• 대한예방한의학회지
• /
• 제19권2호
• /
• pp.113-121
• /
• 2015

Objective : This study was aimed to classify diseases that Traditional Chinese Medicine(TCM) is better at treating. Method : Literature was searched on China National Knowledge Infrastructure(CNKI) and categorized according to literature type, published date and research method. Studied six types of research papers and four types of published books. Results : Experts were surveyed and interviewed, medical records were studied retrospectively, and doubleblind method was used in selecting diseases that TCM was better at treating. There were a total of 372 diseases that TCM was better at treating. By the KCD classification, 45 were in gastrointestinal (12.1%), 39 in urogenital (10.5%), 36 in circulatory (9.7%), 35 in musculoskeletal or connective tissues (9.4%). Conclusion : Total of 372 diseases were classified as diseases that TCM was better at treating, and if the results are used adequately, the values of western and TCM can be maximized and benefit the government, patients and the medical practitioners.

• Childhood Kidney Diseases
• /
• 제27권2호
• /
• pp.64-69
• /
• 2023

Membranoproliferative glomerulonephritis (MPGN) is a complex group of renal diseases characterized by a specific pattern of glomerular injury that includes thickening of the capillary wall and mesangial expansion, leading to a heterogeneous group of conditions. This review article offers a comprehensive overview of MPGN, its new classification, pathophysiology, diagnostic evaluation, and management options.

• The Plant Pathology Journal
• /
• 제39권4호
• /
• pp.319-334
• /
• 2023

Plant disease is an important factor affecting crop yield. With various types and complex conditions, plant diseases cause serious economic losses, as well as modern agriculture constraints. Hence, rapid, accurate, and early identification of crop diseases is of great significance. Recent developments in deep learning, especially convolutional neural network (CNN), have shown impressive performance in plant disease classification. However, most of the existing datasets for plant disease classification are a single background environment rather than a real field environment. In addition, the classification can only obtain the category of a single disease and fail to obtain the location of multiple different diseases, which limits the practical application. Therefore, the object detection method based on CNN can overcome these shortcomings and has broad application prospects. In this study, an annotated apple leaf disease dataset in a real field environment was first constructed to compensate for the lack of existing datasets. Moreover, the Faster R-CNN and YOLOv3 architectures were trained to detect apple leaf diseases in our dataset. Finally, comparative experiments were conducted and a variety of evaluation indicators were analyzed. The experimental results demonstrate that deep learning algorithms represented by YOLOv3 and Faster R-CNN are feasible for plant disease detection and have their own strong points and weaknesses.

• 산업경영시스템학회지
• /
• 제44권3호
• /
• pp.33-38
• /
• 2021

Recently, transfer learning techniques with a base convolutional neural network (CNN) model have widely gained acceptance in early detection and classification of crop diseases to increase agricultural productivity with reducing disease spread. The transfer learning techniques based classifiers generally achieve over 90% of classification accuracy for crop diseases using dataset of crop leaf images (e.g., PlantVillage dataset), but they have ability to classify only the pre-trained diseases. This paper provides with an evaluation scheme on selecting an effective base CNN model for crop disease transfer learning with regard to the accuracy of trained target crops as well as of untrained target crops. First, we present transfer learning models called CDC (crop disease classification) architecture including widely used base (pre-trained) CNN models. We evaluate each performance of seven base CNN models for four untrained crops. The results of performance evaluation show that the DenseNet201 is one of the best base CNN models.

• 한국멀티미디어학회논문지
• /
• 제25권8호
• /
• pp.1212-1223
• /
• 2022

Skin lesions are common diseases that range from skin rashes to skin cancer, which can lead to death. Note that early diagnosis of skin diseases can be important because early diagnosis of skin diseases considerably can reduce the course of treatment and the harmful effect of the disease. Recently, the development of computer-aided diagnosis (CAD) systems based on artificial intelligence has been actively made for the early diagnosis of skin diseases. In a typical CAD system, the accurate classification of skin lesion types is of great importance for improving the diagnosis performance. Motivated by this, we propose a novel deep ensemble classification with multi-scale attention networks. The proposed deep ensemble networks are jointly trained using a single loss function in an end-to-end manner. In addition, the proposed deep ensemble network is equipped with a multi-scale attention mechanism and segmentation information of the original skin input image, which improves the classification performance. To demonstrate our method, the publicly available human skin disease dataset (HAM 10000) and the private animal skin lesion dataset were used for the evaluation. Experiment results showed that the proposed methods can achieve 97.8% and 81% accuracy on each HAM10000 and animal skin lesion dataset. This research work would be useful for developing a more reliable CAD system which helps doctors early diagnose skin diseases.

• 한국음향학회지
• /
• 제38권5호
• /
• pp.568-573
• /
• 2019

폐질환 진단에서 청진은 다른 진단 방식에 비해 단순하고, 폐음을 이용하여 폐질환 환자식별뿐 아니라 폐음과 관련된 질병을 예측할 수 있다. 따라서 본 논문에서는 다양한 합성곱 신경방 방식을 기반으로 폐음을 이용하여 폐질환 환자를 식별하고, 소리특성에 따른 폐음을 분류하여 각 신경망 방식의 분류 성능을 비교한다. 먼저 폐질환 소견을 갖는 흉부 영역에서 단채널 폐음 녹음기기를 이용하여 폐음 데이터를 수집하고, 수집된 시간축 신호를 스펙트럼 형태의 특징값으로 추출하여 각 분류 신경망 방식에 적용한다. 폐 사운드 분류 방식으로는 일반적인 합성곱 신경망, 병렬 구조, 잔류학습이 적용된 구조의 합성곱 신경망을 사용하고 실험을 통해 각 신경망 모델의 폐음 분류 성능을 비교한다.

• Korean Journal of Radiology
• /
• 제22권8호
• /
• pp.1379-1396
• /
• 2021

Rare neurovascular diseases (RNVDs) have not been well-recognized in Korea. They involve the central nervous system and greatly affect the patients' lives. However, these diseases are difficult to diagnose and treat due to their rarity and incurability. We established a list of RNVDs by referring to the previous literature and databases worldwide to better understand the diseases and their current management status. We categorized 68 RNVDs based on their pathophysiology and clinical manifestations and estimated the prevalence of each disease in Korea. Recent advances in genetic, molecular, and developmental research have enabled further understanding of these RNVDs. Herein, we review each disease, while considering its classification based on updated pathologic mechanisms, and discuss the management status of RNVD in Korea.

• Tuberculosis and Respiratory Diseases
• /
• 제39권5호
• /
• pp.380-385
• /
• 1992

• 한국한의학연구원논문집
• /
• 제5권1호
• /
• pp.81-100
• /
• 1999

The result from the research on the disease classifications of the traditional medicine in China, Japan, Taiwan, and North Korea are followings: 1. It is remarkable that China has two different classifications. One is of the diseases named by western medicine and the other is of the syndromes compounded with parts, characters, and pathology of the diseases. The Traditional Chinese Medicine has 615 codes for diseases in 7 departments, and 1684 codes for syndromes. It seems that they have tried to match each disease named by the traditional chinese medicine to each one named by western medicine. But, they have left the diseases impossible to be equivalent to the ones in western medicine themselves and used the same codes of western medicine when the diseases are the same ones in western medicine. 2. In Taiwan, they try to connect the diseases named by the traditional medicine to the ones named by western medicine based on ICD-9. But, they did not attempt to classify the diseases of the traditional medicine by its own ways. The names of diseases in Taiwan medicine include both diseases and syndromes. It is limited to name syndromes by the traditional medicine. And, Taiwan medicine follows ICD in naming injuries. 3. Japan has not got the disease classification for the causes of death, but only the Japanese disease classification for the causes of death, a translation 'The international disease classification for the causes of death. Therefore, The diseases named by traditional medicines are excluded in the public medicine by some Japanese medicines which diagnose through the western medicine and treat by Wa Kang medicine. 4. I can't find out the data over the disease classification for the causes of death by traditional medicine in North Korea. Instead, I can refer to case histories in which differentiation of symptoms and signs and points about them by traditional medicine and the final diagnoses and report about examination by the western medicine has been recorded. In conclusion, It is a distinctive feature that they connect the diseases and the syndromes by the traditional medicine to the ones by the western medicine, and don't tell the diseases from the syndromes.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권12호
• /
• pp.555-560
• /
• 2021

최근 안면 피부 미용에 대한 사람들의 관심이 높아짐에 따라 딥 러닝을 활용한 안면 피부 미용을 위한 피부 질환 인식 연구가 진행되고 있다. 이러한 연구들은 여드름을 비롯한 다양한 피부 질환을 인식한다. 기존의 연구들은 단일 피부 질환만을 인식하지만, 안면에 발생하는 피부 질환은 더 다양하고 복합적으로 발생할 수 있다. 따라서 본 논문에서는 Inception-ResNet V2 모델을 활용하여 다중 레이블 분류 방법으로 여드름, 블랙헤드, 주근깨, 검버섯, 일반 피부, 화이트헤드에 관한 복합적인 피부 질환을 인식한다. 사용한 평가 지표 중 정확도는 98.8%, 해밍 손실은 0.003을 달성하였고, 단일 클래스별 정밀도, 재현율, F1-점수는 모두 96.6% 이상을 달성하였다.