• Journal of the Korean Society of Radiology
• /
• v.16 no.1
• /
• pp.25-34
• /
• 2022

Brain computed tomography (CT) is useful for brain lesion diagnosis, such as brain hemorrhage, due to non-invasive methodology, 3-dimensional image provision, low radiation dose. However, there has been numerous misdiagnosis owing to a lack of radiologist and heavy workload. Recently, object detection technologies based on artificial intelligence have been developed in order to overcome the limitations of traditional diagnosis. In this study, the applicability of a deep learning-based YOLOv5s model was evaluated for brain hemorrhage detection using brain CT images. Also, the effect of hyperparameters in the trained YOLOv5s model was analyzed. The YOLOv5s model consisted of backbone, neck and output modules. The trained model was able to detect a region of brain hemorrhage and provide the information of the region. The YOLOv5s model was trained with various activation functions, optimizer functions, loss functions and epochs, and the performance of the trained model was evaluated in terms of brain hemorrhage detection accuracy and training time. The results showed that the trained YOLOv5s model is able to provide a bounding box for a region of brain hemorrhage and the accuracy of the corresponding box. The performance of the YOLOv5s model was improved by using the mish activation function, the stochastic gradient descent (SGD) optimizer function and the completed intersection over union (CIoU) loss function. Also, the accuracy and training time of the YOLOv5s model increased with the number of epochs. Therefore, the YOLOv5s model is suitable for brain hemorrhage detection using brain CT images, and the performance of the model can be maximized by using appropriate hyperparameters.

• Journal of radiological science and technology
• /
• v.36 no.2
• /
• pp.141-148
• /
• 2013

The CT examination sometimes fail to localize the cerebral hemorrhage part depending on the seriousness and may embarrass the pathologist if he/she is not trained enough for emergencies. Therefore, an assisting role is necessary for examination, automatic and quick detection of the cerebral hemorrhage part, and supply of the quantitative information in emergencies. the computer based automatic detection and recognition system may be of a great service to the bleeding part detection. As a result of this research, we succeeded not only in automatic detection of the cerebral hemorrhage part by grafting threshold value handling, morphological operation, and roundness calculation onto the bleeding part but also in development of the PCA based classifier to screen any wrong choice in the detection candidate group. We think if we apply the new developed system to the cerebral hemorrhage patient in his critical condition, it will be very valuable data to the medical team for operation planning.

• Journal of the Korean Society of Radiology
• /
• v.9 no.6
• /
• pp.369-374
• /
• 2015

In this study we proposed a texture feature analysis algorithm that distinguishes between a normal image and a diseased image using CT images of some brain hemorrhage patients, and generates both Eigen images and test images which can be applied to the proposed computer aided diagnosis system in order to perform a quantitative analysis for 6 parameters. And through the analysis, we derived and evaluated the recognition rate of CT images of brain hemorrhage. As the results of examining over 40 example CT images of brain hemorrhage, the recognition rates representing a specific texture feature-value are as follows: some appeared to be as high as 100% including average gray level, average contrast, smoothness, and Skewness while others showed a little low disease recognition rate: 95% for uniformity and 87.5% for entropy. Consequently, based on this research result, if a software that enables a computer aided diagnosis system for medical images is developed, it will lead to the availability for the automatic detection of a diseased spot in CT images of brain hemorrhage and quantitative analysis. And they can be used as computer aided diagnosis data, resulting in the increased accuracy and the shortened time in the stage of final reading.

• Journal of fish pathology
• /
• v.4 no.2
• /
• pp.87-94
• /
• 1991

In the late summer of 1990 and 1991, mass mortality occured among cage-cultured grouper, Epinephelus septemfasciatus in south cost of Korea. The moribund fish didn't feed and became pale or dark chestnut colour and irregularly swimmed due to the loss of equilibrium, finally the diseased fish fell down side away on the bottom or the surface of cage showing the bent of body and died. The diseased fish showed the extensive hemorrahge in brain, the swelling of spleen and bile duct as the specific syptoms of internal organs. So the gill, skin and other organs of the diseased fish were examined for the presence of pathogenic parasites and bacteria. The parasitic Trichodina sp. were detected only from the gill lamella of the diseased fish, but these parasites seemed to be not a direct causative agents that induced the gross mortality of the cultured grouper. because these parasites were also observed in normal grouper, yellowtail, red seabream and rock bream co-cultured with the diseased grouper in same or near cages. In the viral examination, although isolation of the causative agent by the use of estabilshed cell Lines, RTG-2 and CHSE-214, was not succeed, the normal grouper inoculated intramuscularly with the filtered homogenate of the organs of the diseased fish showed the same external and internal signs with the naturally infected grouper. They died within a week. By using the naturally and the artificially infected fishes, electron microscopic observation revealed numerous hexagonal or polygonal particles in the cytoplasm of liver cells. Based on the these results, we suggest that the mass mortality of the cultured grouper would be occurred by the infection of a viral agent.

• Clinical and Experimental Pediatrics
• /
• v.45 no.8
• /
• pp.1000-1006
• /
• 2002

Purpose : In the course of treatment, patients with hematological or oncological disorders often develop pulmonary complication. The patients who develop a severe pulmonary complication have a poor outlook. The causes of pulmonary complication are either infectious or non-infectious in origin. We have analyzed the etiology and outcome of these patients admitted to the pediatric intensive care unit of Asan Medical Center. Methods : Medical records of 95 patients on Pediatric oncology service who were admitted to pediatric intensive care unit(PICU) of Asan Medical Center from Jan 1997 to May 2000 were retrospectively reviewed. Results : The mean age of the patients was 8.5 years(2 months-18 years). The underlying malignancies of these 95 patients were as following; acute lymphoblastic leukemia(31 cases), lymphoma (11 cases), acute myeloid leukemia(nine cases), brain tumor(eight cases) and other solid tumors(25 cases). Pulmonary complications included pneumonia, acute respiratory failure, pneumothorax and pleural effusion. The most common cause of pulmonary complication was infection(88%) in etiology. The overall mortality rate was 56.8%. Pulmonary complications in these patients carried high rates of mortality regardless of whether they were immune compromised(76%) or not(69%). Even without pulmonary complications, the hematological or oncological patients admitted to PICU had high mortality rates of 43%. Conclusion : Pulmonary complications are frequent finding in the hematological or oncological patients admitted to Intensive Care Unit. The main etiology of these pulmonary complications was infection, which carried a high mortality rate regardless of their immune status at the time when they were admitted to PICU.