http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Mostafapour Samaneh,Gholamiankhah Faeze,Maroufpour Sirwan,Momennezhad Mehdi,Asadinezhad Mohsen,Zakavi Seyed Rasoul,Arabi Hossein,Zaidi Habib 한국CDE학회 2022 Journal of computational design and engineering Vol.9 No.2
We investigate the accuracy of direct attenuation correction (AC) in the image domain for myocardial perfusion SPECT (single-photon emission computed tomography) imaging (MPI-SPECT) using residual (ResNet) and UNet deep convolutional neural networks. MPI-SPECT 99mTc-sestamibi images of 99 patients were retrospectively included. UNet and ResNet networks were trained using non-attenuation-corrected SPECT images as input, whereas CT-based attenuation-corrected (CT-AC) SPECT images served as reference. Chang’s calculated AC approach considering a uniform attenuation coefficient within the body contour was also implemented. Clinical and quantitative evaluations of the proposed methods were performed considering SPECT CT-AC images of 19 subjects (external validation set) as reference. Image-derived metrics, including the voxel-wise mean error (ME), mean absolute error, relative error, structural similarity index (SSI), and peak signal-to-noise ratio, as well as clinical relevant indices, such as total perfusion deficit (TPD), were utilized. Overall, AC SPECT images generated using the deep learning networks exhibited good agreement with SPECT CT-AC images, substantially outperforming Chang’s method. The ResNet and UNet models resulted in an ME of −6.99 ± 16.72 and −4.41 ± 11.8 and an SSI of 0.99 ± 0.04 and 0.98 ± 0.05, respectively. Chang’s approach led to ME and SSI of 25.52 ± 33.98 and 0.93 ± 0.09, respectively. Similarly, the clinical evaluation revealed a mean TPD of 12.78 ± 9.22% and 12.57 ± 8.93% for ResNet and UNet models, respectively, compared to 12.84 ± 8.63% obtained from SPECT CT-AC images. Conversely, Chang’s approach led to a mean TPD of 16.68 ± 11.24%. The deep learning AC methods have the potential to achieve reliable AC in MPI-SPECT imaging.
Azam Eskandari,Shahrokh Nasseri,Hamid Gholamhosseinian,Sare Hosseini,Mohammad Javad Keikhai Farzaneh,Alireza Keramati,Maryam Naji,Atefeh Rostami,Mehdi Momennezhad 대한방사선종양학회 2020 Radiation Oncology Journal Vol.38 No.1
Purpose: The present study was conducted to compare dosimetric parameters for the heart and left lung between free breathing (FB) and deep inspiration breath hold (DIBH) and determine the most important potential factors associated with increasing the lung dose for left-sided breast radiotherapy using image analysis with 3D Slicer software. Materials and Methods: Computed tomography-simulation scans in FB and DIBH were obtained from 17 patients with left-sided breast cancer. After contouring, three-dimensional conformal plans were generated for them. The prescribed dose was 50 Gy to the clinical target volume. In addition to the dosimetric parameters, the irradiated volumes and both displacement magnitudes and vectors for the heart and left lung were assessed using 3D Slicer software. Results: The average of the heart mean dose (Dmean) decreased from 5.97 to 3.83 Gy and V25 from 7.60% to 3.29% using DIBH (p < 0.001). Furthermore, the average of Dmean for the left lung was changed from 8.67 to 8.95 Gy (p = 0.389) and V20 from 14.84% to 15.44% (p = 0.387). Both of the absolute and relative irradiated heart volumes decreased from 42.12 to 15.82 mL and 8.16% to 3.17%, respectively (p < 0.001); however, these parameters for the left lung increased from 124.32 to 223.27 mL (p < 0.001) and 13.33% to 13.99% (p = 0.350). In addition, the average of heart and left lung displacement magnitudes were calculated at 7.32 and 20.91 mm, respectively. Conclusion: The DIBH is an effective technique in the reduction of the heart dose for tangentially treated left sided-breast cancer patients, without a detrimental effect on the left lung.