Explainable, Domain-Adaptive, and Federated Artificial Intelligence in Medicine

Abstract

Artificial intelligence (AI) continues to transform data analysis in many domains. Progress in each domain is driven by a growing body of annotated data, increased computational resources, and technological innovations. In medicine, the sensitivity of the data, the complexity of the tasks, the potentially high stakes, and a requirement of accountability give rise to a particular set of challenges. In this review, we focus on three key methodological approaches that address some of the particular challenges in AI-driven medical decision making. (1) Explainable AI aims to produce a human-interpretable justification for each output. Such models increase confidence if the results appear plausible and match the clinicians expectations. However, the absence of a plausible explanation does not imply an inaccurate model. Especially in highly non-linear, complex models that are tuned to maximize accuracy, such interpretable representations only reflect a small portion of the justification. (2) Domain adaptation and transfer learning enable AI models to be trained and applied across multiple domains. For example, a classification task based on images acquired on different acquisition hardware. (3) Federated learning enables learning large-scale models without exposing sensitive personal health information. Unlike centralized AI learning, where the centralized learning machine has access to the entire training data, the federated learning process iteratively updates models across multiple sites by exchanging only parameter updates, not personal health data. This narrative review covers the basic concepts, highlights relevant corner-stone and state-of-the-art research in the field, and discusses perspectives.

This paper is accepted in IEEE CAA Journal of Automatica Sinica, Nov. 10 2022

References in corpus (12)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Deep Domain Confusion: Maximizing for Domain Invariance
• Deep Subdomain Adaptation Network for Image Classification
• Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis
• Transfer Learning in Magnetic Resonance Brain Imaging: a Systematic Review
• Levels of explainable artificial intelligence for human-aligned conversational explanations
• Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence
• Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey
• COVID-DA: Deep Domain Adaptation from Typical Pneumonia to COVID-19
• Deep Radiomic Analysis for Predicting Coronavirus Disease 2019 in Computerized Tomography and X-ray Images
• Deep radiomic signature with immune cell markers predicts the survival of glioma patients
• Modeling of Textures to Predict Immune Cell Status and Survival of Brain Tumour Patients

Cited by in corpus (4)

• Generalizable and Explainable Deep Learning for Medical Image Computing: An Overview
• Towards a Transparent and Interpretable AI Model for Medical Image Classifications
• From Privacy to Trust in the Agentic Era: A Taxonomy of Challenges in Trustworthy Federated Learning Through the Lens of Trust Report 2.0
• Federated Explainable Artificial Intelligence: Roles, Architectures, Evaluation, and Open Challenges