• 대한의용생체공학회:의공학회지
• /
• 제42권4호
• /
• pp.167-174
• /
• 2021

The purpose of this study is to classify TIFF images, PNG images, and JPEG images using deep learning, and to compare the accuracy by verifying the classification performance. The TIFF, PNG, and JPEG images converted from chest X-ray DICOM images were applied to five deep neural network models performed in image recognition and classification to compare classification performance. The data consisted of a total of 4,000 X-ray images, which were converted from DICOM images into 16-bit TIFF images and 8-bit PNG and JPEG images. The learning models are CNN models - VGG16, ResNet50, InceptionV3, DenseNet121, and EfficientNetB0. The accuracy of the five convolutional neural network models of TIFF images is 99.86%, 99.86%, 99.99%, 100%, and 99.89%. The accuracy of PNG images is 99.88%, 100%, 99.97%, 99.87%, and 100%. The accuracy of JPEG images is 100%, 100%, 99.96%, 99.89%, and 100%. Validation of classification performance using test data showed 100% in accuracy, precision, recall and F1 score. Our classification results show that when DICOM images are converted to TIFF, PNG, and JPEG images and learned through preprocessing, the learning works well in all formats. In medical imaging research using deep learning, the classification performance is not affected by converting DICOM images into any format.

• 대한의용생체공학회:의공학회지
• /
• 제42권6호
• /
• pp.295-303
• /
• 2021

Idiopathic normal-pressure hydrocephalus (INPH) is considered a potentially treatable neurological disorder by shunt surgery and characterized by a triad of symptoms including gait disturbance, cognitive impairment and urinary dysfunction. Although disorders of white matter are generally viewed as the principal pathological features of INPH, analysis of cortical features are important since the destruction of neural tracts could be associated with cortical structural changing. The aim of the study was to determine whether there was any relationship between gait parameter and structural features of cerebral cortex in INPH patients. Gait parameters were measured as follows: step width, toe in/out angle, coefficient of variation (CV) value of stride length, CV value of stride time. After obtaining individual brain MRI of patients with INPH and hemispheric cortical surfaces were automatically extracted from each MR volume, which reconstructed the inner and outer cortical surface. Then, cortical thickness, surface area, and volume were calculated from the cortical surface. As a result, step width was positively correlated with bilateral postcentral gyrus and left precentral gyrus, and toe in/out was positively correlated with left posterior parietal cortex and left insula. Also, the CV value of stride length showed positive correlation in the right superior frontal sulcus, left insula, and the CV value of stride time showed positive correlation in the right superior frontal sulcus. Unique parameter of cerebral cortical changes, as measured using MRI, might underline impairments in distinct gait parameters in patients with INPH.

• 대한의용생체공학회:의공학회지
• /
• 제44권1호
• /
• pp.11-18
• /
• 2023

Currently, studies to predict the risk of rectal cancer surgery select MRI image slices based on the clinical experience of surgeons. The purpose of this study is to semi-automatically select and classify 2D MRI image slides to predict the risk of rectal cancer surgery using biomarkers. The data used were retrospectively collected MRI imaging data of 50 patients who underwent laparoscopic surgery for rectal cancer at Gachon University Gil Medical Center. Expert-selected MRI image slices and non-selected slices were screened and radiomics was used to extract a total of 102 features. A total of 16 approaches were used, combining 4 classifiers and 4 feature selection methods. The combination of Random Forest and Ridge performed with a sensitivity of 0.83, a specificity of 0.88, an accuracy of 0.85, and an AUC of 0.89±0.09. Differences between expert-selected MRI image slices and non-selected slices were analyzed by extracting the top five significant features. Selected quantitative features help expedite decision making and improve efficiency in studies to predict risk of rectal cancer surgery.

• 대한의용생체공학회:의공학회지
• /
• 제44권1호
• /
• pp.53-63
• /
• 2023

There have been many studies from the genetic system to physical activity and emotional expression such that there are gender differences. The purpose of this study was to determine how the structural characteristics of cortical thickness differ between males and females. This study used data from the Human Connectome Project (HCP). To analyze age-specific sexual dimorphisms of cortical thickness, selected 8-80 year old subjects were divided into five detailed age range groups according to each criterion. A total of 1,700 individual brain MRI T1 data were registered in stereotaxic space for analysis and classified into white matter (WM), gray matter (GM), and cerebro-spinal fluid (CSF). For surface-based analysis, the WM/GM surface was reconstructed from a spherical polygon model with 40962 vertices per hemisphere, and each vertex was extended to the GM/CSF boundary. Cortical thickness was then measured between each vertex using the t-link method. In the statistical analysis, intracranial volume was used as a covariate to exclude the effect of the difference in brain size of each individual, and the result of using age as a covariate was added to confirm the age effect within each group. Gender differences in cortical thickness had significant results by group. This may be an index to explain diseases with sexual dimorphism in prevalence or become a basis for explaining the characteristics of each sex that appear in behavior, personality, and aging. Therefore, the results of our study could be a criterion for age classification in future studies and for understanding 'normal' sexual dimorphism.

• 대한의용생체공학회:의공학회지
• /
• 제43권6호
• /
• pp.390-398
• /
• 2022

Ultrasound examination using ultrasound equipment is an ultrasound device that images human organs using sound waves and is used in various areas such as diagnosis, follow-up, and treatment of diseases. However, if the quality of ultrasound equipment is not guaranteed, the possibility of misdiagnosis increases, and the diagnosis rate decreases. Accordingly, The Korean Society of Radiology and Korea society of Ultrasound in Medicine presented guidelines for quality management of ultrasound equipment using ATS-539 phantom. The DenseNet201 classification algorithm shows 99.25% accuracy and 5.17% loss in the Dead Zone, 97.52% loss in Axial/Lateral Resolution, 96.98% accuracy and 20.64% loss in Sensitivity, 93.44% accuracy and 22.07% loss in the Gray scale and Dynamic Range. As a result, it is the best and is judged to be an algorithm that can be used for quantitative evaluation. Through this study, it can be seen that if quantitative evaluation using artificial intelligence is conducted in the qualitative evaluation item of ultrasonic equipment, the reliability of ultrasonic equipment can be increased with high accuracy.

• Journal of Korean Neurosurgical Society
• /
• 제65권4호
• /
• pp.499-506
• /
• 2022

Objective : We conducted this study with the aim of predicting the biological behavior of meningiomas, and determining the benefits of associating histological subtype and grade with the expression of proliferative markers and tumor suppressor proteins. Methods : The study included 29 patients with primary intracranial and intraspinal meningioma diagnosed in the pathology laboratory of Konya City Hospital between January 2014 and December 2020. Clinicopathological characteristics of the patients including parameters such as age and gender were obtained from the hospital records. Histopathological findings were obtained by re-evaluating the preparations stained with Hematoxylin-Eosin, which were extracted from the archive, and by evaluating new sections obtained from paraffin blocks of patients stained with Ki67, p53, and p57 immunohistochemical stains. Results : A moderate correlation was found between tumor size and Ki67 proliferation index (PI) (p=0.003, r=0.530). There was no significant difference between grade I and grade II tumors in terms of p53 (p=0.184) and p57 (p=0.487) expressions. There were higher levels of Ki67 PI in grade II tumors. The histological subtypes of the tumor had no significant difference with Ki67 PI (p=0.018), p53 (p=0.662), and p57 (p=0.368) expressions. Conclusion : In order to obtain more definitive results, there is a need for studies, which are conducted with a greater number of patients and in multiple centers, and in which a long prospective follow-up is planned. The combination of histological, surgical, and imaging markers could make a more sensitive tool for predicting recurrence, and this could also be tested in future studies.

• The Plant Pathology Journal
• /
• 제39권1호
• /
• pp.1-20
• /
• 2023

In the past, rice bakanae was considered an endemic disease that did not cause significant losses in Korea; however, the disease has recently become a serious threat due to climate change, changes in farming practices, and the emergence of fungicide-resistant strains. Since the bakanae outbreak in 2006, its incidence has gradually decreased due to the application of effective control measures such as hot water immersion methods and seed disinfectants. However, in 2013, a marked increase in bakanae incidence was observed, causing problems for rice farmers. Therefore, in this review, we present the potential risks from climate change based on an epidemiological understanding of the pathogen, host plant, and environment, which are the key elements influencing the incidence of bakanae. In addition, disease management options to reduce the disease pressure of bakanae below the economic threshold level are investigated, with a specific focus on resistant varieties, as well as chemical, biological, cultural, and physical control methods. Lastly, as more effective countermeasures to bakanae, we propose an integrated disease management option that combines different control methods, including advanced imaging technologies such as remote sensing. In this review, we revisit and examine bakanae, a traditional seed-borne fungal disease that has not gained considerable attention in the agricultural history of Korea. Based on the understanding of the present significance and anticipated risks of the disease, the findings of this study are expected to provide useful information for the establishment of an effective response strategy to bakanae in the era of climate change.

• 대한의용생체공학회:의공학회지
• /
• 제44권3호
• /
• pp.167-175
• /
• 2023

Chest PA is the basic examination of radiographic imaging. Moreover, Chest PA's demands are constantly increasing because of the Increase in respiratory diseases. However, it is not meeting the demand due to problems such as a shortage of radiological technologist, sexual shame caused by patient contact, and the spread of infectious diseases. There have been many cases of using artificial intelligence to solve this problem. Therefore, the purpose of this research is to build an artificial intelligence dataset of Chest PA and to find a posture evaluation method. To construct the posture dataset, the posture image is acquired during actual and simulated examination and classified correct and incorrect posture of the patient. And to evaluate the artificial intelligence posture method, a posture estimation algorithm is used to preprocess the dataset and an artificial intelligence classification algorithm is applied. As a result, Chest PA posture dataset is validated with in over 95% accuracy in all artificial intelligence classification and the accuracy is improved through the Top-Down posture estimation algorithm AlphaPose and the classification InceptionV3 algorithm. Based on this, it will be possible to build a non-face-to-face automatic Chest PA examination system using artificial intelligence.

• 대한의용생체공학회:의공학회지
• /
• 제44권3호
• /
• pp.182-189
• /
• 2023

CT is a medical device that acquires medical images based on Attenuation coefficient of human organs related to X-rays. In addition, using this theory, it can acquire sagittal and coronal planes and 3D images of the human body. Then, CT is essential device for universal diagnostic test. But Exposure of CT scan is so high that it is regulated and managed with special medical equipment. As the special medical equipment, CT must implement quality control. In detail of quality control, Spatial resolution of existing phantom imaging tests, Contrast resolution and clinical image evaluation are qualitative tests. These tests are not objective, so the reliability of the CT undermine trust. Therefore, by applying an artificial intelligence classification model, we wanted to confirm the possibility of quantitative evaluation of the qualitative evaluation part of the phantom test. We used intelligence classification models (VGG19, DenseNet201, EfficientNet B2, inception_resnet_v2, ResNet50V2, and Xception). And the fine-tuning process used for learning was additionally performed. As a result, in all classification models, the accuracy of spatial resolution was 0.9562 or higher, the precision was 0.9535, the recall was 1, the loss value was 0.1774, and the learning time was from a maximum of 14 minutes to a minimum of 8 minutes and 10 seconds. Through the experimental results, it was concluded that the artificial intelligence model can be applied to CT implements quality control in spatial resolution and contrast resolution.

• 대한정형외과학회지
• /
• 제54권2호
• /
• pp.91-99
• /
• 2019

대부분의 환자는 관절경적 회전근 개 봉합술 후 통증이 완화되고 기능적 호전을 보이지만 일부 환자는 수술 후에도 증상이 지속된다. 재파열은 생물학적, 기술적, 외상적 요인이 복합적으로 작용하여 발생한다. 회전근 개 봉합술 후 재파열이 지속되는 통증의 원인일 수도 원인이 아닐 수도 있다. 따라서 이런 환자들의 평가 및 치료는 난해하여 철저한 문진, 이학적 검사, 적절한 영상 검사를 통해서 통증의 원인에 대한 분석이 이루어져야 한다. 재봉합술의 시행 여부는 환자의 나이, 기능적 요구도 회전근 개의 상태, 수술 전 관절 운동 범위, 삼각근의 상태, 관절과 상완 관절의 관절염의 유무에 따라 결정되어야 한다. 성공적인 재봉합술은 술기뿐만 아니라 수술 전 환자 교육 또한 중요하다.