• Korean Journal of Radiology
• /
• v.24 no.12
• /
• pp.1306-1308
• /
• 2023

• Journal of radiological science and technology
• /
• v.43 no.3
• /
• pp.195-208
• /
• 2020

Artificial intelligence(AI) is a field of computer science that is defined as allowing computers to imitate human intellectual behavior, even though AI's performance is to imitate humans. It is grafted across software-based fields with the advantages of high accuracy and speed of processing that surpasses humans. Indeed, the AI based technology has become a key technology in the medical field that will lead the development of medical image analysis. Therefore, this article introduces and discusses the concept of deep learning-based medical imaging analysis using the principle of algorithms for convolutional neural network(CNN) and back propagation. The research cases application of the AI based medical imaging analysis is used to classify the various disease(such as chest disease, coronary artery disease, and cerebrovascular disease), and the performance estimation comparing between AI based medical imaging classifier and human experts.

• Journal of radiological science and technology
• /
• v.44 no.6
• /
• pp.635-643
• /
• 2021

The results of empirical researches on the diagnosis of lung cancer are insufficient, so it is limited to objectively judge the clinical possibility and utilization according to the accuracy of diagnosis. Thus, this study retrospectively analyzed the lung cancer diagnostic performance of PET-MRI (Positron Emission Tomography-Magnetic Resonance Imaging) by using the decision matrix. This study selected and experimented total 165 patients who received both hematological CEA (Carcinoembryonic Antigen) test and hybrid PET-MRI (¹⁸F-FDG, 5.18 MBq/kg / Body TIM coil. VIVE-Dixon). After setting up the result of CEA (positive:>4 ㎍/ℓ. negative:<2.5㎍/ℓ) as golden data, the lung cancer was found in the image of PET-MRI, and then the SUV_max (positive:>4, negative:<1.5) was measured, and then evaluated the correlation and significance of results of relative diagnostic performance of PET-MRI compared to CEA through the statistical verification (t-test, P>0.05). Through this, the PET-MRI was analyzed as 96.29% of sensitivity, 95.23% of specificity, 3.70% of false negative rate, 4.76% of false positive rate, and 95.75% of accuracy. The false negative rate was 1.06% lower than the false positive rate. The PET-MRI that significant accuracy of diagnosis through high sensitivity and specificity, and low false negative rate and false positive rate of lung cancer, could acquire the fusion image of specialized soft tissue by combining the radio-pharmaceuticals with various sequences, so its clinical value and usefulness are regarded as latently sufficient.

• Progress in Medical Physics
• /
• v.32 no.4
• /
• pp.99-106
• /
• 2021

Purpose: In this study, we aimed to manufacture a patient-specific gel phantom combining three-dimensional (3D) printing and polymer gel and evaluate the radiation dose and dose profile using gel dosimetry. Methods: The patient-specific head phantom was manufactured based on the patient's computed tomography (CT) scan data to create an anatomically replicated phantom; this was then produced using a ColorJet 3D printer. A 3D polymer gel dosimeter called RTgel-100 is contained inside the 3D printing head phantom, and irradiation was performed using a 6 MV LINAC (Varian Clinac) X-ray beam, a linear accelerator for treatment. The irradiated phantom was scanned using magnetic resonance imaging (Siemens) with a magnetic field of 3 Tesla (3T) of the Korea Institute of Nuclear Medicine, and then compared the irradiated head phantom with the dose calculated by the patient's treatment planning system (TPS). Results: The comparison between the Hounsfield unit (HU) values of the CT image of the patient and those of the phantom revealed that they were almost similar. The electron density value of the patient's bone and brain was 996±167 HU and 58±15 HU, respectively, and that of the head phantom bone and brain material was 986±25 HU and 45±17 HU, respectively. The comparison of the data of TPS and 3D gel revealed that the difference in gamma index was 2%/2 mm and the passing rate was within 95%. Conclusions: 3D printing allows us to manufacture variable density phantoms for patient-specific dosimetric quality assurance (DQA), develop a customized body phantom of the patient in the future, and perform a patient-specific dosimetry with film, ion chamber, gel, and so on.

• Journal of the Korean Society of Radiology
• /
• v.8 no.5
• /
• pp.249-254
• /
• 2014

Medical linear accelerator is used for radiotherapy since it was developed in 1952, the utilization rate is further increased. It is used high energy radiotherapy using the energy of the photon of 6 MeV or more is universal at present, but the creation of the neutron by photonuclear reaction cause a problem that is radiation exposure of patients and operators. Therefore, in this study, to analyze the spectrum of the photon beam of 6 to 24 MV that occurred in the medical linear accelerator using the Monte Carlo code MCNPX, the number of photons of 7.41 MeV or more, which is a neutron production threshold energy of tungsten and average energy. The result of 24 MV in the beginning and the 8 MV was 0.59% of the total number of detected photons and it was founded that the number of photons are increased which are possible to cause the photonuclear reaction.

• Journal of radiological science and technology
• /
• v.43 no.2
• /
• pp.65-70
• /
• 2020

PA(postero-anterior) and AP(antero-posterior) chest projections are the most sought-after types of all kinds of projections. But if a radiological technologist puts wrong information about the position in the computer, the orientation of left and right side of an image would be reversed. In order to solve this problem, we utilized CNN(convolutional neural network) which has recently utilized a lot for studies of medical imaging technology and rule-based system. 70% of 111,622 chest images were used for training, 20% of them were used for testing and 10% of them were used for validation set in the CNN experiment. The same amount of images which were used for testing in the CNN experiment were used in rule-based system. Python 3.7 version and Tensorflow r1.14 were utilized for data environment. As a result, rule-based system had 66% accuracy on evaluating whether the orientation reversal on chest x-ray image. But the CNN had 97.9% accuracy on that. Being overcome limitations by CNN which had been shown on rule-based system and shown the high accuracy can be considered as a meaningful result. If some problems which can occur for tasks of the radiological technologist can be separated by utilizing CNN, It can contribute a lot to optimize workflow.

• Journal of the Korean Society of Radiology
• /
• v.1 no.1
• /
• pp.45-49
• /
• 2007

keV-neutron capture gamma-ray spectrum of $^{197}Au$(natural gold) sample have been measured in neutron energy range from 10 to 90 keV using the 3-MV pelletron accelerator of the Research Laboratory for Nuclear Reactors at the Tokyo Institute of Technology. Pulsed keV neutrons were produced from the $^7Li(p,n)^7Be$ reaction by bombarding on the $^7Li$ target with the 1.5-ns bunched proton beam. The incident neutron spectrum on the Au sample was measured by a $^6Li$-glass scintillation detector and TOF method. Capture gamma-rays from Au sample were measured by anti-Compton NaI(TI) spectrometer. Five average neutron energy regions were selected to obtain the neutron capture spectrum. Several gamma-ray peaks in the spectrum were found in the present experiment.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.4
• /
• pp.221-226
• /
• 2014

In this paper, we achieved the study which determined the excellent diagnostic condition and searched the exposure condition with the minimum radiation exposure level having the equal diagnostic ability. To accomplish these study, chest phantom images with lesions and without ones were evaluated at various exposure conditions. With respect to the phantom with lesions and without ones, we obtained the chest PA imaging applied by photographing parts of DR apparatus and the images processed as histogram equalization and edge enhancement method. The images were acquired at the exposure conditions of 2.0, 2.5, 3.2, 4.0 and 5.0mAs. The morphological analysis was performed by ROC curves using the images obtained at each exposure condition. The exposure conditions with the most excellent diagnostic ability and with the equal diagnostic capability having the minimum radiation exposure level were determined by means of sensitivity, specificity and accuracy.

• Journal of Radiation Industry
• /
• v.11 no.3
• /
• pp.131-137
• /
• 2017

To compare the radiation dose and image noise of low dose computed tomography (CT) and high resolution CT using the fixed tube current technique and automatic tube current modulation (CARE Dose 4D). Chest CT and human anthropomorphic phantom were used the RPL (radiophotoluminescence) dosimeters. For image evaluation, standard deviation of mean CT attenuation coefficient and CT attenuation coefficient was measured using ROI analysis function. The effective dose was calculated using CTDIvol and DLP. CARE Dose 4D was reduced by 74.7% and HRCT by 64.4% compared to the fixed tube current technique in low dose CT of chest phantom. In CTDIvol and DLP, the dose of CARE Dose 4D was reduced by fixed tube current technique. For effective dose, CARE Dose 4D was reduced by 47% and HRCT by 46.9% compared to the fixed tube current method, and the dose of CARE Dose 4D was significantly different (p<.05). Noise in the image was higher than that in the fixed tube current technique. Noise difference in the image of CARE Dose 4D in low dose CT was significant (p<.05). The low radiation dose and the noise difference of the CARE Dose 4D were compared with the fixed tube current technique in low dose CT and HRCT using chest phantom. The radiation doses using CARE Dose 4D were in accordance with the national and international dose standards. CARE Dose 4D should be applied to low dose CT and HRCT for clinical examination.

• Journal of radiological science and technology
• /
• v.41 no.6
• /
• pp.545-552
• /
• 2018

The purpose of this study was evaluated the relationship between echocardiography and cardiac computed tomography in normal adults by visual assessment, and evaluated the effective doses of cardiac computed tomography. The subjects were 100 normal patients who visited two general hospitals in Chungnam, from January 1 to May 30, 2018. We obtained images by using these modalities and evaluated the wall thickness and internal dimension of the Left Ventricle with visual assessment. To evaluate the appropriateness of the visual evaluation, two evaluators who were trained for one week were measured and the agreement between the evaluators were verified by statistical analysis. The effective doses of computed tomography were evaluated using the dose length product. As a result, there was a high correlation between the two modalities. The agreement between the two visual evaluator were also highly agreed. The mean X-ray dose of the subjects was $11.1{\pm}3.1mSv$. Although the purpose of imaging is somewhat different in the clinical setting, echocardiography could achieve the same results as radiation-invasive computed tomography. It is thought that utilization will become even larger.