• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.55-58
• /
• 2021

PFCM-R 알고리즘을 적용한 기존의 반려견 진단 방법에서는 클러스터링에서 사용되는 파라미터 값을 경험적으로 설정하고 견주가 입력하는 증상들 사이에서 관련성이 낮은 증상이 필터링 되지 않아서 질병의 도출 성능을 저하시키는 원인이 된다. 따라서 본 논문에서는 노드 활성 함수를 적용하여 증상간의 관련성이 적은 증상 데이터를 제거하여 학습 데이터를 구성한 후, 연상 메모리 알고리즘에 적용하여 반려견의 질병에 대한 진단 성능을 개선시키는 하이브리드 기반 다층 학습 구조를 제안하여 반려견 진단에 적용한다. 기존의 PFCM-R 알고리즘 진단 방법과 제안된 하이브리드 다층 구조 진단 방법을 비교분석한 결과, 기존의 방법보다 제안된 방법이 입력된 증상들에 대해서 기존의 방법보다 관련성이 있는 질병 도출 성능이 23.7%가 개선되었다.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.2
• /
• pp.39-44
• /
• 2021

In this paper, we propose a method of disease diagnosis system that can diagnose the health status of household pets for the people who lack veterinary knowledge. The proposed diagnosis system holds 50 different kinds of diseases with the symptoms for each of them as a database to provide results from symptom input. Each disease database has its own symptom codes for a disease, and by using the disease database, FCM clustering technique is applied to disease which outputs membership degree to determine diseases close to the input symptom as a pet diagnosis result. The implementation results of the proposed pet diagnosis system were obtained by the number of selected symptoms and the possibility values of the diseases that have the selected symptoms being sorted in descending order to derive top 3 diseases closest to the pet's symptom.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.4
• /
• pp.25-34
• /
• 2024

This paper presents the development of a mobile application that detects and identifies canine skin diseases by training a deep learning-based U-Net model to infer the presence and location of skin lesions from images. U-Net, primarily used in medical imaging for image segmentation, is effective in distinguishing specific regions of an image in a polygonal form, making it suitable for identifying lesion areas in dogs. In this study, six major canine skin diseases were defined as classes, and the U-Net model was trained to differentiate among them. The model was then implemented in a mobile app, allowing users to perform lesion analysis and prediction through simple camera shots, with the results provided directly to the user. This enables pet owners to monitor the health of their pets and obtain information that aids in early diagnosis. By providing a quick and accurate diagnostic tool for pet health management through deep learning, this study emphasizes the significance of developing an easily accessible service for home use.

• Journal of Life Science
• /
• v.34 no.6
• /
• pp.434-441
• /
• 2024

Mammary gland tumors are the most common tumors detected in non-spayed female dogs and pose a significant clinical challenge. Due to the strong similarity between canine mammary tumors (CMT) and human breast cancer (HBC), biomarkers identified in HBC can also be detected in CMT. These biomarkers have been shown to offer valuable insights into early diagnosis, prognosis, and treatment strategies. The purpose of this article is to provide a concise overview of CMT biomarkers based on the current literature. Traditional treatments for CMT in dogs typically begin with surgery, followed by chemotherapy, radiotherapy, or hormonal therapy. However, these treatments alone are not always fully effective. A diagnostic biomarker can detect the presence of a disease or the characteristics of a disease and classify an individual's status. Prognostic biomarkers focus on predicting the expected progression, recurrence, or survival of the disease in patients. By utilizing advances in understanding the mechanism of canine-specific mammary gland tumors, the estimation of biomarkers offers hope for improved outcomes in cancer patients. Novel technologies, such as single-cell RNA sequencing analysis, could provide a valuable resource for deciphering intra- and inter-tumoral heterogeneity. This review paper explores current research on CMT biomarkers and suggests directions for their development.

• Journal of Environmental Science International
• /
• v.33 no.4
• /
• pp.279-282
• /
• 2024

This study aimed to verify the results of emotional analysis with respect to canine behavior as reported in the existing animal behavior field based on the dog vestibular emotional reflex (VER) principle, and to evaluate humans and animals based on empathy gained through true communication rather than human-centered interpretation. A total of 200 canines were divided into non-daily and daily situation groups (n=100 each). To assess the psychological and emotional state of each group, these changes were applied to the principle of VER, and six measurement values were selected: positive emotion (balance and energy), negative emotion (tension/anxiety and stress), and body condition (inhibition and neuroticism). The results showed a statistically significant difference (p<0.05) in positive emotions, negative emotions, and body conditions between the two groups. In addition, balance, energy, tension/anxiety, inhibition, and neuroticism were higher in the non-daily situation group than in the daily situation group, with an exception for stress. Compared with the canine daily situation groups, canine in the non-daily situation groups instinctively observed their surroundings to cope with possible threats, had decreased concentration, and elevated vitals due to high-intensity anxiety. This can be perceived as a state of immediate reaction to possible situations/threats. In conclusion, it was confirmed through Vibra Image technology that canine instability mainly affects three factors: positive emotion, negative emotion, and physical condition.

• Korean Journal of Veterinary Research
• /
• v.62 no.3
• /
• pp.25.1-25.9
• /
• 2022

Canine cognitive dysfunction syndrome (CDS) is a neurodegenerative disease that causes cognitive and behavioral disorders and reduces the quality of life in dogs and their guardians. This study reviewed the complementary and alternative medicine (CAM) for CDS and compared the diagnosis and therapy of CAM between CDS in canines and dementia in humans. The evaluation tools for the diagnosis of CDS and dementia were similar in the neurological and neuropsychiatric examinations, daily life activity, cognitive tests, and neuroimaging, but the evaluation for dementia was further subdivided. In CAM, pattern identification is a diagnostic method for accurate, personalized treatment, such as herbal medicine. For herbal medicine treatment of cognitive impairment in canines and humans, a similar pattern identification classified as deficiency (Qi, blood, and Yin) and Excess (phlegm, Qi stagnation, and blood stasis) is being used. However, the veterinary clinical basis for verifying the efficacy and safety of CAM therapies for CDS is limited. Therefore, based on CAM evidence in dementia, it is necessary to establish CDS-targeted CAM diagnostic methods and therapeutic techniques considering the anatomical, physiological, and pathological characteristics of dogs.

• Journal of Veterinary Clinics
• /
• v.26 no.6
• /
• pp.556-562
• /
• 2009

Skin tumors and mammary gland tumors have been shown to be the most common neoplasia in most of the strains of dogs. The risk for tumor development increases significantly with age and the prevalence and distribution are various according to individual tumors. The aim of this study is to classify histopathologically the skin and mammary gland tumors for recent two years, 2005 and 2006. A total of 128 skin and 240 mammary gland samples of dogs were selected that were submitted to National Veterinary Research and Quarantine Service and Kangwon National University from January 1, 2005 to December 31, 2006. The excised tissue were fixed in 10 percent neutral buffered formalin and processed routinely to paraffin wax. Sections were cut at $3{\mu}m$, stained with haematoxylin and eosin. The slides were examined based on the morphological criteria of M. H. Goldschmidt and W. Misdorp under a light microscope. The age of the dogs ranged from 1 to 19 years with a median of 8.7 years. The mean age of the skin and mammary gland tumors was 7.4 and 9.3 years. 47 (12.8%) were males and 259 (70.4%) were female with a male to female ratio of 0.18. Yorkshire terrier and maltese were more susceptible breeds, accounting for 44.3% of skin and mammary gland tumors. In skin tumors, epithelial, adnexal, and mesenchymal origin tumors were 18 (14.1%), 53 (41.4%), and 57 cases (44.5%), repectively. Among the epithelial, adenexal, and mesenchymal origin tumors, basal cell tumor (8.6%), sebaceous adenoma (15.6%), and histiocytoma (25.0%) were predominant in the incidence rate, respectively. In case of mammary gland tumors, 201 (83.8%) were benign and 39 (16.3%) were malignant with a benign to malignant ratio of 5.15. The most frequent mammary gland tumor was benign mixed tumor (35.0%) followed by mammary adenoma-complex type (31.7%).