# Agent with Warm Start and Adaptive Dynamic Termination for Plane Localization in 3D Ultrasound arXiv: https://arxiv.org/abs/2103.14502 ยท HTML: https://mlsanity.com/paper/2103.14502/ ## Key facts - Cited by 10 papers in the map (data through 14 Oct 2026). - Builds on 15 of its 46 references that are in the map. - First posted on arXiv 26 Mar 2021. ## Builds on (most cited first, 15 of 15) - [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014) - [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019) - [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014) - [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015) - [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018) - [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016) - [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015) - [Dueling Network Architectures for Deep Reinforcement Learning](https://mlsanity.com/paper/1511.06581/) (2015) - [Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images](https://mlsanity.com/paper/1808.08114/) (2018) - [SonoNet: Real-Time Detection and Localisation of Fetal Standard Scan Planes in Freehand Ultrasound](https://mlsanity.com/paper/1612.05601/) (2016) - [Active Object Localization with Deep Reinforcement Learning](https://mlsanity.com/paper/1511.06015/) (2015) - [Automatic View Planning with Multi-scale Deep Reinforcement Learning Agents](https://mlsanity.com/paper/1806.03228/) (2018) - [Standard Plane Detection in 3D Fetal Ultrasound Using an Iterative Transformation Network](https://mlsanity.com/paper/1806.07486/) (2018) - [Agent with Warm Start and Active Termination for Plane Localization in 3D Ultrasound](https://mlsanity.com/paper/1910.04331/) (2019) - [Temporal HeartNet: Towards Human-Level Automatic Analysis of Fetal Cardiac Screening Video](https://mlsanity.com/paper/1707.00665/) (2017) ## Built on by (most cited first, 10 of 10) - [A Review on Deep-Learning Algorithms for Fetal Ultrasound-Image Analysis](https://mlsanity.com/paper/2201.12260/) (2022) - [Agent with Tangent-based Formulation and Anatomical Perception for Standard Plane Localization in 3D Ultrasound](https://mlsanity.com/paper/2207.00475/) (2022) - [Deep Reinforcement Learning Framework for Thoracic Diseases Classification via Prior Knowledge Guidance](https://mlsanity.com/paper/2306.01232/) (2023) - [Flip Learning: Weakly Supervised Erase to Segment Nodules in Breast Ultrasound](https://mlsanity.com/paper/2503.20685/) (2025) - [Uncertainty-aware Diffusion and Reinforcement Learning for Joint Plane Localization and Anomaly Diagnosis in 3D Ultrasound](https://mlsanity.com/paper/2506.23538/) (2025) - [Towards deep observation: A systematic survey on artificial intelligence techniques to monitor fetus via Ultrasound Images](https://mlsanity.com/paper/2201.07935/) (2022) - [3D Heart Reconstruction from Sparse Pose-agnostic 2D Echocardiographic Slices](https://mlsanity.com/paper/2507.02411/) (2025) - [UltrasODM: A Dual Stream Optical Flow Mamba Network for 3D Freehand Ultrasound Reconstruction](https://mlsanity.com/paper/2512.07756/) (2025) - [Cross-Modal Ultrasound-MRI Learning for Fetal Brain Ventricular Volumetry and Abnormality Screening](https://mlsanity.com/paper/2608.14763/) (2026) - [Deep Learning-based Intelligent Diagnosis of Congenital Uterine Anomalies in 3D Ultrasound](https://mlsanity.com/paper/2609.15225/) (2026) ## Abstract (arXiv) 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 time-consuming 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 degrees, 2.48mm/10.39 degrees, 2.02mm/10.48 degrees, 2.00mm/14.57 degrees, 2.61mm/9.71 degrees, 3.09mm/9.58 degrees, 1.49mm/7.54 degrees for the transcerebellar, transventricular, transthalamic planes in fetal brain, abdominal plane in fetal abdomen, and mid-sagittal, 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.