ABSTRACT
OBJECTIVE: To assess whether the methodological changes of this new algorithm improves the results of a previously presented strategy. METHODS: We enhance the image and filter out the green channel of the digital color retinography. Multitolerance thresholding was applied to obtain candidate points and make a seed growing region by varying intensities. We took 15 characteristics from each region to train a Fuzzy Artmap neural network using 42 retinal photographs. This network was then applied in the study of 11 good quality retinal photographs included in the diabetic retinopathy early detection screening program, with initial stages of retinopathy, obtained with the Topcon NW200 non-mydriatic retinal camera. RESULTS: Two experienced ophthalmologists detected 52 microaneurysms in 11 images. The algorithm detected 39 microaneurysms and 3,752 more regions, confirming 38 microaneurysm and 135 false positives. The sensitivity is improved compared to the previous algorithm, from 60.53 to 73.08%. False positives have dropped from 41.8 to 12.27 per image. CONCLUSIONS: The new algorithm is better than the previous one, but there is still room for improvement, especially in the initial determination of seeds.
Subject(s)
Algorithms , Aneurysm/diagnosis , Diabetic Angiopathies/diagnosis , Fuzzy Logic , Neural Networks, Computer , Photography/methods , Retinal Artery/pathology , Color , False Positive Reactions , Humans , Image Enhancement/methods , Microcomputers , Predictive Value of Tests , Signal Processing, Computer-AssistedABSTRACT
The present study shows that postnatal "consistent" handling (CH) of rats had long-lasting improving effects on coping with an stressful task (i.e. two-way active avoidance), and that such effects were partially prevented by acute Ro 15-1788 (antagonist of benzodiazepine receptor-BZR; 5 mg/kg) administration. Long-lasting detrimental effects in the same task were also observed in rats which received postnatal "inconsistent" handling (INCH), effects that were slightly increased by acute Ro 15-1788 treatment. Finally, Ro 15-1788 tended to increase avoidance acquisition in non-handled (NH) animals. The observed effects of Ro 15-1788 could be partially attributed to a differential modulation of the process of avoidance acquisition depending on postnatal treatments producing different levels of emotionality.
Subject(s)
Avoidance Learning/physiology , Handling, Psychological , Receptors, GABA-A/drug effects , Adaptation, Psychological/drug effects , Animals , Animals, Newborn/psychology , Avoidance Learning/drug effects , Flumazenil/pharmacology , Male , Rats , Rats, Inbred StrainsABSTRACT
The present study shows that postnatal 'consistent' handling (CH; which consisted of removing the pups from the nest and placing them individually in plastic cages lined with paper towel for a period of 15 min daily between 1 and 22 postnatal days) of rats had long-lasting improving effects on coping with a stressful task (i.e. enhancement on the early acquisition of two-way active avoidance), but such effects were completely prevented when CH treatment was combined with chronic perinatal Ro 15-1788 (7 mg/kg/day, between prenatal day 19 and postnatal day 22) administration (i.e. blockade of benzodiazepine receptor (BZR)). A long-lasting decremental effect was also observed in the same task in rats which received postnatal 'inconsistent' handling (INCH; in which stimulation of pups was changed every day between 1 and 22 postnatal days), without being affected by the concomitant perinatal Ro 15-1788 treatment. These results suggest that intact ontogeny of BZRs is necessary to obtain the enduring positive effects of CH on emotional behavior (i.e. early acquisition of two-way active avoidance).
