Sleep spindle detection using artificial neural networks trained with filtered time-domain EEG: a feasibility study.

An artificial neural network (ANN) based on the Multi-Layer Perceptron (MLP) architecture is used for detecting sleep spindles in band-pass filtered electroencephalograms (EEG), without feature extraction. Following optimum classification schemes, the sensitivity of the network ranges from 79.2% to 87.5%, while the false positive rate ranges from 3.8% to 15.5%. Furthermore, due to the operation of the ANN on time-domain EEG data, there is agreement with visual assessment concerning temporal resolution. Specifically, the total inter-spindle interval duration and the total duration of spindles are calculated with 99% and 92% accuracy, respectively. Therefore, the present method may be suitable for investigations of the dynamics among successive inter-spindle intervals, which could provide information on the role of spindles in the sleep process, and for studies of pharmacological effects on sleep structure, as revealed by the modification of total spindle duration.

Radiotherapy in conjunction with intravenous infusion of 180 mg of disodium pamidronate in management of osteolytic metastases from breast cancer: clinical evaluation, biochemical markers, quality of life, and monitoring of recalcification using assessments of gray-level histogram in plain radiographs.

PURPOSE: To evaluate the clinical improvement and radiographically monitor the effect of local radiotherapy in conjunction with disodium pamidronate (DP) on metastatic osteolytic disease. METHODS AND MATERIALS: Thirty-three patients with osteolytic metastasis from advanced breast cancer received radiotherapy with a 6-MV linear accelerator up to a dose of 30 Gy (3 Gy/fraction, 5 d/wk) combined with 24 monthly sessions of a 180-mg DP infusion. Conventional X-rays were obtained during the first six sessions of DP treatment, retaining the same settings for each exposure. The analysis of the image attributes was based on measuring the first-order statistics of the mean value and energy of gray-level histograms in the osteolytic region. RESULTS: The 6-month measurements compared with baseline showed statistically significant differences (p < 0.01, Wilcoxon test) in energy of gray-level histogram (-10.8%), mean value of gray-level histogram (+9.5%), pain score (-5.8 points), Eastern Cooperative Oncology Group status (-2.4 points), urine hydroxyproline/creatinine ratio (-41.7%), urine calcium/creatinine ratio (-58.8%), and bone alkaline phosphatase (-42.4%). Quality of life as determined by the European Organization for Research and Treatment of Cancer Core Quality of Life Questionnaire (version 3) also improved. During follow-up, 88% of patients had complete and 12% partial responses (International Union Against Cancer radiologic criteria). On multivariate analysis, greater changes in the mean value of the gray-level histogram and negative nodal status were predictors for a reduction in the number of skeletal complications after therapy. Flu-like syndrome occurred in 13 patients (39%) and was well managed with mild antipyretics. CONCLUSION: Image-processing in plain radiographs offers an objective way to assess recalcification. The image-processing indexes, along with the measurements of performance status, quality of life, and biochemical markers, improved significantly. Local radiotherapy combined with long-term high-dose DP up to 180 mg is tolerable and has a high therapeutic response.