Weakly Supervised Estimation of Shadow Confidence Maps in Ultrasound Imaging

by   Qingjie Meng, et al.

Detecting acoustic shadows in ultrasound images is important in many clinical and engineering applications. Real-time feedback of acoustic shadows can guide sonographers to a standardized diagnostic viewing plane with minimal artifacts and can provide additional information for other automatic image analysis algorithms. However, automatically detecting shadow regions is challenging because pixel-wise annotation of acoustic shadows is subjective and time consuming. In this paper we propose a weakly supervised method for automatic confidence estimation of acoustic shadow regions, which is able to generate a dense shadow-focused confidence map. During training, a multi-task module for shadow segmentation is built to learn general shadow features according based image-level annotations as well as a small number of coarse pixel-wise shadow annotations. A transfer function is then established to extend the binary shadow segmentation to a reference confidence map. In addition, a confidence estimation network is proposed to learn the mapping between input images and the reference confidence maps. This confidence estimation network is able to predict shadow confidence maps directly from input images during inference. We evaluate DICE, soft DICE, recall, precision, mean squared error and inter-class correlation to verify the effectiveness of our method. Our method outperforms the state-of-the-art qualitatively and quantitatively. We further demonstrate the applicability of our method by integrating shadow confidence maps into tasks such as ultrasound image classification, multi-view image fusion and automated biometric measurements.


page 1

page 4

page 8

page 10

page 13

page 14

page 15


Ultrasound Confidence Maps of Intensity and Structure Based on Directed Acyclic Graphs and Artifact Models

Ultrasound imaging has been improving, but continues to suffer from inhe...

Can ultrasound confidence maps predict sonographers' labeling variability?

Measuring cross-sectional areas in ultrasound images is a standard tool ...

Cardiac Adipose Tissue Segmentation via Image-Level Annotations

Automatically identifying the structural substrates underlying cardiac a...

CaCL: Class-aware Codebook Learning for Weakly Supervised Segmentation on Diffuse Image Patterns

Weakly supervised learning has been rapidly advanced in biomedical image...

SSA: Semantic Structure Aware Inference for Weakly Pixel-Wise Dense Predictions without Cost

The pixel-wise dense prediction tasks based on weakly supervisions curre...

Weakly Supervised Localisation for Fetal Ultrasound Images

This paper addresses the task of detecting and localising fetal anatomic...

Autoencoder-Based Articulatory-to-Acoustic Mapping for Ultrasound Silent Speech Interfaces

When using ultrasound video as input, Deep Neural Network-based Silent S...

Please sign up or login with your details

Forgot password? Click here to reset