An Algorithm for Learning Shape and Appearance Models without Annotations

TL;DR

This paper introduces an iterative, probabilistic framework for learning shape and appearance models from images without manual annotations, enabling privacy-preserving, distributed analysis and effective feature extraction for classification tasks.

Contribution

It presents a novel EM-like algorithm that learns shape and appearance models without annotations, suitable for privacy-sensitive, distributed medical image analysis.

Findings

Successfully aligned face images without manual landmarks

Demonstrated potential for machine learning with limited data

Handled missing data effectively for cross-validation

Abstract

This paper presents a framework for automatically learning shape and appearance models for medical (and certain other) images. It is based on the idea that having a more accurate shape and appearance model leads to more accurate image registration, which in turn leads to a more accurate shape and appearance model. This leads naturally to an iterative scheme, which is based on a probabilistic generative model that is fit using Gauss-Newton updates within an EM-like framework. It was developed with the aim of enabling distributed privacy-preserving analysis of brain image data, such that shared information (shape and appearance basis functions) may be passed across sites, whereas latent variables that encode individual images remain secure within each site. These latent variables are proposed as features for privacy-preserving data mining applications. The approach is demonstrated qualitatively on the KDEF dataset of 2D face images, showing that it can align images that traditionally require shape and appearance models trained using manually annotated data (manually defined landmarks etc.). It is applied to MNIST dataset of handwritten digits to show its potential for machine learning applications, particularly when training data is limited. The model is able to handle ``missing data'', which allows it to be cross-validated according to how well it can predict left-out voxels. The suitability of the derived features for classifying individuals into patient groups was assessed by applying it to a dataset of over 1,900 segmented T1-weighted MR images, which included images from the COBRE and ABIDE datasets.