Region Proposal Network with Graph Prior and IoU-Balance Loss for Landmark Detection in 3D Ultrasound

04/01/2020
by   Chaoyu Chen, et al.
0

3D ultrasound (US) can facilitate detailed prenatal examinations for fetal growth monitoring. To analyze a 3D US volume, it is fundamental to identify anatomical landmarks of the evaluated organs accurately. Typical deep learning methods usually regress the coordinates directly or involve heatmap-matching. However, these methods struggle to deal with volumes with large sizes and the highly-varying positions and orientations of fetuses. In this work, we exploit an object detection framework to detect landmarks in 3D fetal facial US volumes. By regressing multiple parameters of the landmark-centered bounding box (B-box) with a strict criteria, the proposed model is able to pinpoint the exact location of the targeted landmarks. Specifically, the model uses a 3D region proposal network (RPN) to generate 3D candidate regions, followed by several 3D classification branches to select the best candidate. It also adopts an IoU-balance loss to improve communications between branches that benefits the learning process. Furthermore, it leverages a distance-based graph prior to regularize the training and helps to reduce false positive predictions. The performance of the proposed framework is evaluated on a 3D US dataset to detect five key fetal facial landmarks. Results showed the proposed method outperforms some of the state-of-the-art methods in efficacy and efficiency.

READ FULL TEXT

page 1

page 2

page 4

research
09/21/2016

Detecting facial landmarks in the video based on a hybrid framework

To dynamically detect the facial landmarks in the video, we propose a no...
research
08/31/2019

Joint Segmentation and Landmark Localization of Fetal Femur in Ultrasound Volumes

Volumetric ultrasound has great potentials in promoting prenatal examina...
research
09/14/2022

Landmark Tracking in Liver US images Using Cascade Convolutional Neural Networks with Long Short-Term Memory

This study proposed a deep learning-based tracking method for ultrasound...
research
12/10/2018

Facial Landmark Machines: A Backbone-Branches Architecture with Progressive Representation Learning

Facial landmark localization plays a critical role in face recognition a...
research
05/18/2023

Coordinated Transformer with Position & Sample-aware Central Loss for Anatomical Landmark Detection

Heatmap-based anatomical landmark detection is still facing two unresolv...
research
03/03/2022

Relative distance matters for one-shot landmark detection

Contrastive learning based methods such as cascade comparing to detect (...
research
09/28/2022

Deep Learning based Automatic Quantification of Urethral Plate Quality using the Plate Objective Scoring Tool (POST)

Objectives: To explore the capacity of deep learning algorithm to furthe...

Please sign up or login with your details

Forgot password? Click here to reset