Interpretable surrogate models to approximate the predictions of convolutional neural networks in glaucoma diagnosis

• Published in: Machine learning: science and technology Vol. 4; no. 4; pp. 45024 - 45043
• Main Authors: Sigut, Jose, Fumero, Francisco, Arnay, Rafael, Estévez, José, Díaz-Alemán, Tinguaro
• Format: Journal Article
• Language: English
• Published: Bristol IOP Publishing 01.12.2023
• Subjects: Artificial neural networks; convolutional neuronal networks; Decision trees; Diagnosis; Distillation; Glaucoma; glaucoma diagnosis; interpretable surrogate models; Machine learning; Medical imaging; Neural networks; Salience

Abstract Deep learning systems, especially in critical fields like medicine, suffer from a significant drawback, their black box nature, which lacks mechanisms for explaining or interpreting their decisions. In this regard, our research aims to evaluate the use of surrogate models for interpreting c...