Salt & Pepper Heatmaps: Diffusion-informed Landmark Detection Strategy

TL;DR

This paper introduces a diffusion-informed heatmap approach for anatomical landmark detection, leveraging stochastic diffusion models to generate precise probability regions, achieving state-of-the-art accuracy.

Contribution

It reformulates landmark detection as a generative modeling task using diffusion models to produce accurate, probability-based heatmaps, a novel application in medical imaging.

Findings

Achieves state-of-the-art mean radial error (MRE)

Provides comparable success detection rate (SDR) to existing methods

Utilizes diffusion models to capture landmark prediction fluctuations

Abstract

Anatomical Landmark Detection is the process of identifying key areas of an image for clinical measurements. Each landmark is a single ground truth point labelled by a clinician. A machine learning model predicts the locus of a landmark as a probability region represented by a heatmap. Diffusion models have increased in popularity for generative modelling due to their high quality sampling and mode coverage, leading to their adoption in medical image processing for semantic segmentation. Diffusion modelling can be further adapted to learn a distribution over landmarks. The stochastic nature of diffusion models captures fluctuations in the landmark prediction, which we leverage by blurring into meaningful probability regions. In this paper, we reformulate automatic Anatomical Landmark Detection as a precise generative modelling task, producing a few-hot pixel heatmap. Our method achieves state-of-the-art MRE and comparable SDR performance with existing work.