• International Journal of Computer Science & Network Security
• /
• 제22권4호
• /
• pp.101-110
• /
• 2022

Histopathological analysis of biopsy specimens is still used for diagnosis and classifying the brain tumors today. The available procedures are intrusive, time consuming, and inclined to human error. To overcome these disadvantages, need of implementing a fully automated deep learning-based model to classify brain tumor into multiple classes. The proposed CNN model with an accuracy of 92.98 % for categorizing tumors into five classes such as normal tumor, glioma tumor, meningioma tumor, pituitary tumor, and metastatic tumor. Using the grid search optimization approach, all of the critical hyper parameters of suggested CNN framework were instantly assigned. Alex Net, Inception v3, Res Net -50, VGG -16, and Google - Net are all examples of cutting-edge CNN models that are compared to the suggested CNN model. Using huge, publicly available clinical datasets, satisfactory classification results were produced. Physicians and radiologists can use the suggested CNN model to confirm their first screening for brain tumor Multi-classification.

• 한국멀티미디어학회논문지
• /
• 제25권8호
• /
• pp.1203-1211
• /
• 2022

Melanoma is a skin cancer that starts in pigment-producing cells (melanocytes). The death rates of skin cancer like melanoma can be reduced by early detection and diagnosis of diseases. It is common for doctors to spend a lot of time trying to distinguish between skin lesions and healthy cells because of their striking similarities. The detection of melanoma lesions can be made easier for doctors with the help of an automated classification system that uses deep learning. This study presents a new approach for melanoma classification based on an ensemble of deep convolution neural networks and a Log-Gabor filter. First, we create the Log-Gabor representation of the original image. Then, we input the Log-Gabor representation into a new ensemble of deep convolution neural networks. We evaluated the proposed method on the melanoma dataset collected at Yonsei University and Dongsan Clinic. Based on our numerical results, the proposed framework achieves more accuracy than other approaches.

• International Journal of Computer Science & Network Security
• /
• 제24권4호
• /
• pp.211-221
• /
• 2024

Pakistan is a top producer and exporter of high-quality rice, but traditional methods are still being used for detecting rice diseases. This research project developed an automated rice blast disease diagnosis technique based on deep learning, image processing, and transfer learning with pre-trained models such as Inception V3, VGG16, VGG19, and ResNet50. The modified connection skipping ResNet 50 had the highest accuracy of 99.16%, while the other models achieved 98.16%, 98.47%, and 98.56%, respectively. In addition, CNN and an ensemble model K-nearest neighbor were explored for disease prediction, and the study demonstrated superior performance and disease prediction using recommended web-app approaches.

• 한국의학물리학회지:의학물리
• /
• 제10권3호
• /
• pp.115-123
• /
• 1999

2 차원 심초음파는 좌심실벽 운동을 실시간으로 보여줄 수 있어 국소 좌심실벽 운동장애를 진단하는 데 널리 사용되고 있다. 심초음파를 통하여 국소 좌심실벽 운동기능을 평가하고 정량화하기 위한 많은 연구들이 진행되어왔다. 본 논문에서는 국소 좌심실벽 운동장애의 진단을 위한 좌심실벽 운동 추 적 및 정량적 분석 알고리듬을 제안하였다. 정상 피검자들과 국소 좌심실벽 운동이상 환자로부터 얻은 심초음파 흉골연단축단면 영상들이 알고리듬의 시험을 위해 사용되었다. 자동화된 경계선 검출과 좌심실내벽 윤곽선 연결 알고리듬을 각 프레임들에 적용하였고 영역분할에 기초한 정량적 분석을 수행하였으며 운동량을 의미하는 칼라가 프레임 및 영역별로 심초음파 영상들 위에 덧씌워졌고 칼라화된 영상들이 동영상으로 구현되었다. 제안된 알고리듬은 좌심실벽 운동장애의 자동화된 정량적 진단을 제공하였다.

• 한국산학기술학회논문지
• /
• 제19권1호
• /
• pp.75-84
• /
• 2018

본 철도 유지보수 산업의 효율화를 위해서는 핵심부품의 적시 관리를 통한 부품 가동률 향상 및 철도 운행의 안정성 향상이 필요하다. 또한 유지보수 시스템 고속화에 따른 신뢰성 향상과 핵심부품의 유지보수 비용 절감의 두 가지 측면을 모두 만족시키기 위해, 부품 이력관리와 대규모 빅데이터의 자동화된 분석 기술을 활용한 부품 상태 진단 기술 수요가 증가하고 있다. 이 논문에서는 철도차량의 차상 및 지상 장치로부터 발생되는 실시간 빅데이터 수집, 처리, 분석을 위해서 빅데이터 플랫폼 기반의 철도차량 부품의 상태 데이터 관리시스템을 개발하였으며, 이 시스템의 활용으로 철도차량의 부품 상태정보 및 시스템 리소스에 대한 실시간 모니터링이 가능하다. 또한 빅데이터 플랫폼으로부터 수집된 상태 데이터를 기반으로 분산/병렬처리 및 자동화된 부품 고장진단이 가능한 머신러닝 기법을 제안하였다. 실험결과, 분산/병렬처리 기술이 적용된 알고리즘의 실행시간 단축을 아마존 웹서비스의 가상 인스턴스 생성 시스템을 통해 증명하였으며, random forest 머신러닝 기법을 활용한 고장 진단 모델의 베어링 및 차륜 부품에 대한 상태 예측 정확도가 83%임을 확인하였다.

• Tuberculosis and Respiratory Diseases
• /
• 제42권6호
• /
• pp.838-845
• /
• 1995

연구배경: 현재 국내에서 ADA의 활성치의 측정은 adenosine 기질에서 ADA에 의한 탈아미노작용시 발생하는 암모니아를 Berthelot's 반응을 이용하여 측정하는 Giusti 등에 의한 비색법이 많이 이용되고 있다. 그러나 이 방법은 자동화가 어려워 쉽게 사용하기 어려우며 기기내의 내인성 암모니아 등에 의한 오염의 가능성이 있다. 1993년 Oosthuizen 등은 nucleoside phosphorylase(NP)와 Xanthine oxidase(XOD)을 이용하여 ADA 활성치 측정을 자동화 하였다. 저자들이 측정한 ADA 활성치와 기존의 ADA 활성치 측정결과에 대한 보고를 비교함으로써 Oosthuizen 등에 의한 ADA 활성치 측정의 자동화의 융통성을 알아보고자 하였다. 방법: 1994년 5월부터 1995년 7월까지 연세대학교 원주의과대학부속 원주기독병원에 흉막액으로 입원하여 그 원인이 확진된 162명의 환자를 각각의 원인 질환에 따라서 5개 군(I: 결핵성 흉막액, II: 악성 흉막액, III: 폐렴성 흉막액, V: 여출성 흉막액)으로 나누었으며 Oosthuizen 등에 의한 ADA 활성치 측정법을 Hitachi 747 자동화학분석기에 적용하여 각 군에서 흉막액의 ADA 활성치와 및 흉막액과 혈청에서 ADA 활성치의 비를 측정하였다. 결과: 1) 결핵성 흉막액의 ADA 활성치는 $52.53{\pm}16.43\;U/L$로서 나머지 군에 비하여 통계학적으로 의의있게 높았으며(II, IV, V 군은 p값이 0.001 미만, III 군은 p값이 0.05 미만) 흉막액에서 ADA의 활성치를 30 U/L로 기준하였을 때 결핵성 흉막액과 악성 흉막액의 감별은 민감도(sensitivity) 96%, 특이도(specificity) 93%로 결핵성 흉막염을 진단할 수 있었으며 이는 기존의 보고와 차이가 없었다. 2) 흉막액과 혈청 ADA 치의 비는 결핵성 흉막액에서 $2.29{\pm}0.96$으로 농흉을 제외한 나머지 군에 의해서 통계학적으로 의의있게 높았다(p<0.001). 흉막액과 혈청 ADA 활성치 비를 1.5로 기준하였을 때 결핵성 흉막액과 악성 흉막액의 감별은 민감도 80%, 특이도 88%로 결핵성 흉막액을 진단할 수 있었으며, 이는 기존의 연구 결과와 차이가 없었다. 3) Oosthuizen 동에 의한 ADA 활성치 측정법을 Hitachi 747 자동화학분석기에 적용한 새로운 방법은 r값이 0.971로 Giuisti 등에 의한 기존의 방법과 높은 상관관계를 보였다. 결론: ADA 활성치 측정에 Oosthuizen 등에 제안한 새로운 방법은 현재 사용되는 Giusti 등의 비색법에 의한 ADA 활성치 측정과 차이가 없었으며, 일반 검사실에서도 쉽게 사용될 수 있는 장점이 있었다.

• 대한의생명과학회지
• /
• 제25권4호
• /
• pp.426-430
• /
• 2019

Currently, molecular diagnostic assays based on nucleic acid amplification tests have been shown to effectively detect mycobacterial infections in various types of specimen, however, variable sensitivity was shown in FFPE samples according to the kind of commercial kit used. The present study therefore used automated PCR-reverse blot hybridization assay (REBA) system, REBA Myco-ID HybREAD 480^®, for the rapid identification of Mycobacterium species in various types of human tissue and compared the conventional one-tube nested-PCR assay for detecting Mycobacterium tuberculosis (MTB). In conventional nested-PCR tests, 25 samples (48%) were MTB positive and 27 samples (52%) were negative. In contrast, when conducted PCR-REBA assay, 11 samples (21%) were MTB positive, 20 samples (39%) were NTM positive, 8 samples (15%) were MTB-NTM double positive, and 13 samples (25%) were negative. To determine the accuracy and reliability of the two molecular diagnostic tests, the one-tube nested-PCR and PCR-REBA assays, were compared with histopathological diagnosis in discordant samples. When conducted nested-PCR assay, 10 samples (59%) were MTB positive and seven samples (41%) were negative. In contrast, when conducted PCR-REBA test, three samples (17%) were MTB positive, 10 samples (59%) were NTM positive and four samples (24%) were negative. In conclusion, the automated PCR-REBA system proved useful to identify Mycobacterium species more rapidly and with higher sensitivity and specificity than the conventional molecular assay, one-tube nested-PCR; it might therefore be the most suitable tool for identifying Mycobacterium species in various types of human tissue for precise and accurate diagnosis of mycobacterial infection.

• Korean Journal of Radiology
• /
• 제25권2호
• /
• pp.146-156
• /
• 2024

Objective: Automated breast ultrasound (ABUS) is a relevant imaging technique for early breast cancer diagnosis and is increasingly being used as a supplementary tool for mammography. This study compared the performance of ABUS and handheld ultrasound (HHUS) in detecting and characterizing the axillary lymph nodes (LNs) in patients with breast cancer. Materials and Methods: We retrospectively reviewed the medical records of women with recently diagnosed early breast cancer (≤ T2) who underwent both ABUS and HHUS examinations for axilla (September 2017-May 2018). ABUS and HHUS findings were compared using pathological outcomes as reference standards. Diagnostic performance in predicting any axillary LN metastasis and heavy nodal-burden metastases (i.e., ≥ 3 LNs) was evaluated. The ABUS-HHUS agreement for visibility and US findings was calculated. Results: The study included 377 women (53.1 ± 11.1 years). Among 385 breast cancers in 377 patients, 101 had axillary LN metastases and 30 had heavy nodal burden metastases. ABUS identified benign-looking or suspicious axillary LNs (average, 1.4 ± 0.8) in 246 axillae (63.9%, 246/385). According to the per-breast analysis, the sensitivity, specificity, positive and negative predictive values, and accuracy of ABUS in predicting axillary LN metastases were 43.6% (44/101), 95.1% (270/284), 75.9% (44/58), 82.6% (270/327), and 81.6% (314/385), respectively. The corresponding results for HHUS were 41.6% (42/101), 95.1% (270/284), 75.0% (42/56), 82.1% (270/329), and 81.0% (312/385), respectively, which were not significantly different from those of ABUS (P ≥ 0.53). The performance results for heavy nodal-burden metastases were 70.0% (21/30), 89.6% (318/355), 36.2% (21/58), 97.3% (318/327), and 88.1% (339/385), respectively, for ABUS and 66.7% (20/30), 89.9% (319/355), 35.7% (20/56), 97.0% (319/329), and 88.1% (339/385), respectively, for HHUS, also not showing significant difference (P ≥ 0.57). The ABUS-HHUS agreement was 95.9% (236/246; Cohen's kappa = 0.883). Conclusion: Although ABUS showed limited sensitivity in diagnosing axillary LN metastasis in early breast cancer, it was still useful as the performance was comparable to that of HHUS.

• Korean Journal of Radiology
• /
• 제24권5호
• /
• pp.384-394
• /
• 2023

Objective: Mammographic density is an independent risk factor for breast cancer that can change after neoadjuvant chemotherapy (NCT). This study aimed to evaluate percent changes in volumetric breast density (ΔVbd%) before and after NCT measured automatically and determine its value as a predictive marker of pathological response to NCT. Materials and Methods: A total of 357 patients with breast cancer treated between January 2014 and December 2016 were included. An automated volumetric breast density (Vbd) measurement method was used to calculate Vbd on mammography before and after NCT. Patients were divided into three groups according to ΔVbd%, calculated as follows: Vbd (post-NCT - pre-NCT)/pre-NCT Vbd × 100 (%). The stable, decreased, and increased groups were defined as -20% ≤ ΔVbd% ≤ 20%, ΔVbd% < -20%, and ΔVbd% > 20%, respectively. Pathological complete response (pCR) was considered to be achieved after NCT if there was no evidence of invasive carcinoma in the breast or metastatic tumors in the axillary and regional lymph nodes on surgical pathology. The association between ΔVbd% grouping and pCR was analyzed using univariable and multivariable logistic regression analyses. Results: The interval between the pre-NCT and post-NCT mammograms ranged from 79 to 250 days (median, 170 days). In the multivariable analysis, ΔVbd% grouping (odds ratio for pCR of 0.420 [95% confidence interval, 0.195-0.905; P = 0.027] for the decreased group compared with the stable group), N stage at diagnosis, histologic grade, and breast cancer subtype were significantly associated with pCR. This tendency was more evident in the luminal B-like and triple-negative subtypes. Conclusion: ΔVbd% was associated with pCR in breast cancer after NCT, with the decreased group showing a lower rate of pCR than the stable group. Automated measurement of ΔVbd% may help predict the NCT response and prognosis in breast cancer.

• 동의생리병리학회지
• /
• 제23권5호
• /
• pp.1193-1198
• /
• 2009

Pulse diagnosis is a central diagnosis method used in traditional Oriental medicine. To standardize and modernize the pulse diagnosis method, it is essential to develop an instrument-based reinterpretation of the clinically used pulse images in terms of the physical quantities such as the strength, period, width, length, and depth of the pulse. As a step towards such standardization, we conducted a clinical study on the floating/sinking pulses based on an automated palpation instrument (3D-MAC, Daeyo Medi, Korea) for 213 female subjects in their 20s and 174 female subjects in their 60s. The floating/sinking pulses are the two representative pulse images depending only on the depth of the pulse, and can be conveniently scaled by the coefficient of the floating-sinking pulse ($C_{fs}{\in}(0,1)$), which represents how strong one should apply the hold-down pressure to obtain the maximal pulse strength. As a result, primarily we found that it tends to appear more floating-like pulse ($C_{fs}{\rightarrow}0$) at Gwan and more sinking-like pulse ($C_{fs}{\rightarrow}1$) at Cheek, at both age groups and at both wrists. This result is consistent with a previous study on the geometrical structure of the blood vessel by an ultrasonograph. Second, the pulse tends to be more sinking-like in the age group of 60s than 20s. Finally, the pulses at the right palpation positions were found to be more sinking-like than the left, at both age groups.