[Magnetic resonance imaging of the lungs in cystic fibrosis]. / Magnetresonanztomographie der Lunge bei Mukoviszidose.

CLINICAL ISSUE: Disease severity and mortality in patients with cystic fibrosis (CF) is mainly determined by (progressive) pulmonary lung disease. Early diagnosis and therapy are important and of prognostic value to conserve lung function. STANDARD RADIOLOGICAL METHODS: Primary imaging techniques for lung imaging are x­ray and computed tomography (CT) to monitor disease severity and regional distribution. METHODICAL INNOVATIONS: Radiation-free imaging techniques such as magnetic resonance imaging (MRI) have gained interest over the last decade in order to prevent radiation damage. PERFORMANCE: The main findings of CF lung disease are airway wall thickening, bronchiectasis, and mucus plugging, which are found in up to 60% of preschool age children. Pleural abnormalities and consolidations are often associated with pulmonary exacerbation. Young CF patients often show a mosaic pattern as functional changes and also perfusion defects can be seen from birth in 50% of CF patients by contrast-enhanced perfusion imaging, and in up to 90% of adult patients, with varying degrees of severity. Dilated bronchial arteries indicate an increased risk for hemoptysis. ACHIEVEMENTS: Proton MRI is the sole imaging technique that can show structural and functional lung changes in one examination. Structured assessment using a scoring system helps to systematically grade the extent and severity of all CF-associated changes. CONCLUSIONS: Lung MRI for cystic fibrosis has been recently established as a clinical standard examination and is routinely performed at experienced centers. More recently, it has also been used as an endpoint within the framework of clinical studies.

Application of model-predictive control based on artificial neural networks to optimize the fed-batch process for riboflavin production.

The fed-batch process for commercial production of riboflavin (vitamin B2) was optimized on-line using model-predictive control based on artificial neural networks (ANNs). The information required for process models was extracted from both historical data and heuristic rules. After each cultivation the process model was readapted off-line to include the most recent process data. The control signal (feed rate), however, was optimized on-line at each sampling interval. An optimizer simulated variations in the control signal and assessed the forecasted model outputs according to an objective function. The optimum feed profile for increasing the product yield (YB2/S) and the amount of riboflavin at the time of harvesting was adjusted continuously and applied to the process. In contrast to the control by set-point profiles, the novel ANN-control is able to react on-line to variations in the process and also to incorporate the new process information continuously. As a result, both the total amount of riboflavin produced and the product yield increased systematically by more than 10% and the reproducibility of seven subsequently optimized batches was enhanced.

[Contributions of the epidemiological cancer registries to the evaluation of mammography screening in Germany]. / Beiträge bevölkerungsbezogener Krebsregister zur Evaluation des bundesweiten Mammographie-Screenings. Erste Ergebnisse zu Brustkrebsinzidenz und T-Stadienverteilung von Teilnehmerinnen des Mammographie-Screenings Weser-Ems (MSWE) im bevölkerungsbezogenen Vergleich.

INTRODUCTION: Before the country-wide introduction of mammography screening, testing of the organised screening took place in Weser-Ems, Bremen and Wiesbaden. Important quality assurance parameters (carcinomas detected during checkup intervals, tumour stage distribution, breast cancer incidence rate, breast cancer mortality rate) are to be evaluated via epidemiological cancer registries. For the model region Weser-Ems (MSWE) the record linkage with the epidemiological cancer registry Lower Saxony (EKN) was successfully accomplished. The technical realisation and first comparison analyses for the development of breast cancer incidence and of tumour size are reported. MATERIAL AND METHODS: The target population of the MSWE was 22,600 women aged 50-69 years. They were invited since May 2002 to mammography screening with a screening interval of two years. The record linkage of 12,913 women who participated until February 2004 in the MSWE, was realised by the use of the control number system of the epidemiological cancer registries. The observation time was between 6 and 25 month (median: 15 month). Reference population for comparison analyses were all women between 50 and 69 years of the remaining governmental district Weser-Ems (255,000 women). RESULTS: In the first record linkage 96 screening-cases (ICD-10 C50 + D05) could be identified. Additionally six interval cancers were determined (time between screening and diagnosis in months: median 5.5; mean 7.7). The breast cancer incidence increased in the MSWE area and in the control-area, the rise in the MSWE area being higher. The increase was especially observed with the small tumours. Women with breast cancer diagnosed by screening: 19.8% in-situ-cancer and 18.8% very small tumours < = 10 mm. In the control area Weser-Ems this rate with 5.6% in-situ-cancer and 14.5% very small tumours, was relatively high, indicating the spread of opportunistic mammographies in absence of organised screening. CONCLUSION: First effects of mammography screening can be evaluated early by comparison between screening data and the data of population-based cancer registries. Using the control number system of the epidemiological cancer registries and comparison by pseudonyms the evaluation of quality assurance parameters of the MSWE can be realised in compliance with the data security law. The feedback of cancers, detected during checkup intervals is not covered by the cancer registry law. For the implementation of the guidelines for early recognition cancer legal adjustments will be necessary. This concept can be easily adapted to other screening programme.

Diagnostic and neural analysis of skin cancer (DANAOS). A multicentre study for collection and computer-aided analysis of data from pigmented skin lesions using digital dermoscopy.

BACKGROUND: Early detection of melanomas by means of diverse screening campaigns is an important step towards a reduction in mortality. Computer-aided analysis of digital images obtained by dermoscopy has been reported to be an accurate, practical and time-saving tool for the evaluation of pigmented skin lesions (PSLs). A prototype for the computer-aided diagnosis of PSLs using artificial neural networks (NNs) has recently been developed: diagnostic and neural analysis of skin cancer (DANAOS). OBJECTIVES: To demonstrate the accuracy of PSL diagnosis by the DANAOS expert system, a multicentre study on a diverse multinational population was conducted. METHODS: A calibrated camera system was developed and used to collect images of PSLs in a multicentre study in 13 dermatology centres in nine European countries. The dataset was used to train an NN expert system for the computer-aided diagnosis of melanoma. We analysed different aspects of the data collection and its influence on the performance of the expert system. The NN expert system was trained with a dataset of 2218 dermoscopic images of PSLs. RESULTS: The resulting expert system showed a performance similar to that of dermatologists as published in the literature. The performance depended on the size and quality of the database and its selection. CONCLUSIONS: The need for a large database, the usefulness of multicentre data collection, as well as the benefit of a representative collection of cases from clinical practice, were demonstrated in this trial. Images that were difficult to classify using the NN expert system were not identical to those found difficult to classify by clinicians. We suggest therefore that the combination of clinician and computer may potentially increase the accuracy of PSL diagnosis. This may result in improved detection of melanoma and a reduction in unnecessary excisions.