Background: Despite the high prevalence of seizure, epilepsy and abnormal electroencephalograms in individuals with autism spectrum disorder (ASD), there is little information regarding the relative effectiveness of treatments for seizures in the ASD population. In order to determine the effectiveness of traditional and non-traditional treatments for improving seizures and influencing other clinical factor relevant to ASD, we developed a comprehensive on-line seizure survey.
Methods: Announcements (by email and websites) by ASD support groups asked parents of children with ASD to complete the on-line surveys. Survey responders choose one of two surveys to complete: a survey about treatments for individuals with ASD and clinical or subclinical seizures or abnormal electroencephalograms, or a control survey for individuals with ASD without clinical or subclinical seizures or abnormal electroencephalograms. Survey responders rated the perceived effect of traditional antiepileptic drug (AED), non-AED seizure treatments and non-traditional ASD treatments on seizures and other clinical factors (sleep, communication, behavior, attention and mood), and listed up to three treatment side effects.
Results: Responses were obtained concerning 733 children with seizures and 290 controls. In general, AEDs were perceived to improve seizures but worsened other clinical factors for children with clinical seizure. Valproic acid, lamotrigine, levetiracetam and ethosuximide were perceived to improve seizures the most and worsen other clinical factors the least out of all AEDs in children with clinical seizures. Traditional non-AED seizure and non-traditional treatments, as a group, were perceived to improve other clinical factors and seizures but the perceived improvement in seizures was significantly less than that reported for AEDs. Certain traditional non-AED treatments, particularly the ketogenic diet, were perceived to improve both seizures and other clinical factors. For ASD individuals with reported subclinical seizures, other clinical factors were reported to be worsened by AEDs and improved by non-AED traditional seizure and non-traditional treatments. The rate of side effects was reportedly higher for AEDs compared to traditional non-AED treatments.
Conclusion: Although this survey-based method only provides information regarding parental perceptions of effectiveness, this information may be helpful for selecting seizure treatments in individuals with ASD.
Drosophila melanogaster has been established as a model organism for investigating the developmental gene interactions. The spatio-temporal gene expression patterns of Drosophila melanogaster can be visualized by in situ hybridization and documented as digital images. Automated and efficient tools for analyzing these expression images will provide biological insights into the gene functions, interactions, and networks. To facilitate pattern recognition and comparison, many web-based resources have been created to conduct comparative analysis based on the body part keywords and the associated images. With the fast accumulation of images from high-throughput techniques, manual inspection of images will impose a serious impediment on the pace of biological discovery. It is thus imperative to design an automated system for efficient image annotation and comparison.
Results
We present a computational framework to perform anatomical keywords annotation for Drosophila gene expression images. The spatial sparse coding approach is used to represent local patches of images in comparison with the well-known bag-of-words (BoW) method. Three pooling functions including max pooling, average pooling and Sqrt (square root of mean squared statistics) pooling are employed to transform the sparse codes to image features. Based on the constructed features, we develop both an image-level scheme and a group-level scheme to tackle the key challenges in annotating Drosophila gene expression pattern images automatically. To deal with the imbalanced data distribution inherent in image annotation tasks, the undersampling method is applied together with majority vote. Results on Drosophila embryonic expression pattern images verify the efficacy of our approach.
Conclusion
In our experiment, the three pooling functions perform comparably well in feature dimension reduction. The undersampling with majority vote is shown to be effective in tackling the problem of imbalanced data. Moreover, combining sparse coding and image-level scheme leads to consistent performance improvement in keywords annotation.
Background:
Drosophila gene expression pattern images document the spatiotemporal dynamics of gene expression during embryogenesis. A comparative analysis of these images could provide a fundamentally important way for studying the regulatory networks governing development. To facilitate pattern comparison and searching, groups of images in the Berkeley Drosophila Genome Project (BDGP) high-throughput study were annotated with a variable number of anatomical terms manually using a controlled vocabulary. Considering that the number of available images is rapidly increasing, it is imperative to design computational methods to automate this task.
Results:
We present a computational method to annotate gene expression pattern images automatically. The proposed method uses the bag-of-words scheme to utilize the existing information on pattern annotation and annotates images using a model that exploits correlations among terms. The proposed method can annotate images individually or in groups (e.g., according to the developmental stage). In addition, the proposed method can integrate information from different two-dimensional views of embryos. Results on embryonic patterns from BDGP data demonstrate that our method significantly outperforms other methods.
Conclusion:
The proposed bag-of-words scheme is effective in representing a set of annotations assigned to a group of images, and the model employed to annotate images successfully captures the correlations among different controlled vocabulary terms. The integration of existing annotation information from multiple embryonic views improves annotation performance.
