Improving explainable AI with patch perturbation-based evaluation pipeline: a COVID-19 X-ray image analysis case study.

Recent advances in artificial intelligence (AI) have sparked interest in developing explainable AI (XAI) methods for clinical decision support systems, especially in translational research. Although using XAI methods may enhance trust in black-box models, evaluating their effectiveness has been challenging, primarily due to the absence of human (expert) intervention, additional annotations, and automated strategies. In order to conduct a thorough assessment, we propose a patch perturbation-based approach to automatically evaluate the quality of explanations in medical imaging analysis. To eliminate the need for human efforts in conventional evaluation methods, our approach executes poisoning attacks during model retraining by generating both static and dynamic triggers. We then propose a comprehensive set of evaluation metrics during the model inference stage to facilitate the evaluation from multiple perspectives, covering a wide range of correctness, completeness, consistency, and complexity. In addition, we include an extensive case study to showcase the proposed evaluation strategy by applying widely-used XAI methods on COVID-19 X-ray imaging classification tasks, as well as a thorough review of existing XAI methods in medical imaging analysis with evaluation availability. The proposed patch perturbation-based workflow offers model developers an automated and generalizable evaluation strategy to identify potential pitfalls and optimize their proposed explainable solutions, while also aiding end-users in comparing and selecting appropriate XAI methods that meet specific clinical needs in real-world clinical research and practice.

A Study and Analysis of the Relationship between Visual-Auditory Logos and Consumer Behavior.

Given enterprises' participation in market competition and the development of sensory marketing, in addition to the traditional visual identity, some enterprises gradually begin to pay attention to auditory and then introduce sound design when designing logos. Audio-visual stimulation and media innovation are committed to creating positive attitudes among consumers. This study constructs a model of visual and auditory interactive relationships with consumer behavior using the SOR model. It tests the conceptual model and checks the hypotheses proposed in the study. This study summarizes and contributes to the visual and auditory interactive relationship between information integration, information synergy, mutual competition, and matching degree. It further proposes the influence of purchase intention and consumer support on consumer behavior of perceived brand perception, credibility, and quality perception. The results and highlights ensure brand identities reflect a significant positive result through consumer behavior. In this paper, we collected questionnaires from a random sample of 1407 respondents. We used regression analysis to test the association between visual and auditory interactive relationships as well as consumer behavior. We further verified the mediating role of consumer perception variables. Adding audiovisual logo design to the marketing process can be an effective way for companies and brands to attract customers and increase their support and purchase intentions.