Evaluation of Variable Parameter Active Demons Algorithm-Based Diffusion Tensor Imaging on Ventricular Remodeling after Myocardial Infarction and Nursing

This study aimed to explore the effect of diffusion tensor imaging (DTI) image registration algorithm in the evaluation of ventricular remodeling in patients with myocardial infarction and the therapeutic effect of cross-theoretical model rehabilitation exercise care. The dynamic balance coefficient k was introduced to construct the DTI image registration algorithm k-AD based on the variable parameter AD algorithm. Then, it was compared with demons algorithm and AD algorithm and was applied in 110 patients with acute myocardial infarction. All patients were divided into the 55 cases of experimental group (cross-theoretical model rehabilitation exercise nursing) and 55 cases of control group (routine nursing). The myocardial tissue was labelled as infarction zone (IZ), infarction border zone (IBZ), and noninfarcted zone (NIZ). Finally, the fractional anisotropy (FA) and mean diffusivity (MD) were calculated. The results showed that the mean square error (MSE) of k-AD algorithm reduced to 0 after 35 iterations. The descent speed was obviously faster than AD and demons algorithms. The overlap of eigenvalue-eigenvector pairs (OVL-EEP) value of k-AD algorithm (0.25) was smaller than demons (0.81) and AD algorithms (0.56) ( P < 0.05 ). The FA value in IZ was notably smaller than IBZ and NIZ, while the MD value was greater than those ( P < 0.05 ). After nursing intervention, the FA value of myocardial infarction area in the experimental group was notably higher in contrast to control group, but the MD value was notably lower in contrast to it ( P < 0.05 ). In short, the DTI image registration algorithm k-AD based on the variable parameter AD algorithm was remarkably better than the demons and AD algorithms in convergence and DTI image registration. FA and MD values obtained by DTI registration image based on k-AD algorithm could clearly indicate the ventricular remodeling after myocardial infarction and the rehabilitation effect of cross-theoretical model rehabilitation exercise nursing intervention.

Analysis of Image Features and TCM Syndrome Types of Lobar Pneumonia in Children Based on Mean Square Deviation Lung CT Image Registration Algorithm

The aim was to analyze the application of computed tomography (CT) images in the diagnosis of lesions, and the composition of traditional Chinese medicine (TCM) syndromes in children with lobar pneumonia. Lung CT image registration algorithm was constructed based on optimized mean square deviation (OMSD) algorithm, which was applied to CT images of 188 children patients with lobar pneumonia before and after treatment. Besides, free-form deformation (FFD) algorithm and mean square deviation (MSD) algorithm were introduced for comparison with OMSD. Results showed that sum of squared differences (SSD) of OMSD was significantly lower than that of MSD and FFD ( P < 0.05 ). The mutual information (MI), relative overlap rate (ROR), and rcc of OMSD were markedly higher than those of MSD and FFD ( P < 0.05 ). After treatment, the number of pulmonary interstitial thickening, lobular interstitial thickening, ground-glass shadow, patchy shadow, consolidation shadow, pleural thickening, pleural effusion, lymphadenopathy, pneumothorax, and mediastinal emphysema decreased sharply in contrast to before treatment ( P < 0.05 ). Among the selected children, there were 184 children patients with empirical TCM syndrome, accounting for 97.85%, and its dominant syndrome was wind-heat closed lung syndrome (52.75%) and phlegm-heat closed lung syndrome (46.11%). The main symptoms of wind-heat closed and phlegm-heat closed lung syndrome were fever, cough, and pulmonary rales. In conclusion, OMSD was superior to MSD and FFD in lung CT image registration. CT registration image based on OMSD could clearly display the intrapulmonary and extrapulmonary manifestations of children patients, so as to enhance the clinical diagnosis effect. Besides, wind-heat closed lung syndrome and phlegm-heat closed lung syndrome were the common types of TCM syndrome of children pneumonia with the common symptoms of fever and cough.

A Rotation-Invariant Optical and SAR Image Registration Algorithm Based on Deep and Gaussian Features

Traditional feature matching methods of optical and synthetic aperture radar (SAR) used gradient are sensitive to non-linear radiation distortions (NRD) and the rotation between two images. To address this problem, this study presents a novel approach to solving the rigid body rotation problem by a two-step process. The first step proposes a deep learning neural network named RotNET to predict the rotation relationship between two images. The second step uses a local feature descriptor based on the Gaussian pyramid named Gaussian pyramid features of oriented gradients (GPOG) to match two images. The RotNET uses a neural network to analyze the gradient histogram of the two images to derive the rotation relationship between optical and SAR images. Subsequently, GPOG is depicted a keypoint by using the histogram of Gaussian pyramid to make one-cell block structure which is simpler and more stable than HOG structure-based descriptors. Finally, this paper designs experiments to prove that the gradient histogram of the optical and SAR images can reflect the rotation relationship and the RotNET can correctly predict them. The similarity map test and the image registration results obtained on experiments show that GPOG descriptor is robust to SAR speckle noise and NRD.

Adaptive planning based on single beam optimization in passive scattering carbon ion radiotherapy for patients with pancreatic cancer

Background Daily anatomical deviations may distort the dose distribution in carbon ion radiotherapy (CIRT), which may cause treatment failure. Therefore, this study aimed to perform re-planning to maintain the dose coverage in patients with pancreatic cancer with passive scattering CIRT. Methods Eight patients with pancreatic cancer and 95 daily computed tomography (CT) sets were examined. Two types of adaptive plans based on new range compensators (RCs) (AP-1) and initial RCs (AP-2) were generated. In AP-2, each beam was optimized by manually adjusting the range shifter thickness and spread-out Bragg peak size to make dose reduction by < 3% of the original plan. Doses of the original plan with bone matching (BM) and tumor matching (TM) were examined for comparison. We calculated the accumulated dose using the contour and intensity-based deformable image registration algorithm. The dosimetric differences in respect to the original plan were compared between methods. Results Using TM and BM, mean ± standard deviations of daily CTV V95 (%) difference from the original plan was − 5.1 ± 6.2 and − 8.8 ± 8.8, respectively, but 1.2 ± 3.4 in AP-1 and − 0.5 ± 2.1 in AP-2 (P < 0.001). AP-1 and AP-2 enabled to maintain a satisfactory accumulated dose in all patients. The dose difference was 1.2 ± 2.8, − 2,1 ± 1.7, − 7.1 ± 5.2, and − 16.5 ± 15.0 for AP-1, AP-2, TM, and BM, respectively. However, AP-2 caused a dose increase in the duodenum, especially in the left–right beam. Conclusions The possible dose deterioration should be considered when performing the BM, even TM. Re-planning based on single beam optimization in passive scattering CIRT seems an effective and safe method of ensuring the treatment robustness in pancreatic cancer. Further study is necessary to spare healthy tissues, especially the duodenum.