• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1000-1011
• /
• 2021

In recent years, using Deep Learning methods to apply for medical and biomedical image analysis has seen many advancements. In clinical, using Deep Learning-based approaches for cancer image analysis is one of the key applications for cancer detection and treatment. However, the scarcity and shortage of labeling images make the task of cancer detection and analysis difficult to reach high accuracy. In 2015, the Unet model was introduced and gained much attention from researchers in the field. The success of Unet model is the ability to produce high accuracy with very few input images. Since the development of Unet, there are many variants and modifications of Unet related architecture. This paper proposes a new approach of using Unet++ with pretrained EfficientNet as backbone architecture for breast tumor cell nuclei segmentation and uses the multi-organ transfer learning approach to segment nuclei of breast tumor cells. We attempt to experiment and evaluate the performance of the network on the MonuSeg training dataset and Triple Negative Breast Cancer (TNBC) testing dataset, both are Hematoxylin and Eosin (H & E)-stained images. The results have shown that EfficientUnet++ architecture and the multi-organ transfer learning approach had outperformed other techniques and produced notable accuracy for breast tumor cell nuclei segmentation.

• Journal of Korean Academy of Nursing
• /
• v.3 no.1
• /
• pp.41-51
• /
• 1972

In this article, the writer attempted to study the followings: (1) mother's knowledge of milk feeding (including method of sterilization, formula and feeding) (2) reasons of artificial feeding (3) how much mothers are concerned about their artificial feeding infants (4) condition of growth and development of artificial feeding infants. As the object of study, 96 mothers with artificial feeding infants, who had consulted dep't of pediatrics of two Hospitals in Seoul (Korea Hospital and Med. College Woo Suk Hospital, Korea Uni.) and well baby clinic of the two Health Centers (Sung Dong and Dongdaemoon), were randomly sampled. The data were treated by the statistic method of chi-square and percentage, and come to the following conclusion. 1. Knowledge of milk feeding Sterilization: 70 percentages of mothers know about the milk sterilization (including bottle, nipple and instrument), but 55 percentages of them do not know the nipple sterilization correctly. Formula: 69 percentages of mothers follow the indicator or in accordance with doctor's directions, but 31 percentages do at their option by reasons that the baby often coughs up the milk, the baby is too small, the baby often has digestive troubles, or the baby grow fleshy heavily etc, except family economic problems. Feeding: only half of mothers know the correct feeding method, especially they do not know how to determine the heat degree of milk and how to bubble up the baby correctly. They just do feeding according to the accepted usages. 2. Reasons of artificial feeding Of the reasons of artificial feeding, 18 percentages were caused by infants and 82 percentages by mothers. Most of the reasons are mainly due to the lack of breast milk and sufficient supply of nourishments rather than mother's deficiency or mother's abnormality. 3. Mother's concern for artificial feeding infants Mothers who are sharply concerned for their artificial feeding baby's growth and development: 63%, mothers who made the baby (artificial feeding infant) routine vaccinated: 81%, mothers who ear anxious about the baby's future personality forming : 68%, mothers who care about the baby's condition of nourishment; 60%, mothers who are anxious about tile selection of baby's food; 54%. 4. The growth and development of artificial feeding infants compared with Korean average infants. The artificial feeding infants are above the Korean average infants in stature by 1.21 centimeters and in weight by 0.3 kilograms. Conclusion: It has been said that there is no better food for infant than the breast milk. However, the artificial feeding has been used for the supplement of nourishments and as substitute food for the breast milk. And this artificial feeding could give the married women the chance to act in society and more opportunity to develop themselves and to work for others at home and other fields. Considering these advantages, artificial feeding should not be exclusive, but preferably should be more improved and inquired positively. And even in artificial feeding, what is most important is that mothers should recognize the requirement and need of artificial feeding clearly and correctly, and they should be accustomed to the correct knowledge and skills of artificial feeding in order to practice it appropriately. In some degree, they should be properly trained in school education process.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.6
• /
• pp.2813-2818
• /
• 2012

Background: Considerable evidence suggests that metadherin (MTDH) is a potentially crucial mediator of tumor malignancy and an important therapeutic target for simultaneously enhancing chemotherapy efficacy and reducing metastasis risk. Inhibition of MTDH expression by RNA interference has been shown in several previous research, but silencing MTDH expression by microRNA (miRNA) interference in breast cancer has not been established. In the present study, we investigated the role of MTDH-miRNA in down-regulation of proliferation, motility and migration of breast carcinoma cells. Methods: Expression vectors of recombinant plasmids expressing artificial MTDH miRNA were constructed and transfected to knockdown MTDH expression in MDA-MB-231 breast cancer cells. Expression of MTDH mRNA and protein was detected by RT-PCR and Western blot, respectively. MTT assays were conducted to determine proliferation, and wound healing assays and transwell migration experiments for cell motility and migration. Results: Transfection of recombinant a plasmid of pcDNA-MTDH-miR-4 significantly suppressed the MTDH mRNA and protein levels more than 69% in MDA-MB-231 breast cancer cells. This knockdown significantly inhibited proliferation, motility and migration as compared with controls. Conclusions: MTDH-miRNA may play an important role in down-regulating proliferation, motility and migration in breast cancer cells, and should be considered as a potential small molecule inhibitor therapeutic targeting strategy for the future.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.44 no.4
• /
• pp.610-625
• /
• 2020

This study suggests an alternative breast-prosthesis-making process for female breast cancer patients. From June 2018 to July 2018, we conducted a study using nine females between the ages 40-50 who never had breast cancer. We recorded the reported subjective sensations and objective physiological responses to different types of artificial breast materials: Trulife silicon breast prostheses (TS) and hand-made silk breast prostheses (HS). Considering the materials used in TS and HS individually, we studied the subjective sensation with regards to how each material functioned in a photo (VP), movement (VM) and the visual tactility (VT) sense. The results showed that comparing VP and VT led to more significant differences than those comparing VM and VT. In addition, there was a significant difference in terms of tactile sensation when comparing TS and HS with respect to subjective responses to texture. Subjects reported that HS felt more comfortable and gave a better cooling sensation. However, the measured objective physiological responses indicated that skin temperature was higher with HS than TS when touched. This research contributes to scholarship around alternative and new materials to build breast prostheses for women with breast cancer.

• Journal of the Korean Society of Systems Engineering
• /
• v.17 no.2
• /
• pp.91-97
• /
• 2021

User interface for cancer classification system is a software application with clinician's friendly tools and functions to diagnose cancer from pathology images. Pathology evolved from manual diagnosis to computer-aided diagnosis with the help of Artificial Intelligence tools and algorithms. In this paper, we explained each block of the project life cycle for the implementation of automated breast cancer classification software using AI and machine learning algorithms to classify normal and invasive breast histology images. The system was designed to help the pathologists in an automatic and efficient diagnosis of breast cancer. To design the classification model, Hematoxylin and Eosin (H&E) stained breast histology images were obtained from the ICIAR Breast Cancer challenge. These images are stain normalized to minimize the error that can occur during model training due to pathological stains. The normalized dataset was fed into the ResNet-34 for the classification of normal and invasive breast cancer images. ResNet-34 gave 94% accuracy, 93% F Score, 95% of model Recall, and 91% precision.

• Journal of the Korean Society of Radiology
• /
• v.84 no.6
• /
• pp.1397-1402
• /
• 2023

Nodular fasciitis is a benign fibroblastic proliferation rarely reported in the breast. We report the case of a 55-year-old woman who presented with imaging findings that resembled a malignancy. Mammography revealed an isodense nodule with partially indistinct margin in the right breast, showing the abnormality score 75% on artificial intelligence. Ultrasonography revealed an oval hypoechoic nodule with microlobulated margin, echogenic halo, increased blood flow, and soft elasticity. After core needle biopsy and excision, nodular fasciitis was diagnosed. Although nodular fasciitis of the breast is rare, it may mimic malignancy; therefore, it should be considered as a differential diagnosis to prevent unnecessary intervention.

• Women's Health Nursing
• /
• v.1 no.2
• /
• pp.155-173
• /
• 1995

The purpose of this research was to obtain information about the performance of breast-feeding by employed mother and the supportive accommodation in the work place. The survey questionnaire was answered by 323 employed mothers who had child over the six months and visited the pediatric clinic in the hospital and the public health center in Seoul. The results were as follows : 1. Of the 323 employed mothers, 4.7% of mothers performed breast-feeding, 58.3% of mothers did artificial-feeding and 37% of mothers did mixed-feeding during the six months after birth of baby. 2. The characteristics of employed mothers found to be related breast-feeding include Age, Education, Number of Baby, Type of Delivery, Place of Delivery, Obtaining Information On Breast-Feeding. 3. The performance of breast-feeding during the work was different significantly according to the mother's job(medical and non-medical) and the method of feeding. 4. The reasons why they could not perform the breast-feeding include not enough time because of working(80.4%) and lack of knowledge about breast-feeding method with combining employment. 5. The results showed that the rest supports of the work environment was insufficient to perform breast-feeding in he workplace except maternal leave.

• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1363-1369
• /
• 2018

Breast cancer is one of the most common cancers in women worldwide. In Korea, breast cancer is most common cancer in women followed by thyroid cancer. The purpose of this study is to evaluate the possibility of using deep - run model for segmentation of breast masses and to identify the best deep-run model for breast mass segmentation. In this study, data of patients with breast masses were collected at Asan Medical Center. We used 596 images of mammography and 596 images of gold standard. In the area of interest of the medical image, it was cut into a rectangular shape with a margin of about 10% up and down, and then converted into an 8-bit image by adjusting the window width and level. Also, the size of the image was resampled to $150{\times}150$. In Deconvolution net, the average accuracy is 91.78%. In U-net, the average accuracy is 90.09%. Deconvolution net showed slightly better performance than U-net in this study, so it is expected that deconvolution net will be better for breast mass segmentation. However, because of few cases, there are a few images that are not accurately segmented. Therefore, more research is needed with various training data.

• Journal of the Korean Dietetic Association
• /
• v.3 no.2
• /
• pp.169-181
• /
• 1997

In this study, I made researches of 510 mothers who breed their infants in total (256 boys & 254 girls), among which 410 in urban area and 100 in the rural area, as an object of the investigation so as to make an intensive examination and analysis of the actual state of feeding nutritive method, grasp several related factors, and finally suggest the elementary data for both campaign encouraging breast feeding and the infant feeding education. 1. Mothers showed the meaningful local differences as in an education and income level at 1% and as in a delivery type at 5%. 2. To have decided the feeding conditions according to the residences by the Kaup index distribution (P<0.05) resulted in a meaningful difference according to regions and also made us be more thoughtful of the overnutrition in the urban area than in the rural area, and it didn't showed a meaningful difference the nutritive state according to the infant feeding method thought desirable (P<0.01). 3. The feeding methods consist of breast feeding at 21.8%, artificial feeding at 48.8%, and the mixed one at 29.4%. As for the feeding method thought desirable, breast feeding was 52%. Even though they were thinking that breast feeding is better, the breast feeding case didn't go beyond 32.5% only and as for the actual feeding methods it showed a meaningful difference according to the feeding method thought desirable (P<0.01). 4. Regarding the reasons why they chose breast milk, it was 64%, the most because mother's milk contains the immune system, 63.1% for the baby's health, 52.3% because of its most because breast milk is of little quantity, 37.8% because of the mother's occupation, 14.1% because they have fed the baby artificially from the beginning and so on. Considering the reasons why they chose the mixed feeding, it was 70.7%, the most because the amount of breast milk a little, 27.3%, the next one, because of the mother's occupation and so on. 5. The respondents who answered that how to increase the number of breast feeding population depends on the reinforcement of breast feeding education for the women were 190 (37.3%), the most among all 150 persons and those who had the opinion that they should spread and actualize the temporary childcare rest (from office) system for the women who have jobs were the secondly most, 107 (21%).

• Archives of Plastic Surgery
• /
• v.49 no.6
• /
• pp.710-715
• /
• 2022

Background The latissimus musculocutaneous flap (LD flap) is a useful option for breast reconstruction following mastectomy. It has the advantage of obtaining sufficient tissue padding and natural shape by using autologous tissue. However, with the emergence of the skin-sparing mastectomy technique and artificial dermis matrix, direct-to-implant (DTI) breast reconstruction has become the first choice of surgery. The purpose of this study was to compare the satisfaction levels of patients who underwent DTI and LD flap with implant using patient-reported Breast-Q results. Methods A retrospective study was performed reviewing the records of 49 women who underwent immediate breast reconstruction with DTI or LD flap with implant and responded to the BREAST-Q questionnaire after the operation. The patient-reported breast-Q results were analyzed and correlated to the demographic information and intraoperative information. Results A total of 26 patients who underwent reconstruction with LD flap with implant and 23 patients with DTI were identified and responded to the questionnaire after an average of 32.3 and 10.4 months postoperation, respectively. According to the patient response to the breast-q values, satisfaction with breast was 60.0 and 57.0 points, psychosocial well-being 61.0 and 60.0 points, and sexual well-being 41.0 and 43.0 points in the two groups. Overall, there was no significant difference in the breastQ score between the two groups. Conclusion Patients who underwent DTI breast reconstruction seemed equally satisfied with the appearance and outcome of their breast reconstruction compared with LD flap with implant. Therefore, it appears that DTI is adequately replacing LD with implant.