Towards the Use of Saliency Maps for Explaining Low-Quality Electrocardiograms to End Users

@article{Lucic2022TowardsTU,
  title={Towards the Use of Saliency Maps for Explaining Low-Quality Electrocardiograms to End Users},
  author={Ana Lucic and Sheeraz Ahmad and Amanda Furtado Brinhosa and Qingzi Vera Liao and Himani Agrawal and Umang Bhatt and Krishnaram Kenthapadi and Alice Xiang and M. de Rijke and Nicholas Roberto Drabowski},
  journal={ArXiv},
  year={2022},
  volume={abs/2207.02726}
}
When using medical images for diagnosis, either by clinicians or artificial intelligence (AI) systems, it is important that the images are of high quality. When an image is of low quality, the medical exam that produced the image often needs to be redone. In telemedicine, a common problem is that the quality issue is only flagged once the patient has left the clinic, meaning they must return in order to have the exam redone. This can be especially difficult for people living in remote regions, who… 
[PDF] Semantic Reader
1 Citation

Figures and Tables from this paper

One Citation

Beyond-Accuracy Goals, Again

    M. de Rijke
    Computer Science
    Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining
  • 2023
Improving the performance of information retrieval systems tends to be narrowly scoped. Often, better prediction performance is considered the only metric of improvement. As a result, work on…

48 References

Human-Centered Tools for Coping with Imperfect Algorithms During Medical Decision-Making

The needs of pathologists when searching for similar images retrieved using a deep learning algorithm are identified, and tools that empower users to cope with the search algorithm on-the-fly are developed, communicating what types of similarity are most important at different moments in time.

One Map Does Not Fit All: Evaluating Saliency Map Explanation on Multi-Modal Medical Images

The MSFI (Modality-Specific Feature Importance) metric is proposed to examine whether saliency maps can highlight modality-specific important features and guide the choices of saliency map methods and provide insights to propose new ones targeting clinical applications.

Improving Diagnostic Viewing of Medical Images using Enhancement Algorithms

This study proposed Contrast Limited Adaptive Histogram Equalization (CLAHE) which is one of the techniques in a computer image processing domain which was used to amend contrast in images.

"Hello AI": Uncovering the Onboarding Needs of Medical Practitioners for Human-AI Collaborative Decision-Making

This work investigates the key types of information medical experts desire when they are first introduced to a diagnostic AI assistant, providing a richer understanding of what experts find important in their introduction to AI assistants before integrating them into routine practice.

CheXplain: Enabling Physicians to Explore and Understand Data-Driven, AI-Enabled Medical Imaging Analysis

CheXplain is a system that enables physicians to explore and understand AI-enabled chest X-ray analysis and discusses recommendations for future work to design and implement explainable medical AI systems that encompass four recurring themes: motivation, constraint, explanation, and justification.

Using a Deep Learning Algorithm and Integrated Gradients Explanation to Assist Grading for Diabetic Retinopathy.

A survey on deep learning in medical image analysis

An Evaluation of the Doctor-Interpretability of Generalized Additive Models with Interactions

Doctors can correctly interpret risk functions of generalized additive models with interactions and also feel confident to do so, but the evaluation also identified several interpretability issues and it showed that interpretability of generalized additive models depends on the complexity of risk functions.

Co-Design and Evaluation of an Intelligent Decision Support System for Stroke Rehabilitation Assessment

The importance of human centered design and development of a machine learning-based decision support system that presents contextually relevant information and salient explanations on its prediction for better adoption in practice is discussed.

Clinical Decision Support: a 25 Year Retrospective and a 25 Year Vision

CDS has evolved dramatically over the past 25 years and will likely evolve just as dramatically or more so over the next 25 years.