ACSwinNet: A Deep Learning-Based Rigid Registration Method for Head-Neck CT-CBCT Images in Image-Guided Radiotherapy DOI Creative Commons

Kuankuan Peng,

Danyu Zhou,

Kaiwen Sun

et al.

Sensors, Journal Year: 2024, Volume and Issue: 24(16), P. 5447 - 5447

Published: Aug. 22, 2024

Accurate and precise rigid registration between head-neck computed tomography (CT) cone-beam (CBCT) images is crucial for correcting setup errors in image-guided radiotherapy (IGRT) head neck tumors. However, conventional methods that treat the as a single entity may not achieve necessary accuracy region, which particularly sensitive to radiation radiotherapy. We propose ACSwinNet, deep learning-based method CT-CBCT registration, aims enhance precision region. Our approach integrates an anatomical constraint encoder with segmentations of tissues organs also employ Swin Transformer-based network cases large initial misalignment perceptual similarity metric address intensity discrepancies artifacts CT CBCT images. validate proposed using dataset acquired from clinical patients. Compared method, our exhibits lower target error (TRE) landmarks region (reduced 2.14 ± 0.45 mm 1.82 0.39 mm), higher dice coefficient (DSC) (increased 0.743 0.051 0.755 0.053), structural index 0.854 0.044 0.870 0.043). effectively addresses challenge low has been limitation methods. This demonstrates significant potential improving IGRT

Language: Английский

Balancing data consistency and diversity: Preprocessing and online data augmentation for multi-center deep learning-based MR-to-CT synthesis DOI

Songyue Han,

Cédric Hemon, Blanche Texier

et al.

Pattern Recognition Letters, Journal Year: 2025, Volume and Issue: 189, P. 56 - 63

Published: Jan. 10, 2025

Language: Английский

Citations

1
Adaptive deep CNN: an effective Alzheimer’s affected MRI image registration using heuristic-aided deep learning model and patch-based level fusion DOI
Vaidehi Deshmukh, Shilpa S. Chapadgaonkar, Manisha Kowdiki

et al.

Pattern Analysis and Applications, Journal Year: 2025, Volume and Issue: 28(2)

Published: March 24, 2025

Language: Английский

Citations

0
3D Unsupervised deep learning method for magnetic resonance imaging-to-computed tomography synthesis in prostate radiotherapy DOI Creative Commons
Blanche Texier, Cédric Hemon,

Adélie Queffelec

et al.

Physics and Imaging in Radiation Oncology, Journal Year: 2024, Volume and Issue: 31, P. 100612 - 100612

Published: July 1, 2024

Language: Английский

Citations

1
ACSwinNet: A Deep Learning-Based Rigid Registration Method for Head-Neck CT-CBCT Images in Image-Guided Radiotherapy DOI Creative Commons

Kuankuan Peng,

Danyu Zhou,

Kaiwen Sun

et al.

Sensors, Journal Year: 2024, Volume and Issue: 24(16), P. 5447 - 5447

Published: Aug. 22, 2024

Accurate and precise rigid registration between head-neck computed tomography (CT) cone-beam (CBCT) images is crucial for correcting setup errors in image-guided radiotherapy (IGRT) head neck tumors. However, conventional methods that treat the as a single entity may not achieve necessary accuracy region, which particularly sensitive to radiation radiotherapy. We propose ACSwinNet, deep learning-based method CT-CBCT registration, aims enhance precision region. Our approach integrates an anatomical constraint encoder with segmentations of tissues organs also employ Swin Transformer-based network cases large initial misalignment perceptual similarity metric address intensity discrepancies artifacts CT CBCT images. validate proposed using dataset acquired from clinical patients. Compared method, our exhibits lower target error (TRE) landmarks region (reduced 2.14 ± 0.45 mm 1.82 0.39 mm), higher dice coefficient (DSC) (increased 0.743 0.051 0.755 0.053), structural index 0.854 0.044 0.870 0.043). effectively addresses challenge low has been limitation methods. This demonstrates significant potential improving IGRT

Language: Английский

Citations

0