Mahalanobis Distance for Class Averaging of Cryo-EM Images

TL;DR

This paper introduces a Mahalanobis-distance-based affinity measure for cryo-EM image classification, significantly improving class averaging and achieving state-of-the-art results on synthetic datasets.

Contribution

A novel Mahalanobis-distance-like similarity measure for cryo-EM images enhances class averaging accuracy over existing methods.

Findings

Improved classification accuracy on synthetic datasets

Enhanced detection of similar cryo-EM images

State-of-the-art performance in class averaging

Abstract

Single particle reconstruction (SPR) from cryo-electron microscopy (EM) is a technique in which the 3D structure of a molecule needs to be determined from its contrast transfer function (CTF) affected, noisy 2D projection images taken at unknown viewing directions. One of the main challenges in cryo-EM is the typically low signal to noise ratio (SNR) of the acquired images. 2D classification of images, followed by class averaging, improves the SNR of the resulting averages, and is used for selecting particles from micrographs and for inspecting the particle images. We introduce a new affinity measure, akin to the Mahalanobis distance, to compare cryo-EM images belonging to different defocus groups. The new similarity measure is employed to detect similar images, thereby leading to an improved algorithm for class averaging. We evaluate the performance of the proposed class averaging procedure on synthetic datasets, obtaining state of the art classification.