• Journal of Korea Multimedia Society
• /
• v.19 no.4
• /
• pp.736-746
• /
• 2016

In this paper, we propose an automatic prostate cancer detection method using position, signal intensity and texture feature based on SVM in multi-parametric MR images. First, to align the prostate on DWI and ADC map to T2wMR, the transformation parameters of DWI are estimated by normalized mutual information-based rigid registration. Then, to normalize the signal intensity range among inter-patient images, histogram stretching is performed. Second, to detect prostate cancer areas in T2wMR, SVM classification with position, signal intensity and texture features was performed on T2wMR, DWI and ADC map. Our feature classification using multi-parametric MR imaging can improve the prostate cancer detection rate on T2wMR.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.80-96
• /
• 2022

Nowadays, artificial intelligence promotes the rapid development of skin cancer detection technology, and the federated skin cancer detection model (FSDM) and dual generative adversarial network model (DGANM) solves the fragmentation and privacy of data to a certain extent. To overcome the problem that the many-objective evolutionary algorithm (MaOEA) cannot guarantee the convergence and diversity of the population when solving the above models, a many-objective evolutionary algorithm based on integrated strategy (MaOEA-IS) is proposed. First, the idea of federated learning is introduced into population mutation, the new parents are generated through sub-populations employs different mating selection operators. Then, the distance between each solution to the ideal point (SID) and the Achievement Scalarizing Function (ASF) value of each solution are considered comprehensively for environment selection, meanwhile, the elimination mechanism is used to carry out the select offspring operation. Eventually, the FSDM and DGANM are solved through MaOEA-IS. The experimental results show that the MaOEA-IS has better convergence and diversity, and it has superior performance in solving the FSDM and DGANM. The proposed MaOEA-IS provides more reasonable solutions scheme for many scholars of skin cancer detection and promotes the progress of intelligent medicine.

• Journal of Gastric Cancer
• /
• v.22 no.4
• /
• pp.306-318
• /
• 2022

Gastric cancer (GC) is associated with high morbidity and mortality rates. Thus, early diagnosis is important to improve disease prognosis. Endoscopic assessment represents the most reliable imaging method for GC diagnosis; however, it is semi-invasive and costly and heavily depends on the skills of the endoscopist, which limit its clinical applicability. Therefore, the search for new sensitive biomarkers for the early detection of GC using noninvasive sampling collection methods has attracted much attention among scientists. Urine is considered an ideal biofluid, as it is readily accessible, less complex, and relatively stable than plasma and serum. Over the years, substantial progress has been made in screening for potential urinary biomarkers for GC. This review explores the possible applications and limitations of urinary biomarkers in GC detection and diagnosis.

• Journal of Biomedical Engineering Research
• /
• v.30 no.2
• /
• pp.122-128
• /
• 2009

Cancer serum biomarkers have advanced our ability to more accurately predict tumor classification, prognostic/metastatic potential, and response potential to novel chemotherapies. Serum amyloid A (SAA) and Vascular endothelial growth factor (VEGF) have potential utility as a serum biomarker for lung cancer. Quantum dots, nanometer-sized crystals, have a high quantum yield, sensitivity, and pronounced photostability. The properties of quantum dots can be efficiently applied to the detection of serum biomarkers in immunoassays as fluorescent probe. We used quantum dots as fluorescent probes in immunoassays and attempted to detect serum amyloid A and vascular endothelial growth factor as serum biomarkers of lung cancer. This fluorescence immunoassay based on the properties of quantum dots is applicable to the detection of serum biomarkers for lung cancer. The fluorescence immunoassay with quantum dots should allow the efficient and specific detection of serum amyloid A (SAA) for the possible diagnosis of lung cancer.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.6
• /
• pp.2547-2553
• /
• 2015

Purpose: The present study concerns the effectiveness of an educational intervention for improving knowledge, attitudes and practices (KAP) of breast cancer early detection among target group women (TGW) in the district of Gampaha, Sri Lanka. Materials and Methods: The study was a community-based intervention. Two medical officer of health areas in Gampaha district were selected using random sampling as intervention (IA) and control (CA). Public health midwives (PHMs) in the IA were exposed to the educational intervention first, conducted the same among the TGW through PHMs. KAP was assessed using an interviewer- administrated questionnaire among 260 TGW from each area selected using cluster sampling before and six months after the intervention. Results: The overall median scores for KAP among TGW in IG increased significantly from pre intervention level of 54% (IQR: 46-59%), 50% (IQR: 41-59%), and 0% (IQR: 0-20%) to post intervention level of 77% (IQR: 72-82%), 68% (IQR: 59- 76 %) and 40% (IQR: 20-60%) respectively. In CG, overall median scores for KAP remained almost the same at pre intervention 54% (IQR:44-59%), 50% (IQR:36-59%) and 0% (IQR: 0-20%) and post intervention 54% (IQR:46-59%), 50% (IQR:36-64%) and 0% (IQR: 0-20%) respectively. Conclusions: The educational intervention was found to be effective.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.21
• /
• pp.9375-9378
• /
• 2014

Background: A piezoelectric immunosensor for early cervical cancer detection was developed involving short analyis time and less invasive technique for $p16^{INK4a}$, a protein that has been linked to cervical cancer. Materials and Methods: $5{\mu}L$ of 5.0 mg/mL $p16^{INK4a}$ antibody and then supernatant from different clinical samples from West China Second University Hospital (Sichuan, China) were dripped on the center of the AT-cut crystal through a micro-injector. Absorption of the $p16^{INK4a}$ by antibody caused a shift in the resonant frequency of the immunosensor, and the resonant frequency was correlated to the amount of the $p16^{INK4a}$ in the supernatant. Results: The greater severity of lesion grading, the greater the expression level of $p16^{INK4a}$. Conclusion: Degree of cervical cancer lesion development could be determined by detected amount of $p16^{INK4a}$ in different clinical samples.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.11
• /
• pp.4745-4749
• /
• 2015

Background: The aim of this study was to assess detection of circulating tumor cells (CTC) using anti-CEA pre and post surgery in Chilean patients with colo-rectal cancer. Materials and Methods: The presence of CTCs was evaluated in 80 colorectal cancer patients pre and post surgery using standard immunocytochemistry and the results were compared with findings for standard clinico-pathological parameters. Results: In patients presurgery CEA (+) CTCs were frequently found, with no relation to tumor size or nodal status. After surgery, the presence of CTCs was associated with such clinico-pathological parameters. The frequency of CTC detection in node positive patients did not change after surgery. In patients with metastasis there was also no change in the frequency of CTC detection, and clusters of 3 or more CTCs were evident. Conclusions: Secondary CTCs are associated with clinico-pathological parameters only after surgical removal of the primary tumor, and might be important in identifying patients at high risk of relapse. Primary CTCs detected before surgical removal are frequently found, are not associated with the clinico-pathological parameters and might have a role in cancer screening. These findings suggest the need for studies with a larger population of patients.

• Journal of Bone Metabolism
• /
• v.25 no.4
• /
• pp.213-217
• /
• 2018

Patients with gastrointestinal disease (GI) are at risk for osteopenia or osteoporosis, which can lead to fractures. Although these patients may be at risk from a young age, gastroenterologists often overlook this fact in practice. There are well-known GI diseases associated with osteopenia and osteoporosis, such as the post-gastrectomy state, inflammatory bowel disease (IBD), and celiac disease. As there is an increase in the prevalence of IBD patients, newly diagnosed celiac disease in adulthood, and gastric cancer survivors following gastrectomy, bone disease in these patients becomes an important issue. Here, we have discussed osteoporosis and fractures in GI disease, especially in the postgastrectomy state, IBD, and celiac disease. Although the pathogenesis of bone loss in each disease has not been fully identified, we have confirmed that the prevalence of osteoporosis and fractures in each of these diseases is high. There are scarce studies comparing the prevalence of osteoporosis or osteoporotic fractures in GI disease patients with studies in postmenopausal women, and specific guidelines for their management in each disease have not been established. Intensive surveillance and management are needed to ensure that these patients attain peak bone mass for age and sex to prevent fractures.

• Journal of Digestive Cancer Research
• /
• v.11 no.1
• /
• pp.21-29
• /
• 2023

Despite recent advancements in the diagnosis and treatment of pancreatic cancer, clinical results remain dismal. Furthermore, there are no reliable biomarkers or alternatives beyond carbohydrate antigen 19-9. Circulating tumor cells (CTCs) may be a potential biomarker, but their therapeutic application is constrained by their rarity in peripheral venous blood. Theoretically, the portal vein can be a more appropriate location for the detection of CTCs, because the first venous drainage of pancreatic cancer is portal circulation. According to several studies, the number and detection rate of CTCs may be higher in the portal blood than in the peripheral blood. CTC counts in the portal blood are strongly correlated with several prognostic parameters such as hepatic metastasis, recurrence after surgery, and survival. The phenotypic and genotypic properties analyzed in the captured portal CTCs can assist us to comprehend tumor heterogeneity and predicting the prognosis of pancreatic cancer. The investigations to date are limited by small sample sizes and varied CTC detection techniques. Therefore, a large number of prospective studies are required to confirm portal CTCs as a valid biomarker in pancreatic cancer.

• Journal of Biomedical Engineering Research
• /
• v.18 no.4
• /
• pp.357-364
• /
• 1997

The early detection of breast cancer is clearly a key ingredient for reducing breast cancer mortality. Microcalcification is the only visible feature of the DCIS's(ductal carcinoma in situ) which consist 15 ~ 20% of screening-detected breast cancer. Therefore, the analysis of the shapes and distributions of microcalcifications is very significant for the early detection. The automatic detection procedures have b(:on the concern of digital image processing for many years. We proposed here one efficient method which is essentially statistical pattern classification accelerated by one representative feature, correlation coefficient. We compared the results by this additional feature with results by a simple gray level thresholding. The average detection rate was increased from 48% by gray level feature only to 83% by the proposed method The performances were evaluated with TP rates and FP counts, and also with Bayes errors.