Biomedical subjects

J Näppi

Publications and source records attributed to J Näppi.

4 recordsLinked to original sources

PubMed2001

Algorithmic 3D simulation of breast calcifications for digital mammography.

We present a framework for algorithmic three-dimensional simulation of breast calcifications. The simulated calcifications can be viewed from any angle at a higher spatial resolution than currently available for digital mammography, and they can be placed onto a simulated or real mammographic background to provide example cases for computers and radiologists. In order to simulate calcification clusters, we also show how to simulate duct networks and terminal ductal lobular units. We evaluated the model with a double-blind evaluation of 60 cases with four experienced radiologists by mixing 30 cases of simulated calcification clusters on a real or simulated mammographic background with 30 cases of real breast calcification clusters digitized at a spatial resolution of 15 microm from high-resolution radiographs of 5 mm slices of breast specimens. The results indicate that the majority of the 2D projections of the 3D simulated calcifications compare favorably with the radiographic images of real breast calcifications.

Algorithms↗

PubMed2001

Three-dimensional computer-aided diagnosis scheme for detection of colonic polyps.

We have developed a three-dimensional (3-D) computer-aided diagnosis scheme for automated detection of colonic polyps in computed tomography (CT) colonographic data sets, and assessed its performance based on colonoscopy as the gold standard. In this scheme, a thick region encompassing the entire colonic wall is extracted from an isotropic volume reconstructed from the CT images in CT colonography. Polyp candidates are detected by first computing of 3-D geometric features that characterize polyps, folds, and colonic walls at each voxel in the extracted colon, and then segmenting of connected components corresponding to suspicious regions by hysteresis thresholding based on these geometric features. We apply fuzzy clustering to these connected components to obtain the polyp candidates. False-positive (FP) detections are then reduced by computation of several 3-D volumetric features characterizing the internal structures of the polyp candidates, followed by the application of discriminant analysis to the feature space generated by these volumetric features. The locations of the polyps detected by our computerized method were compared to the gold standard of conventional colonoscopy. The performance was evaluated based on 43 clinical cases, including 12 polyps determined by colonoscopy. Our computerized scheme was shown to have the potential to detect polyps in CT colonography with a clinically acceptable high sensitivity and a low FP rate.

Algorithms↗

PubMed2000

A multiscale algorithm for segmenting calcifications from high-resolution mammographic specimen radiographs.

We have developed a multiscale algorithm for segmenting breast calcifications from high-resolution specimen radiographs. The algorithm was evaluated using 152 mammographic regions of interest digitized at a 15-microm spatial resolution. The true-positive detection rate was approximately 97.4% with 0.67 false-positives per image, and the segmentation error of individual calcification particles was approximately 5%. The performance of the algorithm is highly satisfactory.

Algorithms↗

PubMedDate not supplied

Accurate segmentation of the breast region from digitized mammograms.

The segmentation of a digital mammogram into the breast region and the background is a necessary prerequisite in computer-assisted diagnosis of mammograms. By the exclusion of the background region, the accuracy of the analysis is increased and the running-time is decreased. The algorithm which segments the breast region from the background should be fully automated and give correct results for all kinds of digitized mammograms, including low-quality images. In this paper we present such an algorithm based on histogram thresholding, morphological filtering and contour modeling. Quantitative test results indicate that the computed boundary follows the estimated boundary accurately.

Algorithms↗