• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2007년도 춘계학술발표대회
• /
• pp.326-327
• /
• 2007

We investigated whether the CT images of hepatic lesions could be analyzed by computer-aided diagnosis (CAD) tool. We retrospectively reanalyzed 14 liver CT images (10 hepatocellular cancers and 4 benign liver lesions; patients who presented with hepatic masses). The hepatic lesions on CT were segmented by rectangular ROI technique and the morphologic features were extracted and quantitated using fractal texture analysis. The contrast enhancement of hepatic lesions was also quantified and added to the differential diagnosis. The best discriminating function combining the textural features and the values of contrast enhancement of the lesions was created using linear discriminant analysis. Textural feature analysis showed moderate accuracy in the differential diagnosis of hepatic lesions, but statistically insignificant. Combining textural analysis and contrast enhancement value resulted in improved diagnostic accuracy, but further studies are needed.

• 대한한의진단학회지
• /
• 제14권1호
• /
• pp.70-78
• /
• 2010

Objectives : To qualify or enhance the diagnostic ability of students in Oriental Medicine, so called standardized patients are ideal modality, but because it's a man-based method, more convenient tools are required. Computer-based diagnostic ability test program gives effective way for the very purpose. So we made a pilot software evaluating Pattern Identification ability in Oriental Medicine. Methods and Materials : The pilot software was coded with Microsoft's EXCEL VBA. 87 names of Zheng (Symptom Pattern) and 674 names of symptom (including some signs) are adopted from the former standardization works conducted by Korean Institute of Oriental Medicine (KIOM) in 1996. Results : Compared with some manned modalities to test Pattern Identification ability, the test by this software shows superiority in convenience and objectivity. Conclusion : This software is world's first program to perform computer-based evaluation of Pattern Identification in Oriental Medicine, and it gives effective way to complement both written test and manned clinical performance test (CPX).

• 재활복지공학회논문지
• /
• 제10권1호
• /
• pp.87-92
• /
• 2016

본 논문에는 관심 영역의 폐실질 영역을 양성과 악성 결절의 분류를 위한 특징인자에 포함으로써 분류성능을 개선하였다. CT를 통해 확인되는 매우 작은 폐결절(4~10mm)은 고형 종양 내에 CT 데이터 복셀 수가 제한되어 기존 컴퓨터보조 진단도구를 통해 처리하기가 어렵다. 이러한 아주 작은 폐 결절의 경우 분석을 위해 주변의 실질을 포함하여 특징인자를 추출하는 것이 CT 복셀 세트를 증가시킬 수 있으며, CT 스캐너와 매개 변수에 대한 컴퓨터 보조진단도구의 유연성을 확보함으로써 진단 성능을 개선할 수 있다. 나이브 베이스와 SVM 약분류기를 이용하는 아다부스트 학습을 통해 304개의 특징인자로부터 유효한 특징인자를 결정하였으며, 제안한 방법을 COPDGene 데이터에 적용한 결과 100%의 정확도, 민감도 및 특이도의 결과를 획득하여 컴퓨터 보조진단에 유용하게 사용될 수 있음을 보였다.

• Nuclear Medicine and Molecular Imaging
• /
• 제41권3호
• /
• pp.201-208
• /
• 2007

목적: 유방암의 감별진단에서 기존의 유방 초음파 검사나 핵의학 유방SPECT의 진단성능에는 한계가 있다. 저자들은 초음파 컴퓨터진단시스템(CAD: computer aided diagnosis)의 적용에 의하여 유방 SPECT의 진단성능이 향상되는지를 알아보았다. 대상 및 방법: 유방초음파 및 유방 SPECT(Tc-99m tetrofosmin)를 시행하고 수술후 확진된 여자환자 40명(21명:악성종양, 19명:양성병변)의 영상자료를 분석하였다. 유방초음파영상을 컴퓨터분석 소프트웨어를 이용하여 병변의 경계를 분리한 후, 영상의 형태학적 특성들을 추출하였다. 초음파영상에서 추출된 형태학적 특성 중에서 감별능력이 있는 것으로 판단된 특성들을 골라 정량화하였다. 정량화된 형태학적 특성값들을 유방SPECT에서 구한 병변 대 반대측 유방의 방사능비와 판별분석에 의하여 결합하여 새로운 파라메터인 D-수치를 산출하였다. 유방SPECT의 병변 방사능비, 유방초음파 컴퓨터진단시스템의 악성확률 및 두가지를 결합한 D-수치에 대하여 수신자판단특성곡선(ROC curve) 분석을 이용하여 최적 판별 수치(cut-off value)를 구하고 이에 의한 유방암 진단의 예민도, 특이도 및 정확도를 계산하여 유방 SPECT과 초음파 컴퓨터진단시스템의 결합에 의한 진단성능을 기존의 유방 SPECT의 진단성능과 비교하였다. 결과: ROC curve분석상에서 유방암 진단에 대한 성능은 유방초음파의 컴퓨터 분석시스템 및 유방SPECT 각각 모두 우수하였다(area under curve=0.831 and 0.846). 두 결과를 통계적인 방법으로 결합하였을 때 ROC curve분석의 area under curve는(0.860) 향상되었으나, 최적 판별 수치(cut-off value)에 의한 유방암 진단의 예민도, 특이도 및 정확도에는 통계적인 차이는 없었다. 결론: 유방초음파의 컴퓨터분석시스템의 결과를 유방 SPECT에 적용하여 유방암의 진단성능을 향상시킬 수 있었지만 통계적으로는 유의하지 못하였다. 향후 추가적인 연구가 필요할 것으로 보인다.

• 대한유전성대사질환학회지
• /
• 제6권1호
• /
• pp.40-51
• /
• 2006

Purpose: A personal computer-based system was developed for automated metabolic profiling of organic aciduria and aminoacidopathy by gas chromatography-mass spectrometry and data interpretation for the diagnosis of metabolic disorders Methods: For automatic data profiling and interpretation, we compiled retention time, two target ions and their intensity ratio for 77 organic acids and 13 amino acids metabolites. Metabolites above the cut-off values were flagged as abnormal compounds. The data interpretation was a based on combination of flagged metabolites. Diagnostic or index metabolites were categorized into three groups, "and", "or" and "NO" compiled for each disorder to improve the specificity of the diagnosis. Groups "and" and "or" comprised essential and optional compounds, respectively, to reach a specific diagnosis. Group "NO" comprised metabolites that must be absent to make a definite diagnosis. We tested this system by analyzing patients with confirmed Propionic aciduria and others. Results: In all cases, the diagnostic metabolites were identified and correct diagnosis was founded to be made among the possible disease suggested by the system. Conclusion: The study showed that the developed method could be the method of choices in rapid, sensitive and simultaneous screening for organic aciduria and amino acidopathy with this simplified automated system.

• Korean Journal of Radiology
• /
• 제21권10호
• /
• pp.1150-1160
• /
• 2020

Objective: To describe the experience of implementing a deep learning-based computer-aided detection (CAD) system for the interpretation of chest X-ray radiographs (CXR) of suspected coronavirus disease (COVID-19) patients and investigate the diagnostic performance of CXR interpretation with CAD assistance. Materials and Methods: In this single-center retrospective study, initial CXR of patients with suspected or confirmed COVID-19 were investigated. A commercialized deep learning-based CAD system that can identify various abnormalities on CXR was implemented for the interpretation of CXR in daily practice. The diagnostic performance of radiologists with CAD assistance were evaluated based on two different reference standards: 1) real-time reverse transcriptase-polymerase chain reaction (rRT-PCR) results for COVID-19 and 2) pulmonary abnormality suggesting pneumonia on chest CT. The turnaround times (TATs) of radiology reports for CXR and rRT-PCR results were also evaluated. Results: Among 332 patients (male:female, 173:159; mean age, 57 years) with available rRT-PCR results, 16 patients (4.8%) were diagnosed with COVID-19. Using CXR, radiologists with CAD assistance identified rRT-PCR positive COVID-19 patients with sensitivity and specificity of 68.8% and 66.7%, respectively. Among 119 patients (male:female, 75:44; mean age, 69 years) with available chest CTs, radiologists assisted by CAD reported pneumonia on CXR with a sensitivity of 81.5% and a specificity of 72.3%. The TATs of CXR reports were significantly shorter than those of rRT-PCR results (median 51 vs. 507 minutes; p < 0.001). Conclusion: Radiologists with CAD assistance could identify patients with rRT-PCR-positive COVID-19 or pneumonia on CXR with a reasonably acceptable performance. In patients suspected with COVID-19, CXR had much faster TATs than rRT-PCRs.

• 한국콘텐츠학회논문지
• /
• 제14권11호
• /
• pp.362-369
• /
• 2014

본 연구는 골다공증 환자의 Digital 요추 측부 영상을 이용하여 질감특징의 통계적 분석으로 컴퓨터 보조진단 시스템 구현과 질병의 조기진단 및 치료를 위한 실험적인 모형 연구로 신뢰성 있는 보조적 진단 정보를 제공함으로써 골다공증에 대한 정확한 진단 방향을 제시하고자 하였다. 이를 위해서 정상인의 Digital 방사선 요추 측부 영상과 골다공증 환자의 Digital 방사선 요추 측부 영상을 실험 영상으로 하여 설정된 ROI에 대한 통계적 질감특징 값을 6가지 parameter로 나타냈다. 골다공증에 대한 질감특징분석 값 중 Average Gray Level에서 95%로 최고 높은 인식률을 나타내었고, Uniformity에서 80%로 가장 낮은 인식률을 나타내었다. 또한 Average Contrast에서 82.5%, Smoothness에서 90%, Skewness에서 87.5%, Entropy에서 87.5%를 나타내어 6가지 Parameter에서 모두 80%이상의 높은 인식률을 나타내 알고리즘의 안정성을 입증하였다. 따라서 본 연구 결과를 토대로 의료영상의 컴퓨터자동진단 시스템으로 발전된 프로그램을 coding 한다면 의료영상의 병소부위 자동검출, 질병 진단을 위한 예비 진단자료, 질병의 확진을 위한 자료제공, 제한된 장비로도 진단 가능, 의료영상의 판독시간 단축에 유용하게 사용될 수 있으리라 사료된다.

• 공학교육연구
• /
• 제16권1호
• /
• pp.54-63
• /
• 2013

This study aims to investigate relationships among self-directed learning readiness [SDLR], prerequisite mathematics test score and achievement level in college mathematics. For this purpose, the adjusted SDLRS (self-directed learning readiness scale) of Guglielmino's model, the score of mathematics diagnostic assesment and first semester college mathematics score among 424 freshmen students of engineering department of D university in 2011 were used and analyzed. Research results are as follows: Firstly, freshmen of engineering department had average level of SDLR, though they showed relative low level of self-direction, passion and time control ability. Secondly, considering SDLR with the mathematics diagnostic assesment score (3 groups: high, middle, low), there were no statistically significant differences. Thirdly, concerning SDLR according to the achievement level in college mathematics, a group which acquired good achievement showed higher level of SDLR compared with middle or lowachievement group. Differences among three groups were statistically significant. Lastly, there were affirmative relationships between SDLR, mathematics diagnostic assesment score and achievement in college mathematics. Furthermore, mathematics diagnostic assesment score and achievement level in college mathematics were found to be the most closely related. Based on the results, we suggest strategies to elevate SDLR of engineering department students and improve their achievement in college mathematics.

• International Journal of Computer Science & Network Security
• /
• 제24권4호
• /
• pp.67-76
• /
• 2024

Diabetic retinopathy is a threatening complication of diabetes, caused by damaged blood vessels of light sensitive areas of retina. DR leads to total or partial blindness if left untreated. DR does not give any symptoms at early stages so earlier detection of DR is a big challenge for proper treatment of diseases. With advancement of technology various computer-aided diagnostic programs using image processing and machine learning approaches are designed for early detection of DR so that proper treatment can be provided to the patients for preventing its harmful effects. Now a day machine learning techniques are widely applied for image processing. These techniques also provide amazing result in this field also. In this paper we discuss various machine learning and deep learning based techniques developed for automatic detection of Diabetic Retinopathy.

• Korean Journal of Radiology
• /
• 제24권9호
• /
• pp.890-902
• /
• 2023

Objective: The clinical impact of artificial intelligence-based computer-aided detection (AI-CAD) beyond diagnostic accuracy remains uncertain. We aimed to investigate the influence of the clinical implementation of AI-CAD for chest radiograph (CR) interpretation in daily practice on the rate of referral for chest computed tomography (CT). Materials and Methods: AI-CAD was implemented in clinical practice at the Seoul National University Hospital. CRs obtained from patients who visited the pulmonology outpatient clinics before (January-December 2019) and after (January-December 2020) implementation were included in this study. After implementation, the referring pulmonologist requested CRs with or without AI-CAD analysis. We conducted multivariable logistic regression analyses to evaluate the associations between using AI-CAD and the following study outcomes: the rate of chest CT referral, defined as request and actual acquisition of chest CT within 30 days after CR acquisition, and the CT referral rates separately for subsequent positive and negative CT results. Multivariable analyses included various covariates such as patient age and sex, time of CR acquisition (before versus after AI-CAD implementation), referring pulmonologist, nature of the CR examination (baseline versus follow-up examination), and radiology reports presence at the time of the pulmonology visit. Results: A total of 28546 CRs from 14565 patients (mean age: 67 years; 7130 males) and 25888 CRs from 12929 patients (mean age: 67 years; 6435 males) before and after AI-CAD implementation were included. The use of AI-CAD was independently associated with increased chest CT referrals (odds ratio [OR], 1.33; P = 0.008) and referrals with subsequent negative chest CT results (OR, 1.46; P = 0.005). Meanwhile, referrals with positive chest CT results were not significantly associated with AI-CAD use (OR, 1.08; P = 0.647). Conclusion: The use of AI-CAD for CR interpretation in pulmonology outpatients was independently associated with an increased frequency of overall referrals for chest CT scans and referrals with subsequent negative results.