• 대한의용생체공학회:의공학회지
• /
• 제44권2호
• /
• pp.118-124
• /
• 2023

Many recent studies have reported that the quality of input learning data was vital to the detection of regions of interest. However, due to a lack of research on the quality of learning data on lesion detetcting using gastroscopy, we aimed to quantify the impact of quality difference in endoscopic images to lesion detection models using Image Quality Assessment (IQA) algorithms. Through IQA methods such as BRISQUE (Blind/Referenceless Image Spatial Quality Evaluation), Laplacian Score, and PSNR (Peak Signal-To-Noise) algorithm on 430 sheets of high quality data (HQD) and 430 sheets of low quality data (PQD), we showed that there were significant differences between high and low quality images in lesion detecting through BRISQUE and Laplacian scores (p<0.05). The PSNR value showed 10.62±1.76 dB on average, illustrating the lower lesion detection performance of PQD than HQD. In addition, F1-Score of HQD showed higher detection performance at 77.42±3.36% while F1-Score of PQD showed 66.82±9.07%. Through this study, we hope to contribute to future gastroscopy lesion detection assistance systems that involve IQA algorithms by emphasizing the importance of using high quality data over lower quality data.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2022년도 제66차 하계학술대회논문집 30권2호
• /
• pp.343-344
• /
• 2022

간암에는 크게 두 종류가 있는데 하나는 간에서 생긴 종양이 악성종양으로 진행된 것이고 다른 하나는 다른 장기에서 생긴 암이 간으로 전이되는 것이다. 본 논문에서는 간에서 생긴 종양이 악성종양으로 진행되는 것을 조기 발견하고 막고자 Object Detect 모델인 YOLO v5의 다섯 가지 모델을 비교하여 악성 종양으로의 발전 가능성이 있는 간의 lesion을 찾아보았다.

• 대한치과의사협회지
• /
• 제49권3호
• /
• pp.153-158
• /
• 2011

Oral precancerous lesion is a morphologically altered tissue in which oral cancer is more likely to occur than is apparently normal counterpart. As dentists always do oral examination and dental treatment, with fundamental knowledge and attention of this lesion, it is relatively easy to find one. If followed by proper treatment and management, it is possible to minimize its oral cancer progression, or at least delay it. Even if it were to progress to oral cancer, very early detection is possible. However, no specific biomarkers are present at the moment that could reveal oral precnacerous lesion that is high risk of oral cancer progression. Since early detection of oral cancer followed by treatment could show good prognosis with just a simple ablative surgery. Dentists should also instruct people to avoid risk factor related oral cancer progression and take natural compound having anticancer effect. Hereby, As a primary care givers, dentists play an important role in prevention of oral cancer.

• 대한수의학회지
• /
• 제42권2호
• /
• pp.219-224
• /
• 2002

We report the seasonal prevalence of the mycoplasmal pneumoniae of swine (MPS) in slaughter pigs from July of 1999 to June of 2000. Gross finding of lung lesion observed and examined by dot-ELISA. In gross finding of lung lesion from 750 pig samples, 465 (62.0%) was MPS, and 129 (17.2%) was single or double infection with actinobacillosis and pasturellosis. However, 156 (20.8%) had no lesion. In seasonal detection, the prevalence was found to be winter (69.5%), autumn (63.5%), summer (60.0%) and spring (54.7%) in orderly frequency. In dot-ELISA, the result was showed the positive reaction (x16>titre) with 58.0% and negative (x4

• 대한골관절종양학회지
• /
• 제11권1호
• /
• pp.32-39
• /
• 2005

목적: 최근에는 연부 종양의 진단에 FDG-PET을 이용하기 위한 연구가 다양하게 이루어지고 있다. 그러나, 그 임상적 유용성에 대해서는 알려져 있지 않다. 이 연구의 목적은 기존의 진단법과 비교하여 FDG-PET의 유용성을 평가하는 데 있다. 대상 및 방법: 연구 대상은 2001년 3월에서 2002년 3월 사이에 연부 조직 종양으로 진단받은 29명의 환자(남자 16명, 여자 13명, 평균 47세)를 대상으로 하였다. 모든 환자군에서 기존의 검사법과 FDG-PET을 시행하였다. 타당성 검증에서 국소 병변은 모든 경우 조직검사로 판단하였고, 전이 병변은 조직 검사와 6개월 간의 추시 결과로 판단하였다. 각각의 진단은 독립적으로 시행되었으며, 진단의 정확도와 누적 비용-정확도율을 측정하였다. 결과: 국소 병변의 진단에서 MRI와 FDG-PET의 민감도, 특이도, 정확도는 각각 91%, 57%, 83% 와 95%, 43%, 83%이었다. 원격 전이의 진단에서 기존의 검사법과 FDG-PET의 민감도, 특이도, 정확도는 각각 77%, 89%, 87% 와 92%, 94%, 93%이었다. 누적 비용-정확도율은 145,000원/% 이었다. 종양의 등급별 민감도 분석에서 고등급의 종양이 가장 비용-효용성이 높았다. 결론: 국소부위의 재발과 잔존 종양의 진단에서 FDG-PET의 정확도는 MRI와 차이가 없었다. 반면, 원격 전이의 진단은 FDG-PET이 기존의 검사 보다 정확하였다. 고등급 종양의 경우 저등급 종양보다 FDG-PET의 유용성이 큰 것을 알 수 있었다.

• 대한의용생체공학회:의공학회지
• /
• 제26권4호
• /
• pp.207-214
• /
• 2005

Breast cancer detection using electrical impedance techniques is based on numerous experimental findings that cancerous tissues have higher electrical conductivity values than normal tissues. Lately, by taking advantage of the structure of current flows underneath a planar probe of array electrodes, a mathematical formula to find lesions from a measured trans­admittance map has been derived. In order to experimentally validate its mathematical analysis and the suggested lesion estimation algorithm, we developed a 256-channel trans-admittance scanner (TAS) for probing anomalies underneath a planar array of electrodes. In this paper, we describe the design and implementation of the TAS. Its performance together with the lesion estimation algorithm was evaluated using saline phantoms. Further studies are proposed to validate the system on human subjects.

• Journal of Electrical Engineering and Technology
• /
• 제12권1호
• /
• pp.436-442
• /
• 2017

A novel method of Skin lesion segmentation based on the combination of Texture and Neural Network is proposed in this paper. This paper combines the textures of different pixels in the skin images in order to increase the performance of lesion segmentation. For segmenting skin lesions, a two-step process is done. First, automatic border detection is performed to separate the lesion from the background skin. This begins by identifying the features that represent the lesion border clearly by the process of Texture analysis. In the second step, the obtained features are given as input towards the Recurrent Echo state neural networks in order to obtain the segmented skin lesion region. The proposed algorithm is trained and tested for 862 skin lesion images in order to evaluate the accuracy of segmentation. Overall accuracy of the proposed method is compared with existing algorithms. An average accuracy of 98.8% for segmenting skin lesion images has been obtained.

• Journal of Multimedia Information System
• /
• 제1권1호
• /
• pp.77-85
• /
• 2014

Usually, the skin pigmentation detection and diagnosis are made by clinicians. In this process it is subjective and non-quantitative. We develop an approach to detect and measure the different pigmentation lesions base on computer vision technology. In the paper we study several usually used skin-detecting color space like HSV, YCbCr and normalized RGB. We compare their performance with illumination influence for detecting the pigmentation lesions better. Base on a relatively stable color space, we propose an approach which is RGB channels vector difference characteristic for the detection. After the object region detection, we also use the difference to measure the difference between the lesion and the surrounding normal skin. From the experiment results, our approach can effectively detect the pigmentation lesion, and perform robustness with different illumination.

• 한국멀티미디어학회논문지
• /
• 제24권8호
• /
• pp.979-987
• /
• 2021

Multiple Sclerosis (MS) can be early diagnosed by detecting lesions in brain magnetic resonance images (MRI). Unsupervised anomaly detection methods based on autoencoder have been recently proposed for automated detection of MS lesions. However, these autoencoder-based methods were developed only for 2D images (e.g. 2D cross-sectional slices) of MRI, so do not utilize the full 3D information of MRI. In this paper, therefore, we propose a novel 3D autoencoder-based framework for detection of the lesion volume of MS in MRI. We first define a 3D convolutional neural network (CNN) for full MRI volumes, and build each encoder and decoder layer of the 3D autoencoder based on 3D CNN. We also add a skip connection between the encoder and decoder layer for effective data reconstruction. In the experimental results, we compare the 3D autoencoder-based method with the 2D autoencoder models using the training datasets of 80 healthy subjects from the Human Connectome Project (HCP) and the testing datasets of 25 MS patients from the Longitudinal multiple sclerosis lesion segmentation challenge, and show that the proposed method achieves superior performance in prediction of MS lesion by up to 15%.

• 대한의용생체공학회:의공학회지
• /
• 제18권2호
• /
• pp.113-120
• /
• 1997

This paper presents an optimal design for the SPECT reconstruction filter, based on a physical limit of SPECT lesion detection capability. To increase the performance of the filter on lesion detectability, the filter design was focused on increasing the local SyW ratio of a threshold lesion, that was determined by minimum detectable lesion size (MDU) from SPECT lesion detectabllity contrast-detail curve. The proposed filter showed flexible window characteristics of resolution recovery and noise smoothing for MDLSs in the resolution-limited and photon-limited regions, respectively, compennting for the relative impact of the main limitation factors on threshold detectability. The simulated results showed good adaptability of the proposed filter to the changes in physical parameters of photon counts, object contrast, and detector system resolution.