• Journal of the Korean Society of Radiology
• /
• v.18 no.3
• /
• pp.267-273
• /
• 2024

Using a cloud-based vertex AI platform that can develop an artificial intelligence learning model without coding, this study easily developed an artificial intelligence learning model by the non-professional general public and confirmed its clinical applicability. Nine dental diseases and 2,999 root disease X-ray images released on the Kaggle site were used for the learning data, and learning, verification, and test data images were randomly classified. Image classification and multi-label learning were performed through hyper-parameter tuning work using a learning pipeline in vertex AI's basic learning model workflow. As a result of performing AutoML(Automated Machine Learning), AUC(Area Under Curve) was found to be 0.967, precision was 95.6%, and reproduction rate was 95.2%. It was confirmed that the learned artificial intelligence model was sufficient for clinical diagnosis.

• Journal of Biomedical Engineering Research
• /
• v.41 no.5
• /
• pp.195-202
• /
• 2020

Needle detection in ultrasound images is sometimes difficult due to obstruction of fat tissues. Accurate needle detection using continuous ultrasound (CUS) images is a vital stage of treatment planning for tissue biopsy and brachytherapy. The main goal of the study is classified into two categories. First, new detection model, i.e. D-Attention Unet, is developed by combining the context information of 3D medical data and CUS images. Second, the D-Attention Unet model was compared with other models to verify its usefulness for needle detection in continuous ultrasound images. The continuous needle images taken with ultrasonic waves were converted into still images for dataset to evaluate the performance of the D-Attention Unet. The dataset was used for training and testing. Based on the results, the proposed D-Attention Unet model showed the better performance than other 3 models (Unet, D-Unet and Attention Unet), with Dice Similarity Coefficient (DSC), Recall and Precision at 71.9%, 70.6% and 73.7%, respectively. In conclusion, the D-Attention Unet model provides accurate needle detection for US-guided biopsy or brachytherapy, facilitating the clinical workflow. Especially, this kind of research is enthusiastically being performed on how to add image processing techniques to learning techniques. Thus, the proposed method is applied in this manner, it will be more effective technique than before.

• Journal of Dental Rehabilitation and Applied Science
• /
• v.31 no.2
• /
• pp.158-168
• /
• 2015

This article describes how to use digital system in a fully edentulous case that diagnosis to definitive prosthesis fabrication. While proceeding oral scan and CBCT taking, digital markers were attached on maxillary palate and lower existing denture. Using CBCT image and oral scan image, the bone contour and anatomical structures were analyzed and flapless surgical guide, customized abutment and prosthesis were made. After the osseointegration, the definitive prosthesis was fabricated using the oral scan image with scan body. It provides clinicians with a fast workflow and improves clinical efficiency.

• Journal of Korean society of Dental Hygiene
• /
• v.19 no.1
• /
• pp.33-44
• /
• 2019

Objectives: To investigate how dental hygienists who have never used a digital oral scanner perceive the impression acquisition and evidence needed for prosthesis planning by using a digital oral scanner. Methods: From July 1, 2017 to December 31, 2017, subjects from Daegu, Gyeongsangbuk-do, Korea, were selected. The purpose of the study was described to dental hygienists who had never used a digital intraoral scanner. Questionnaires were distributed to the students selected. Of the 137 questionnaires distributed, 93 were used in the analysis after excluding 44 completed questionnaires that had errors or missing answers. Results: Of the respondents, 33.7% (36/93) were aged ${\geq}30$ years, 68.8% graduated from a 3-year vocational college course, 33.5% were aged ${\geq}33$ years, and 61.3%. At present, our center has the largest number of clinics (92.5%). The difficulty of impression taking using the digital oral scanner significantly differed (p<0.05) according to age and current occupation (p<0.05). Impression taking using a digital oral scanner significantly affected the present workflow of dental hygienists and their interest in sharing information about future use of digital oral scanner (p<0.01). Conclusions: If more routes are available to access digital intraoral scanners and more systems are developed for clinical use, the digital intraoral scanner could become digitized in the dental system; thereby, the existing impressions could be replaced with digitized impressions. With digital intraoral scanners, the expansion of the business of dental hygiene can be expected.

• Progress in Medical Physics
• /
• v.31 no.3
• /
• pp.111-123
• /
• 2020

Deep learning (DL) is a subset of machine learning and artificial intelligence that has a deep neural network with a structure similar to the human neural system and has been trained using big data. DL narrows the gap between data acquisition and meaningful interpretation without explicit programming. It has so far outperformed most classification and regression methods and can automatically learn data representations for specific tasks. The application areas of DL in radiation oncology include classification, semantic segmentation, object detection, image translation and generation, and image captioning. This article tries to understand what is the potential role of DL and what can be more achieved by utilizing it in radiation oncology. With the advances in DL, various studies contributing to the development of radiation oncology were investigated comprehensively. In this article, the radiation treatment process was divided into six consecutive stages as follows: patient assessment, simulation, target and organs-at-risk segmentation, treatment planning, quality assurance, and beam delivery in terms of workflow. Studies using DL were classified and organized according to each radiation treatment process. State-of-the-art studies were identified, and the clinical utilities of those researches were examined. The DL model could provide faster and more accurate solutions to problems faced by oncologists. While the effect of a data-driven approach on improving the quality of care for cancer patients is evidently clear, implementing these methods will require cultural changes at both the professional and institutional levels. We believe this paper will serve as a guide for both clinicians and medical physicists on issues that need to be addressed in time.

• The Journal of Advanced Prosthodontics
• /
• v.15 no.1
• /
• pp.22-32
• /
• 2023

PURPOSE. Digital technology has enabled improvements in the fitting accuracy of denture bases via milling techniques. The aim of this study was to evaluate the trueness and precision of digital and analog techniques for manufacturing complete dentures (CDs). MATERIALS AND METHODS. Sixty identical CDs were manufactured using different production protocols. Digital and analog technologies were compared using the reference geometric approach, and the Δ-error values of eight areas of interest (AOI) were calculated. For each AOI, a precise number of measurement points was selected according to sensitivity analyses to compare the Δ-error of trueness and precision between the original model and manufactured prosthesis. Three types of statistical analysis were performed: to calculate the intergroup cumulative difference among the three protocols, the intergroup among the AOIs, and the intragroup difference among AOIs. RESULTS. There was a statistically significant difference between the dentures made using the oversize process and injection molding process (P < .001), but no significant difference between the other two manufacturing methods (P = .1227). There was also a statistically significant difference between the dentures made using the monolithic process and the other two processes for all AOIs (P = .0061), but there was no significant difference between the other two processes (P = 1). Within each group, significant differences among the AOIs were observed. CONCLUSION. The monolithic process yielded better results, in terms of accuracy (trueness and precision), than the other groups, although all three processes led to dentures with Δ-error values well within the clinical tolerance limit.

• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.141-147
• /
• 2022

In a broad sense, the definition of digital health care is an industrial area that manages personal health and diseases through the convergence of the health care industry and ICT. In a narrow sense, various medical technologies are used to manage medical services to improve patient health. This paper aims to provide design guidelines so that artificial intelligence technology can be applied stably and efficiently to more diverse digital health care fields in the future by introducing use cases of artificial intelligence and machine learning techniques applied in the digital health care field. For this purpose, in this thesis, the medical field and the daily life field are divided and examined. The two regions have different data characteristics. By further subdividing the two areas, we looked at the use cases of artificial intelligence algorithms according to data characteristics and problem definitions and characteristics. Through this, we will increase our understanding of artificial intelligence technologies used in the digital health care field and examine the possibility of using various artificial intelligence technologies.

• Hip & pelvis
• /
• v.36 no.1
• /
• pp.26-36
• /
• 2024

Total hip arthroplasty (THA) is a frequently performed procedure; the objective is restoration of native hip biomechanics and achieving functional range of motion (ROM) through precise positioning of the prosthetic components. Advanced three-dimensional (3D) imaging and computed tomography (CT)-based navigation are valuable tools in both the preoperative planning and intraoperative execution. The aim of this study is to provide a thorough overview on the applications of CT scans in both the preoperative and intraoperative settings of primary THA. Preoperative planning using CT-based 3D imaging enables greater accuracy in prediction of implant sizes, leading to enhancement of surgical workflow with optimization of implant inventory. Surgeons can perform a more thorough assessment of posterior and anterior acetabular wall coverage, acetabular osteophytes, anatomical landmarks, and thus achieve more functional implant positioning. Intraoperative CT-based navigation can facilitate precise execution of the preoperative plan, to attain optimal positioning of the prosthetic components to avoid impingement. Medial reaming can be minimized preserving native bone stock, which can enable restoration of femoral, acetabular, and combined offsets. In addition, it is associated with greater accuracy in leg length adjustment, a critical factor in patients' postoperative satisfaction. Despite the higher costs and radiation exposure, which currently limits its widespread adoption, it offers many benefits, and the increasing interest in robotic surgery has facilitated its integration into routine practice. Conducting additional research on ultra-low-dose CT scans and examining the potential for translation of 3D imaging into improved clinical outcomes will be necessary to warrant its expanded application.

• Journal of Genetic Medicine
• /
• v.7 no.1
• /
• pp.59-66
• /
• 2010

Purpose: Quantitative fluorescent polymerase chain reaction (QF-PCR) allows for the rapid prenatal diagnosis of common aneuploidies. The main advantages of this assay are its low cost, speed, and automation, allowing for large-scale application. However, despite these advantages, it is not a routine method for prenatal aneuploidy screening in Korea. Our objective in the present study was to validate the performance of QF-PCR using short tandem repeat (STR) markers in a Korean population as a means for rapid prenatal diagnosis. Material and Methods: A QF-PCR assay using an Elucigene kit (Gen-Probe, Abingdon, UK), containing 20 STR markers located on chromosomes 13, 18, 21, X and Y, was performed on 847 amniotic fluid (AF) samples for prenatal aneuploidy screening referred for prenatal aneuploidy screening from 2007 to 2009. The results were then compared to those obtained using conventional cytogenetic analysis. To evaluate the informativity of STR markers, the heterozygosity index of each marker was determined in all the samples. Results: Three autosomes (13, 18, and 21) and X and Y chromosome aneuploidies were detected in 19 cases (2.2%, 19/847) after QF-PCR analysis of the 847 AF samples. Their results are identical to those of conventional cytogenetic analysis, with 100% positive predictive value. However, after cytogenetic analysis, 7 cases (0.8%, 7/847) were found to have 5 balanced and 2 unbalanced chromosomal abnormalities that were not detected by QF-PCR. The STR markers had a slightly low heterozygosity index (average: 0.76) compared to those reported in Caucasians (average: 0.80). Submicroscopic duplication of D13S634 marker, which might be a unique finding in Koreans, was detected in 1.4% (12/847) of the samples in the present study. Conclusion: A QF-PCR assay for prenatal aneuploidy screening was validated in our institution and proved to be efficient and reliable. However, we suggest that each laboratory must perform an independent validation test for each STR marker in order to develop interpretation guidelines of the results and must integrate QF-PCR into the routine cytogenetic laboratory workflow.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.17
• /
• pp.7085-7090
• /
• 2014

Objective: To make the clinical evaluation of a solid-state human papillomavirus (HPV) sampling medium in combination with an economical HPV testing method ($careHPV^{TM}$) for cervical cancer screening. Methods: 396 women aged 25-65 years were enrolled for cervical cancer screening, and four samples were collected. Two samples were collected by woman themselves, among which one was stored in DCM preservative solution (called "liquid sample") and the other was applied on the Whatman Indicating FTA $Elute^{(R)}$ card (FTA card). Another two samples were collected by physician and stored in DCM preservative solution and FTA card, respectively. All the samples were detected by $careHPV^{TM}$ test. All the women were administered a colposcopy examination, and biopsies were taken for pathological confirmation if necessary. Results: FTA card demonstrated a comparable sensitivity of detecting high grade Cervical Intraepithelial Neoplasia (CIN) with the liquid sample carrier for self and physician-sampling, but showed a higher specificity than that of liquid sample carrier for self-sampling (FTA vs Liquid: 79.0% vs 71.6%, p=0.02). Generally, the FTA card had a comparable accuracy with that of Liquid-based medium by different sampling operators, with an area under the curve of 0.807 for physician &FTA, 0.781 for physician &Liquid, 0.728 for self & FTA, and 0.733 for self &Liquid (p>0.05). Conclusions: FTA card is a promising sample carrier for cervical cancer screening. With appropriate education programmes and further optimization of the experimental workflow, FTA card based self-collection in combination with centralized $careHPV^{TM}$ testing can help expand the coverage of cervical cancer screening in low-resource areas.