Enhanced nnU-Net Architectures for Automated MRI Segmentation of Head and Neck Tumors in Adaptive Radiation Therapy

Lecture notes in computer science, Journal Year: 2025, Volume and Issue: unknown, P. 50 - 64

Published: Jan. 1, 2025

Language: Английский

---

Overview of the Head and Neck Tumor Segmentation for Magnetic Resonance Guided Applications (HNTS-MRG) 2024 Challenge

Lecture notes in computer science, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 35

Published: Jan. 1, 2025

Language: Английский

---

Foreground Background Difference Knowledge‐Based Small Sample Target Segmentation for Image‐Guided Radiation Therapy

International Journal of Imaging Systems and Technology, Journal Year: 2025, Volume and Issue: 35(2)

Published: March 1, 2025

ABSTRACT The aim of this paper is to exploit a small sample (data scarcity) target segmentation technique for image‐guided radiation therapy. grounded on prototype‐based approach—widely used method. In paper, we propose foreground–background difference knowledge learning framework perform the task. Its main differences from traditional approaches and novel contributions may be enumerated in two aspects: (1) A subdivision strategy generate multiple prototypes each class support images, generated prototype build collection query foreground background prototypes. (2) cross‐prototype attention module learn correlation inter‐class transfer iterative updates. advantage our that: intra‐class set can comprehensively reflect features, avoiding high computational complexity caused by dense matching; provides comprehensive information, greatly supporting accurate set. 5‐shot SegRap dataset experiment, proposed model achieved Dice coefficients 82.23% same‐domain setting 81.01% cross‐domain setting. Similarly, HECKTOR2022 it 83.59% 81.48% For BTCV CHAOS datasets, attained 79.00% 79.70%, respectively. These results demonstrate model's accuracy, efficiency, generalization. This study presents significant advancement medical image introducing that effectively addresses data scarcity. By leveraging intra‐ mechanisms, ensures robust generalization reliable performance across paving way efficient precise clinical applications with minimal reliance large annotated datasets.

Language: Английский

---

A registration algorithm-guided framework for more accurate adaptive radiotherapy segmentation

Radiation Physics and Chemistry, Journal Year: 2025, Volume and Issue: unknown, P. 112918 - 112918

Published: May 1, 2025

Language: Английский

---