• Journal of the Korea Computer Graphics Society
• /
• v.28 no.2
• /
• pp.11-19
• /
• 2022

Recently, various researches on medical image generation have been suggested, and it becomes crucial to accurately evaluate the quality and diversity of the generated medical images. For this purpose, the expert's visual turing test, feature distribution visualization, and quantitative evaluation through IS and FID are evaluated. However, there are few methods for quantitatively evaluating medical images in terms of fidelity and diversity. In this paper, images are generated by learning a chest CT dataset of non-small cell lung cancer patients through DCGAN and PGGAN generative models, and the performance of the two generative models are evaluated in terms of fidelity and diversity. The performance is quantitatively evaluated through IS and FID, which are one-dimensional score-based evaluation methods, and Precision and Recall, Improved Precision and Recall, which are two-dimensional score-based evaluation methods, and the characteristics and limitations of each evaluation method are also analyzed in medical imaging.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.19 no.2
• /
• pp.55-62
• /
• 2015

Purpose Various methods for reducing radiation exposure have been continuously being developed. The aim of this study is to evaluate effectiveness of dose reduction, image quality and PET SUV changes by applying combination of automatic exposure dose(AEC), automated dose-optimized selection of X-ray tube voltage(CAREkV) and sinogram affirmed iterative reconstruction(SAFIRE) which can be controled by user. Materials and Methods Torso, AAPM CT performance and IEC body phantom images were acquired using biograph mCT64, (Siemens, Germany) PET/CT scanner. Standard CT condition was 120 kV, 40 mAs. Radiation exposure and noise were evaluated by applying AEC, CAREkV(120 kV, 40 mAs) and SAFIRE(120 kV, 25 mAs) with torso phantom compare to standard CT condition. And torso, AAPM and IEC phantom images were acquired with combination of 3 methods in condition of 120 kV, 25 mAs to evaluate radiation exposure, noise, spatial resolution and SUV changes. Results When applying AEC, CTDIvol and DLP were decreased by 50.52% and 50.62% compare to images which is not applying AEC. mAs was increased by 61.5% to compensate image quality according to decreasing 20 kV when applying CAREkV. However, CTDIvol and DLP were decreased by 6.2% and 5.5%. When reference mAs was the lower and strength was the higher, reduction of radiation exposure rate was the bigger. Mean SD and DLP were decreased by 2.2% and 38% when applying SAFIRE even though mAs was decreased by 37.5%(from 40 mAs to 25 mAs). Combination of 3 methods test, SD decreased by 5.17% and there was no significant differences in spatial resolution. And mean SD and DLP were decreased by 6.7% and 36.9% compare to 120 kV, 40 mAs with AEC. For SUV test, there was no statistical differences(P>0.05). Conclusion Combination of 3 methods shows dose reduction effect without degrading image quality and SUV changes. To reduce radiation exposure in PET/CT study, continuous effort is needed by optimizing various dose reduction methods.

• Journal of Korea Multimedia Society
• /
• v.23 no.3
• /
• pp.468-475
• /
• 2020

In this paper, we proposed a three-dimensional visualization system for medical images in augmented reality based on deep learning. In the proposed system, the artificial neural network model performed fully automatic segmentation of the region of lung and pulmonary nodule from chest CT images. After applying the three-dimensional volume rendering method to the segmented images, it was visualized in augmented reality devices. As a result of the experiment, when nodules were present in the region of lung, it could be easily distinguished with the naked eye. Also, the location and shape of the lesions were intuitively confirmed. The evaluation was accomplished by comparing automated segmentation results of the test dataset to the manual segmented image. Through the evaluation of the segmentation model, we obtained the region of lung DSC (Dice Similarity Coefficient) of 98.77%, precision of 98.45%, recall of 99.10%. And the region of pulmonary nodule DSC of 91.88%, precision of 93.05%, recall of 90.94%. If this proposed system will be applied in medical fields such as medical practice and medical education, it is expected that it can contribute to custom organ modeling, lesion analysis, and surgical education and training of patients.

• Journal of the Korean Society of Radiology
• /
• v.13 no.1
• /
• pp.111-118
• /
• 2019

Chest digital tomosynthesis has become a practical imaging modality because it can solve the problem of anatomy overlapping in conventional chest radiography. However, because of both limited scan angle and finite-size detector, a portion of chest cannot be represented in some or all of the projection. These bring a discontinuity in intensity across the field of view boundaries in the reconstructed slices, which we refer to as the truncation artifacts. The purpose of this study was to reduce truncation artifacts using a weighted normalization approach and to investigate the performance of this approach for our prototype chest digital tomosynthesis system. The system source-to-image distance was 1100 mm, and the center of rotation of X-ray source was located on 100 mm above the detector surface. After obtaining 41 projection views with ${\pm}20^{\circ}$ degrees, tomosynthesis slices were reconstructed with the filtered back projection algorithm. For quantitative evaluation, peak signal to noise ratio and structure similarity index values were evaluated after reconstructing reference image using simulation, and mean value of specific direction values was evaluated using real data. Simulation results showed that the peak signal to noise ratio and structure similarity index was improved respectively. In the case of the experimental results showed that the effect of artifact in the mean value of specific direction of the reconstructed image was reduced. In conclusion, the weighted normalization method improves the quality of image by reducing truncation artifacts. These results suggested that weighted normalization method could improve the image quality of chest digital tomosynthesis.

• Progress in Medical Physics
• /
• v.11 no.1
• /
• pp.59-71
• /
• 2000

It is possible to obtain a fast CT scan during breath holding with spiral technique. But the risk of radiation is increased due to detailed and repeated scans. However, the limitation of X-ray doses is not fully specified on CT, yet. Therefore, the purpose of the present study is to define the limitation of X-ray doses on CT The CT unit was somatom plus 4. Alderson Rando phantom, Solenoid water phantom, TLD, and reader were used. For determining adequate position and size of organs, the measurement of distance(${\pm}$2mm) from the midline of vertebral body was performed in 40 women(20~40 years). On the brain scan for 8:8(8mm slice thickness, 8mm/sec movement velocity of the table) and 10:10(10mm slice thickness, 10mm/sec movement velocity of the table) methods, the absorption doses of exposed area of the 10:10 were slightly higher than those of 8:8. The doses of unexposed uterus were negligible on the brain scan for both 8:8 and 10:10. On the chest scan for 8:8, 8:10(8mm slice thickness, 10mm/sec movement velocity of the table), 10:10, 10:12(10mm slice thickness, 12mm/sec movement velocity of the table) and 10:15(10mm slice thickness, 15mm/sec movement velocity of the table) methods, 8:8 method of the absorption doses of exposure area was the most highest and 10:15 method was the most lowest. The absorption doses of 8:10 method was relatively lower than those of the other methods. In conclusion, the 8:10 method is the most suitable to give a low radiation burden to patient without distorting image quality.

• Journal of the Korean Society of Radiology
• /
• v.6 no.4
• /
• pp.281-290
• /
• 2012

The difference of radiation dose of MDCT due to different protocols between hospitals was analyzed by CTDI, DLP, the number of Slice and the number of DLP/Slice in 30 cases of the head, the abdomen and the chest that have 10 cases each from MDCT examination of the department of diagnostic imaging of three general hospitals in Gyeongsangbuk-do. The difference of image quality, CTDI, DLP, radiation dose in the eye and radiation dose in thyroid was analyzed after both helical scan and normal scan for head CT were performed because a protocol of head CT is relatively simple and head CT is the most frequent case. Head CT was significantly higher in two-thirds of hospitals compared to A hospital that does not exceed a CTDI diagnostic reference level (IAEA 50mGy, Korea 60mGy) (p<0.001). DLP was higher in one-third of hospitals than a diagnostic reference level of IAEA 1,050mGy.cm and Korea 1,000mGy.cm and two-thirds exceeded the recommendation of Korea and those were significantly higher than A hospital that does not exceed a diagnostic reference level (p<0.001). Abdomen CT showed 119mGy that was higher than a diagnostic reference level of IAEA 25mGy and Korea 20mGy in one-third. DLP in all hospitals was higher that Korea recommendation of 700mGy.cm. Among target hospitals, C hospital showed high radiation dose in all tests because MPR and 3D were of great importance due to low pitch and high Tube Curren. To analyze the difference of radiation dose by scan methods, normal scan and helical scan for head CT of the same patient were performed. In the result, CTDI and DLP of helical CT were higher 63.4% and 93.7% than normal scan (p<0.05, p<0.01). However, normal scan of radiation dose in thyroid was higher 87.26% (p<0.01). Beam of helical CT looked like a bell in the deep part and the marginal part so thyroid was exposed with low radiation dose deviated from central beam. In addition, helical scan used Gantry angle perpendicularly and normal scan used it parallel to the orbitomeatal line. Therefore, radiation dose in thyroid decreased in helical scan. However, a protocol in this study showed higher radiation dose than diagnostic reference level of KFDA. To obey the recommendation of KFDA, low Tube Curren and high pitch were demanded. In this study, the difference of image quality between normal scan and helical scan was not significant. Therefore, a standardized protocol of normal scan was generally used and protective gear for thyroid was needed except a special case. We studied a part of CT cases in the local area. Therefore, the result could not represent the entire cases. However, we confirmed that patient's radiation dose in some cases exceeded the recommendation and the deviation between hospitals was observed. To improve this issue, doctors of diagnostic imaging or technologists of radiology should perform CT by the optimized protocol to decrease a level of CT radiation and also reveal radiation dose for the right to know of patients. However, they had little understanding of the situation. Therefore, the effort of relevant agencies with education program for CT radiation dose, release of radiation dose from CT examination and addition of radiation dose control and open CT contents into evaluation for hospital services and certification, and also the effort of health professionals with the best protocol to realize optimized CT examination.

• Journal of the Korean Society of Radiology
• /
• v.3 no.1
• /
• pp.29-39
• /
• 2009

In this paper has proposed to the recognition of the disease on medical images using neural network. The neural network is constructed as three-layers of the input-layer, the hidden-layer and the output-layer. The training method applied for the recognition of disease region is adaptive error back-propagation. The low-frequency region analyzed by DWT are expressed by matrix. The coefficient-values of the characteristic polynomial applied are n+1. The normalized maximum value +1 and minimum value -1 in the range of tangent-sigmoid transfer function are applied to be use as the input vector of the neural network. To prove the validity of the proposed methods used in the experiment with a simulation experiment, the input medical image recognition rate the evaluation of areas of disease. As a result of the experiment, the characteristic polynomial coefficient of low-frequency area matrix, conversed to 4 level DWT, was proved to be optimum to be applied to the feature parameter. As for the number of training, it was marked fewest in 0.01 of learning coefficient and 0.95 of momentum, when the adaptive error back-propagation was learned by inputting standardized feature parameter into organized neural network. As to the training result when the learning coefficient was 0.01, and momentum was 0.95, it was 100% recognized in fifty-five times of the stomach image, fifty-five times of the chest image, forty-six times of the CT image, fifty-five times of ultrasonogram, and one hundred fifty-seven times of angiogram.

• Radiation Oncology Journal
• /
• v.27 no.1
• /
• pp.42-48
• /
• 2009

Purpose: The introduction of image guided radiation therapy/four-dimensional radiation therapy (IGRT/4DRT) potentially increases the accumulated dose to patients from imaging and verification processes as compared to conventional practice. It is therefore essential to investigate the level of the imaging dose to patients when IGRT/4DRT devices are installed. The imaging dose level was monitored and was compared with the use of pre-IGRT practice. Materials and Methods: A four-dimensional CT (4DCT) unit (GE, Ultra Light Speed 16), a simulator (Varian Acuity) and Varian IX unit with an on-board imager (OBI) and cone beam CT (CBCT) were installed. The surface doses to a RANDO phantom (The Phantom Laboratory, Salem, NY USA) were measured with the newly installed devices and with pre-existing devices including a single slice CT scanner (GE, Light Speed), a simulator (Varian Ximatron) and L-gram linear accelerator (Varian, 2100C Linac). The surface doses were measured using thermo luminescent dosimeters (TLDs) at eight sites-the brain, eye, thyroid, chest, abdomen, ovary, prostate and pelvis. Results: Compared to imaging with the use of single slice non-gated CT, the use of 4DCT imaging increased the dose to the chest and abdomen approximately ten-fold ($1.74{\pm}0.34$ cGy versus $23.23{\pm}3.67$cGy). Imaging doses with the use of the Acuity simulator were smaller than doses with the use of the Ximatron simulator, which were $0.91{\pm}0.89$ cGy versus $6.77{\pm}3.56$ cGy, respectively. The dose with the use of the electronic portal imaging device (EPID; Varian IX unit) was approximately 50% of the dose with the use of the L-gram linear accelerator ($1.83{\pm}0.36$ cGy versus $3.80{\pm}1.67$ cGy). The dose from the OBI for fluoroscopy and low-dose mode CBCT were $0.97{\pm}0.34$ cGy and $2.3{\pm}0.67$ cGy, respectively. Conclusion: The use of 4DCT is the major source of an increase of the radiation (imaging) dose to patients. OBI and CBCT doses were small, but the accumulated dose associated with everyday verification need to be considered.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.20 no.1
• /
• pp.13-19
• /
• 2016

Purpose In order to calculate the left ventricular ejection fraction (LVEF) accurately, it is important to acquire the best septal view of left ventricle in the multi-gated cardiac blood pool scan (GBP). This study aims to acquire the best septal view by measuring angle of ventricular septal wall (${\theta}$) using enhanced CT scan and compare with conventional method using left anterior oblique (LAO) 45 view. Materials and Methods From March to July in 2015, we analyzed the 253 patients who underwent both enhanced chest CT and GBP scan in the department of nuclear medicine at National Cancer Center. Angle (${\theta}$) between ventricular septum and imaginary midline was measured in transverse image of enhanced chest CT scan, and the patients whose difference between the angle of ${\theta}$ and 45 degree was more than 10 degrees were included. GBP scan was acquired using both LAO 45 and LAO ${\theta}$ views, and LVEFs measured by automated and manual region of interest (Auto-ROI and Manual-ROI) modes respectively were analyzed. Results $Mean{\pm}SD$ of ${\theta}$ on total 253 patients was $37.0{\pm}8.5^{\circ}$. Among them, the patients whose difference between 45 and ${\theta}$ degrees were more than ${\pm}10$ degrees were 88 patients ($29.3{\pm}6.1^{\circ}$). In Auto-ROI mode, there was statistically significant difference between LAO 45 and LAO ${\theta}$ (LVEF $45=62.0{\pm}6.6%$ vs. LVEF ${\theta}=64.0{\pm}5.6%$; P = 0.001). In Manual-ROI mode, there was also statistically significant difference between LAO 45 and LAO ${\theta}$ (LVEF $45=66.7{\pm}7.2%$ vs. LVEF ${\theta}=69.0{\pm}6.4%$; P < 0.001). Intraclass correlation coefficients of both methods were more than 95%. In case of comparison between Auto-ROI and Manual ROI of each LAO 45 and LAO ${\theta}$, there was no significant difference statistically. Conclusion We could measure the angle of ventricular septal wall accurately by using transverse image of enhanced chest CT and applied to LAO acquisition in the GBP scan. It might be the alternative method to acquire the best septal view of LAO effectively. We could notify significant difference between conventional LAO 45 and LAO ${\theta}$ view.

• The Journal of Korean Society for Radiation Therapy
• /
• v.15 no.1
• /
• pp.53-60
• /
• 2003

I. Purpose It is essential to have the correct body contour information for the calculation of dose distribution. The role of CT images in the radiation oncology field has been increased. But there still exists a method to use cast or lead wire for the body contour drawing. This traditional method has drawbacks such as in accurate and time consuming procedure. This study has been designed to overcome this problem. II. Materials and Methods A digital camera is attached to a pole which stands on the opposite side of the gantry. Positional information was acquired from an image of the phantom which is specially designed for this study and located on the isocenter level of the simulator Laser line on the patients skin or on the phantom surface was digitized and reconstructed as the contour. Verification of usefulness this technique has been done with various shape of phantoms and a patients chest III. Results and Conclusions Contours from the traditional method with the cast or lead wire and the digital image method showed good agreement within experimetal error range. This technique showed more efficiente in time and convenience. For irregular shaped contour, like H&N region, special care are needed. The results suggest that more study is needed. To use of the another photogrammatory techinique with two camera system may be better for the actual clinical application