Uncertain Feature-refinement Attention Unet: Considering Suitable Convolutional Neural Network Model for Real-time Segmentation in Markerless Tumor Tracking
Open Access
- 1 October 2025
- journal article
- Published by Wolters Kluwer Health in Journal of Medical Physics
- Vol. 50 (4) , 636-649
Abstract
Purpose: In markerless tumor tracking (MTT) with deep learning, model performance suffers from domain shifts due to noise and anatomical changes. This study aimed to develop a convolutional neural network (CNN) model for real-time MTT segmentation. Methods: An Uncertain Feature-refinement Attention Unet (UFA-Unet), designed based on insights into CNN behavior under domain distribution shifts that occur between digitally reconstructed radiographs (DRRs) and kV X-ray fluoroscopic (XF) images, is proposed. A qualitative ablation study was performed to examine the contribution of each UFA-Unet component to segmentation accuracy. The model feasibility of UFA-Unet was evaluated through quantitative and phantom studies. The quantitative study included ten lung cancer cases, each containing two datasets (1 st -plan and 2 nd -plan), with a mean interval of 28 days between four-dimensional computed tomography (4DCT) acquisitions. Patient-specific models were trained on 1 st -plan DRRs and validated using noise-injected 1 st -and 2 nd -plan DRRs. In the phantom study, UFA-Unet was trained with only a single exhalation phase (T50) of 4DCT data and evaluated using dynamic phantom XF images with 25-mm amplitude motion. UFA-Unet was compared against U-Net, Attention-Unet, and Swin-Unet. Results: The ablation study confirmed that each component suppressed over-activation to improve segmentation accuracy. In the quantitative study, UFA-Unet maintained superior performance compared with conventional models on both 1 st - and 2 nd -plan DRRs with noise injection. Furthermore, in the phantom study, UFA-Unet demonstrated robust tracking under previously unseen respiratory phases, achieving a 95 th percentile 3D error of 0.61–3.13 mm and consistently outperforming conventional models. Conclusion: UFA-Unet provides accurate, robust, and real-time segmentation, thus demonstrating its suitability for clinical MTT.Keywords
This publication has 25 references indexed in Scilit:
- Simultaneous object detection and segmentation for patient‐specific markerless lung tumor tracking in simulated radiographs with deep learningMedical Physics, 2023
- Deep learning‐based markerless lung tumor tracking in stereotactic radiotherapy using Siamese networksMedical Physics, 2023
- Explainability and controllability of patient‐specific deep learning with attention‐based augmentation for markerless image‐guided radiotherapyMedical Physics, 2022
- Data augmentation: A comprehensive survey of modern approachesArray, 2022
- The markerless lung target tracking AAPM Grand Challenge (MATCH) resultsMedical Physics, 2021
- Markerless Pancreatic Tumor Target Localization Enabled By Deep LearningInternational Journal of Radiation Oncology - Biology - Physics (IJROBP), 2019
- Novel real-time tumor-contouring method using deep learning to prevent mistracking in X-ray fluoroscopyRadiological Physics and Technology, 2017
- Intra‐ and inter‐fractional liver and lung tumor motions treated with SBRT under active breathing controlJournal of Applied Clinical Medical Physics, 2017
- Using 3D printing techniques to create an anthropomorphic thorax phantom for medical imaging purposesMedical Physics, 2017
- The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information RepositoryJournal of Digital Imaging, 2013