RESUMO
Deep learning approaches for clinical predictions based on magnetic resonance imaging data have shown great promise as a translational technology for diagnosis and prognosis in neurological disorders, but its clinical impact has been limited. This is partially attributed to the opaqueness of deep learning models, causing insufficient understanding of what underlies their decisions. To overcome this, we trained convolutional neural networks on structural brain scans to differentiate dementia patients from healthy controls, and applied layerwise relevance propagation to procure individual-level explanations of the model predictions. Through extensive validations we demonstrate that deviations recognized by the model corroborate existing knowledge of structural brain aberrations in dementia. By employing the explainable dementia classifier in a longitudinal dataset of patients with mild cognitive impairment, we show that the spatially rich explanations complement the model prediction when forecasting transition to dementia and help characterize the biological manifestation of disease in the individual brain. Overall, our work exemplifies the clinical potential of explainable artificial intelligence in precision medicine.
RESUMO
Optogenetic systems use light to precisely control and investigate cellular processes. Until recently, there had been few instruments available for applying controlled light doses to cultures of cells. The optoPlate, a programmable array of 192 LEDs, was developed to meet this need. However, LED performance varies, and without calibration there are substantial brightness differences between LEDs on an optoPlate. Here we present a method for calibrating an optoPlate that uses a programmable microscope stage and optical power meter to automatically measure all 192 LEDs of an optoPlate. The resulting brightness measurements are used to calculate calibration values that tune the electrical current supplied to each optoPlate LED to reduce brightness variation in optogenetic experiments.