On the role of deep learning model complexity in adversarial robustness for medical images.

BACKGROUND: Deep learning (DL) models are highly vulnerable to adversarial attacks for medical image classification. An adversary could modify the input data in imperceptible ways such that a model could be tricked to predict, say, an image that actually exhibits malignant tumor to a prediction that it is benign. However, adversarial robustness of DL models for medical images is not adequately studied. DL in medicine is inundated with models of various complexity-particularly, very large models. In this work, we investigate the role of model complexity in adversarial settings. RESULTS: Consider a set of DL models that exhibit similar performances for a given task. These models are trained in the usual manner but are not trained to defend against adversarial attacks. We demonstrate that, among those models, simpler models of reduced complexity show a greater level of robustness against adversarial attacks than larger models that often tend to be used in medical applications. On the other hand, we also show that once those models undergo adversarial training, the adversarial trained medical image DL models exhibit a greater degree of robustness than the standard trained models for all model complexities. CONCLUSION: The above result has a significant practical relevance. When medical practitioners lack the expertise or resources to defend against adversarial attacks, we recommend that they select the smallest of the models that exhibit adequate performance. Such a model would be naturally more robust to adversarial attacks than the larger models.

shinyDeepDR: A user-friendly R Shiny app for predicting anti-cancer drug response using deep learning.

Advancing precision oncology requires accurate prediction of treatment response and accessible prediction models. To this end, we present shinyDeepDR, a user-friendly implementation of our innovative deep learning model, DeepDR, for predicting anti-cancer drug sensitivity. The web tool makes DeepDR more accessible to researchers without extensive programming experience. Using shinyDeepDR, users can upload mutation and/or gene expression data from a cancer sample (cell line or tumor) and perform two main functions: "Find Drug," which predicts the sample's response to 265 approved and investigational anti-cancer compounds, and "Find Sample," which searches for cell lines in the Cancer Cell Line Encyclopedia (CCLE) and tumors in The Cancer Genome Atlas (TCGA) with genomics profiles similar to those of the query sample to study potential effective treatments. shinyDeepDR provides an interactive interface to interpret prediction results and to investigate individual compounds. In conclusion, shinyDeepDR is an intuitive and free-to-use web tool for in silico anti-cancer drug screening.

DepLink: an R Shiny app to systematically link genetic and pharmacologic dependencies of cancer.

Motivation: Large-scale genetic and pharmacologic dependency maps are generated to reveal genetic vulnerabilities and drug sensitivities of cancer. However, user-friendly software is needed to systematically link such maps. Results: Here, we present DepLink, a web server to identify genetic and pharmacologic perturbations that induce similar effects on cell viability or molecular changes. DepLink integrates heterogeneous datasets of genome-wide CRISPR loss-of-function screens, high-throughput pharmacologic screens and gene expression signatures of perturbations. The datasets are systematically connected by four complementary modules tailored for different query scenarios. It allows users to search for potential inhibitors that target a gene (Module 1) or multiple genes (Module 2), mechanisms of action of a known drug (Module 3) and drugs with similar biochemical features to an investigational compound (Module 4). We performed a validation analysis to confirm the capability of our tool to link the effects of drug treatments to knockouts of the drug's annotated target genes. By querying with a demonstrating example of CDK6, the tool identified well-studied inhibitor drugs, novel synergistic gene and drug partners and insights into an investigational drug. In summary, DepLink enables easy navigation, visualization and linkage of rapidly evolving cancer dependency maps. Availability and implementation: The DepLink web server, demonstrating examples and detailed user manual are available at https://shiny.crc.pitt.edu/deplink/. Supplementary information: Supplementary data are available at Bioinformatics Advances online.

Prediction of Human Performance Using Electroencephalography under Different Indoor Room Temperatures.

Varying indoor environmental conditions is known to affect office worker’s performance; wherein past research studies have reported the effects of unfavorable indoor temperature and air quality causing sick building syndrome (SBS) among office workers. Thus, investigating factors that can predict performance in changing indoor environments have become a highly important research topic bearing significant impact in our society. While past research studies have attempted to determine predictors for performance, they do not provide satisfactory prediction ability. Therefore, in this preliminary study, we attempt to predict performance during office-work tasks triggered by different indoor room temperatures (22.2 °C and 30 °C) from human brain signals recorded using electroencephalography (EEG). Seven participants were recruited, from whom EEG, skin temperature, heart rate and thermal survey questionnaires were collected. Regression analyses were carried out to investigate the effectiveness of using EEG power spectral densities (PSD) as predictors of performance. Our results indicate EEG PSDs as predictors provide the highest R² (> 0.70), that is 17 times higher than using other physiological signals as predictors and is more robust. Finally, the paper provides insight on the selected predictors based on brain activity patterns for low- and high-performance levels under different indoor-temperatures.

Prediction of temperature induced office worker's performance during typing task using EEG.

Understanding how indoor environment affects office worker's performance and developing methods to predict human performance in changing indoor environment have become highly important research topic bearing significant economic and sociological impact. While past research groups have attempted to find predictors for performance they do not provide satisfactory predictions. We conduct in this paper a study to predict human performance by developing a regression model using neurophysiological signals collected from electroencephalogram (EEG), during simulated office-work tasks under different indoor room temperatures (22°C and 30°C). We found that using brain power spectral densities (PSD) from EEG as predictors provides the higher R2 than predictors using skin temperature or heart rate by approximately over 3 folds. Finally, we showed that the predictor using EEG is more robust than regression models using skin temperature and heart rate. Our work shows the potential of using brain signals to accurately predict human office work performance.

Detection of control or idle state with a likelihood ratio test in asynchronous SSVEP-based brain-computer interface systems.

We consider the detection of the control or idle state in an asynchronous Steady-state visually evoked potential (SSVEP)-based brain computer interface system. We propose a likelihood ratio test using Canonical Correlation Analysis (CCA) scores calculated from the EEG measurements. The test exploits the state-specific distributions of CCA scores. The algorithm was tested on offline measurements from 42 participants and the results should a significant improvement in detection error rate over the support vector machine classifier. The proposed test is also shown to be robust against training sample size.