• 산업공학
• /
• 제21권4호
• /
• pp.394-402
• /
• 2008

The objective of this paper is to design segmentation algorithm for applying the breast ultrasound image to CAD(Computer Aided Diagnosis). This study is conducted after understanding limits, used algorithm and demands of CAD system by interviewing with a medical doctor and analyzing related works based on a general CAD framework that is consisted of five step-establishment of plan, analysis of needs, design, implementation and test & maintenance. Detection function of CAD is accomplished by Canny algorithm and arithmetic operations for segmentation. In addition to, long computing time is solved by extracting ROI (Region Of Interests) and applying segmentation technical methods based morphology algorithm. Overall course of study is conducted by verification of medical doctor. And validity and verification are satisfied by medical doctor's confirmation. Moreover, manual segmentation of related works, restrictions on the number of tumor and dependency of image resolution etc. was solved. This study is utilized as a support system aided doctors' subjective diagnosis even though a lot of future studies is needed for entire application of CAD system.

• Imaging Science in Dentistry
• /
• 제46권4호
• /
• pp.245-249
• /
• 2016

Purpose: This study was designed to evaluate differences in the required visibility of anatomic structures according to the diagnostic tasks of implant planning and periapical diagnosis. Materials and Methods: Images of a real skull phantom were acquired under 24 combinations of different exposure conditions in a cone-beam computed tomography scanner (60, 70, 80, 90, 100, and 110 kV and 4, 6, 8, and 10 mA). Five radiologists evaluated the visibility of anatomic structures and the image quality for diagnostic tasks using a 6-point scale. results: The visibility of the periodontal ligament space showed the closest association with the ability to use an image for periapical diagnosis in both jaws. The visibility of the sinus floor and canal wall showed the closest association with the ability to use an image for implant planning. Variations in tube voltage were associated with significant differences in image quality for all diagnostic tasks. However, tube current did not show significant associations with the ability to use an image for implant planning. conclusion: The required visibility of anatomic structures varied depending on the diagnostic task. Tube voltage was a more important exposure parameter for image quality than tube current. Different settings should be used for optimization and image quality evaluation depending on the diagnostic task.

• 한국컴퓨터정보학회논문지
• /
• 제13권6호
• /
• pp.87-94
• /
• 2008

홍채진단은 홍채의 패턴, 색, 기타 다른 특징들을 조사하여 환자의 병을 진단하는 대체의학이다. 그러나 기존의 연구는 흑백 홍채영상을 이용하여 홍채 내의 특정 패턴을 검출하는 알고리즘 연구로 홍채의 칼라 정보로부터 건강상태를 체크하는 진단시스템으로 사용하기에는 부족하다. 본 논문에서는 칼라 홍채영상과 의료정보 데이터베이스를 이용하는 홍채진단시스템을 개발하였다. 개발한 시스템은 홍채카메라는 갖는 입력모듈, 홍채병소징후 검출 모듈, 의료정보 데이터베이스, 출력 모듈 등 4가지 모듈로 되어있다. 칼라 홍채영상으로부터 7가지 주요 홍채병소징후를 추출하고 검진의 정확도를 위해 병소 수동 편집 기능을 제공한다. 병소를 분석하는 단계에서는 홍채학에 기반한 의료정보와 개인 이력 관리 모듈을 이용한다. 제안한 시스템은 기존 시스템의 비해 다양한 기능이 추가되어 홍채진단 시스템으로 활용 가능하다.

• Journal of Chest Surgery
• /
• 제18권4호
• /
• pp.563-568
• /
• 1985

Two cases of situs inversus totalis with isolated congenital heart disease were treated at department of cardiothoracic surgery, Chungnam National University Hospital. Sixteen months old girl was operated under diagnosis of PDA with mirro-image dextrocardia by triple ligation. Fifteen months old girl was managed under diagnosis of VSD with mirro-image dextrocardia by simple closure of VSD with extracorporeal circulation. The former had smooth postoperative course, but the latter was died of asphyxia due to vomitus on postoperative second day

• 대한의용생체공학회:의공학회지
• /
• 제26권4호
• /
• pp.185-191
• /
• 2005

In this paper, we proposed a downscaled 3D object technique using medical images for telediagnostic use. The proposed system consisted of downscaling/thresholding processes for building a downscaled 3D object and a process for obtaining 2D images at specific angles for diagnosis support. We used 80 slices of Digital Imaging and Communication in Medicine(DICOM) CT images as sample images and the platform-independent Java language for the experiment. We confirmed that the total image set size and transmission time of the original DICOM image set using a down-scaled 3D object decreased approximately $99\%\;and\;98.41\%,$ respectively. With additional studies, the proposed technique obtained from these results will become useful in supporting diagnosis for home and hospital care.

• 한국통신학회논문지
• /
• 제32권4C호
• /
• pp.389-395
• /
• 2007

기존의 필름 X-Ray 및 CCD(Charge Coupled Device) 방식은 공간적인 제약과 진단 시간이 많이 걸리는 단점이 있다. 본 논문에서는 기존 방식들의 단점을 보완할 수 있는 TFT-DXD 방식의 digital X-ray detector (DR1000C)를 이용한 고효율 의료 영상처리시스템을 구현하였다. 본 논문에서 제안하는 DR1000C를 이용한 의료용 영상처리시스템은 기존의 X-Ray 방식에 비해 공간 효율성이 높고 진단 시간이 짧아진다는 장점이 있다. 영상처리시스템에서 획득한 영상을 고화질로 만들기 위해 1900*1200의 해상도를 가지는 LCD 컨트롤 드라이버를 개발하였고, 영상의 성능향상을 위해 enhancement unsharp masking 기법을 제안하여, 기존의 방식과 비교하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• 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.

• Journal of International Society for Simulation Surgery
• /
• 제1권2호
• /
• pp.62-66
• /
• 2014

Image registration is the process for finding the correct geometrical transformation that brings one image in precise spatial correspondence with another image. There are limitations on the visualization of simple overlay between two different modality images because two different modality images have different anatomical information, resolution, and viewpoint. In this paper, various image registration methods and their applications are introduced. With the recent advance of medical imaging device, image registration is used actively in diagnosis support, treatment planning, surgery guidance and monitoring the disease progression.

• 대한예방한의학회지
• /
• 제26권2호
• /
• pp.25-35
• /
• 2022

Objectives : This study aims to analyze the patents filed in the clinical diagnosis sector where technologies have been actively developed since the advent of the 4th industrial revolution. Methods : The analysis has been conducted in two ways - the period from 2016 to 2021 and the time points before and after COVID-19 - by visualizing based on the word cloud method. Results : Over two thirds of patents has been filed in the A61B sector (71.8%) and cure, sensor, self diagnosis, control, and breakdown have been observed in the period above. During the overall period (2016~2021), 'ultrasound'(7.5%), 'image'(5.1%), 'skin'(4.0%), 'treatment'(3.4%), and 'artificial intelligence(2.5%)' were the frequently patent applications technologies. In addition, 'ultrasound'(6.2%), 'image'(5.5%), 'skin'(4.0%), 'treatment' (3.7%), and 'portable'(1.7%) appeared most frequently before COVID-19 whereas 'ultrasound(5.5%)', 'artificial intelligence(4.2%)', 'diagnostic device'(1.9%), 'dimentia'(1.6%), and 'diagnostic kit'(1.4%) emerged the most after COVID-19. Conclusion : This study is meaningful in that it showed the technological development trend in the digital diagnosis sector and it was found that the Korean medicine field should contribute to this field more actively in the future.

• Current Optics and Photonics
• /
• 제7권3호
• /
• pp.283-296
• /
• 2023

An intraoral spectral domain optical coherence tomography (SD-OCT) system has been developed, using a custom-built hand-held scanner and spectrometer. The hand-held OCT probe, based on a microelectromechanical systems scanner and a self-built miniaturized drive circuit, had a field of view sufficient for dental diagnosis. The spectrometer using a fabricated f-theta lens provided the image depth required for dental diagnosis. The axial and transverse resolutions of the OCT system in air were 7.5 ㎛ and 12 ㎛ respectively. The hand-held probe could scan an area of 10 × 10 mm², and the spectrometer could image along a depth of 2.5 mm. To verify the utility of the developed OCT system, OCT images of tooth hard and soft tissues were acquired, and a user-interface program for diagnosis was developed. Early caries and microcracks that were difficult to diagnose with existing methods could be found, and the state of restoration could be observed. Measuring the depth of the gingival sulcus, distinguishing subgingival calculus, and detecting an implant under the gingiva suggested the possibility of the SD-OCT system as a diagnostic for dental soft tissues. Through the presented OCT images, the capability of the developed SD-OCT system for dental diagnosis was demonstrated.