Biomedical subjects

R Uppaluri

Publications and source records attributed to R Uppaluri.

6 recordsLinked to original sources

PubMed1999

Pulmonary CT image classification with evolutionary programming.

RATIONALE AND OBJECTIVES: It is often difficult to classify information in medical images from derived features. The purpose of this research was to investigate the use of evolutionary programming as a tool for selecting important features and generating algorithms to classify computed tomographic (CT) images of the lung. MATERIALS AND METHODS: Training and test sets consisting of 11 features derived from multiple lung CT images were generated, along with an indicator of the target area from which features originated. The images included five parameters based on histogram analysis, 11 parameters based on run length and co-occurrence matrix measures, and the fractal dimension. Two classification experiments were performed. In the first, the classification task was to distinguish between the subtle but known differences between anterior and posterior portions of transverse lung CT sections. The second classification task was to distinguish normal lung CT images from emphysematous images. The performance of the evolutionary programming approach was compared with that of three statistical classifiers that used the same training and test sets. RESULTS: Evolutionary programming produced solutions that compared favorably with those of the statistical classifiers. In separating the anterior from the posterior lung sections, the evolutionary programming results were better than two of the three statistical approaches. The evolutionary programming approach correctly identified all the normal and abnormal lung images and accomplished this by using less features than the best statistical method. CONCLUSION: The results of this study demonstrate the utility of evolutionary programming as a tool for developing classification algorithms.

Algorithms↗

PubMed1999

Interstitial lung disease: A quantitative study using the adaptive multiple feature method.

We have previously described an adaptive multiple feature method (AMFM) for the objective assessment of global and regional changes in pulmonary parenchyma to detect emphysema. This computerized method uses a combination of statistical and fractal texture features for characterization of lung tissues based upon high resolution computed tomography (HRCT) scans. This present study was a substantial extension of the AMFM to simultaneously discriminate between multiple pulmonary disease processes. Normal subjects and those with emphysema, idiopathic pulmonary fibrosis (IPF), or sarcoidosis were studied. The AMFM was compared with two currently utilized computer-based methods: mean lung density (MLD) and the histogram analysis (HIST). Globally, when comparing two-subject groups the AMFM overall accuracy was 2 to 18% better than the overall accuracy of MLD and as much as 36% better than the accuracy of the HIST methods. In three-subject group discrimination tasks, the AMFM performed 7 to 27% better than the MLD and 4 to 36% better than the HIST methods. Finally, in discriminating all four subject groups at a time, the AMFM overall accuracy was 81%, which was 21% better than the MLD and 25% better than the HIST method. In most three-subject group comparisons and in the four-subject group comparison, the AMFM was significantly (p < 0.01) better than the MLD and HIST methods. Next, the AMFM was applied to local discrimination between normal and each disease group individually. The normal versus emphysema, normal versus IPF, and normal versus sarcoidosis samples were discriminated with an accuracy of 95, 86, and 77%, respectively. The AMFM is an objective quantitative method that can be adapted for successful discrimination of multiple parenchymal lung diseases.

Diagnosis, Computer-Assisted↗

PubMed1999

Computer recognition of regional lung disease patterns.

We have developed an objective, reproducible, and automated means for the regional evaluation of the pulmonary parenchyma from computed tomography (CT) scans. This method, known as the Adaptive Multiple Feature Method (AMFM) assesses as many as 22 independent texture features in order to classify a tissue pattern. In this study, the six tissue patterns characterized were: honeycombing, ground glass, bronchovascular, nodular, emphysemalike, and normal. The lung slices were evaluated regionally using 31 x 31 pixel regions of interest. In each region of interest, an optimal subset of texture features was evaluated to determine which of the six patterns the region could be characterized as. The computer output was validated against experienced observers in three settings. In the first two readings, when the observers were blinded to the primary diagnosis of the subject, the average computer versus observer agreement was 44.4 +/- 8.7% and 47.3 +/- 9.0%, respectively. The average interobserver agreement for the same two readings were 48.8 +/- 9.1% and 52.2 +/- 10.0%, respectively. In the third reading, when the observers were provided the primary diagnosis, the average computer versus observer agreement was 51.7 +/- 2.9% where as the average interobserver agreement was 53.9 +/- 6.2%. The kappa statistic of agreement between the regions, for which the majority of the observers agreed on a pattern type, versus the computer was found to be 0.62. For regional tissue characterization, the AMFM is 100% reproducible and performs as well as experienced human observers who have been told the patient diagnosis.

Diagnosis, Computer-Assisted↗

PubMed1997

Quantification of pulmonary emphysema from lung computed tomography images.

A texture-based adaptive multiple feature method (AMFM) for evaluating pulmonary parenchyma from computed tomography (CT) images is described. This method incorporates multiple statistical and fractal texture features. The AMFM was compared to two previously published methods, namely, mean lung density (MLD) and the lowest fifth percentile of the histogram (HIST). First, the ability of these methods to detect subtle differences in ventral-dorsal lung density gradient in the prone normal lung was studied. Second, their abilities to differentiate between normal and emphysematous whole lung slices were compared. Finally, regional analyses comparing normal and emphysematous regions were performed by dividing the lungs. In the CT slices into six equal regions, ventral to dorsal, and analyzing each region separately. The results demonstrated that the AMFM could separate the ventral from the dorsal one-third of the normal prone lung with 89.8% accuracy, compared to an accuracy of 74.6% with the MLD and 64.4% with the HIST methods. The normal and emphysematous slices were separated on a global basis with 100.0% accuracy using the AMFM as compared to an accuracy of 94.7% and 97.4% using the MLD and HIST methods, respectively. The regional normal and emphysematous tissues were discriminated with an average accuracy of 97.9%, 89.9%, and 99.1% with the AMFM, MLD, and HIST methods, respectively. The three methods and the pulmonary function tests in the normal and emphysema groups were poorly correlated. Quantitative texture analysis using adaptive multiple features holds promise for the objective noninvasive evaluation of the pulmonary parenchyma.

Humans↗

PubMed1995

Genetic dissection of thyroid hormone receptor beta: identification of mutations that separate hormone binding and transcriptional activation.

The thyroid hormone receptors (TR) are members of the nuclear receptor family of ligand-mediated transcription factors. The large region of TR that lies C-terminal to its DNA-binding domain subserves functions of ligand binding, dimerization, and transactivation. Little is known regarding the structural or functional determinants of these processes. We have utilized genetic screening in the yeast Saccharomyces cerevisiae to identify residues involved in these functions. Random mutations of the rat TR beta 1 isoform between amino acid residues 179 and 456 were screened, and mutants with reduced hormone-dependent activation of reporter gene activity were isolated. In this paper we describe the characterization of a class of mutants that exhibit a dissociation between hormone binding and transcriptional activation. These mutants retained hormone binding (> 15% of the wild-type level) yet failed to transactivate a reporter gene. A number of these mutations occurred within the D region, which links the DNA-binding and ligand-binding domains of the receptor. One subset of these mutations abrogated DNA binding, supporting a role of the D region in this process. The remainder retain DNA binding and thus highlight residues critical for receptor activation. In addition, an unexpected group of "superactivator" mutations that led to enhanced hormone-dependent activation in S. cerevisiae were found. These mutations localized to the carboxy-terminal portion of the receptor in a region which contains elements conserved across the superfamily of nuclear receptors. The hormone-dependent phenotype of these superactivator mutations suggests an important role of this segment in ligand-mediated transcriptional activation.

Amino Acid Sequence↗

PubMed1988

Isolation of ribonucleic acid from the unactivated rat liver glucocorticoid receptor.

We have reported that the 7-8S form of the rat liver glucocorticoid receptor is associated with RNA. Whether the unactivated 9-10S form of the glucorticoid receptor is also associated with RNA is less clear. Here we provide evidence that the unactivated 9-10S receptor is indeed associated with RNA. Unactivated 9-10S receptor was partially purified by diethylaminoethyl (DEAE)-cellulose chromatography in the presence of molybdate, an activation inhibitor. This preparation was then bound to BuGR-2, a mouse monoclonal antibody of the immunoglobulin G (IgG)-2 class to the rat liver glucocorticoid receptor, or to nonspecific mouse IgG-2. The antibody-antigen complex was then bound to protein A sepharose and washed to remove extraneous RNA. When the receptor was dissociated from the antibody and the RNA extracted and end-labeled, a distinct band of approximately 170 nucleotide (nt) was found that was specific for the BuGR-2 purified receptor. This band could also be found in DEAE-cellulose receptor that had been isolated from sucrose gradients. The DEAE-cellulose receptor was then cross-linked with formaldehyde before mixing with BuGR-2 in order to permit more vigorous washing of the antigen-antibody complex. In addition to the 170 nt RNA band, another distinct band at approximately 400 nt was seen that was specific to the BuGR-2 derived isolate. These results provide evidence that the 9-10S form of the glucocorticoid receptor from rat liver is associated with RNA.

Animals↗