IVLGMLFeb 25, 2020

Variational Inference and Bayesian CNNs for Uncertainty Estimation in Multi-Factorial Bone Age Prediction

arXiv:2002.10819v11 citations
AI Analysis

This work addresses the need for uncertainty quantification in age estimation for legal and clinical medicine, where point estimates can be misleading, but it appears incremental as it applies existing Bayesian methods to a specific domain.

The paper tackled the problem of predicting chronological age from MRI data by introducing a multi-factorial method that uses Variational Inference with a Bayesian CNN to estimate predictive uncertainty, distinguishing model uncertainty from data uncertainty interpreted as biological variation.

Additionally to the extensive use in clinical medicine, biological age (BA) in legal medicine is used to assess unknown chronological age (CA) in applications where identification documents are not available. Automatic methods for age estimation proposed in the literature are predicting point estimates, which can be misleading without the quantification of predictive uncertainty. In our multi-factorial age estimation method from MRI data, we used the Variational Inference approach to estimate the uncertainty of a Bayesian CNN model. Distinguishing model uncertainty from data uncertainty, we interpreted data uncertainty as biological variation, i.e. the range of possible CA of subjects having the same BA.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes