• Journal of Broadcast Engineering
• /
• v.18 no.5
• /
• pp.702-712
• /
• 2013

In this paper, we proposed an algorithm that extracts the airway and lung without loss of information in spite of the pulmonary vessel and nodules of the chest wall in the chest CT images. We use a mask image in order to improve the performance and to save processing time of airway and lung segmentation. In the second step, by converting left and right lungs to binary image using the morphological information, we have removed the solitary pulmonary nodule to identify the value of the threshold lung and the chest wall. The last step is to connect the outer shell of the lung with cubic Spline interpolation by adding the perfect pixel and computing the distance of the removed part. Experimental results using Matlab verified that the proposed method could overcome the drawbacks of the conventional methods.

• Journal of Biomedical Engineering Research
• /
• v.42 no.3
• /
• pp.80-85
• /
• 2021

We developed a model to classify the absence of cervical cancer using deep learning from the cervical image to which the histogram equalization algorithm was applied, and to compare the performance of each model. A total of 4259 images were used for this study, of which 1852 images were normal and 2407 were abnormal. And this paper applied Image Sharpening(IS), Histogram Equalization(HE), and Contrast Limited Adaptive Histogram Equalization(CLAHE) to the original image. Peak Signal-to-Noise Ratio(PSNR) and Structural Similarity index for Measuring image quality(SSIM) were used to assess the quality of images objectively. As a result of assessment, IS showed 81.75dB of PSNR and 0.96 of SSIM, showing the best image quality. CLAHE and HE showed the PSNR of 62.67dB and 62.60dB respectively, while SSIM of CLAHE was shown as 0.86, which is closer to 1 than HE of 0.75. Using ResNet-50 model with transfer learning, digital image-processed images are classified into normal and abnormal each. In conclusion, the classification accuracy of each model is as follows. 90.77% for IS, which shows the highest, 90.26% for CLAHE and 87.60% for HE. As this study shows, applying proper digital image processing which is for cervical images to Computer Aided Diagnosis(CAD) can help both screening and diagnosing.

• Advances in nano research
• /
• v.12 no.2
• /
• pp.185-195
• /
• 2022

Deep learning is another field of artificial intelligence (AI) utilized for computer aided diagnosis (CAD) and image processing in scientific research. Considering numerous mechanical repetitive tasks, reading image slices need time and improper with geographical limits, so the counting of image information is hard due to its strong subjectivity that raise the error ratio in misdiagnosis. Regarding the highest mortality rate of Lung cancer, there is a need for biopsy for determining its class for additional treatment. Deep learning has recently given strong tools in diagnose of lung cancer and making therapeutic regimen. However, identifying the pathological lung cancer's class by CT images in beginning phase because of the absence of powerful AI models and public training data set is difficult. Convolutional Neural Network (CNN) was proposed with its essential function in recognizing the pathological CT images. 472 patients subjected to staging FDG-PET/CT were selected in 2 months prior to surgery or biopsy. CNN was developed and showed the accuracy of 87%, 69%, and 69% in training, validation, and test sets, respectively, for T1-T2 and T3-T4 lung cancer classification. Subsequently, CNN (or deep learning) could improve the CT images' data set, indicating that the application of classifiers is adequate to accomplish better exactness in distinguishing pathological CT images that performs better than few deep learning models, such as ResNet-34, Alex Net, and Dense Net with or without Soft max weights.

• Journal of Biomedical Engineering Research
• /
• v.44 no.3
• /
• pp.211-217
• /
• 2023

Recently, many studies have introduced artificial intelligence systems in the surgical process to reduce the incidence and mortality of complications in patients. Bleeding is a major cause of operative mortality and complications. However, there have been few studies conducted on detecting bleeding in surgical videos. To advance the development of deep learning models for detecting intraoperative hemorrhage, three models have been trained and compared; such as, YOLOv5, RetinaNet50, and RetinaNet101. We collected 1,016 bleeding images extracted from five surgical videos. The ground truths were labeled based on agreement from two specialists. To train and evaluate models, we divided the datasets into training data, validation data, and test data. For training, 812 images (80%) were selected from the dataset. Another 102 images (10%) were used for evaluation and the remaining 102 images (10%) were used as the evaluation data. The three main metrics used to evaluate performance are precision, recall, and false positive per image (FPPI). Based on the evaluation metrics, RetinaNet101 achieved the best detection results out of the three models (Precision rate of 0.99±0.01, Recall rate of 0.93±0.02, and FPPI of 0.01±0.01). The information on the bleeding detected in surgical videos can be quickly transmitted to the operating room, improving patient outcomes.

• The Journal of Korean Academy of Prosthodontics
• /
• v.61 no.4
• /
• pp.328-343
• /
• 2023

Recently, a method of fabricating an esthetic anterior fixed prosthesis by integrating data such as three-dimensional facial scan and jaw motion to form a virtual patient with dynamic occlusion has been introduced. This enables smooth communication with patients during the diagnosis process, improves the predictability of esthetic prosthetic treatment, and lowers the possibility of occlusal adjustment. In this case report, a virtual patient with dynamic occlusion was created in which the results of the treatment were simulated, and esthetic maxillary anterior fixed prosthesis was fabricated. With the aid of the virtual patient, the final restorations were satisfactory both in terms of esthetic and function.

• The Journal of the Korea Contents Association
• /
• v.13 no.5
• /
• pp.303-310
• /
• 2013

Thyroid nodular disease is the most frequently appeared in thyroid disease. Thyroid ultrasonography offers location of nodules, size, the number, information of internal echo characteristic. Thus, it makes possible to sort high-risk nodule containing high possibility about thyroid cancer and to induct precisely when take a Fine Needle Biopsy Aspiration. On thyroid nodule, the case which is diagnosed as malignant is less than 5% but screening test is very important on ultrasound and also must be reduced unnecessary procedure. Therefore, in this study an approach for describing a region is to quantity its texture content. We applied TFA algorithm on case which has been pathologically diagnosed as papillary thyroid cancer. we obtained experiment image which set the ROI on ultrasound and cut the $50{\times}50$ pixel size, histogram equalization. Consequently, Disease recognition detection efficiency of GLavg, SKEW, UN, ENT parameter were high as 91~100%. It is suggestion about possibility on CAD which distinguishes thyroid nodule. In addition, it will be helpful to differential diagnosis of thyroid nodule. If the study on additional parameter algorithm is continuously progressed from now on, it is able to arrange practical base on CAD and it is possible to apply various disease in the thyroid US.

• Annals of Clinical Neurophysiology
• /
• v.12 no.1
• /
• pp.21-26
• /
• 2010

Background: Although quantitative sensory test (QST) is being used with increasing frequency for measuring sensory thresholds in clinical practice and epidemiologic studies, there has been no age-matched normative data in Korean adults. The objective of this study is to evaluate the value of QST in diabetic polyneuropathy with normal range in Korean adults. Methods: The Computer Aided Sensory Examination IV 4,2 (WR Medical Electronics Co., Stillwater, Minnesota, U.S.A.), with 4,2,1 stepping algorithm was used to determine vibration and cold perception threshold in 70 normal controls and 19 patients with diabetic polyneuropathy aged from 21 to 79 years. The data were used to define age-matched upper and lower normal limits and normal range of side to side difference. We also evaluated the duration of diabetes, serum HbA1C level, and findings of nerve conduction study (NCS) and QST in patients with diabetic polyneuropathy. Results: In normal adults, sensory thresholds slightly increased with age, and a slight side-to-side difference was observed. The diagnostic sensitivity of QST was not higher than NCS in patients with diabetic polyneuropathy (36.8% vs. 42.1%, p=0.716), especially among elderly patients. Conclusions: QST might be used as a complementary test for NCS in the diagnosis of diabetic polyneuropathy. Although the QST is a simple method for the evaluation of peripheral nerve function, there are some limitations. Most of all, because the QST measuring is dependent on the subjective response of patients, the degree of concentration and cooperation of the patients can significantly affect the result. And thus, attention should be paid during the interpretation of QST results in patients with peripheral neuropathy.

• Korean Journal of Cognitive Science
• /
• v.9 no.1
• /
• pp.31-39
• /
• 1998

This paper describes an electronic performance support system called HELPS(Handler Electronic Learning Performence Support) for semiconductor testing e equipment. The purpose of this system is to improve productivity of operators by providing just-in-time, on-the-job, mutimedia-based system information for operational support, training, and knowledge-based trouble shooting and repair. HELPS is composed of a operation module and a trouble shooting module. The operation module uses multimedia and hypermedia to provide the detailed and easily accessible information about equipment to users. Multimedia incorporate multiple. media forms including still and video images. animations 'texts' graphics. and audio. Hypermedia a are provided through a hierarchical information structure which offers not only specific information which is needed to perform a task to experienced operators. but detailed system guidance and information to novice operators. The trouble shooting module is composed of an integrated mutimedia-supported expert system which assists operators in trouble shooting and equipment repair. After diagnosis through the use of the expert system. multimedia advice is presented to the user in either still images with text or motion sequences with sound HELPS is evaluated in term of training time and trouble shooting and repair time. It improved productivity by saving more than 30% of the total time used without the system. This s system has the potential to improve productivity when it is used with ICAIOntellignet Computer Aided Instruction) and virtual reality.

• Investigative Magnetic Resonance Imaging
• /
• v.21 no.4
• /
• pp.233-241
• /
• 2017

Purpose: To report on the current practices in breast magnetic resonance imaging (MRI) in Korea. Materials and Methods: We invited the 68 members of the Korean Society of Breast Imaging who were working in hospitals with available breast MRI to participate in a survey on how they performed and interpreted breast MRI. We asked one member from each hospital to respond to the survey. A total of 22 surveys from 22 hospitals were analyzed. Results: Out of 22 hospitals, 13 (59.1%) performed at least 300 breast MRI examinations per year, and 5 out of 22 (22.7%) performed > 1200 per year. Out of 31 machines, 14 (45.2%) machines were 1.5-T scanners and 17 (54.8%) were 3.0-T scanners. All hospitals did contrast-enhanced breast MRI. Full-time breast radiologists supervised the performance and interpreted breast MRI in 19 of 22 (86.4%) of hospitals. All hospitals used BI-RADS for MRI interpretation. For computer-aided detection (CAD), 13 (59.1%) hospitals sometimes or always use it and 9 (40.9%) hospitals did not use CAD. Two (9.1%) and twelve (54.5%) hospitals never and rarely interpreted breast MRI without correlating the mammography or ultrasound, respectively. The majority of respondents rarely (13/21, 61.9%) or never (5/21, 23.8%) interpreted breast MRI performed at an outside facility. Of the hospitals performing contrast-enhanced examinations, 15 of 22 (68.2%) did not perform MRI-guided interventional procedures. Conclusion: Breast MRI is extensively performed in Korea. The indication and practical patterns are diverse. The information from this survey would provide the basis for the development of Korean breast MRI practice guidelines.

• The Korean Journal of Nuclear Medicine
• /
• v.38 no.3
• /
• pp.233-240
• /
• 2004

Purpose: We developed a computer-aided classifier using artificial neural network (ANN) to discriminate the cerebral metabolic pattern of medial and lateral temporal lobe epilepsy (TLE). Materials and Methods: We studied brain F-18-FDG PET images of 113 epilepsy patients sugically and pathologically proven as medial TLE (left 41, right 42) or lateral TLE (left 14, right 16). PET images were spatially transformed onto a standard template and normalized to the mean counts of cortical regions. Asymmetry indices for predefined 17 mirrored regions to hemispheric midline and those for medial and lateral temporal lobes were used as input features for ANN. ANN classifier was composed of 3 independent multi-layered perceptrons (1 for left/right lateralization and 2 for medial/lateral discrimination) and trained to interpret metabolic patterns and produce one of 4 diagnoses (L/R medial TLE or L/R lateral TLE). Randomly selected 8 images from each group were used to train the ANN classifier and remaining 51 images were used as test sets. The accuracy of the diagnosis with ANN was estimated by averaging the agreement rates of independent 50 trials and compared to that of nuclear medicine experts. Results: The accuracy in lateralization was 89% by the human experts and 90% by the ANN classifier Overall accuracy in localization of epileptogenic zones by the ANN classifier was 69%, which was comparable to that by the human experts (72%). Conclusion: We conclude that ANN classifier performed as well as human experts and could be potentially useful supporting tool for the differential diagnosis of TLE.