• Journal of the Korean Society of Radiology
• /
• v.16 no.5
• /
• pp.595-602
• /
• 2022

This study tried to suggest the most efficient learning rate for accurate and efficient automatic diagnosis of medical images for chest X-ray pneumonia images using deep learning. After setting the learning rates to 0.1, 0.01, 0.001, and 0.0001 in the Inception V3 deep learning model, respectively, deep learning modeling was performed three times. And the average accuracy and loss function value of verification modeling, and the metric of test modeling were set as performance evaluation indicators, and the performance was compared and evaluated with the average value of three times of the results obtained as a result of performing deep learning modeling. As a result of performance evaluation for deep learning verification modeling performance evaluation and test modeling metric, modeling with a learning rate of 0.001 showed the highest accuracy and excellent performance. For this reason, in this paper, it is recommended to apply a learning rate of 0.001 when classifying the presence or absence of pneumonia on chest X-ray images using a deep learning model. In addition, it was judged that when deep learning modeling through the application of the learning rate presented in this paper could play an auxiliary role in the classification of the presence or absence of pneumonia on chest X-ray images. In the future, if the study of classification for diagnosis and classification of pneumonia using deep learning continues, the contents of this thesis research can be used as basic data, and furthermore, it is expected that it will be helpful in selecting an efficient learning rate in classifying medical images using artificial intelligence.

• Journal of the Korean Society of Radiology
• /
• v.84 no.4
• /
• pp.809-823
• /
• 2023

Trauma is an injury to the body that involves multiple anatomical and pathophysiological changes caused by forces acting from outside the body. The number of patients with trauma is increasing as our society becomes more sophisticated. The importance and demand of traumatology are growing due to the development and spread of treatment and diagnostic technologies. In particular, damage to the large blood vessels of the chest can be life-threatening, and the sequelae are often severe; therefore, diagnostic and therapeutic methods are becoming increasingly important. Trauma to nonaortic vessels of the thorax and aorta results in varying degrees of physical damage depending on the mechanism of the accident and anatomical damage involved. The main damage is hemorrhage from non-aortic vessels of the thorax and aorta, accompanied by hemodynamic instability and coagulation disorders, which can be life-threatening. Immediate diagnosis and rapid therapeutic access can often improve the prognosis. The treatment of trauma can be surgical or interventional, depending on the patient's condition. Among them, interventional procedures are increasingly gaining popularity owing to their convenience, rapidity, and high therapeutic effectiveness, with increasing use in more trauma centers worldwide. Typical interventional procedures for patients with thoracic trauma include embolization for non-aortic injuries and thoracic endovascular aortic repair for aortic injuries. These procedures have many advantages over surgical treatments, such as fewer internal or surgical side effects, and can be performed more quickly than surgical procedures, contributing to improved outcomes for patients with trauma.

• Journal of the Korean Society of Radiology
• /
• v.84 no.6
• /
• pp.1324-1336
• /
• 2023

Purpose This study aimed to compare the diagnostic performance of cardiac CT and transthoracic echocardiogram (TTE) depending on the degree of valvular calcification and bicuspid aortic valve (BAV) subtype. Materials and Methods This retrospective study included 266 consecutive patients (106 with BAV and 160 with tricuspid aortic valve) who underwent cardiac CT and TTE before aortic valve replacement. Cardiac CT was used to evaluate the morphology of the aortic valve, and a calcium scoring scan was used to quantify valve calcium. The aortic valves were classified into fused and two-sinus types. The diagnostic accuracy of cardiac CT and TTE was calculated using a reference standard for intraoperative inspection. Results CT demonstrated significantly higher sensitivity, negative predictive value, and accuracy than TTE in detecting BAV (p < 0.001, p < 0.001, and p = 0.003, respectively). The TTE sensitivity tended to decrease as valvular calcification increased. The error rate of TTE for CT was 10.9% for the twosinus type of BAV and 28.3% for the fused type (p = 0.044). Conclusion Cardiac CT had a higher diagnostic performance in detecting BAV than TTE and may help diagnose BAV, particularly in patients with severe valvular calcification.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.133-134
• /
• 2015

흉부 X-ray 영상에서 몸체 및 관심영역 분할 기법은 의료 X-ray 영상의 화질 개선 알고리즘을 더 효과적으로 적용하기 위해 전처리 단계로 영상의 물체와 배경을 분할하거나 관심영역만을 분할하는 방법이다. 보통 화질 개선 알고리즘을 적용할 때 영상의 밝기 정보나 주파수 정보를 이용하여 영상 디테일과 대비를 개선하는 방법을 사용한다. 영상 전체에 이러한 알고리즘을 적용하는 경우 불필요한 배경 정보가 포함되기 때문에 디테일과 대비가 떨어질 수 있다. 본 논문은 사용자가 보고자 하는 부분의 정보만을 사용하도록 물체를 분할하는 알고리즘을 제안한다. 1 단계로 몸체 분할 알고리즘을 이용하여 배경 성분의 정보를 제외하고 2 단계에서는 몸체의 중심인 폐와 폐사이의 장기 정보만을 볼 때의 관심영역 분할 알고리즘으로 팔이나 목, 복부의 불필요한 정보를 제외하는 방법을 제안한다.

• The Journal of the Korea Contents Association
• /
• v.11 no.2
• /
• pp.322-330
• /
• 2011

To compare of quality control for chest radiography between special examination (SEP) and medical institution for pneumoconiosis (MIP). For the first time, we had visited at 33 institutions (SEP; 17 institutions, MIP; 16 institutions) to evaluate the quality control of chest radiography which is used in diagnosis of patients with pneumoconiotic complications. Image quality was rated by two experienced chest radiologists, and evaluated for radiological technique (RT), reading environment (RE) and image quality (IQ) between SEP and MIP according to the guideline published by OSHRI. Generator capacity, used duration and modality of chest radiography equipment were not signigicant difference between SEP and MIP, but there were signigicant difference in tube voltage and grid ratio used for chest radiography except to tube current and exposure time. SEP was statistically significant higher in RT (71.2 vs. 54.5, p=0.015), RE (78.8 vs. 51.5, p=0.007) to MIP, but not significant difference in IQ (64.8 vs. 59.3, p=0.180). For reliable and precisional diagnosis of patients with pneumoconiotic complications, the MIP requires the evaluation and education of quality control for improving chest radiography.

• Journal of the Korean Society of Radiology
• /
• v.82 no.4
• /
• pp.817-825
• /
• 2021

Hypersensitivity pneumonitis (HP) is an interstitial lung disease (ILD) characterized by an inhaled inciting antigen that leads to the inflammation of the lung parenchyma and small airway with immunologic reactions. Over the last decades, the most effective therapeutic option for HP has been limited to antigen avoidance. The differential diagnosis of HP from other ILDs is the beginning of treatment as well as diagnosis. However, the presence of several overlapping clinical and radiologic features makes differentiating HP from other ILDs particularly challenging. In 2020, a multidisciplinary committee of experts from the American Thoracic Society, Japanese Respiratory Society, and Asociación Latinoamericana del Tórax suggested a new clinical practice guideline classifying HP into nonfibrotic and fibrotic phenotypes on the basis of chest high-resolution CT (HRCT) findings. Therefore, we introduced a new diagnostic algorithm based on chest HRCT in the clinical practice guideline for the diagnosis of HP.

• The Journal of the Korea Contents Association
• /
• v.13 no.3
• /
• pp.204-210
• /
• 2013

The patients who had been operated total mastectomy are different from general women in their breasts thickness due to breast surgery. As a result, digital chest image from total mastectomy patients will be different attenuation. The main objective for this study is to show that a proper Ion chamber standard combination measuring MTF which is objective basis for Digital image, when be x-ray for total mastectomy patient. We have designed the unique number that shown Left is 1, Right is 2, Center is 3 and have put the edge phantom on detector ion chamber. Lastly, we have obtained experiment images. The evaluations of all image quality have measured by 50% MTF of spatial resolution and absorption dose using Matlab(R2007a). The result showed that average exposure condition, MTF value, absorption dose for 1+3 and 2+3 combinations were 2.745 mAs, 1.925 lp/mm, 0.688 mGy. Consequently, that showed high MTF, DQE and low dose than other combinations. Therefore, a proper changes of ion chambers are able to improve image quality and to reduce radiation exposure when be X-ray for total mastectomy patients. Also, it will be possible to standard for application chamber combination and utilization on clinical detection.

• Journal of KIISE:Software and Applications
• /
• v.33 no.11
• /
• pp.942-952
• /
• 2006

We propose an automatic segmentation method for identifying pulmonary structures using gray-level information of chest CT images. Our method consists of following five steps. First, to segment pulmonary structures based on the difference of gray-level value, we select the threshold using optimal thresholding. Second, we separate the thorax from the background air and then the lungs and airways from the thorax by applying the inverse operation of 2D region growing in chest CT images. To eliminate non-pulmonary structures which has similar intensities with the lungs, we use 3D connected component labeling. Third, we segment the trachea and left and right mainstem bronchi using 3D branch-based region growing in chest CT images. Fourth, we can obtain accurate lung boundaries by subtracting the result of third step from the result of second step. Finally, we select the threshold in accordance with histogram analysis and then segment radio-dense pulmonary vessels by applying gray-level thresholding to the result of the second step. To evaluate the accuracy of proposed method, we make a visual inspection of segmentation result of lungs, airways and pulmonary vessels. We compare the result of the conventional region growing with the result of proposed 3D branch-based region growing. Experimental results show that our proposed method extracts lung boundaries, airways, and pulmonary vessels automatically and accurately.

• Journal of the Korean Society of Radiology
• /
• v.15 no.5
• /
• pp.613-620
• /
• 2021

The purpose of this study is to propose a convolutional neural network model that can classify normal and abnormal(cardiomegaly) in chest X-ray images. The training data and test data used in this paper were used by acquiring chest X-ray images of patients diagnosed with normal and abnormal(cardiomegaly). Using the proposed deep learning model, we classified normal and abnormal(cardiomegaly) images and verified the classification performance. When using the proposed model, the classification accuracy of normal and abnormal(cardiomegaly) was 99.88%. Validation of classification performance using normal images as test data showed 95%, 100%, 90%, and 96% in accuracy, precision, recall, and F1 score. Validation of classification performance using abnormal(cardiomegaly) images as test data showed 95%, 92%, 100%, and 96% in accuracy, precision, recall, and F1 score. Our classification results show that the proposed convolutional neural network model shows very good performance in feature extraction and classification of chest X-ray images. The convolutional neural network model proposed in this paper is expected to show useful results for disease classification of chest X-ray images, and further study of CNN models are needed focusing on the features of medical images.

• Journal of the Korean Society of Radiology
• /
• v.5 no.6
• /
• pp.421-426
• /
• 2011

This research was accomplished to assess dose effects on image quality at computed radiography (CR). The ultimate target of the research was finding optimized exposure that provides necessary image quality for the clinical chest diagnosis. Modulation transfer function (MTF), normalized noise power spectrum (NNPS), and Noise equivalent quanta (NEQ) corresponding to the different doses were measured for the assessment of image quality. The preparation of "edge test device" used in MTF measurement and experimental geometry setup were followed by the recommendations of International Electrotechnical Commission (IEC). The experimental results show the necessary image quality can be achieved even at a half of the automatic exposure control (AEC) setting dose for chest diagnosis. It means that the patient exposure can be reduced dramatically by using optimized dose.