An improved SIFT algorithm based method for detecting of tumor tissue movement in respiratory motion
Pan, Q.; Luan, s.; Zhang, F.; Tian, L.; Wu, G.; Fan, Y.
Show abstract
BackgroundThis paper intends to make use of the excellent performance of the SIFT algorithm to accurately calculate the displacement of tumor tissues during respiratory movement. Material and methodFirst, we moved phantoms to up,down,right,left respectively to simulate the different directions of movement during respiratory. And rotated phantom to left and right respectively by the angle of 5,10,30,45. Then, used SIFT and cross-correlation algorithms to search the phantoms. Last, use the t-test to check the differences between different directions. ResulThe t-test result proved that there was no significant difference in the detection of moving phantom in all directions. There was no statistical difference between the SIFT of the moving motif and the cross-correlation. The detection results of rotating phantom indicated that the SIFT test results could be used to detect distortion. ConclusionSIFT algorithm can be used to calculate the distortion caused by the thoracic tissue during respiratory movement.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Estimation of Three-Dimensional Chromatin Morphology for Nuclear Classification and Characterisation 97%
- Segmentation of Pancreatic Ductal Adenocarcinoma (PDAC) and surrounding vessels in CT images using deep convolutional neural networks and Texture Descriptors 96%
- Effective Deep Learning Approaches for Predicting COVID-19 Outcomes from Chest Computed Tomography Volumes 94%
Similar papers in this journal
- Development of a Coupled Simulation Toolkit for Computational Radiation Biology Based on Geant4 and CompuCell3D 93%
- High precision fluorescence tomography-guided system for pre-clinical radiation research: system design and validation 93%
- Deep learning-based auto-segmentation of swallowing and chewing structures 93%
Similar papers in this journal
Similar papers in this journal
- A computationally efficient approach to segmentation of the aorta and coronary arteries using deep learning 95%
- Accurate detection of non-proliferative diabetic retinopathy in optical coherence tomography images using convolutional neural networks 95%
- Modeling and Visualization of Rice Root Based on Morphological Parameters 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.