A Hierarchical Descriptor Framework for On-the-Fly Anatomical Location Matching between Longitudinal Studies

TL;DR

This paper introduces a fast, hierarchical descriptor-based method for matching anatomical locations in longitudinal medical images, enabling near real-time comparison without extensive pre-processing or training.

Contribution

The proposed framework offers a novel, training-free approach for anatomical location matching that is faster and more accurate than existing methods, applicable across different imaging modalities.

Findings

Achieved more accurate matching than Deep Lesion Tracker.

Reduced computational time to milliseconds on a single CPU.

Demonstrated effectiveness across CT and MR modalities.

Abstract

We propose a method to match anatomical locations between pairs of medical images in longitudinal comparisons. The matching is made possible by computing a descriptor of the query point in a source image based on a hierarchical sparse sampling of image intensities that encode the location information. Then, a hierarchical search operation finds the corresponding point with the most similar descriptor in the target image. This simple yet powerful strategy reduces the computational time of mapping points to a millisecond scale on a single CPU. Thus, radiologists can compare similar anatomical locations in near real-time without requiring extra architectural costs for precomputing or storing deformation fields from registrations. Our algorithm does not require prior training, resampling, segmentation, or affine transformation steps. We have tested our algorithm on the recently published Deep Lesion Tracking dataset annotations. We observed more accurate matching compared to Deep Lesion Tracker while being 24 times faster than the most precise algorithm reported therein. We also investigated the matching accuracy on CT and MR modalities and compared the proposed algorithm's accuracy against ground truth consolidated from multiple radiologists.