Deep Learning-Based Reconstruction of Interventional Tools from Four X-Ray Projections for Tomographic Interventional Guidance

TL;DR

This paper introduces a deep learning pipeline that reconstructs and segments interventional tools from only four X-ray projections, enabling real-time 4D guidance for minimally invasive procedures with high accuracy and low dose.

Contribution

It presents a novel deep learning approach for reconstructing and segmenting interventional tools from minimal projection data, improving guidance accuracy and safety.

Findings

High accuracy in tool reconstruction from four projections

Real-time processing capability demonstrated

Potential to improve minimally invasive intervention guidance

Abstract

Image guidance for minimally invasive interventions is usually performed by acquiring fluoroscopic images using a C-arm system. However, the projective data provide only limited information about the spatial structure and position of interventional tools such as stents, guide wires or coils. In this work we propose a deep learning-based pipeline for real-time tomographic (four-dimensional) interventional guidance at acceptable dose levels. In the first step, interventional tools are extracted from four cone-beam CT projections using a deep convolutional neural network (CNN). These projections are then reconstructed and fed into a second CNN, which maps this highly undersampled reconstruction to a segmentation of the interventional tools. Our pipeline is capable of reconstructing interventional tools from only four x-ray projections without the need for a patient prior with very high accuracy. Therefore, the proposed approach is capable of overcoming the drawbacks of today's interventional guidance and could enable the development of new minimally invasive radiological interventions by providing full spatiotemporal information about the interventional tools.