China
Africa
Explore chapters and articles related to this topic
Biomedical Engineering and Informatics Using Artificial Intelligence
Published in Saravanan Krishnan, Ramesh Kesavan, B. Surendiran, G. S. Mahalakshmi, Handbook of Artificial Intelligence in Biomedical Engineering, 2021
Prostate-Specific Antigen (PSA): The PSA test is a blood test that measures the level of PSA in the bloodstream. The PSA test is currently the best method for identifying an increased risk of localized prostate cancer. PSA values tend to rise with age, and the total PSA levels (ng/ml) recommended by the Prostate Cancer Risk Management Programme are as follows: 50–59 years: PSA ≥ 3.0,60–69 years: PSA ≥ 4.0, and70 and over: PSA > 5.0.
Big Data in Prostate Cancer
Published in Ayman El-Baz, Jasjit S. Suri, Big Data in Multimodal Medical Imaging, 2019
Islam Reda, Ashraf Khalil, Mohammed Ghazal, Ahmed Shalaby, Mohammed Elmogy, Ahmed Aboelfetouh, Ali Mahmoud, Mohamed Abou El-Ghar, Ayman El-Baz
PSA screening is a blood-based screening that measures the PSA level in the blood. An increased value of PSA indicates a higher probability for prostate cancer. However, elevated levels of PSA may also signify other conditions, such as prostatitis or benign prostatic hyperplasia. If the blood PSA levels exceed four nanograms per millimeter (4 ng/mL), patients undergo further screening, such as biopsy, to confirm the presence or absence of the prostate cancer. Generally, the sensitivity and specificity of PSA screening are higher than the DRE screening [10].
A DCE-MRI-Based Noninvasive CAD System for Prostate Cancer Diagnosis
Published in Ayman El-Baz, Gyan Pareek, Jasjit S. Suri, Prostate Cancer Imaging, 2018
F. Khalifa, A. Shalaby, Mohamed Abou El-Ghar, Jasjit S. Suri, A. El-Baz
Prostate cancer is the most frequently diagnosed male malignancy and the second leading cause (after lung cancer) of cancer-related death in the United States, with more than 238,000 new cases and a mortality rate of about 30,000 in 2013 [13]. Early diagnosis improves the effectiveness of treatment and increases the patient’s chances of survival. Compared to other types of cancers such as lung cancer, prostate cancer, when treated by removing the prostate gland, has a zero chance of recurrence. There are many techniques that are used for the diagnosis of prostate cancer. The main diagnostic tools for prostate cancer are digital rectal exam (DRE), serum concentration using prostate-specific antigen (PSA) blood test, and needle biopsy. The DRE test is carried out by a skilled physician who manually feels for any abnormalities in the prostate gland through the rectum. The DRE is inexpensive and easy to perform. However, the accuracy of a DRE examination is not high enough and depends on physician experience. Also, it can only detect tumors with sufficient volumes. Another screening test for the diagnosis of prostate cancer is performed using PSA—an enzyme that is secreted by the prostatic cells. The higher the values of PSA, the more likely the prostate gland is to have cancer. However, PSA is associated with a high risk of overdiagnosis of prostate cancer as higher PSA levels may reflect other conditions, such as an enlarged or inflamed prostate [14]. In addition, PSA screening lacks the ability to provide accurate information about the location and the extent of the cancer. If either the DRE or PSA tests raises any concern, a needle biopsy is performed to collect tissue samples from the prostate, which are analyzed in a lab to determine whether or not cancer cells are present. Biopsy remains the gold standard for diagnosis of prostate cancer, but it is the last resort because of its invasive nature, high costs, and potential morbidity rates. Additionally, the relatively small needle biopsy samples have a higher possibility of producing false positive diagnosis.
Integration of biological and statistical models toward personalized radiation therapy of cancer
Published in IISE Transactions, 2019
Xiaonan Liu, Mirek Fatyga, Teresa Wu, Jing Li
We apply the integrated model to the dataset according to the steps in Figure 3. Recall that the integrated model includes a step for consistency correction, for the case where the population fraction of complication, , is smaller than the sample fraction of complication, . In our dataset, while in the published literature on population-based studies (Tucker et al., 2012). Therefore, consistency correction is needed. Furthermore, to choose the optimal tuning parameters, we adopt a model selection criterion called AICc, which includes a correction for the original AIC under small sample sizes (Hurvich and Tsai, 1989). The results from the integrated model are as follows: Among all the patient-specific variables included in the dataset, six are selected using AICc: diabetes status, prostate volume, PSA, statins use, ADT status, T-stage. The optimal is found to be 0.154. These results are consistent with findings in the literature. For example, statins are a class of drugs often prescribed by doctors to help lower cholesterol levels in the blood. Statins use is negatively related to the probability of complication, indicating that the use of statins might be protective against the development of the 2+ acute rectal complication by patients. At least one biological mechanism behind this seemingly protective effect has been suggested (Malek, 2015), and a relatively recent study reported a similar result, namely a negative association between acute rectal complication during pelvic RT and the use of statins (Wedlake et al., 2012). This corroborates our finding. PSA is a blood test that is commonly used to detect prostate cancer; the higher the level of PSA, the higher the chance the patient has prostate cancer. Finally, knowing that the range of is between zero and one, the optimal found by the integrated model is small. This is consistent with prior findings (Bentzen et al., 2010) and agrees with clinical expectation; the rectum is a serial organ, and it is well-known that serial organs tend to have small (Gulliford et al., 2012; Li et al., 2012).