• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2352-2355
• /
• 2003

In recent yeas, studies on computer aided diagnosis (CAD) using image analysis on CT images have been conducted with respect to various diseases. Extracting ground-glass opacities (GGO) on lung CT images is one of such subjects, though it has not found an established method yet. If the region of ground-glass opacities is large on CT images, it can be detected without much difficulty. On the other hand, if the region is small, it is still difficult to find it exactly. In the latter case, increasing overlooking possibility cannot be avoided according to smaller size of the region. To solve this difficulty, this paper proposes an automatic technique for extracting ground-glass opacities on lung CT images employing some statistical parameters of a gray level histogram and a differential histogram. The proposed technique is applied to some lung CT images in the performed experiment. The results are shown with discussion on future work.

• Journal of Biomedical Engineering Research
• /
• v.44 no.5
• /
• pp.303-314
• /
• 2023

This study aimed to assess the practical feasibility of advanced deformable image registration (DIR) algorithms in radiotherapy by employing two distinct datasets. The first dataset included 14 4D lung CT scans and 31 head and neck CT scans. In the 4D lung CT dataset, we employed the DIR algorithm to register organs at risk and tumors based on respiratory phases. The second dataset comprised pre-, mid-, and post-treatment CT images of the head and neck region, along with organ at risk and tumor delineations. These images underwent registration using the DIR algorithm, and Dice similarity coefficients (DSCs) were compared. In the 4D lung CT dataset, registration accuracy was evaluated for the spinal cord, lung, lung nodules, esophagus, and tumors. The average DSCs for the non-learning-based SyN and NiftyReg algorithms were 0.92±0.07 and 0.88±0.09, respectively. Deep learning methods, namely Voxelmorph, Cyclemorph, and Transmorph, achieved average DSCs of 0.90±0.07, 0.91±0.04, and 0.89±0.05, respectively. For the head and neck CT dataset, the average DSCs for SyN and NiftyReg were 0.82±0.04 and 0.79±0.05, respectively, while Voxelmorph, Cyclemorph, and Transmorph showed average DSCs of 0.80±0.08, 0.78±0.11, and 0.78±0.09, respectively. Additionally, the deep learning DIR algorithms demonstrated faster transformation times compared to other models, including commercial and conventional mathematical algorithms (Voxelmorph: 0.36 sec/images, Cyclemorph: 0.3 sec/images, Transmorph: 5.1 sec/images, SyN: 140 sec/images, NiftyReg: 40.2 sec/images). In conclusion, this study highlights the varying clinical applicability of deep learning-based DIR methods in different anatomical regions. While challenges were encountered in head and neck CT registrations, 4D lung CT registrations exhibited favorable results, indicating the potential for clinical implementation. Further research and development in DIR algorithms tailored to specific anatomical regions are warranted to improve the overall clinical utility of these methods.

• Journal of Korea Multimedia Society
• /
• v.8 no.5
• /
• pp.641-650
• /
• 2005

In this parer, curve stopping function based on the CT number of lung parenchyma from CT lung images is proposed to detect lung region in replacement of conventional edge indication function in geodesic active contour model. We showed that the proposed method was able to detect lung region more effectively than conventional method by applying three kinds of measurement numerically. And, we verified the effectiveness of proposed method visually by observing the detection Procedure on actual CT images. Because lung parenchyma region could be precisely detected from actual EBCT (electron beam computer tomography) lung images, we were sure that the Proposed method could aid to early diagnosis of lung disease and local abnormality of function.

• Journal of Radiation Protection and Research
• /
• v.40 no.1
• /
• pp.17-24
• /
• 2015

To improve accuracy of dose calculation on kilovoltage cone beam computed tomography (kV CBCT) images, a custom-made phantom was fabricated to acquire an accurate CT number to electron density curve by full scatter of cone beam x-ray. To evaluate the dosimetric accuracy, 9 volumetric modulated arc therapy (VMAT) plans for head and neck (HN) cancer and 9 VMAT plans for lung cancer were generated with an anthropomorphic phantom. Both CT and CBCT images of the anthropomorphic phantom were acquired and dose-volumetric parameters on the CT images with CT density curve (CTCT), CBCT images with CT density curve ($CBCT_{CT}$) and CBCT images with CBCT density curve ($CBCT_{CBCT}$) were calculated for each VMAT plan. The differences between $CT_{CT}$ vs. $CBCT_{CT}$ were similar to those between $CT_{CT}$ vs. $CBCT_{CBCT}$ for HN VMAT plans. However, the differences between $CT_{CT}$ vs. $CBCT_{CT}$ were larger than those between $CT_{CT}$ vs. $CBCT_{CBCT}$ for lung VMAT plans. Especially, the differences in $D_{98%}$ and $D_{95%}$ of lung target volume were statistically significant (4.7% vs. 0.8% with p = 0.033 for $D_{98%}$ and 4.8% vs. 0.5% with p = 0.030 for $D_{95%}$). In order to calculate dose distributions accurately on the CBCT images, CBCT density curve generated with full scatter condition should be used especially for dose calculations in the region of large inhomogeneity.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.13 no.1
• /
• pp.82-85
• /
• 2009

Purpose: The purpose of this study was to evaluate the effect of extended CT field of view (FOV) on PET/CT of Standardized uptake value (SUV) when imaging extends beyond the CT FOV. Materials and Methods: CT images were reconstructed at different FOV sizes (500 and 700 mm). Two sets of CT images were reconstructed from the CT projection data by using two FOV sizes. Twenty patients were used in this study. PET images were reconstructed using attenuation maps with 500 mm CT FOV and 700 mm extended CT FOV images. Region of interests (ROIs) drawn on the PET images. In addition, twenty patients' PET images reconstructed by 500 mm CT FOV and 700 mm extended CT FOV were compared with $SUV_{max}$. Results: When using attenuation maps with 700 mm extended CT FOV, the $SUV_{max}$ analysis of liver (p=0.000), lung (p=0.007), mediastinum (p=0.001) were statistically significant. Conclusions: 700 mm extended CT FOV helps to recover the true activity distribution in the PET emission data. In addition, 700 mm extended CT FOV has affected SUV measurement of liver, lung, mediastinum.

• Korean Journal of Radiology
• /
• v.22 no.3
• /
• pp.476-488
• /
• 2021

Objective: We aimed to develop a deep neural network for segmenting lung parenchyma with extensive pathological conditions on non-contrast chest computed tomography (CT) images. Materials and Methods: Thin-section non-contrast chest CT images from 203 patients (115 males, 88 females; age range, 31-89 years) between January 2017 and May 2017 were included in the study, of which 150 cases had extensive lung parenchymal disease involving more than 40% of the parenchymal area. Parenchymal diseases included interstitial lung disease (ILD), emphysema, nontuberculous mycobacterial lung disease, tuberculous destroyed lung, pneumonia, lung cancer, and other diseases. Five experienced radiologists manually drew the margin of the lungs, slice by slice, on CT images. The dataset used to develop the network consisted of 157 cases for training, 20 cases for development, and 26 cases for internal validation. Two-dimensional (2D) U-Net and three-dimensional (3D) U-Net models were used for the task. The network was trained to segment the lung parenchyma as a whole and segment the right and left lung separately. The University Hospitals of Geneva ILD dataset, which contained high-resolution CT images of ILD, was used for external validation. Results: The Dice similarity coefficients for internal validation were 99.6 ± 0.3% (2D U-Net whole lung model), 99.5 ± 0.3% (2D U-Net separate lung model), 99.4 ± 0.5% (3D U-Net whole lung model), and 99.4 ± 0.5% (3D U-Net separate lung model). The Dice similarity coefficients for the external validation dataset were 98.4 ± 1.0% (2D U-Net whole lung model) and 98.4 ± 1.0% (2D U-Net separate lung model). In 31 cases, where the extent of ILD was larger than 75% of the lung parenchymal area, the Dice similarity coefficients were 97.9 ± 1.3% (2D U-Net whole lung model) and 98.0 ± 1.2% (2D U-Net separate lung model). Conclusion: The deep neural network achieved excellent performance in automatically delineating the boundaries of lung parenchyma with extensive pathological conditions on non-contrast chest CT images.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.16 no.2
• /
• pp.68-80
• /
• 2012

Purpose : More recently, combined PET/MR scanners have been developed in which the MR data can be used for both anatometabolic image formation and attenuation correction of the PET data. For quantitative PET information, correction of tissue photon attenuation is mandatory. The attenuation map is obtained from the CT scan in the PET/CT. In the case of PET/MR, the attenuation map can be calculated from the MR image. The purpose of this study was to assess the quantitative differences between MR-based and CT-based attenuation corrected PET images. Materials and Methods : Using the uniform cylinder phantom of distilled water which has 199.8 MBq of $^{18}F$-FDG put into the phantom, we studied the effect of MR-based and CT-based attenuation corrected PET images, of the PET-CT using time of flight (TOF) and non-TOF iterative reconstruction. The images were acquired from 60 minutes at 15-minute intervals. Region of interests were drawn over 70% from the center of the image, and the Scanners' analysis software tools calculated both maximum and mean SUV. These data were analyzed by one way-anova test and Bland-Altman analysis. MR images are segmented into three classes(not including bone), and each class is assigned to each region based on the expected average attenuation of each region. For clinical diagnostic purpose, PET/MR and PET/CT images were acquired in 23 patients (Ingenuity TF PET/MR, Gemini TF64). PET/CT scans were performed approximately 33.8 minutes after the beginnig of the PET/MR scans. Region of interests were drawn over 9 regions of interest(lung, liver, spleen, bone), and the Scanners' analysis software tools calculated both maximum and mean SUV. The SUVs from 9 regions of interest in MR-based PET images and in CT-based PET images were compared. These data were analyzed by paired t test and Bland-Altman analysis. Results : In phantom study, MR-based attenuation corrected PET images generally showed slightly lower -0.36~-0.15 SUVs than CT-based attenuation corrected PET images (p<0.05). In clinical study, MR-based attenuation corrected PET images generally showed slightly lower SUVs than CT-based attenuation corrected PET images (excepting left middle lung and transverse Lumbar) (p<0.05). And percent differences were -8.01.79% lower for the PET/MR images than for the PET/CT images. (excepting lung) Based on the Bland-Altman method, the agreement between the two methods was considered good. Conclusion : PET/MR confirms generally lower SUVs than PET/CT. But, there were no difference in the clinical interpretations made by the quantitative comparisons with both type of attenuation map.

• Journal of radiological science and technology
• /
• v.35 no.1
• /
• pp.59-64
• /
• 2012

Recently, SPECT/CT system has been applied to many diseases, however, the application is not extensively applied at pulmonary disease. Especially, in case that, the pulmonary embolisms suspect at the CT images, SPECT is performed. For the accurate diagnosis, SPECT/CT tests are subsequently undergoing.However, without SPECT/CT, there are some limitations to apply these procedures. With SPECT/CT, although, most of the examination performed after CT. Moreover, such a test procedures generate unnecessary dual irradiation problem to the patient. In this study, we evaluated the amount of unnecessary irradiation, and the usefulness of fusion images of pulmonary disease, which independently acquired from SPECT and CT. Using NEMA PhantomTM (NU2-2001), SPECT and CT scan were performed for fusion images. From June 2011 to September 2010, 10 patients who didn't have other personal history, except lung disease were selected (male: 7, female: 3, mean age: $65.3{\pm}12.7$). In both clinical patient and phantom data, the fusion images scored higher than SPECT and CT images. The fusion images, which is combined with pulmonary vessel images from CT and functional images from SPECT, can increase the detection possibility in detecting pulmonary embolism in the resin of lung parenchyma. It is sure that performing SPECT and CT in integral SPECT/CT system were better. However, we believe this protocol can give more informative data to have more accurate diagnosis in the hospital without integral SPECT/CT system.

• Tuberculosis and Respiratory Diseases
• /
• v.57 no.6
• /
• pp.515-521
• /
• 2004

With the increasing resolution of modern CT scanners, analysis of the larger numbers of images acquired in a lung screening exam or diagnostic study is necessary, which also needs high accuracy and reproducibility. Recent developments in the computerized analysis of medical images are expected to aid radiologists and other healthcare professional in various diagnostic tasks of medical image interpretation. This article is to provide a brief overview of some of computer-aided diagnosis schemes in chest CT.

• Advances in nano research
• /
• v.12 no.2
• /
• pp.185-195
• /
• 2022

Deep learning is another field of artificial intelligence (AI) utilized for computer aided diagnosis (CAD) and image processing in scientific research. Considering numerous mechanical repetitive tasks, reading image slices need time and improper with geographical limits, so the counting of image information is hard due to its strong subjectivity that raise the error ratio in misdiagnosis. Regarding the highest mortality rate of Lung cancer, there is a need for biopsy for determining its class for additional treatment. Deep learning has recently given strong tools in diagnose of lung cancer and making therapeutic regimen. However, identifying the pathological lung cancer's class by CT images in beginning phase because of the absence of powerful AI models and public training data set is difficult. Convolutional Neural Network (CNN) was proposed with its essential function in recognizing the pathological CT images. 472 patients subjected to staging FDG-PET/CT were selected in 2 months prior to surgery or biopsy. CNN was developed and showed the accuracy of 87%, 69%, and 69% in training, validation, and test sets, respectively, for T1-T2 and T3-T4 lung cancer classification. Subsequently, CNN (or deep learning) could improve the CT images' data set, indicating that the application of classifiers is adequate to accomplish better exactness in distinguishing pathological CT images that performs better than few deep learning models, such as ResNet-34, Alex Net, and Dense Net with or without Soft max weights.