Commentary on explainable artificial intelligence methods: SHAP and LIME

no code implementations • 3 May 2023 • Ahmed Salih, Zahra Raisi-Estabragh, Ilaria Boscolo Galazzo, Petia Radeva, Steffen E. Petersen, Gloria Menegaz, Karim Lekadir

eXplainable artificial intelligence (XAI) methods have emerged to convert the black box of machine learning models into a more digestible form.

Explainable artificial intelligence Explainable Artificial Intelligence (XAI)

Characterizing the contribution of dependent features in XAI methods

no code implementations • 4 Apr 2023 • Ahmed Salih, Ilaria Boscolo Galazzo, Zahra Raisi-Estabragh, Steffen E. Petersen, Gloria Menegaz, Petia Radeva

Explainable Artificial Intelligence (XAI) provides tools to help understanding how the machine learning models work and reach a specific outcome.

Explainable artificial intelligence Explainable Artificial Intelligence (XAI)

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

no code implementations • 9 Jul 2022 • Guang Yang, Arvind Rao, Christine Fernandez-Maloigne, Vince Calhoun, Gloria Menegaz

This paper aims at providing an overview on XAI in biomedical data processing and points to an upcoming Special Issue on Deep Learning in Biomedical Image and Signal Processing of the IEEE Signal Processing Magazine that is going to appear in March 2022.

Explainable Artificial Intelligence (XAI)

NODDI-SH: a computational efficient NODDI extension for fODF estimation in diffusion MRI

no code implementations • 28 Aug 2017 • Mauro Zucchelli, Maxime Descoteaux, Gloria Menegaz

Exploiting the ability of Spherical Harmonics (SH) to model spherical functions, we propose a new reconstruction model for DMRI data which is able to estimate both the fiber Orientation Distribution Function (fODF) and the relative volume fractions of the neurites in each voxel, which is robust to multiple fiber crossings.

Benchmarking