VoxelMorph-Based Non-Rigid Chest CT Registration With Multi-Frequency Encoding and Curriculum Learning

VoxelMorph, a widely adopted deep learning framework for non-rigid image registration, often encounters challenges in precisely aligning lung regions in chest computed tomography (CT) due to limited soft-tissue contrast, a scarcity of stable anatomical landmarks, and substantial inter-scan pose vari...

وصف كامل

التفاصيل البيبلوغرافية

المؤلفون الرئيسيون:	Yamato Kohara, Ryohei Nakayama, Motonori Nagata, Yasutaka Ichikawa, Hajime Sakuma
التنسيق:	Artigo
اللغة:	Inglês
منشور في:	IEEE 2026-01-01
سلاسل:	IEEE Access
الموضوعات:	Chest computed tomography (CT) curriculum learning deep learning non-rigid image registration multi-frequency encoding
الوصول للمادة أونلاين:	https://ieeexplore.ieee.org/document/11406103/
الوسوم:	إضافة وسم لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!