• 한국방사선학회논문지
• /
• 제16권4호
• /
• pp.453-462
• /
• 2022

본 논문에서는 의료 영상 분석 분야에서 이용되고 있는 AI(Artificial Intelligence)기술을 문헌 검토를 통해 분석하였다. 문헌 검색은 중심어(keyword)를 사용하여 PubMed, ResearchGate, Google 및 Cochrane Review의 문헌 검색을 수행했다. 문헌 검색을 통해 114개의 초록을 검색하였고 그 중 16개의 중복된 것을 제외하고 98개의 초록을 검토했다. 검토된 문헌에서 AI가 응용되고 있는 분야는 분류(Classification), 국소화(Localization), 질병의 탐지(Detection), 질병의 분할(Segmentation), 합성 영상의 적합도(Fit degree) 등으로 나타났다. 기계학습(ML: Machine Learning)을 위한 모델은 특징 추출을 한 후 신경망의 네트워크에 특징 값을 입력하는 방식은 지양되는 것으로 나타났다. 그 대신에 신경망의 은닉층을 여러 개로 하는 심층학습(DL: Deep Learning) 방식으로 변화되고 있는 것으로 나타났다. 그 이유는 컴퓨터의 메모리 량의 증가와 계산속도의 향상, 빅 데이터의 구축 등으로 특징 추출을 DL 과정에서 처리하는 것으로 사료된다. AI를 이용한 의료영상의 분석을 의료에 적용하기 위해서는 의사의 역할이 중요하다. 의사는 AI 알고리즘의 예측을 해석하고 분석할 수 있어야 한다. 이러한 이해를 위해서는 현재 의사를 위한 추가 의학 교육 및 전문성 개발과 의대에 재학 중인 학습자를 위한 개정된 커리큘럼이 필요해 보인다.

• International Journal of Computer Science & Network Security
• /
• 제23권5호
• /
• pp.53-64
• /
• 2023

Early detection of endometrial carcinoma in uterus is essential for effective treatment. Endometrial carcinoma is the worst kind of endometrium cancer among the others since it is considerably more likely to affect the additional parts of the body if not detected and treated early. Non-invasive medical computer vision, also known as medical image processing, is becoming increasingly essential in the clinical diagnosis of various diseases. Such techniques provide a tool for automatic image processing, allowing for an accurate and timely assessment of the lesion. One of the most difficult aspects of developing an effective automatic categorization system is the absence of huge datasets. Using image processing and deep learning, this article presented an artificial endometrium cancer diagnosis system. The processes in this study include gathering a dermoscopy images from the database, preprocessing, segmentation using hybrid Fuzzy C-Means (FCM) and optimizing the weights using the Whale Optimization Algorithm (WOA). The characteristics of the damaged endometrium cells are retrieved using the feature extraction approach after the Magnetic Resonance pictures have been segmented. The collected characteristics are classified using a deep learning-based methodology called Long Short-Term Memory (LSTM) and Bi-directional LSTM classifiers. After using the publicly accessible data set, suggested classifiers obtain an accuracy of 97% and segmentation accuracy of 93%.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2020년도 제61차 동계학술대회논문집 28권1호
• /
• pp.5-6
• /
• 2020

현대 의학에서 의료 영상은 수많은 영상처리 의료기기의 핵심이다. PACS(Picture Archiving Communication System)를 통해 관리되는 의료 영상 자료들은 요청에 따라 저장, 검색 및 전송을 수행하여 신속한 의료 서비스를 가능하게 한다. 그러나 만약에 관리자의 실수로 의료 영상 데이터가 바뀐다면 이는 사용자로 하여금 불편함과 낮은 신뢰성을 야기한다. 그리하여 본 논문에서는 서포트 벡터 머신 기반의 HOG(Histogram of Oriented Gradients) 특징 벡터를 이용하여 X-ray와 MRI(Magnetic Resonance Imaging) 사진을 분류하고 의료 영상 분류의 가능성을 제시하는 것을 목표로 한다.

• 대한의용생체공학회:의공학회지
• /
• 제43권5호
• /
• pp.353-360
• /
• 2022

Laryngeal disease harms quality of life, and laryngoscopy is critical in identifying causative lesions. This study extracts and analyzes using radiomics quantitative features from the lesion in laryngoscopy images and will fit and validate a classifier for finding meaningful features. Searching the region of interest for lesions not classified by the YOLOv5 model, features are extracted with radionics. Selected the extracted features are through a combination of three feature selectors, and three estimator models. Through the selected features, trained and verified two classification models, Random Forest and Gradient Boosting, and found meaningful features. The combination of SFS, LASSO, and RF shows the highest performance with an accuracy of 0.90 and AUROC 0.96. Model using features to select by SFM, or RIDGE was low lower performance than other things. Classification of larynx lesions through radiomics looks effective. But it should use various feature selection methods and minimize data loss as losing color data.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.97-99
• /
• 2021

최근 고령화 사회가 지속됨에 따라, 치매(Dementia)에 대한 관심이 높아지고 있다. 그 중에서 알츠하이머병(Alzheimer's disease)는 전체 치매 환자의 50~60%로 가장 많은 비율을 차지하는 퇴행성 뇌질환으로, 현재 의료계에선 알츠하이머병에 대한 명확한 예방법 및 치료법에 대해 내놓지 못하고 있으며, 치매 발병 전 조기 치료 및 조기 예방법에 대한 중요성이 강조되고 있다. 본 논문에서는 정상인과 알츠하이머병에 걸린 환자의 MRI 데이터셋을 활용하여 컨볼루션 신경망을 중심으로 여러 가지 활성화 함수를 접목시켜, 가장 효율적인 활성화 함수를 찾고자 한다. 또한 알츠하이머 치매분류 모델링을 통해 향후 의료분야에 적합한 치매 구분 모델링으로 활용하고자 한다.

• 한국정보처리학회논문지
• /
• 제6권10호
• /
• pp.2707-2715
• /
• 1999

Recently, there have been researches to automate processing and analysing images in the medical field using image processing technique, a fast communication network, and high performance hardware. In this paper, we propose a system to be able to analyze morphological abnormality of red-blood cells for peripheral blood image using image processing techniques. To do this, we segment red-blood cells in the blood image acquired from microscope with CCD camera and then extract UNL fourier features to classify them into 15 classes. We reduce the number of multi-variate features using PCA to construct a more efficient classifier. Our system has the best performance in recognition rate, compared with two other algorithms, LVQ3 and k-NN. So, we show that it can be applied to a pathological guided system.

• Journal of Information Processing Systems
• /
• 제17권3호
• /
• pp.453-461
• /
• 2021

Many deep learning approaches have been studied for image classification in computer vision. However, there are not enough data to generate accurate models in medical fields, and many datasets are not annotated. This study presents a new method that can use both unlabeled and labeled data. The proposed method is applied to classify cervix images into normal versus cancerous, and we demonstrate the results. First, we use a patch self-supervised learning for training the global context of the image using an unlabeled image dataset. Second, we generate a classifier model by using the transferred knowledge from self-supervised learning. We also apply attention learning to capture the local features of the image. The combined method provides better performance than state-of-the-art approaches in accuracy and sensitivity.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1995년도 추계학술대회
• /
• pp.177-182
• /
• 1995

Since one property(i.e. coarseness, orientation, regularity, granularity etc.) of ultrasound liver images was not sufficiently enough to classify the characteristics of livers, we used the multi-feature vectors from ultrasound images to diagnose the liver disease. The proposed classifier, which uses the multi-feature vectors and Bayes decision rule, performed well for the classification of normal, fat and cirrhosis liver. In our simulation, we used the Battacharyya distance and Hotelling Trace Criterion to select the best multi-feature vectors for the classifier and obtained less classification errors than other methods using single feature vector.

• 한국멀티미디어학회논문지
• /
• 제21권6호
• /
• pp.659-666
• /
• 2018

The classification of the tablets recovered according to prescription changes is usually carried out manually by a number of pharmacists at the hospitals. Relatively high-wage pharmacists carry out the reclassification of the tablets, which results in a large loss of time and labor, and if the tablets are incorrectly classified, this can lead to medical accidents. In order to overcome these problems, a new automatic tablet classifying machine has been introduced. In the conventional automatic tablet classifying machine, tablets having various shapes, sizes, and colors are transferred to a classifying machine through the line feeder. Problems such as breakaway of the tablets from the line feeder, pilling of the tablets in the line feeder, and appearance contamination of the tablets occur. In this paper, we propose a system that automatically classifies the shape, size, and color of tablets through individual supply method by vacuum adsorption and image processing.

• International Journal of Computer Science & Network Security
• /
• 제21권6호
• /
• pp.101-106
• /
• 2021

Breast cancer is the number one cause of deaths from cancer in women, knowing the type of breast cancer in the early stages can help us to prevent the dangers of the next stage. The performance of the deep learning depends on large number of labeled data, this paper presented convolutional neural network for classification breast cancer from images to benign or malignant. our network contains 11 layers and ends with softmax for the output, the experiments result using public BreakHis dataset, and the proposed methods outperformed the state-of-the-art methods.