Statistical analysis of multivariate planar curves and applications to X-ray classification

TL;DR

This paper introduces a novel statistical framework for analyzing multivariate planar curves, specifically applied to classify X-ray images by shape, improving diagnosis accuracy in medical imaging.

Contribution

It extends shape analysis to multivariate curves, addressing alignment issues and enabling shape-based classification in medical image analysis.

Findings

Effective detection of cardiomegaly in segmented X-rays

Robustness demonstrated on synthetic data

Enhanced shape analysis for medical diagnosis

Abstract

Recent developments in computer vision have enabled the availability of segmented images across various domains, such as medicine, where segmented radiography images play an important role in diagnosis-making. As prediction problems are common in medical image analysis, this work explores the use of segmented images (through the associated contours they highlight) as predictors in a supervised classification context. Consequently, we develop a new approach for image analysis that takes into account the shape of objects within images. For this aim, we introduce a new formalism that extends the study of single random planar curves to the joint analysis of multiple planar curves-referred to here as multivariate planar curves. In this framework, we propose a solution to the alignment issue in statistical shape analysis. The obtained multivariate shape variables are then used in functional classification methods through tangent projections. Detection of cardiomegaly in segmented X-rays and numerical experiments on synthetic data demonstrate the appeal and robustness of the proposed method.