• Radiation Oncology Journal
• /
• v.27 no.3
• /
• pp.169-172
• /
• 2009

Intraocular metastasis is the most common malignancy of the eye. The frequency of intraocular metastasis in all the patients dying of cancer is about 12% and ocular metastases will be detected more frequently in the future because the patients with malignant tumor are now living longer. Intraocular metastasis can cause a serious clinical problem such as blindness. The early recognition and treatment of intraocular metastasis are very important clinical oncologic issues to maintain vision and to maximize the quality of life. However, significance of intraocular metastasis is still under-evaluated for practicing oncologists. External beam radiotherapy is a safe, effective palliative treatment in terms of preserving both the vision and the eye globe.

• Journal of the Korean Society of Radiology
• /
• v.5 no.1
• /
• pp.37-49
• /
• 2011

To examine the possible changes in the SNRs, CNRs, and ADC values for lumbar spines with metastasis based on the DW images before and after contrast agent injection taken from metastatic spinal cancer patients using a 1.5 T MR machine. The quantitative analysis revealed that in case of spinal cancer subjects, both SNRs and CNRs at all of those assessed locations significantly increased on the DWI after contrast agent injection compared to before, while on the ADC map images, SNRs significantly decreased. On the other hand, significantly decreased ADC values at all the assessed locations were found on the ADC map images. With reference to the normal group, significantly increased SNRs were found at all of the assessed locations on the DWI image after injection compared to before, while significantly decreased SNRs were found on the ADC map images. Also, significantly decreased ADC values at all the assessed locations were found on the ADC map images. For the qualitative analysis, after contrast agent injection, significantly increased signal intensities were found at the locations with spinal cancer on the DWI. In contrast, significantly decreased signal intensities were found on the ADC map images. The implication from the results showing that SNR and CNR significantly increased while ADC value significantly decreased at, above, and below the location of metastatic spinal cancer on DWI after contrast agent injection is that DWI obtained after contrast agent injection can be made available for wider application to vertebral disorders.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.655-657
• /
• 2021

It is challenging to find breast ultrasound image training dataset to develop an accurate machine learning model due to various regulations, personal information issues, and expensiveness of acquiring the images. However, studies targeting transfer learning for ultrasound breast cancer images classification have not been able to achieve high performance compared to radiologists. Here, we propose an improved transfer learning model for ultrasound breast cancer classification using publicly available dataset. We argue that with a proper combination of ImageNet pre-trained model and optimizer, a better performing model for ultrasound breast cancer image classification can be achieved. The proposed model provided a preliminary test accuracy of 99.5%. With more experiments involving various hyperparameters, the model is expected to achieve higher performance when subjected to new instances.

• Radiation Oncology Journal
• /
• v.15 no.4
• /
• pp.321-329
• /
• 1997

Purpose : It is well known that the risk of lymph nodes metastases to head and neck cancers are influenced by the location and size of the Primary tumor. as well as the degree and types of histological differentiation. However, data on the statistical analyses of lymph node metastases from the head and neck cancers among Korean Population are not available at present. In order to obtain current status of such data, we have analyzed cancer patients at the department of radiation oncology, korea universityhospital for radiation treatment. Materials and Methods : We have evaluated nine-hundred and ninetyseven (997) head and neck cancer Patients who visited to the Department of radiation oncology, between November 1981 to December 1995. After careful physical examinations and CAT scan, Patients were divided into two groups, those with positive lymph node metastases and with negative lymph node metastases. The nodal status were classified according to the TNM system of American Joint Committee on Cancer (AJCC) Besults : Four-hundred and sixteen Patients out of the 997 patients were lymph node positive $(42\%)$ and 581 patients were lymph node negative $(58\%)$ when they were first presented at the department of radiation oncelogy. According to the AJCC classification, the distribution of positive lymph node is as follow: Nl:106 $(25.5\%),\;N2a:100\;(24\%),\;N2b:68\;(16.4\%),\;N2c:69\;(16.6\%),\;3:73\;(15\%).$ respectively. The frequency of lymph node metastases according to the primary sites is as follow : larynx 283 $(28.5\%)$, paranasal sinuses: 182 $(18\%),\;oropharynx:144\;(14.5\%)\;nasopharynx:122(12\%),\;oral\;cavity\;92\;(9\%),\;hypopharynx:71\;(7\%),\;falivary\;gland:58\;(6\%)$ unknown primary:31 $(3\%),\;skin:\;14(2\%)$,. The most frequent Primary site for the positive Iymph node metastases was nasopharynx $(71\%)$ followed by hypopharynx $(69\%),\;oropharynx\;(64\%),\;oral\;cavity\;(39\%)$ The most common histologic type was squamous cell carcinoma (652/997: $65.4\%$). followed by malignant lymphoma $(109/997:11\%)$. Conclusion : Statistical results of lymph node metastases from head and neck cancer at our department were very similar to those obtained from other countries. It is concluded that the location of Primary cancer influences sites of metastases on head and neck, and stage of the primary cancer also influences the development of metastatic lesions. Since the present study is limited on the data collected from one institute. further statistical analyses on Korean cancer Patients are warrented.

• Journal of the Korea Convergence Society
• /
• v.8 no.12
• /
• pp.49-53
• /
• 2017

Breast cancer is the sccond most female cancer patient in the entire female cancer patient, and has emerged as the highest contributor to female cancer deaths. If breast cancer id detected early, the cure rate is 92 percent. However, if early detection fails, breast cancer has a very high rate of metastasis. The transition from cancer to cancer has become more successful as cancer progresses. Early diagnosis of cancer is an important factor in improving quality of life. Examples of breast cancer include Mammograph, ultrasound, and Momotome. Mommography is not only painful for the examiner, but also for easy access to breast cancer exam inations. In this paper, breast cancer diagnosis data mammograph data was used. In addition, the Neural Network were classified for early diagnosis of breast cancer early using NEWFM. After learning of data using NEWFM, the accuracy of the breast cancer data classification was 84.4391%.

• The Journal of the Korea Contents Association
• /
• v.8 no.12
• /
• pp.236-245
• /
• 2008

The cancer patient who leads Bone scan and the PET study from in the nuclear medical study what is enforced with the link of early detection and the time which spreads, it will be able to accomplish a positive treatment with the data which presumes that time it researches a degree as cancer discovery initially and only difference of final period the bay it knows. The patient who receives a cancer decision it will be able to accomplish the necessary defense it will be able to delay the time in order, the maximum control the possibility of doing will be becomes the judgement. Cancer decision to initially the nuclear study and treatment it will be in parallel with effort and the investment which are constant and the schedule hour will elapse and to after difficulty some the case which comes to be negligent will be frequent and it will appear with him there to be a possibility of knowing, it will be caused by and the transfer of the cancer sell will be activity. It has a treatment objective and are to each medical treatment agency against and the medical treatment agency worker it will be able to overlook is not the portion is the private plan which needs a more positive disposal, it does.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.134-136
• /
• 2021

Research related to early diagnosis of breast cancer using artificial intelligence algorithms has been actively conducted in recent years. Although various algorithms that classify breast cancer based on a few publicly available ultrasound breast cancer images have been published, these methods show various limitations such as, processing speed and accuracy suitable for the user's purpose. To solve this problem, in this paper, we propose a multi-stage transfer learning where ResNet model trained on ImageNet is transfer learned to microscopic cancer cell line images, which was again transfer learned to classify ultrasound breast cancer images as benign and malignant. The images for the experiment consisted of 250 breast cancer ultrasound images including benign and malignant images and 27,200 cancer cell line images. The proposed multi-stage transfer learning algorithm showed more than 96% accuracy when classifying ultrasound breast cancer images, and is expected to show higher utilization and accuracy through the addition of more cancer cell lines and real-time image processing in the future.

• Journal of Nutrition and Health
• /
• v.53 no.4
• /
• pp.369-380
• /
• 2020

Purpose: It has been previously reported that breast tumor incidence, growth, and metastasis are stimulated by high-fat diet but reduced by caloric restriction. However, few studies have elucidated the effects of dietary change from a high-fat diet after breast cancer initiation. Therefore, in this study, we attempted to provide practical assistance to breast cancer prevention and management by investigating the effects of dietary change from a high-fat diet to normal diet on breast cancer growth and metastasis. Methods: The experimental animals were divided into 2 groups (high-fat diet control [HFC] group and diet restriction [DR] group) and consumed a high-fat diet for 8 weeks. 4T1 cells were transplanted into subcutaneous fat or tail vein to measure the growth and metastasis of breast cancer. The HFC and DR groups continuously ingested either high-fat diet or AIG-93G diet for 5 weeks or 3 weeks, respectively. Cell proliferation and apoptosis markers from tumor tissues were analyzed by Western blot analysis. The data were analyzed using the SPSS 25.0 package program. Results: The results show that the DR group significantly reduced breast tumor initiation, growth, and tumor tissue weight compared to the HFC group. The DR group suppressed tumor growth by decreasing proliferation and inducing apoptosis through down-regulation of Bcl-xL and up-regulation of caspase-3 activity. Furthermore, the DR group significantly reduced numbers of metastasized tumors in lung tissues. Conclusion: These results suggest that dietary change from a high-fat diet to normal diet decreased breast growth by reducing cell proliferation and inducing apoptosis and metastasis. Taken together, these results indicate that dietary change to a low-fat and balanced diet might suppress breast tumor growth and metastasis even after tumor diagnosis.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2003.10a
• /
• pp.61-65
• /
• 2003

암의 성장을 정확하게 예측할 수 있다면 암으로 고통 받는 많은 사람들에게 적절한 치료 및 처방을 내릴 수 있을 것이다. 그 동안 암의 성장을 예측하기 위하여 많은 연구가 진행되어왔는데 크게 나누어 하향식 설계 방법과 상향식 설계 방법이 있다. 하향식 방법은 전체적인 흐름을 파악하기는 쉽지만, 지역적 특성을 고려하기 어렵다는 단점이 있고, 상향식 방법은 지역적 특성은 고려하기 쉽지만, 전체적인 흐름을 파악하기 어려운 단점이 있다. 본 논문에서는 두 가지 방법을 혼합한 방법을 사용하여 지역적으로는 불규칙적인 암의 성장 모습과 암이 다른 조직으로 전이되는 모습을 동시에 관찰 할 수 있게 하였다. 아울러 시뮬레이션된 암의 모형이 실제 임상학적인 모습과 유사하다는 것을 발견하였다.

• The Journal of the Korean bone and joint tumor society
• /
• v.8 no.2
• /
• pp.48-53
• /
• 2002

Although direct skeletal muscle invasion by carcinoma is well recognized, distant metastasis to skeletal muscle is uncommon. Furthermore, multifocal skeletal muscle metastasis is a very exceptional event. Some factors such as variable intra-muscular blood flow, mechanical factors including turbulent blood flow and muscle contraction, intra-muscular acidic condition, lactic acid, protease inhibitors in the extra-cellular matrix were proposed as causes of the rarity of distant metastasis to skeletal muscle. We report here a case of a 67 year old male who had multifocal skeletal muscle metastasis from the transitional cell carcinoma of left kidney.