ExplainabilityTransparencyTrustworthinesscs.LG
eXplainable Artificial Intelligence on Medical Images: A Survey
Matteus Vargas Simão da Silva, Rodrigo Reis Arrais, Jhessica Victoria Santos da Silva, Felipe Souza Tânios, Mateus Antonio Chinelatto, Natalia Backhaus Pereira, Renata De Paris, Lucas Cesar Ferreira Domingos, Rodrigo Dória Villaça, Vitor Lopes Fabris, Nayara Rossi Brito da Silva, Ana Claudia Akemi Matsuki de Faria, Jose Victor Nogueira Alves da Silva, Fabiana Cristina Queiroz de Oliveira Marucci, Francisco Alves de Souza Neto, Danilo Xavier Silva, Vitor Yukio Kondo, Claudio Filipi Gonçalves dos Santos
May 12, 2023
arXiv.org
4 citations
2 influential
Key Takeaways
-
Medical AI systems need explanation, not just accuracy: The paper emphasizes that deep learning models used in medical diagnosis require "rigorous assessment" and explanation to all stakeholders involved in patient care, indicating that a model's accuracy alone is insufficient for clinical adoption.
-
XAI addresses the "black box" problem in healthcare: Explainable AI (XAI) techniques help translate opaque machine learning decisions into understandable explanations, which is critical for doctors and patients to trust and validate AI-assisted diagnoses across diseases like cancers and COVID-19.
-
XAI is becoming standard practice in medical AI research: The survey documents that explainability has grown into a "recent field" with numerous studies applying XAI methods to medical imaging, suggesting this is now an expected component of responsible medical AI development rather than an optional feature.
-
Multiple diseases benefit from explainable medical AI: The paper identifies applications across diverse conditions (cancers, COVID-19, and others), indicating that XAI's importance spans different medical domains and isn't limited to a single disease area.
Abstract
Over the last few years, the number of works about deep learning applied to the medical field has increased enormously. The necessity of a rigorous assessment of these models is required to explain these results to all people involved in medical exams. A recent field in the machine learning area is explainable artificial intelligence, also known as XAI, which targets to explain the results of such black box models to permit the desired assessment. This survey analyses several recent studies in the XAI field applied to medical diagnosis research, allowing some explainability of the machine learning results in several different diseases, such as cancers and COVID-19.