Abstract

MINUTTI-MARTINEZ, Carlos; ESCALANTE-RAMIREZ, Boris  and  OLVERES-MONTIEL, Jimena. PumaMedNet-CXR: An Explainable Generative Artificial Intelligence for the Analysis and Classification of Chest X-Ray Images. Comp. y Sist. [online]. 2023, vol.27, n.4, pp.909-920.  Epub May 17, 2024. ISSN 2007-9737.  https://doi.org/10.13053/cys-27-4-4777.

In this paper, we introduce PumaMedNet-CXR, a generative AI designed for medical image classification, with a specific emphasis on Chest X-ray (CXR) images. The model effectively corrects common defects in CXR images, offers improved explainability, enabling a deeper understanding of its decision-making process. By analyzing its latent space, we can identify and mitigate biases, ensuring a more reliable and transparent model. Notably, PumaMedNet-CXR achieves comparable performance to larger pre-trained models through transfer learning, making it a promising tool for medical image analysis. The model’s highly efficient autoencoder-based architecture, along with its explainability and bias mitigation capabilities, contribute to its significant potential in advancing medical image understanding and analysis.

Keywords : Medical image analysis; autoencoder; explainable artificial intelligence; chest X-Ray.