Deformable-Detection Transformer for Microbubble Localization in Ultrasound Localization Microscopy

TL;DR

This paper introduces a deformable transformer-based method for microbubble localization in ultrasound microscopy, improving accuracy and efficiency over previous transformer models by using multi-scale deformable attention.

Contribution

It adapts the DEformable DETR model for microbubble localization, addressing DETR's limitations with small objects and training time, and demonstrates improved performance in ultrasound super-resolution imaging.

Findings

Enhanced precision and recall in microbubble localization

Better super-resolution maps compared to previous methods

Reduced training time and improved small object detection

Abstract

To overcome the half a wavelength resolution limitations of ultrasound imaging, microbubbles (MBs) have been utilized widely in the field. Conventional MB localization methods are limited whether by exhaustive parameter tuning or considering a fixed Point Spread Function (PSF) for MBs. This questions their adaptability to different imaging settings or depths. As a result, development of methods that don't rely on manually adjusted parameters is crucial. Previously, we used a transformer-based approach i.e. DEtection TRansformer (DETR) (arXiv:2005.12872v3 and arXiv:2209.11859v1) to address the above mentioned issues. However, DETR suffers from long training times and lower precision for smaller objects. In this paper, we propose the application of DEformable DETR (DE-DETR) ( arXiv:2010.04159) for MB localization to mitigate DETR's above mentioned challenges. As opposed to DETR, where attention is casted upon all grid pixels, DE-DETR utilizes a multi-scale deformable attention to distribute attention within a limited budget. To evaluate the proposed strategy, pre-trained DE-DETR was fine-tuned on a subset of the dataset provided by the IEEE IUS Ultra-SR challenge organizers using transfer learning principles and subsequently we tested the network on the rest of the dataset, excluding the highly correlated frames. The results manifest an improvement both in precision and recall and the final super-resolution maps compared to DETR.