A minimalistic approach to classifying Alzheimer's disease using simple and extremely small convolutional neural networks.

BACKGROUND: There is a broad interest in deploying deep learning-based classification algorithms to identify individuals with Alzheimer's disease (AD) from healthy controls (HC) based on neuroimaging data, such as T1-weighted Magnetic Resonance Imaging (MRI). The goal of the current study is to investigate whether modern, flexible architectures such as EfficientNet provide any performance boost over more standard architectures. METHODS: MRI data was sourced from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and processed with a minimal preprocessing pipeline. Among the various architectures tested, the minimal 3D convolutional neural network SFCN stood out, composed solely of 3x3x3 convolution, batch normalization, ReLU, and max-pooling. We also examined the influence of scale on performance, testing SFCN versions with trainable parameters ranging from 720 up to 2.9 million. RESULTS: SFCN achieves a test ROC AUC of 96.0% while EfficientNet got an ROC AUC of 94.9 %. SFCN retained high performance down to 720 trainable parameters, achieving an ROC AUC of 91.4%. COMPARISON WITH EXISTING METHODS: The SFCN is compared to DenseNet and EfficientNet as well as the results of other publications in the field. CONCLUSIONS: The results indicate that using the minimal 3D convolutional neural network SFCN with a minimal preprocessing pipeline can achieve competitive performance in AD classification, challenging the necessity of employing more complex architectures with a larger number of parameters. This finding supports the efficiency of simpler deep learning models for neuroimaging-based AD diagnosis, potentially aiding in better understanding and diagnosing Alzheimer's disease.

Constructing personalized characterizations of structural brain aberrations in patients with dementia using explainable artificial intelligence.

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.

Automated calibration of optoPlate LEDs to reduce light dose variation in optogenetic experiments.

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.