · Oct 2005
Improving geometric accuracy in the presence of susceptibility difference artifacts produced by metallic implants in magnetic resonance imaging.
Geometric and intensity distortions due to the presence of metallic implants in magnetic resonance imaging impede the full exploitation of this advanced imaging modality. The aim of this study is to provide a method for (a) quantifying and (b) reducing the implant distortions in patient images. Initially, a set of reference images (without distortion) was obtained by imaging a custom-designed three-dimensional grid phantom. ⋯ The results demonstrate successful correction of grid phantom images with a metallic implant. Furthermore, the calculated correction was applied to porcine thigh images bearing the same metallic implant, simulating a patient environment. Qualitative and quantitative assessments of the proposed correction method are included.
-
IEEE Trans Med Imaging · Sep 2005
Contextual encoding in uniform and adaptive mesh-based lossless compression of MR images.
We propose and evaluate a number of novel improvements to the mesh-based coding scheme for 3-D brain magnetic resonance images. This includes: 1) elimination of the clinically irrelevant background leading to meshing of only the brain part of the image; 2) content-based (adaptive) mesh generation using spatial edges and optical flow between two consecutive slices; 3) a simple solution for the aperture problem at the edges, where an accurate estimation of motion vectors is not possible; and 4) context-based entropy coding of the residues after motion compensation using affine transformations. ⋯ The mesh-based schemes have been shown to be effective for the compression of 3-D brain computed tomography data also. Adaptive mesh-based schemes perform marginally better than the uniform mesh-based methods, at the expense of increased complexity.
-
IEEE Trans Med Imaging · Sep 2005
Comparative StudyRobust active appearance models and their application to medical image analysis.
Active appearance models (AAMs) have been successfully used for a variety of segmentation tasks in medical image analysis. However, gross disturbances of objects can occur in routine clinical setting caused by pathological changes or medical interventions. This poses a problem for AAM-based segmentation, since the method is inherently not robust. ⋯ We demonstrate the robustness of the method in a variety of examples with different noise conditions. The RAAM performance is quantitatively demonstrated in two substantially different applications, diaphragm segmentation and rheumatoid arthritis assessment. In all cases, the robust method shows an excellent behavior, with the new method tolerating up to 50% object area covered by gross gray-level disturbances.
-
IEEE Trans Med Imaging · Sep 2005
Computer-aided diagnostic scheme for distinction between benign and malignant nodules in thoracic low-dose CT by use of massive training artificial neural network.
Low-dose helical computed tomography (LDCT) is being applied as a modality for lung cancer screening. It may be difficult, however, for radiologists to distinguish malignant from benign nodules in LDCT. Our purpose in this study was to develop a computer-aided diagnostic (CAD) scheme for distinction between benign and malignant nodules in LDCT scans by use of a massive training artificial neural network (MTANN). ⋯ Our scheme achieved an Az (area under the ROC curve) value of 0.882 in a round-robin test. Our scheme correctly identified 100% (76/76) of malignant nodules as malignant, whereas 48% (200/413) of benign nodules were identified correctly as benign. Therefore, our scheme may be useful in assisting radiologists in the diagnosis of lung nodules in LDCT.