At the Department of Radiology of the University of Graz a PACS has been installed and is used in... more At the Department of Radiology of the University of Graz a PACS has been installed and is used in daily routine. This PACS is interfaced with a RIS. Our experiences show that one of the most urgent clinical interest in PACS is not the reporting on the diagnostic console, but the image transfer to clinical departments where they are not available or only with time delays. Therefore we provide the decentralised access to the images within the PACS and activate the image transfer to the end users of the diagnostic information.
Die Entwicklung digitaler bildgebender Verfahren ebenso wie die Entwicklung im Computerbereich fu... more Die Entwicklung digitaler bildgebender Verfahren ebenso wie die Entwicklung im Computerbereich fuhren tendenziell zur Moglichkeit eines Krankenhauses, in dem die Entstehung, Ubertragung, Auswertung und Archivierung von Bildern auf digitalem Weg erfolgt.
OBJECTIVE To evaluate the possibilities of describing and discriminating common nevi and malignan... more OBJECTIVE To evaluate the possibilities of describing and discriminating common nevi and malignant melanoma tissue with features based on spectral properties of the Daubechies 4 wavelet transform. STUDY DESIGN Images of common nevi and malignant melanoma were dissected in square elements. The wavelet coefficients were calculated inside the square elements. The diagonal coefficients and related power spectra were used for further analysis. The analysis results served as guide for the selection of features, including standard deviations of wavelet coefficients inside the frequency bands and the energy of the frequency bands. These features describe properties of the frequency bands, representing information on different scales. To test the usefulness of the features for discrimination, a study set of 80 cases was classified by classification and regression trees analysis. The set was divided into a training set and a test set. RESULTS In the case of benign common nevi, the energies of...
aim of this study is to check the application of machine learning algorithms for the computer aid... more aim of this study is to check the application of machine learning algorithms for the computer aided diagnosis of confocal laser scanning microscopy (CLSM) views of skin lesions. The images were dissected in equal square elements where the features, based on spectral properties of the wavelet transform, were calculated out. The images were discriminated according their features by several machine learning algorithms, based on tree classifiers, function classifiers and lazy classi- fiers. The results were evaluated and show that tree classifiers allow the best discrimination be- tween CLSM views of benign common nevi and malignant melanoma.
The frequency of melanoma doubles every 20 years. The early detection of malignant changes augmen... more The frequency of melanoma doubles every 20 years. The early detection of malignant changes augments the therapy success. Confocal laser scanning microscopy (CLSM) enables the noninvasive examination of skin tissue. To diminish the need for training and to improve diagnostic accuracy, computer-aided diagnostic systems are required. Two approaches are presented: a multiresolution analysis and an approach based on deep layer convolutional neural networks. For the diagnosis of the CLSM views, architectural structures such as micro-anatomic structures and cell nests are used as guidelines by the dermatologists. Features based on the wavelet transform enable an exploration of architectural structures at different spatial scales. The subjective diagnostic criteria are objectively reproduced. A tree-based machine-learning algorithm captures the decision structure explicitly and the decision steps are used as diagnostic rules. Deep layer neural networks require no a priori domain knowledge. They are capable of learning their own discriminatory features through the direct analysis of image data. However, deep layer neural networks require large amounts of processing power to learn. Therefore, modern neural network training is performed using graphics cards, which typically possess many hundreds of small, modestly powerful cores that calculate massively in parallel. Readers will learn how to apply multiresolution analysis and modern deep learning neural network techniques to medical image analysis problems.
We present the introduction of a new generation of techniques for early and specific diagnosis of... more We present the introduction of a new generation of techniques for early and specific diagnosis of inflammatory, immune and degenerative eye diseases. We concentrate on the applications of the SELDI-TOF (Surface enhanced laser desorption ionisation - time of flight) mass spectroscopy in combination with molecular modelling and visualization for the analysis of the aqueous humour. For our study we used aqueous humour from 25 patients undergoing cataract operation. SELDI-TOF consists on one part of an apparatus allowing the laser bombarding of molecules on a solid surface and on the other part on a system which measure the time of flight of the molecules. During the measurement the molecules are liberated from the matrix and carried to the detector. Specific proteins can be identified by the characteristic peaks of the spectrogram. Albumin and gamma-globulin were found to a considerable extend in the aqueous humour. An increased amount has been detected in inflammatory humour. The quan...
E I Elektrotechnik Und Informationstechnik, Apr 1, 2006
The purpose of this study was to evaluate the feasibility and usability of digital image fusion o... more The purpose of this study was to evaluate the feasibility and usability of digital image fusion of different phases in spiral CT studies of the head and neck. Patients with squamous cell carcinomas underwent dual-phase spiral CT using a contrast material. The images of the early phase were showing optimal vascular enhancement. The images of the late phase were showing optimal tumor conspicuity. Selected images of the early phase were fused with selected images of the late phase by application of user-centered developed software. The image fusion was done in a semi-automatically way on a desktop computer (PC). The relationship between tumors and adjacent vessels was better visualized on the fused images than on the original source images. As a conclusion it can be emphasized, that digital image fusion of early and late phases enabled combined opacification of vessels and squamous cell carcinomas, which facilitated the topographic assessment of the tumors size and spread.
Microarray analysis makes it possible to determine thousands of gene expression values simultaneo... more Microarray analysis makes it possible to determine thousands of gene expression values simultaneously. Changes in gene expression, as a response to diseases, can be detected allowing a better understanding and differentiation of diseases at a molecular level. By comparing different kinds of tissue, for example healthy tissue and cancer tissue, the microarray analysis indicates induced gene activity, repressed gene activity or when there is no change in the gene activity level. Fundamental patterns in gene expression are extracted by several clustering and machine learning algorithms. Certain kinds of cancer can be divided into subtypes, with different clinical outcomes, by their specific gene expression patterns. This enables a better diagnosis and tailoring of individual patient treatments.
Tumour biology : the journal of the International Society for Oncodevelopmental Biology and Medicine, Jan 31, 2015
Genetic alterations causing constitutive activation of the nuclear factor kappa B (NF-κB) signali... more Genetic alterations causing constitutive activation of the nuclear factor kappa B (NF-κB) signaling pathway has been associated with the development of lymphomas. A20 (TNFAIP3) is a key regulator of NF-κB signaling. Its suppressor functions are often inactivated by deletions and/or mutations in various hematologic malignancies. Since we recently found the rs143002189 polymorphism in the A20 loci in our multiple myeloma samples, we further investigated this polymorphism in different lymphoid neoplasias. For this purpose, we tested 479 cases of the most common B cell malignancies for the presence of the rs143002189 polymorphism. We found a significant higher occurrence of the rs143002189 polymorphism in diffuse large B cell lymphoma (DLBCL) compared to non-neoplastic controls and other types of B cell malignancies. Furthermore, structure analyses of the mutated A20 protein led to the assumption that the new steric interaction within the protein is responsible for a reduced or inactiva...
At the Department of Radiology of the University of Graz a PACS has been installed and is used in... more At the Department of Radiology of the University of Graz a PACS has been installed and is used in daily routine. This PACS is interfaced with a RIS. Our experiences show that one of the most urgent clinical interest in PACS is not the reporting on the diagnostic console, but the image transfer to clinical departments where they are not available or only with time delays. Therefore we provide the decentralised access to the images within the PACS and activate the image transfer to the end users of the diagnostic information.
Die Entwicklung digitaler bildgebender Verfahren ebenso wie die Entwicklung im Computerbereich fu... more Die Entwicklung digitaler bildgebender Verfahren ebenso wie die Entwicklung im Computerbereich fuhren tendenziell zur Moglichkeit eines Krankenhauses, in dem die Entstehung, Ubertragung, Auswertung und Archivierung von Bildern auf digitalem Weg erfolgt.
OBJECTIVE To evaluate the possibilities of describing and discriminating common nevi and malignan... more OBJECTIVE To evaluate the possibilities of describing and discriminating common nevi and malignant melanoma tissue with features based on spectral properties of the Daubechies 4 wavelet transform. STUDY DESIGN Images of common nevi and malignant melanoma were dissected in square elements. The wavelet coefficients were calculated inside the square elements. The diagonal coefficients and related power spectra were used for further analysis. The analysis results served as guide for the selection of features, including standard deviations of wavelet coefficients inside the frequency bands and the energy of the frequency bands. These features describe properties of the frequency bands, representing information on different scales. To test the usefulness of the features for discrimination, a study set of 80 cases was classified by classification and regression trees analysis. The set was divided into a training set and a test set. RESULTS In the case of benign common nevi, the energies of...
aim of this study is to check the application of machine learning algorithms for the computer aid... more aim of this study is to check the application of machine learning algorithms for the computer aided diagnosis of confocal laser scanning microscopy (CLSM) views of skin lesions. The images were dissected in equal square elements where the features, based on spectral properties of the wavelet transform, were calculated out. The images were discriminated according their features by several machine learning algorithms, based on tree classifiers, function classifiers and lazy classi- fiers. The results were evaluated and show that tree classifiers allow the best discrimination be- tween CLSM views of benign common nevi and malignant melanoma.
The frequency of melanoma doubles every 20 years. The early detection of malignant changes augmen... more The frequency of melanoma doubles every 20 years. The early detection of malignant changes augments the therapy success. Confocal laser scanning microscopy (CLSM) enables the noninvasive examination of skin tissue. To diminish the need for training and to improve diagnostic accuracy, computer-aided diagnostic systems are required. Two approaches are presented: a multiresolution analysis and an approach based on deep layer convolutional neural networks. For the diagnosis of the CLSM views, architectural structures such as micro-anatomic structures and cell nests are used as guidelines by the dermatologists. Features based on the wavelet transform enable an exploration of architectural structures at different spatial scales. The subjective diagnostic criteria are objectively reproduced. A tree-based machine-learning algorithm captures the decision structure explicitly and the decision steps are used as diagnostic rules. Deep layer neural networks require no a priori domain knowledge. They are capable of learning their own discriminatory features through the direct analysis of image data. However, deep layer neural networks require large amounts of processing power to learn. Therefore, modern neural network training is performed using graphics cards, which typically possess many hundreds of small, modestly powerful cores that calculate massively in parallel. Readers will learn how to apply multiresolution analysis and modern deep learning neural network techniques to medical image analysis problems.
We present the introduction of a new generation of techniques for early and specific diagnosis of... more We present the introduction of a new generation of techniques for early and specific diagnosis of inflammatory, immune and degenerative eye diseases. We concentrate on the applications of the SELDI-TOF (Surface enhanced laser desorption ionisation - time of flight) mass spectroscopy in combination with molecular modelling and visualization for the analysis of the aqueous humour. For our study we used aqueous humour from 25 patients undergoing cataract operation. SELDI-TOF consists on one part of an apparatus allowing the laser bombarding of molecules on a solid surface and on the other part on a system which measure the time of flight of the molecules. During the measurement the molecules are liberated from the matrix and carried to the detector. Specific proteins can be identified by the characteristic peaks of the spectrogram. Albumin and gamma-globulin were found to a considerable extend in the aqueous humour. An increased amount has been detected in inflammatory humour. The quan...
E I Elektrotechnik Und Informationstechnik, Apr 1, 2006
The purpose of this study was to evaluate the feasibility and usability of digital image fusion o... more The purpose of this study was to evaluate the feasibility and usability of digital image fusion of different phases in spiral CT studies of the head and neck. Patients with squamous cell carcinomas underwent dual-phase spiral CT using a contrast material. The images of the early phase were showing optimal vascular enhancement. The images of the late phase were showing optimal tumor conspicuity. Selected images of the early phase were fused with selected images of the late phase by application of user-centered developed software. The image fusion was done in a semi-automatically way on a desktop computer (PC). The relationship between tumors and adjacent vessels was better visualized on the fused images than on the original source images. As a conclusion it can be emphasized, that digital image fusion of early and late phases enabled combined opacification of vessels and squamous cell carcinomas, which facilitated the topographic assessment of the tumors size and spread.
Microarray analysis makes it possible to determine thousands of gene expression values simultaneo... more Microarray analysis makes it possible to determine thousands of gene expression values simultaneously. Changes in gene expression, as a response to diseases, can be detected allowing a better understanding and differentiation of diseases at a molecular level. By comparing different kinds of tissue, for example healthy tissue and cancer tissue, the microarray analysis indicates induced gene activity, repressed gene activity or when there is no change in the gene activity level. Fundamental patterns in gene expression are extracted by several clustering and machine learning algorithms. Certain kinds of cancer can be divided into subtypes, with different clinical outcomes, by their specific gene expression patterns. This enables a better diagnosis and tailoring of individual patient treatments.
Tumour biology : the journal of the International Society for Oncodevelopmental Biology and Medicine, Jan 31, 2015
Genetic alterations causing constitutive activation of the nuclear factor kappa B (NF-κB) signali... more Genetic alterations causing constitutive activation of the nuclear factor kappa B (NF-κB) signaling pathway has been associated with the development of lymphomas. A20 (TNFAIP3) is a key regulator of NF-κB signaling. Its suppressor functions are often inactivated by deletions and/or mutations in various hematologic malignancies. Since we recently found the rs143002189 polymorphism in the A20 loci in our multiple myeloma samples, we further investigated this polymorphism in different lymphoid neoplasias. For this purpose, we tested 479 cases of the most common B cell malignancies for the presence of the rs143002189 polymorphism. We found a significant higher occurrence of the rs143002189 polymorphism in diffuse large B cell lymphoma (DLBCL) compared to non-neoplastic controls and other types of B cell malignancies. Furthermore, structure analyses of the mutated A20 protein led to the assumption that the new steric interaction within the protein is responsible for a reduced or inactiva...
Uploads
Papers by Marco Wiltgen