Assisted Probe Positioning for Ultrasound Guided Radiotherapy Using Image Sequence Classification

TL;DR

This paper presents a real-time multi-task neural network system that classifies ultrasound images and recommends probe adjustments to improve prostate radiotherapy accuracy, reducing operator dependency and interoperator variability.

Contribution

The study introduces a novel multi-input multi-task deep learning approach combining image and spatial data for probe positioning in ultrasound-guided radiotherapy, demonstrating high accuracy and potential clinical utility.

Findings

Achieved 97.2% anatomical classification accuracy with unanimous observer consensus.

Attained 94.9% accuracy in probe adjustment recommendations.

Identified probe alignment within 3.7° of expert labels, comparable to interobserver variability.

Abstract

Effective transperineal ultrasound image guidance in prostate external beam radiotherapy requires consistent alignment between probe and prostate at each session during patient set-up. Probe placement and ultrasound image inter-pretation are manual tasks contingent upon operator skill, leading to interoperator uncertainties that degrade radiotherapy precision. We demonstrate a method for ensuring accurate probe placement through joint classification of images and probe position data. Using a multi-input multi-task algorithm, spatial coordinate data from an optically tracked ultrasound probe is combined with an image clas-sifier using a recurrent neural network to generate two sets of predictions in real-time. The first set identifies relevant prostate anatomy visible in the field of view using the classes: outside prostate, prostate periphery, prostate centre. The second set recommends a probe angular adjustment to achieve alignment between the probe and prostate centre with the classes: move left, move right, stop. The algo-rithm was trained and tested on 9,743 clinical images from 61 treatment sessions across 32 patients. We evaluated classification accuracy against class labels de-rived from three experienced observers at 2/3 and 3/3 agreement thresholds. For images with unanimous consensus between observers, anatomical classification accuracy was 97.2% and probe adjustment accuracy was 94.9%. The algorithm identified optimal probe alignment within a mean (standard deviation) range of 3.7$^{\circ}$ (1.2$^{\circ}$) from angle labels with full observer consensus, comparable to the 2.8$^{\circ}$ (2.6$^{\circ}$) mean interobserver range. We propose such an algorithm could assist ra-diotherapy practitioners with limited experience of ultrasound image interpreta-tion by providing effective real-time feedback during patient set-up.