Biomedical subjects

Andreas Albrecht

Publications and source records attributed to Andreas Albrecht.

4 recordsLinked to original sources

PubMed2005

Computer-assisted diagnosis of focal liver lesions on CT images evaluation of the Perceptron algorithm.

RATIONALE AND OBJECTIVE: The purpose of the study was to investigate a modified version of a so-called Perceptron algorithm in detecting focal liver lesions on CT scans. MATERIALS AND METHODS: The modified Perceptron algorithm is based on simulated annealing with a logarithmic cooling schedule and was implemented on a standard workstation. The algorithm was trained with 400 normal and 400 pathologic CT scans of the liver. An additional 100 normal and 100 pathologic scans were then used to test the detection of pathology by the algorithm. The total of 1000 scans used in the study were selected from the portal venous phase of upper abdominal CT examinations performed in patients with normal findings or hypovascularized liver lesions. The pathologic scans contained 1 to 4 focal liver lesions. For the preliminary version of the algorithm used in this study, it was necessary to define regions of interest that were converted to a matrix of 119 x 119. RESULTS: Training of the algorithm with 400 examples each of normal and abnormal findings took about 75 hours. Subsequently, the testing took several seconds for processing each scan. The diagnostic accuracy in discriminating scans with and without focal liver lesions achieved for the 200 test scans was approximately 99%. The error rate for pathologic and normal scans was comparable to results reported in the literature, which, however, were obtained for much smaller test sets. CONCLUSION: The modified Perceptron algorithm has an accuracy of close to 99% in detecting pathology on CT scans of the liver showing either normal findings or hypovascularized focal liver lesions.

Algorithms↗

PubMed2003

An Epicurean learning approach to gene-expression data classification.

We investigate the use of perceptrons for classification of microarray data where we use two datasets that were published in [Nat. Med. 7 (6) (2001) 673] and [Science 286 (1999) 531]. The classification problem studied by Khan et al. is related to the diagnosis of small round blue cell tumours (SRBCT) of childhood which are difficult to classify both clinically and via routine histology. Golub et al. study acute myeloid leukemia (AML) and acute lymphoblastic leukemia (ALL). We used a simulated annealing-based method in learning a system of perceptrons, each obtained by resampling of the training set. Our results are comparable to those of Khan et al. and Golub et al., indicating that there is a role for perceptrons in the classification of tumours based on gene-expression data. We also show that it is critical to perform feature selection in this type of models, i.e. we propose a method for identifying genes that might be significant for the particular tumour types. For SRBCTs, zero error on test data has been obtained for only 13 out of 2308 genes; for the ALL/AML problem, we have zero error for 9 out of 7129 genes that are used for the classification procedure. Furthermore, we provide evidence that Epicurean-style learning and simulated annealing-based search are both essential for obtaining the best classification results.

Algorithms↗

PubMed2003

Towards a standardized format for the description of a novel species (of an established genus): Ochrobactrum gallinifaecis sp. nov.

A format for the description of single novel species is proposed, which should facilitate the reviewing process by assisting the provision of data in a standardized form. The abstract must be short and concise, highlighting phylogenetic position, morphology and chemotaxonomy for genus affiliation, the genotypic and phenotypic basis for species differentiation, and the name and deposition numbers from two public culture collections in different countries for the type strain: A Gram-negative, rod-shaped, non-spore-forming bacterium (Iso 196(T)) was isolated from chicken faeces. On the basis of 16S rRNA gene sequence similarity, strain Iso 196(T) was shown to belong to the alpha-2 subclass of the Proteobacteria related to Ochrobactrum tritici (95.6%), Ochrobactrum grignonense (95.0%) and Ochrobactrum anthropi (94.6%), and the phylogenetic distance from any validly described species within the genus Brucella was less than 95%. Chemotaxonomic data (major ubiquinone - Q-10; major polyamines - spermidine and putrescine; major polar lipids - phosphatidylethanolamine, phosphatidylglycerol and phosphatidylcholine; major fatty acids - C(18 : 1)omega7c and C(19 : 0) cyclo omega8c) supported the affiliation of strain Iso 196(T) to the genus Ochrobactrum. The results of DNA-DNA hybridization and physiological and biochemical tests allowed genotypic and phenotypic differentiation of strain Iso 196(T) from the four validly published Ochrobactrum species. Iso 196(T) therefore represents a new species, for which the name Ochrobactrum gallinifaecis sp. nov. is proposed, with the type strain Iso 196(T) (= DSM 15295(T) = CIP 107753(T)).

Bacterial Typing Techniques↗

PubMed2002

Psychrobacter faecalis sp. nov., a new species from a bioaerosol originating from pigeon faeces.

The taxonomy of strain Iso-46T isolated from a bioaerosol generated by cleaning of a pigeon faeces contaminated room was investigated in a polyphasic approach. The beige pigmented Gram-negative, oxidase-negative organism contained a quinone system with mainly ubiquinone Q-8, and the polar lipid profile was composed of phosphatidylethanolamine, phosphatidylglycerol and diphosphatidylglycerol, beside some hitherto uncharacterized phospholipids. Major polyamines were spermidine and putrescine and also small amounts of cadaverine. The analysis of the fatty acids revealed 3-OH 12:0 and 3-OH 14:0 (within summed feature 3) as hydroxylated fatty acids. These chemotaxonomic characteristics suggest that the strain belongs to the gamma-subclass of the Proteobacteria namely into the genus Psychrobacter. Analysis of the 16S rRNA gene supported the allocation into the genus Psychrobacter, but showing similarities to all described species of this genus lower than 97%. Iso-46T was able to grow on MacConkey agar and other high nutrient containing media within a temperature range of 4 degrees C to 36 degrees C. On the basis of nutritional and further physiological features, a clear differentiation from all other Psychrobacter species was possible. For these reasons it is proposed to create a new species with the name Psychrobacter faecalis sp. nov.

Aerosols↗