Explainable AI (XAI) In Biomedical Signal and Image Processing: Promises and Challenges

Yang, Guang; Rao, Arvind; Fernández-Maloigne, Christine; Calhoun, Vince D.; Menegaz, Gloria

doi:10.1109/icip46576.2022.9897629

Cited by 7 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Be more specific, the XAI applied to biomedical signal and image processing has been further discussed in ref. [43], which also provides inspiration for a more generalized direction of our research afterwards.…”

Section: Discussionmentioning

confidence: 97%

Deep MR parametric imaging with the learned L + S model and attention mechanism

Cheng

Zhu

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

Magnetic resonance (MR) parametric imaging can help the assessment of some certain diseases with its various contrast mechanisms. However, the main issue of MR parametric imaging is the long acquisition time, introducing many problems such as uncomfortable experiences for patients and motion artefacts. With the deep learning methods developing, some unrolling ones have been introduced to MR imaging as solutions. The purpose of this study is to improve both the quality and the speed of parametric imaging. The proposed method, named as LSA-Net, introduced a learned low rank plus sparsity model with attention mechanism to reconstruct highly under-sampled data for MR parametric imaging. The L+S model was used to represent the shared image structure among the parameterweighted images as low-rank part and the difference among images and the ideal model as sparse part. Besides, the attention block was introduced to effectively improved quality for the region of interest, which was most concerned in clinical applications. Then the parameter map was generated from the reconstructed parameter-weighted images by its exponential model. The LSA-Net was evaluated on the in-vivo 3D T 1𝜌 mapping, showing better performance on both image quality and time consumed than the comparing methods including LLR, SCOPE, L+S, and L+S-Net. INTRODUCTIONMR parametric imaging is a promising technique to detect subtle microscopic damage with various contrast mechanisms, enabling early diagnosis of diseases [1, 2]. Take T 1𝜌 as an exam-This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Section: Discussionmentioning

confidence: 97%

Deep MR parametric imaging with the learned L + S model and attention mechanism

Cheng

Zhu

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…When broadening our view to the biomedical or healthcare domain in general, there are some reviews (e.g. [ 16 , 21 , 27 ]) that capture current use cases of XAI for biomedical and healthcare data, as well as the ethical and legal debate surrounding the topic. However, research that synthesizes the scattered literature on XAI for omics data is scarce.…”

Section: Objectivesmentioning

confidence: 99%

Explainable artificial intelligence for omics data: a systematic mapping study

Toussaint,

Leiser,

Thiebes

et al. 2023

Briefings in Bioinformatics

View full text Add to dashboard Cite

Researchers increasingly turn to explainable artificial intelligence (XAI) to analyze omics data and gain insights into the underlying biological processes. Yet, given the interdisciplinary nature of the field, many findings have only been shared in their respective research community. An overview of XAI for omics data is needed to highlight promising approaches and help detect common issues. Toward this end, we conducted a systematic mapping study. To identify relevant literature, we queried Scopus, PubMed, Web of Science, BioRxiv, MedRxiv and arXiv. Based on keywording, we developed a coding scheme with 10 facets regarding the studies’ AI methods, explainability methods and omics data. Our mapping study resulted in 405 included papers published between 2010 and 2023. The inspected papers analyze DNA-based (mostly genomic), transcriptomic, proteomic or metabolomic data by means of neural networks, tree-based methods, statistical methods and further AI methods. The preferred post-hoc explainability methods are feature relevance (n = 166) and visual explanation (n = 52), while papers using interpretable approaches often resort to the use of transparent models (n = 83) or architecture modifications (n = 72). With many research gaps still apparent for XAI for omics data, we deduced eight research directions and discuss their potential for the field. We also provide exemplary research questions for each direction. Many problems with the adoption of XAI for omics data in clinical practice are yet to be resolved. This systematic mapping study outlines extant research on the topic and provides research directions for researchers and practitioners.

show abstract

“…This is a strong limitation when the interpretability of the model is a requirement, for example when experts are interested in exploring the feature space for determining feature importance [14]. To alleviate this shortcoming, much research on Explainable Artificial Intelligence (XAI) [15,16] has been conducted in recent years, aiming to add the ability to get human-understandable explanations of the model's reasoning; that is, making black-box models more transparent [17,18]. Amongst the most popular explainable ML approaches, we find Local Interpretable Model-agnostic Explanations (LIME) [19] and SHapley Additive exPlanations (SHAP) [20].…”

Section: Introductionmentioning

confidence: 99%

Understanding predictions of drug effectiveness using explainable Machine Learning models

König,

Vellido

2024

Preprint

View full text Add to dashboard Cite

Purpose: The analysis of absorption, distribution, metabolism, and excretion (ADME) molecular properties is of relevance to drug design, as they directly inﬂuence the drug’s eﬀectiveness at its target location. This study concerns their prediction, using explainable Machine Learning (ML) models. The aim of the study is to ﬁnd which molecular features are relevant to the prediction of the diﬀerent ADME properties and measure their impact on the predictive model. Methods: The relative relevance of individual features for ADME activity is gauged by estimating feature importance in ML models’ predictions. Feature importance is calculated using feature permutation and the individual impact of features is measured by SHAP additive explanations. Results: The study reveals the relevance of speciﬁc molecular descriptors for each ADME property and quantiﬁes their impact on the ADME property prediction. Conclusion: The reported research illustrates how explainable ML models can provide detailed insights about the individual contributions of molecular features to the ﬁnal prediction of an ADME property, as an eﬀort to support experts in the process of drug candidate selection through a better understanding of the impact of molecular features.

show abstract

Explainable AI (XAI) In Biomedical Signal and Image Processing: Promises and Challenges

Cited by 7 publications

References 23 publications

Deep MR parametric imaging with the learned L + S model and attention mechanism

Deep MR parametric imaging with the learned L + S model and attention mechanism

Explainable artificial intelligence for omics data: a systematic mapping study

Understanding predictions of drug effectiveness using explainable Machine Learning models

Contact Info

Product

Resources

About