SonoSelect: Efficient Ultrasound Perception via Active Probe Exploration
This addresses the need for more efficient ultrasound perception in medical diagnostics by reducing scanning and processing costs, though it appears incremental as it builds on existing active exploration and sequential decision-making frameworks.
The paper tackles the problem of reducing redundancy in ultrasound scanning by proposing SonoSelect, an active probe exploration method that adaptively guides probe movement based on observations, achieving promising multi-view organ classification accuracy with only 2 out of N views and specific coverage rates for kidney cyst detection.
Ultrasound perception typically requires multiple scan views through probe movement to reduce diagnostic ambiguity, mitigate acoustic occlusions, and improve anatomical coverage. However, not all probe views are equally informative. Exhaustively acquiring a large number of views can introduce substantial redundancy, increase scanning and processing costs. To address this, we define an active view exploration task for ultrasound and propose SonoSelect, an ultrasound-specific method that adaptively guides probe movement based on current observations. Specifically, we cast ultrasound active view exploration as a sequential decision-making problem. Each new 2D ultrasound view is fused into a 3D spatial memory of the observed anatomy, which guides the next probe position. On top of this formulation, we propose an ultrasound-specific objective that favors probe movements with greater organ coverage, lower reconstruction uncertainty, and less redundant scanning. Experiments on the ultrasound simulator show that SonoSelect achieves promising multi-view organ classification accuracy using only 2 out of N views. Furthermore, for a more difficult kidney cyst detection task, it reaches 54.56% kidney coverage and 35.13% cyst coverage, with short trajectories consistently centered on the target cyst.