Contrastive Rendering for Ultrasound Image Segmentation

10/10/2020
by   Haoming Li, et al.
16

Ultrasound (US) image segmentation embraced its significant improvement in deep learning era. However, the lack of sharp boundaries in US images still remains an inherent challenge for segmentation. Previous methods often resort to global context, multi-scale cues or auxiliary guidance to estimate the boundaries. It is hard for these methods to approach pixel-level learning for fine-grained boundary generating. In this paper, we propose a novel and effective framework to improve boundary estimation in US images. Our work has three highlights. First, we propose to formulate the boundary estimation as a rendering task, which can recognize ambiguous points (pixels/voxels) and calibrate the boundary prediction via enriched feature representation learning. Second, we introduce point-wise contrastive learning to enhance the similarity of points from the same class and contrastively decrease the similarity of points from different classes. Boundary ambiguities are therefore further addressed. Third, both rendering and contrastive learning tasks contribute to consistent improvement while reducing network parameters. As a proof-of-concept, we performed validation experiments on a challenging dataset of 86 ovarian US volumes. Results show that our proposed method outperforms state-of-the-art methods and has the potential to be used in clinical practice.

READ FULL TEXT

page 2

page 4

page 8

research
11/22/2021

Exploring Feature Representation Learning for Semi-supervised Medical Image Segmentation

This paper presents a simple yet effective two-stage framework for semi-...
research
09/25/2021

Contrastive Learning for Mitochondria Segmentation

Mitochondria segmentation in electron microscopy images is essential in ...
research
01/05/2019

Fully-automatic segmentation of kidneys in clinical ultrasound images using a boundary distance regression network

It remains challenging to automatically segment kidneys in clinical ultr...
research
07/05/2022

MMGL: Multi-Scale Multi-View Global-Local Contrastive learning for Semi-supervised Cardiac Image Segmentation

With large-scale well-labeled datasets, deep learning has shown signific...
research
04/06/2023

Implicit Anatomical Rendering for Medical Image Segmentation with Stochastic Experts

Integrating high-level semantically correlated contents and low-level an...
research
12/06/2016

Fine-grained Recurrent Neural Networks for Automatic Prostate Segmentation in Ultrasound Images

Boundary incompleteness raises great challenges to automatic prostate se...
research
11/24/2020

Good and Bad Boundaries in Ultrasound Compounding: Preserving Anatomic Boundaries While Suppressing Artifacts

Ultrasound 3D compounding is important for volumetric reconstruction, bu...

Please sign up or login with your details

Forgot password? Click here to reset