• 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.

• Investigative Magnetic Resonance Imaging
• /
• v.3 no.2
• /
• pp.167-172
• /
• 1999

Purpose : To evaluate the detection rate of hyperacute intracerebral hemorrhage in echo planar imaging (EPI) and other MR sequences. materials and Methods : Intracerebral hemorrhage was experimentally induced in ten rats. EPI, fast spin-echo (FSE) T2 weighted images, fluid attenuated inversion recovery (FLAIR), spin-echo (SE) T1 weighted images and gradient echo (GE) T1 weight ed images of rat's brains were obtained 2 hours after onset of intracerebral hemorrhage. EPI and FSE T2 images were additionally obtained 30 min and 1 hour after onset of hemorrhage in 3 and 6 rat, repeatedly, For objective visual assessment, discrimination between the lesion and normal brain parenchyma was evaluated on various MR sequences by three radiologists. For quantitative assessment, contrast-to-noise ratio (CNR) was calculated fro hemorrhage-normal brain parenchyma. Statistical analysis was performed usning the Wilcoxon-Ranks test. Results : EPI, FLAIR, and FSE T2 images showed high signal intensity lesions. The lesion discrimination was easier on EPI than on other sequences, and also EPI showed higher signal intensity for the subjective visual assessment. In quantitative evaluation, CNR of the hemorrhagic lesion versus normal brain parenchyma were higher on EPI and FLAIR images (p<0.01). There was no difference in CNR between EPI and FLAIR (p>0.10). On MR images obtained 30 minutes and 1 hour after the onset of intracerebral hemorrhage, the lesion detection was feasible on both EPI and FSE T2 images showing high signal intensity. Conclusion : EPI showed higher detection rate as compared with other MR sequences and could be useful in early detection and evaluation of intracerebral hemorrhage.

• 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.

• Parasites, Hosts and Diseases
• /
• v.51 no.6
• /
• pp.755-757
• /
• 2013

Gnathostoma spinigerum can cause subarachnoid hemorrhage (SAH). The detection of specific antibodies in serum against G. spinigerum antigen is helpful for diagnosis of neurognathostomiasis. There is limited data on the frequency of G. spinigerum infection in non-traumatic SAH. A series of patients diagnosed as non-traumatic SAH at the Srinagarind Hospital, Khon Kaen University, Thailand between January 2011 and January 2013 were studied. CT or MR imaging of the brain was used for diagnosis of SAH. Patients were categorized as aneurysmal subarachnoid hemorrhage (A-SAH) or non-aneurysmal subarachnoid hemorrhage (NA-SAH) according to the results of cerebral angiograms. The presence of specific antibodies in serum against 21- or 24-kDa G. spinigerum antigen was determined using the immunoblot technique. The detection rate of antibodies was compared between the 2 groups. Of the 118 non-traumatic SAH patients for whom cerebral angiogram and immunoblot data were available, 80 (67.8%) patients had A-SAH, whereas 38 (32.2%) had NASAH. Overall, 23.7% were positive for specific antibodies against 21- and /or 24-kDa G. spinigerum antigen. No significant differences were found in the positive rate of specific antibodies against G. spinigerum in both groups (P-value=0.350).

• Journal of Oral Medicine and Pain
• /
• v.37 no.3
• /
• pp.135-139
• /
• 2012

Hereditary hemorrhagic telangiectasia is a rare autosomal dorminant disease that features abnormal and fragile vascular dilations of terminal vessels in skin and mucous membranes, as well as arteriovenous malformations of internal organs, particularly lungs, brain, and liver. Often patients have not been diagnosed with HHT for a long time, and undiagnosed HHT patients unnecessarily develop serious complications such as severe life-threatening hemorrhage, stroke or brain abscess. Therefore, early detection and appropriate screening is very important. Early detection of HHT allows the appropriate screening for the presence of silent disease such as AVMs in the lungs, liver, or brain, and preventive treatment in the patient and their affected family members. Dentists should be familiar with HHT because the telangiectases on skin and oral mucosa are often the most dramatic and most easily identified component of HHT. Recently, we experienced a case of HHT. We present the case with a review of the literature.

• Investigative Magnetic Resonance Imaging
• /
• v.12 no.2
• /
• pp.170-177
• /
• 2008

Purpose : To evaluate usefulness of MR imaging after serial brain US in the high-risk neonates before discharge of the neonatal intensive care unit. Materials and Methods : Retrospective comparison of 412 US and 121 MR scans in 121 neonates and young infants were performed. Grading of germinal matrix/intraventricular hemorrhage (GMH/IVH) was performed and presence of intracranial hemorrhage other than GMH/IVH and parencyma lesions was also analyzed. Results : Among the 242 lateral ventricles, Seven GMH and 46 IVH were additionally detected by MRI. On the other hand, 30 GMH were only detected by US. US demonstrated Grade 1/2/3/4 GMH/IVH in 24/8/13/0 ventricles each, while each grades were identified in 3, 49, 10, 2 ventricles on MR images. Other intracranial lesions additionally detected on MR images were cerebral hemorrhage (n=4), cerebellar hemorrhage (n=4), extraaxial hemorrhage (n=8), diffuse excessive signal change of the white matter (n=72), non-cavitary lesion (n=4), encephalomalacia (n=2), and ventriculomegaly (n=5). Conclusion : MR imaging could be an excellent complimentary study after serial brain US for additional detection of the intracranial pathology, particularly IVH and white matter lesions, though US would be better in follow-up of GMH in some neonates.

• The Journal of Korean Medicine
• /
• v.25 no.4
• /
• pp.95-107
• /
• 2004

Objective : The inappropriate or excessive apoptosis has been known to be associated with neurodegenerative disorders including intracranial hemorrhage(ICH). Paeoniae radix, in traditional Korean medicine, has played its role as blood­nourisher and yin-astringent. In the present study, the effect of Paeoniae radix on the inhibition of neurodegeneration in the brain of rats after artificial ICH and on the resulting apoptosis was investigated. Methods : 30 rats were divided into 6 equal groups ; the sham-operation group, the hemorrhage-induction group, the hemorrhage-induction with 10, 50, 100, and 200 mg/kg Paeoniae radix-treated group, respectively. Stereotactic surgery was performed and collagenase was infused to induce ICH in the region of CA1 of hippocampus of rats. The sham group took only saline infusion. For 7 days after the surgery, 4 testing groups had intraperitoneal injections of Paeoniae radix extract. The step-down inhibitory avoidance task, measurement of neurodegeneration degree in the CA1 region of the hippocampus, and detection of caspase-3 and newly generated cells in the dentate gyrus were done after animal sacrifice. Results : Rats receiving Paeoniae radix extract showed increased latency time in the inhibitory avoidance task. The extension of neuron-deprived areas in the CA1 region was significantly suppressed in the Paeonia treated groups. Also expressions of caspase-3 in the CA1 region and cortex were significantly inhibited in the Paeonia treated groups. The cell proliferation was evaluated by means of BrdU methods and proved to be decreased in the Paeonia treated groups. Conclusion : These results suggest that Paeoniae radix has potential to suppress short-tenn memory loss after devastating neurologic accidents. Also it was proved that Paeoniae radix has a neuroprotective effect and alleviates central nervous complications following intracerebral hemorrhage. Furthermore, it may imply that this medicinal plant can be widely used for vascular dementia and other neurodegenerative disorders.

• Biomedical Science Letters
• /
• v.18 no.4
• /
• pp.399-405
• /
• 2012

The brain is the body's most organized and controlled organ, and it governs various psychological and mental functions. A brain abnormality could greatly affect one's physical and mental abilities, and consequently one's social life. Brain disorders can be broadly categorized into three main afflictions: stroke, brain tumor, and dementia. Among these, stroke is a common disease that occurs owing to a disorder in blood flow, and it is accompanied by a sudden loss of consciousness and motor paralysis. The main types of strokes are infarction and hemorrhage. The exact diagnosis and early treatment of an infarction are very important for the patient's prognosis and for the determination of the treatment direction. In this study, texture features were analyzed in order to develop a prototype auto-diagnostic system for infarction using computer auto-diagnostic software. The analysis results indicate that of the six parameters measured, the average brightness, average contrast, flatness, and uniformity show a high cognition rate whereas the degree of skewness and entropy show a low cognition rate. On the basis of these results, it was suggested that a digital CT image obtained using the computer auto-diagnostic software can be used to provide valuable information for general CT image auto-detection and diagnosis for pre-reading. This system is highly advantageous because it can achieve early diagnosis of the disease and it can be used as supplementary data in image reading. Further, it is expected to enable accurate medical image detection and reduced diagnostic time in final-reading.

• Journal of Korean Neurosurgical Society
• /
• v.46 no.4
• /
• pp.365-369
• /
• 2009

Objective : Susceptibility-weighted image (SWI) is a sensitive magnetic resonance image (MRI) technique to detect cerebral microbleeds (MBLs). which would not be detected by conventional MRI. We performed SWI to detect MBLs and investigated its usefulness in the evaluation of mild traumatic brain injury (MTBI) patients. Methods : From December 2006 to June 2007, twenty-one MTBI patients without any parenchymal hemorrhage on conventional MRI were selected. Forty-two patients without trauma were selected for control group. According to the presence of MBLs, we divided the MTBI group into MBLs positive [SWI (+)] and negative [SWI (-)] group. Regional distribution of MBLs and clinical factors were compared between groups. Results : Fifty-one MBLs appeared in 16 patients of SWI (+) group and 16 MBLs in 10 patients of control group [control (+)], respectively. In SWI (+) group, MBLs were located more frequently in white matters than in deep nucleus different from the control (+) group (p<0.05). Nine patients (56.3%) of SW (+) group had various neurological deficits (disorientation in 4, visual field defect in 2, hearing difficulty in 2 and Parkinson syndrome in 1). Initial Glasgow Coma Scale (GCS)/mean Glasgow Outcome Scale (GOS) were $13.9{\pm}1.5/4.7{\pm}0.8$ and $15.0{\pm}0.0/5.0{\pm}0.0$ in SWI (+) and SWI (-) groups, respectively (p<0.05). Conclusion : Traumatic cerebral MBLs showed characteristic regional distribution, and seemed to have an importance on the initial neurological status and the prognosis. SWI is useful for detection of traumatic cerebral MBLs, and can provide etiologic evidences for some post-traumatic neurologic deficits which were unexplainable with conventional MRI.

• Investigative Magnetic Resonance Imaging
• /
• v.5 no.2
• /
• pp.149-154
• /
• 2001

Purpose : Our aim was to evaluate the usefulness of fluid-attenuated inversion recovery (FLAIR) MR imaging for detection of acute subarachnoid hemorrhage (SAH) compared with unenhanced CT. Materials and methods ; We compared FLAIR MR images with unenhanced CT scans in 28 patients with acute SAH. Findings of SAH on CT and MR images were graded as 0 (absence), 1 (suspicious), 2 (definite) in the cerebral sulci, sylvian fissure, basal cistern, and cisterns of the posterior fossa. We also compared FLAIR MR images of 28 patients with those of 35 normal subjects, and then the sensitivity, specificity, and diagnostic accuracy of FLAIR MR image for detection of acute SAH were calculated. Results : FLAIR MR image was superior to CT in detecting SAH in the posterior fossa ($1.41{\pm}0.74{\;}vs{\;}0.78{\pm}0.80$; p<0.05) and cortical sulci ($1.11{\pm}0.80{\;}vs{\;}0.70{\pm}0.83$; p<0.05). There was no significant difference between FLAIR MR image and CT in detecting SAH in the basal cistern and sylvian fissure. The sensitivity, specificity, and diagnostic accuracy of FLAIR MR image for detection of SAH were 100% in all. Conclusion : FLAIR MR image is useful in detecting acute SAH, especially in patients with small amount of SAH or SAH in the posterior fossa.