Meeting Banner
Abstract #2617

Uncertainties and bias in quantification by deep learning in magnetic resonance spectroscopy

Rudy Rizzo1,2, Martyna Dziadosz1,2, Sreenath Pruthviraj Kyathanahally3, and Roland Kreis1,2
1Magnetic Resonance Methodology, Institute of Diagnostic and Interventional Neuroradiology, University of Bern, Bern, Switzerland, 2Translational Imaging Center, sitem-insel, Bern, Switzerland, 3Department Systems Analysis, Integrated Assessment and Modelling, Data Science for Environmental Research group, Dübendorf, Switzerland


Deep Learning has introduced the possibility to speed up quantitation in Magnetic Resonance Spectroscopy. However, questions arise about how to access and relate to prediction uncertainties. Distributions of predictions and Monte-Carlo dropout are here used to investigate data and model related uncertainties, exploiting ground truth knowledge (in-silico set up). It is confirmed that DL is a dataset-biased technique, showing higher uncertainties toward the edges of its training set. Surprisingly, metabolites present in high concentrations suffer from comparable high uncertainties as when present in low concentrations. Evaluating and respecting fitting uncertainties is equally crucial for DL and traditional approaches.

This abstract and the presentation materials are available to members only; a login is required.

Join Here