# A deep learning approach for patchless estimation of ultrasound quantitative parametric image with uncertainty measurement

## TL;DR

This paper introduces a deep learning method to estimate ultrasound quantitative parametric images, specifically scatterer number density, without the need for patch-based analysis, while also providing uncertainty measurements for the predictions.

## Contribution

The study presents a novel deep learning approach that eliminates the patching process in QUS parameter estimation and incorporates uncertainty quantification.

## Key findings

- Accurate estimation of scatterer number density without patching.
- Uncertainty maps effectively indicate confidence levels in predictions.
- Method outperforms traditional patch-based estimation techniques.

## Abstract

Quantitative ultrasound (QUS) aims to find properties of scatterers which are related to the tissue microstructure. Among different QUS parameters, scatterer number density has been found to be a reliable biomarker for detecting different abnormalities. The homodyned K-distribution (HK-distribution) is a model for the probability density function of the ultrasound echo amplitude that can model different scattering scenarios but requires a large number of samples to be estimated reliably. Parametric images of HK-distribution parameters can be formed by dividing the envelope data into small overlapping patches and estimating parameters within the patches independently. This approach imposes two limiting constraints, the HK-distribution parameters are assumed to be constant within each patch, and each patch requires enough independent samples. In order to mitigate those problems, we employ a deep learning approach to estimate parametric images of scatterer number density (related to HK-distribution shape parameter) without patching. Furthermore, an uncertainty map of the network's prediction is quantified to provide insight about the confidence of the network about the estimated HK parameter values.