# More Knowledge is Better: Cross-Modality Volume Completion and 3D+2D Segmentation for Intracardiac Echocardiography Contouring

## TL;DR

This paper introduces a novel cross-modality deep learning framework that leverages both 3D geometrical data and CT images to improve automatic segmentation of the left atrium and pulmonary veins from noisy intracardiac echocardiography images, aiding atrial fibrillation treatment.

## Contribution

It presents the first automatic segmentation method for ICE images using a cross-modality approach combining 3D geometry and CT data, outperforming traditional 2D methods.

## Key findings

- Significant improvement over 2D segmentation models.
- Effective use of CT data enhances segmentation of less-observed structures.
- Model evaluated on 11,000 ICE images from 150 patients.

## Abstract

Using catheter ablation to treat atrial fibrillation increasingly relies on intracardiac echocardiography (ICE) for an anatomical delineation of the left atrium and the pulmonary veins that enter the atrium. However, it is a challenge to build an automatic contouring algorithm because ICE is noisy and provides only a limited 2D view of the 3D anatomy. This work provides the first automatic solution to segment the left atrium and the pulmonary veins from ICE. In this solution, we demonstrate the benefit of building a cross-modality framework that can leverage a database of diagnostic images to supplement the less available interventional images. To this end, we develop a novel deep neural network approach that uses the (i) 3D geometrical information provided by a position sensor embedded in the ICE catheter and the (ii) 3D image appearance information from a set of computed tomography cardiac volumes. We evaluate the proposed approach over 11,000 ICE images collected from 150 clinical patients. Experimental results show that our model is significantly better than a direct 2D image-to-image deep neural network segmentation, especially for less-observed structures.