• Imaging Science in Dentistry
• /
• v.53 no.4
• /
• pp.271-281
• /
• 2023

Purpose: The objective of this scoping review was to investigate the applicability and performance of various convolutional neural network (CNN) models in tooth numbering on panoramic radiographs, achieved through classification, detection, and segmentation tasks. Materials and Methods: An online search was performed of the PubMed, Science Direct, and Scopus databases. Based on the selection process, 12 studies were included in this review. Results: Eleven studies utilized a CNN model for detection tasks, 5 for classification tasks, and 3 for segmentation tasks in the context of tooth numbering on panoramic radiographs. Most of these studies revealed high performance of various CNN models in automating tooth numbering. However, several studies also highlighted limitations of CNNs, such as the presence of false positives and false negatives in identifying decayed teeth, teeth with crown prosthetics, teeth adjacent to edentulous areas, dental implants, root remnants, wisdom teeth, and root canal-treated teeth. These limitations can be overcome by ensuring both the quality and quantity of datasets, as well as optimizing the CNN architecture. Conclusion: CNNs have demonstrated high performance in automated tooth numbering on panoramic radiographs. Future development of CNN-based models for this purpose should also consider different stages of dentition, such as the primary and mixed dentition stages, as well as the presence of various tooth conditions. Ultimately, an optimized CNN architecture can serve as the foundation for an automated tooth numbering system and for further artificial intelligence research on panoramic radiographs for a variety of purposes.

• Journal of Yeungnam Medical Science
• /
• v.13 no.1
• /
• pp.110-115
• /
• 1996

The ESR is one of the oldest laboratory test still in use. Although it lacks specificity in diagnosis, it can be effective for monitoring disease activity and following-up. The Westergren method is used for reference method, however coefficient of variation has been described 0.8% to 22.9% according to the literature. Since the ESR was invented in 1921, measurement technique has developed and automated measurement is introduced. We analyzed one hundred forty-three patient samples using $SEDIsystem^{TM}$ automated ESR measuring system and compared with modified Westergren and Wintrobe methods. Comparison between $SEDIsystem^{TM}$ and modified Westergren for ESR measurement yields the following regression equation; y = 0.863x - 1.69 (r=0.830), $SEDIsystem^{TM}$ and Wintrobe y = 1.14x - 14.7 (r=0.789), respectively. We repeated measurement to evaluate reliability, results are not significant in statistically. In conclusion, $SEDIsystem^{TM}$ automated ESR measurement correlated with modified Westergren and Wintrobe methods, reveal reliable results after 4 hours and can report rapidly for large samples. Thus, these results indicate that $SEDIsystem^{TM}$ automated ESR measurement may be useful tool for clinical practice.

• Korean Journal of Microbiology
• /
• v.44 no.2
• /
• pp.130-134
• /
• 2008

Modern automated culture systems have increased the isolation rate of microorganisms and shortened the time to detection, reducing experimental errors in diagnosis of infecting agents. BacT/ALERT 3D system is based on the colorimetric detection of $CO_2$ produced by the growing microorganisms. In order to evaluate the efficiency of the detection system, sterility test were performed using 6 bacteria. With standard aerobic and anaerobic bottles containing the liquid media, both three aerobic bacteria (P. aeruginosa, M. luteus, B. subtilis) and a facultative bacterium S. aureus were detected up to 1 CFU in 31.44 hr. In addition, growth of anaerobic C. sporogenes was recognized up to 1 CFU in 15.96 hr. The slowly growing bacteria P. acnes was detected up to 10,000 CFU in 129.36 hr. In comparison with conventional culture method, BacT/ALERT 3D automated culture system was more sensitive and saved detection time up to$2\sim10$ hr. Therefore, this automated culture system enables to efficiently detect bacteria in clinical samples and biological medicines.

• Progress in Medical Physics
• /
• v.30 no.2
• /
• pp.49-58
• /
• 2019

Purpose: Automated analytical systems have begun to emerge as a database system that enables the scanning of medical images to be performed on computers and the construction of big data. Deep-learning artificial intelligence (AI) architectures have been developed and applied to medical images, making high-precision diagnosis possible. Materials and Methods: For diagnosis, the medical images need to be labeled and standardized. After pre-processing the data and entering them into the deep-learning architecture, the final diagnosis results can be obtained quickly and accurately. To solve the problem of overfitting because of an insufficient amount of labeled data, data augmentation is performed through rotation, using left and right flips to artificially increase the amount of data. Because various deep-learning architectures have been developed and publicized over the past few years, the results of the diagnosis can be obtained by entering a medical image. Results: Classification and regression are performed by a supervised machine-learning method and clustering and generation are performed by an unsupervised machine-learning method. When the convolutional neural network (CNN) method is applied to the deep-learning layer, feature extraction can be used to classify diseases very efficiently and thus to diagnose various diseases. Conclusions: AI, using a deep-learning architecture, has expertise in medical image analysis of the nerves, retina, lungs, digital pathology, breast, heart, abdomen, and musculo-skeletal system.

• Journal of Yeungnam Medical Science
• /
• v.18 no.1
• /
• pp.13-29
• /
• 2001

The enzyme activities of creatine kinase (CK), its isoenzyme MB (CK-MB) and of lactate dehydrogenase isoenzyme 1 (LD-1) have been used for years in diagnosing patients with chest pain in order to differentiate patients with acute myocardial infarction (AMI) from non-AMI patients. These methods are easy to perform as automated analyses, but they are not specific for cardiac muscle damage. During the early 90's the situation changed. First, creatine kinase ME mass (CK-MB mass) replaced the measurement of CK-MB activity. Subsequently cardiac-specific proteins, troponin T (cTnT) and troponin I (cTnI) appeared and displacing LD-1 analysis. However, troponin concentrations in blood increase only from four to six hours after onset of chest pain. Therefore a rapid marker such as myoglobin, fatty acid binding protein or glycogen phosphorylase BB could be used in early diagnosis of AMI. On the other hand, CK-MB isoforms alone may also be useful in rapid diagnosis of cardiac muscle damage. Myoglobin, CK-MB mass, cTnT and cTnI are nowadays widely used in diagnosing patients with acute chest pain. Myoglobin is not cardiac-specific and therefore requires supplementation with some other analyses such as troponins to support the myoglobin value. Troponins are very highly cardiac-specific. Only the sera of some patients with severe renal failure, which requires hemodialysis, have elevated cTnT and/or cTnI without there being any evidence of cardiac damage. The latest studies have shown that elevated troponin levels in sera of hemodialysis patients point to an increased risk of future cardiac events in a similar manner to the elevated troponin values in sera of patients with unstable angina pectoris. In addition, the bedside tests for cTnT and cTnI alone- or together with myoglobin and CK-ME mass can be used instead of quantitative analyses in the diagnosis of patients with chest pain. These rapid tests are easy to perform and they do not require expensive instrumentation. For the diagnosis of patient with chest pain, routinely myoglobin and CK-ME mass measurements should be performed whenever they are requested (24 h/day) and cTnT or cTnI on admission to the hospital and then 4-6 and 12 hours later and maintained less than 10% in imprecision.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.11
• /
• pp.395-398
• /
• 1997

Human pulse represents the physical characteristics of heart and cardiovascular system. Therefore, malfunctions and errors of heart and cardiovascular system can be determined by using an automatic diagnosis system that can detect the pulse signal. Not only will the computerised system preclude the possibilities of observational errors by giving an accurate measurement with great stability, but minimize the possibilities of misinterpretation by using an automated diagnostic logic. A new combinational fiber-optic sensor, which has a detecting part and a transmitting part was used to acquire radial pulse signal noninvasively. The development of P-5 transducer makes it possible to obtain more effective detection and obvious display of pulse signals in the aspect of reliability. Using P-5 transducer in the field of plethysomography and MAC- JIN, one of our diagnoses in Korean traditional medicine, it is expected that we can ontain quantitative and valuable information or the diagnosis of human pulses.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.945-961
• /
• 2019

Tongue diagnosis is one of the most important diagnostic methods in Traditional Chinese Medicine (TCM). Tongue image segmentation aims to extract the image object (i.e., tongue body), which plays a key role in the process of manufacturing an automated tongue diagnosis system. It is still challenging, because there exists the personal diversity in tongue appearances such as size, shape, and color. This paper proposes an innovative segmentation method that uses image thresholding, gray projection and active contour model (ACM). Specifically, an initial object region is first extracted by performing image thresholding in HSI (i.e., Hue Saturation Intensity) color space, and subsequent morphological operations. Then, a gray projection technique is used to determine the upper bound of the tongue body root for refining the initial object region. Finally, the contour of the refined object region is smoothed by ACM. Experimental results on a dataset composed of 100 color tongue images showed that the proposed method obtained more accurate segmentation results than other available state-of-the-art methods.

• KNOM Review
• /
• v.23 no.1
• /
• pp.18-25
• /
• 2020

Recently, a research on a smart factory was developed from a concept of factory automation(FA) to the formation of collecting and analyzing data. This trend is accelerated as the development of communication technology(5G) and IoT devices are developed in various ways according to the field situation. In addition, digital transformation has been actively conducted in the strengthening corporate competitiveness, and various optimization studies are being conducted through process re-adjustment by combining data received from various IoT equipment and automated facilities. Therefore, in this paper, we propose a system architecture and its related components in diagnosing and repairing facility failure using a prediction system which is one of the related researches.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38C no.10
• /
• pp.887-895
• /
• 2013

Metastatic bone cancer, the cancer which occurred in the various organs and progressively spread to bone, is one of the complications in cancer patients. This cancer is divided into the osteoblast and osteolytic metastasis. Although Computer Tomography(CT) could be an useful tool in diagnosis of bone metastasis, lesions are often missed by the visual inspection and it makes clinicians difficult to detect metastasis earlier. Therefore, in this study, we construct a three-dimensional(3D) volume rendering data from tomography images of the chest CT, and apply a 3D based image processing algorithm to them for detection bone metastasis lesions. Then we perform a three-dimensional visualization of the detected lesions.From our test using 10 clinical cases, we confirmed 94.1% of average sensitivity for osteoblast, and 90.0% of average sensitivity, respectively. Consequently, our findings showed a promising possibility and potential usefulness in diagnosis of metastastic bone cancer.

• The Korean Journal of Cytopathology
• /
• v.9 no.1
• /
• pp.55-61
• /
• 1998

To compare the diagnostic yields and complication rates of transthoracic fine needle aspiration cytology(FNAC) and gun biopsy in the diagnosis of pulmonary mass, a retrospective review was performed in 125 cases. Under the fluoroscopic guide, FNAC was performed by 20G Chiba needle in 91 cases, core biopsy was done by 18.5 G vaccum needle attached with automated biopsy gun in 74 cases and both procedures were done together in 37 cases. Overall sensitivity was 88.4% in FNAC and 87.5% in gun biopsy. For malignant pulmonary tumors, correct type correlation with final diagnosis was obtained in 33(76.7%) out of 43 cases by FNAC and 30(75.0%) out of 40 cases by gun biopsy. For benign pulmonary lesions, there were correct type correlation in 14(35.0%) out of 40 cases by FNAC and 14(53.8%) out of 26 cases by gun biopsy. The complication was pneumothorax and hemoptysis. Pneumothorax occured in 11.1% of FNAC, 10.9% of gun biopsy and 10.9% of both technique, among which chest tube drainages were necessary in one patient by gun biopsy and in three patients by both technique. Although no significant difference of diagnositc accuracy and complication rate was found between FNAC and gun biopsy, gun biopsy was more helpful in the diagnosis of pulmonary benign lesions than FNAC.