Offset regression networks for view plane estimation in 3D fetal ultrasound

Schmidt-Richberg, Alexander; Schadewaldt, Nicole; Klinder, Tobias; Lenga, Matthias; Trahms, Robert; Canfield, Earl; Roundhill, David; Lorenz, Cristian

doi:10.1117/12.2512697

Cited by 11 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with the general linear regression model, the SVR model is more tolerant to the calculation of loss by constructing interval belts on both sides of the function [6]. Only sample points that are outside of the belts are to be considered when calculating the loss of the model.…”

Section: Support Vector Regressionmentioning

confidence: 99%

Research on anti-breast cancer candidate drugs analysis based on random forest model and genetic algorithm

Yue

2023

Second International Conference on Applied Statistics, Computational Mathematics, and Software Engineering (ASCMSE 2023)

View full text Add to dashboard Cite

Breast cancer is one common cancer with high fatality rate worldwide. Based on consideration of pharmacokinetics and toxicity, this study aims to build a model to investigate compounds which can be used for candidate drugs to resist breast cancer. Using SVR model, GBRT model and random forest algorithm, this study established a quantitative prediction model for the bioactivity of compounds to Erα, and SVM model, SGD model and random forest algorithm were constructed for predicting the 5 ADMET properties of the compounds. Finally, based on the above models and analysis, compounds with better biological activity against ERα and better ADMET properties were selected in this paper. This study definitively established the model for selecting compounds which can be used as anti-breast drug candidates, and further research is needed to add more pharmacokinetic properties in the model to improve its applicability.

show abstract

Section: Support Vector Regressionmentioning

confidence: 99%

Research on anti-breast cancer candidate drugs analysis based on random forest model and genetic algorithm

Yue

2023

Second International Conference on Applied Statistics, Computational Mathematics, and Software Engineering (ASCMSE 2023)

View full text Add to dashboard Cite

show abstract

“…Recently, Ryou et al [28] proposed to locate the fetus by random forest and detect SPs by CNNs sequentially. Schmidt-Richberg et al [29] introduced a deep learning based regression framework to estimate SP locations. Li et al [30] proposed a deep neural network to move the estimated plane to the target SP iteratively.…”

Section: Related Workmentioning

confidence: 99%

Agent With Warm Start and Adaptive Dynamic Termination for Plane Localization in 3D Ultrasound

Yang

Dou

Huang

et al. 2021

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

Accurate standard plane (SP) localization is the fundamental step for prenatal ultrasound (US) diagnosis. Typically, dozens of US SPs are collected to determine the clinical diagnosis. 2D US has to perform scanning for each SP, which is timeconsuming and operator-dependent. While 3D US containing multiple SPs in one shot has the inherent advantages of less user-dependency and more efficiency. Automatically locating SP in 3D US is very challenging due to the huge search space and large fetal posture variations. Our previous study proposed a deep reinforcement learning (RL) framework with an alignment module and active termination to localize SPs in 3D US automatically. However, termination of agent search in RL is important and affects the practical deployment. In this study, we enhance our previous RL framework with a newly designed adaptive dynamic termination to enable an early stop for the agent searching, saving at most 67% inference time, thus boosting the accuracy and efficiency of the RL framework at the same time. Besides, we validate the effectiveness and generalizability of our algorithm extensively on our in-house multi-organ datasets containing 433 fetal brain volumes, 519 fetal abdomen volumes, and 683 uterus volumes. Our approach achieves localization error of 2.52mm/10.26 • , 2.48mm/10.39 • , 2.02mm/10.48 • , 2.00mm/14.57 • , 2.61mm/9.71 • , 3.09mm/9.58 • , 1.49mm/7.54 • for the transcerebellar, transventricular, transthalamic planes in fetal brain, abdominal plane in fetal abdomen, and midsagittal, transverse and coronal planes in uterus, respectively. Experimental results show that our method is general and has the potential to improve the efficiency and standardization of US scanning.

show abstract

“…A number of methods have been proposed to detect the standard scan planes from 3D US volumes. Some methods used CNNs to regress the transformation from the current plane to the standard plane [14] [15], but this kind of prediction may cause abrupt changes in position rather than gradual and continuous changes, which is undesirable for the probe navigation task. Alansary et al [11] parameterized a plane as ax + by + cz + d = 0, and customized an RL agent to learn step-by-step adjustment of the plane parameters to find the standard plane in 3D MRI scans.…”

Section: Related Workmentioning

confidence: 99%

Autonomous Navigation of an Ultrasound Probe Towards Standard Scan Planes with Deep Reinforcement Learning

Li,

Wang,

et al. 2021

Preprint

View full text Add to dashboard Cite

Autonomous ultrasound (US) acquisition is an important yet challenging task, as it involves interpretation of the highly complex and variable images and their spatial relationships. In this work, we propose a deep reinforcement learning framework to autonomously control the 6-D pose of a virtual US probe based on real-time image feedback to navigate towards the standard scan planes under the restrictions in real-world US scans. Furthermore, we propose a confidencebased approach to encode the optimization of image quality in the learning process. We validate our method in a simulation environment built with real-world data collected in the US imaging of the spine. Experimental results demonstrate that our method can perform reproducible US probe navigation towards the standard scan plane with an accuracy of 4.91mm/4.65 • in the intra-patient setting, and accomplish the task in the intra-and inter-patient settings with a success rate of 92% and 46%, respectively. The results also show that the introduction of image quality optimization in our method can effectively improve the navigation performance.

show abstract

Offset regression networks for view plane estimation in 3D fetal ultrasound

Cited by 11 publications

References 4 publications

Research on anti-breast cancer candidate drugs analysis based on random forest model and genetic algorithm

Research on anti-breast cancer candidate drugs analysis based on random forest model and genetic algorithm

Agent With Warm Start and Adaptive Dynamic Termination for Plane Localization in 3D Ultrasound

Autonomous Navigation of an Ultrasound Probe Towards Standard Scan Planes with Deep Reinforcement Learning

Contact Info

Product

Resources

About