PubMed Health⌕ Search

Biomedical subjects

J Kreusch

Publications and source records attributed to J Kreusch.

18 recordsLinked to original sources
PubMed1999

Feature selection for optimized skin tumor recognition using genetic algorithms.

In this paper, a new approach to computer supported diagnosis of skin tumors in dermatology is presented. High resolution skin surface profiles are analyzed to recognize malignant melanomas and nevocytic nevi (moles), automatically. In the first step, several types of features are extracted by 2D image analysis methods characterizing the structure of skin surface profiles: texture features based on cooccurrence matrices, Fourier features and fractal features. Then, feature selection algorithms are applied to determine suitable feature subsets for the recognition process. Feature selection is described as an optimization problem and several approaches including heuristic strategies, greedy and genetic algorithms are compared. As quality measure for feature subsets, the classification rate of the nearest neighbor classifier computed with the leaving-one-out method is used. Genetic algorithms show the best results. Finally, neural networks with error back-propagation as learning paradigm are trained using the selected feature sets. Different network topologies, learning parameters and pruning algorithms are investigated to optimize the classification performance of the neural classifiers. With the optimized recognition system a classification performance of 97.7% is achieved.

Algorithms↗
PubMed1999

Computer-supported diagnosis of melanoma in profilometry.

Laser profilometry offers new possibilities to improve non-invasive tumor diagnostics in dermatology. In this paper, a new approach to computer-supported analysis and interpretation of high-resolution skin-surface profiles of melanomas and nevocellular nevi is presented. Image analysis methods are used to describe the profile's structures by texture parameters based on co-occurrence matrices, features extracted from the Fourier power spectrum, and fractal features. Different feature selection strategies, including genetic algorithms, are applied to determine the best possible subsets of features for the classification task. Several architectures of multilayer perceptrons with error back-propagation as learning paradigm are trained for the automatic recognition of melanomas and nevi. Furthermore, network-pruning algorithms are applied to optimize the network topology. In the study, the best neural classifier showed an error rate of 4.5% and was obtained after network pruning. The smallest error rate in all, of 2.3%, was achieved with nearest neighbor classification.

Diagnosis, Differential↗
PubMed1998

Image analysis and pattern recognition for computer supported skin tumor diagnosis.

A new approach to computer supported recognition of melanoma and naevocytic naevi based on high resolution skin surface profiles is presented. Profiles are generated by sampling an area of 4 x 4 mm2 at a resolution of 125 sample points per mm with a laser profilometer at a vertical resolution of 0.1 micron. With image analysis algorithms Haralick's texture parameters, Fourier features and features based on fractal analysis are extracted. Genetic algorithms are employed successfully to select good feature subsets for the following classification process. As quality measure for feature subsets, the error rate of the nearest neighbor classifier estimated with the leaving-one-out method is used. Classification is performed with feed forward back-propagation network and the nearest neighbor classifier. Classification performance of the neural classifier is optimized using different topologies, learning parameters and pruning algorithms. The best neural classifier achieved an error rate of 4.5% and was found after network pruning. The best result with an error rate of 2.3% was obtained with the nearest neighbor classifier.

Algorithms↗
PubMed1996

[Incident light microscopic characterization of vascular patterns in skin tumors].

The search for vascular structures in skin tumors by incident light microscopy has revealed a surprisingly high proportion of vascularized tumours. Characteristic vascular patterns, in some cases highly tumour-specific, have been defined. The vascular structure is a valuable feature for characterization and differentiation of skin tumours, especially for amelanotic malignant melanoma. We propose a flowchart procedure for analysis and diagnosis of skin tumours using incident light microscopy, which appears to be valuable for advanced image analytic techniques.

Capillaries↗
PubMed1995

[Bacillary angiomatosis].

Bacillary angiomatosis (BA) is a rare infectious disease usually associated with HIV infection. Recent molecular biologic investigations confirm that both Rochalimaea henselae and Rochalimaea quintana can cause BA. The bacteria can be identified by Warthin-Starry staining and electron microscopy. The typical clinical signs are solitary or multiple dermal or subcutaneous nodules. Bone, liver, spleen and other organs may also be involved. We describe the clinical and histological features of a 39-year-old HIV-infected patient with cutaneous and bony lesions of BA. All manifestations of BA disappeared during therapy with erythromycin.

AIDS-Related Opportunistic Infections↗
PubMed1994

Treatment of subgingival implant surfaces with Teflon-coated sonic and ultrasonic scaler tips and various implant curettes. An in vitro study.

Removal of plaque and calculus by means of sonic and ultrasonic scalers causes considerable damage to implants. With a view to avoiding the aggressive effects of these instruments, an experimental study was carried out for which conventional sonic and ultrasonic scalers were coated with Teflon. The effects of these instruments on implant surfaces was then compared with that of plastic and metal implant curettes. Stereo-microscopy, scanning electron microscopy and surface profilometry were used to detect and record damage to implant surfaces and changes in surface roughness. Generation and propagation of heat in subgingival simulation of use of sonic and ultrasonic scalers were also recorded by means of temperature measurements at the implant surface. The results revealed that no discernible damage was caused by Teflon-coated sonic and ultrasonic scalers or implant curettes made of plastic on smooth titanium surfaces. Instrument material residues were found on rough implant surfaces. It was not the intention of this study to provide an analysis of the prerequisites for the cleaning of rough implant surfaces, but rather to determine what type of damage is to be expected when contact is made with smooth and rough surfaces unintentionally. Temperature measurements during the subgingival use of sonic and ultrasonic scalers indicated satisfactory functioning of the cooling system. Coating of sonic and ultrasonic scaler tips with Teflon thus facilitates the use of high-frequency instruments to achieve professional cleaning of implants.

Dental Implants↗
PubMed1991

[Standardized epiluminescent microscopy for differentiating melanocytic and non-melanocytic pigment nevi].

Epiluminescent microscopy (ELM) has been widely accepted as a non-invasive, rapid technique for the differentiation of pigmented skin lesions. The method is valuable for distinguishing melanocytic and non-melanocytic tumors, as well as for identifying malignant melanoma. Due to great morphological variability of pigmented lesions considerable experience is required. Based on a morphological analysis of 600 pigmented skin lesions, a diagnostic procedure was developed that permits a reproducible description and diagnosis of a given lesion and facilitates training in ELM.

Basal Cell Carcinoma↗
PubMed1990

[Structural analysis of melanocytic pigment nevi using epiluminescence microscopy. Review and personal experiences].

Epiluminescent microscopy is now used frequently for the differential diagnosis of pigmented skin lesions. In order to improve the distinction between benign and malignant melanocytic tumours it seemed advisable to develop a standardized pathway of epiluminescent microscopical analysis and to determine the frequency of structures recognizable with the microscope. A total of 600 melanocytic lesions were examined by epiluminescent microscopy, photographed and classified histologically after excision, revealing 426 naevocellular naevi and 174 melanoma. The experience achieved during the course of the investigation was used as the basis of a procedure for stepwise analysis of keratin layer, pigment structures and blood vessels. The most important findings are described and referred to malignancy. The photographs were analysed for the frequency of occurrence of various pigment structures in different types of lesions. The results differ in several aspects from previous findings.

Diagnosis, Differential↗
PubMed1990

[Epiluminescence image of lentiginous junctional nevi].

Occasionally, in patients with pigmented skin lesions referred for epiluminescence microscopy (ELM) the lesions are deep black naevi that even experienced dermatologists suspect might be malignant melanomas. The surface of these lesions is abnormal, often scaly, but their general aspect is regular and not characterized by any gross asymmetry. Inspection by ELM reveals additional features, which, if present in a typical combination, indicate a benign lesion. One simple examination can be enough to exclude malignancy. Histological examination allows the diagnosis of lentiginous junctional naevocytic naevi. Two typical cases are presented.

Adult↗
PubMed1981

Acetyl coenzyme A and coenzyme a contents of growing clostridium kluyveri as determined by isotope assays.

CoASH and some of its acyl derivatives, especially acetyl-SCoA, occupy a central position in the energy metabolism of the anaerobic Clostridium kluyveri, both as intermediates and as regulatory effectors. The steady state concentrations of these compounds were determined in growing cultures of this organism using an anaerobic and fast deproteinization technique and radio isotope assays. Acetyl-SCoA was determined as [1-14C]citrate formed in the presence of [4-14C]oxaloacetate and citrate synthase; 0.49 mumol/g cell wet wt. were found. CoASH, CoAS-SCoA after borohydride reduction, and total acyl derivatives of coenzyme A after hydrolysis of the thiol esters were converted to thioethers with [2,3-14C]N-ethylmaleimide and brought to radiochemical purity by chromatographic methods. While disulfides of coenzyme A were undetectable, 0.13 mumol CoASH and 1.17 mumol of total acyl-SCoA per g wet wt. were found. These data are consistent with the regulatory scheme of the energy metabolism of C. kluyveri previously proposed.

Acetyl Coenzyme A↗