Uncertainty Estimation for Dual View X-ray Mammographic Image Registration Using Deep Ensembles

TL;DR

This paper introduces deep ensemble techniques to estimate uncertainty in dual-view mammographic image registration, helping clinicians better assess lesion correspondence.

Contribution

The novel contribution is the use of deep ensembles with a modified CNN architecture to provide uncertainty estimates for dual-view lesion registration.

Findings

Ensemble-based uncertainty ellipses correlate with registration accuracy in mammographic views.

Uncertainty estimates help reduce false alarms in computer-aided detection by matching CC/MLO lesion detects.

The techniques improve diagnostic capability by aiding multi-view lesion correspondence.

Abstract

Techniques are developed for generating uncertainty estimates for convolutional neural network (CNN)-based methods for registering the locations of lesions between the craniocaudal (CC) and mediolateral oblique (MLO) mammographic X-ray image views. Multi-view lesion correspondence is an important task that clinicians perform for characterizing lesions during routine mammographic exams. Automated registration tools can aid in this task, yet if the tools also provide confidence estimates, they can be of greater value to clinicians, especially in cases involving dense tissue where lesions may be difficult to see. A set of deep ensemble-based techniques, which leverage a negative log-likelihood (NLL)-based cost function, are implemented for estimating uncertainties. The ensemble architectures involve significant modifications to an existing CNN dual-view lesion registration algorithm. Three architectural designs are evaluated, and different ensemble sizes are compared using various performance metrics. The techniques are tested on synthetic X-ray data, real 2D X-ray data, and slices from real 3D X-ray data. The ensembles generate covariance-based uncertainty ellipses that are correlated with registration accuracy, such that the ellipse sizes can give a clinician an indication of confidence in the mapping between the CC and MLO views. The results also show that the ellipse sizes can aid in improving computer-aided detection (CAD) results by matching CC/MLO lesion detects and reducing false alarms from both views, adding to clinical utility. The uncertainty estimation techniques show promise as a means for aiding clinicians in confidently establishing multi-view lesion correspondence, thereby improving diagnostic capability.

The online version contains supplementary material available at 10.1007/s10278-024-01244-1.

Figures