The interpretation of medical images is one of the most difficult tasks in computer vision, largely because of the high degree of variability associated with normal and abnormal appearances. This thesis introduces a systematic method for the detection of microcalcifications as one of the most important signs of early breast cancer. It involves a four step procedure. The first step is blob detection to detect regions of microcalcification size range. The second step involves a specially designed directional region growing method to find the best fitting boundaries for each blob region. A newly developed combination of classifiers is then applied to label each region as a microcalcification or background. The final processing step involves a search for the existence of clusters of microcalcifications using a hierarchical nearest mean clustering method. The contributions of the work to the field of image processing are; a new blob detection system; a novel region growing method and a theoretical framework for combining classifiers which use a combination of shared and distinct representations. Here specifically, we present a blob detection method with the capability of detecting any suspected blob of specific size range. Then a new region growing method is developed based on a unique directional growing process providing predictable behaviour for the method. The application of two discontinuity measures is considered for the extraction of two fitting boundaries representing information about the region and its local background. The information conveyed by the boundaries and their associated regions is used to compute reliable representations for labelling each blob region. The robustness of the region growing method to the choice of a starting point and to Gaussian noise is examined on real images. We demonstrate that commonly used classifiers provide reliable results in labelling the suspected regions. In spite of achieving an acceptable performance using different individual classifiers, a decision fusion rule involving a weighted combination of classifiers is developed and its performance on the problem is investigated. The combination rule is applicable when mixed mode representations (some shared and some individual features) are used. A comparative study of the individtial classifiers and also of conventional classifier combination techniques with the weighted combiner is performed on independent test sets. The results achieved with the presented algorithm are very promising and approaching a level where a clinical pilot evaluation for screening purposes would be warranted.

Lung cancer is the most common cause of cancer-related deaths in the United States. Prevention and early detection of lung cancer are imperative in decreasing lung cancer mortality. Screening for lung cancer with low-dose computed tomography (LDCT) decreases lung cancer by 20%. Several organizations introduced lung cancer screening (LCS) guidelines in 2013, including Centers for Medicare and Medicaid (CMS) and the United States Preventive Services Task Force. However, LCS participation for eligible patients remains low, due in part to the complexity of the LCS process. The goal of this practice improvement project was to increase the knowledge of rural primary care providers regarding LCS guidelines and the related CMS requirements and to increase their confidence in initiating shared decision-making (SDM) discussions. An educational intervention consisting of a LCS educational session and a toolkit was implemented in two rural clinics. Providers at both clinics reported a benefit to the educational intervention. Pre-, immediate post-, and two-month post-education surveys were collected to evaluate the impact of the educational intervention, including provider knowledge of LCS guidelines and CMS requirements, and confidence in SDM. Project results demonstrated an increased knowledge of LCS guidelines and CMS requirements with the greatest knowledge at immediate post-education and a high level of knowledge remaining at two months post-education. A small, nonsignificant, increase in provider confidence in initiating SDM discussions occurred. At both clinics, data collected through chart audit demonstrated an improvement in documentation needed to determine LCS eligibility and increased the percentage of patients identified at high risk for lung cancer and thus, eligible for LCS. At one clinic these changes were significant. The data were further examined for SDM discussions and referrals for LDCT or to specialist for LCS with one clinic increasing SDM documentation and LDCT referrals post-education. In conclusion, although further research is needed in implementation processes of LCS, specifically in consistent documentation to improve determination of LCS eligibility of patients, this practice improvement project found education increased provider knowledge and ability to complete requirements needed to improve LDCT screenings for lung cancer.

Indiana University-Purdue University Indianapolis (IUPUI) / Women who are medically underserved may be less likely to obtain provider-based cervical cancer screening because of structural and intrapersonal barriers. Self-collection for human papillomavirus (HPV) testing, a method for women to collect their own sample through a vaginal swab or urine collection, has accuracy comparable to provider-based cervico-vaginal HPV testing and may be useful in overcoming barriers to provider-based cervical cancer screening. The purpose of this dissertation study is to examine factors associated with self-collection for HPV testing, psychometrically test Diffusion of Innovations (DOI) instruments, and identify preferences for self-collection for HPV testing. Three distinct aims were developed: 1) factors (sociodemographic, health-related, and theoretical variables) associated with mailed return of vaginal self-collection for HPV testing, 2) psychometric examination of DOI ÷instruments (relative advantages and complexity), and 3) dimensions of self-collection and characteristic preferences to self-collection for HPV testing stratified by age cohorts. This dissertation involved two cross-sectional studies. In Chapters 2-3, data were collected from women (n=168) at food pantries and online. Women were eligible if they were: 1) female, 2) between the ages of 30-65, 3) could read and speak English, and 4) at 2019 federal poverty guidelines for income and family size as defined by the Department of Health and Human Services. Women were not eligible if they had a history of hysterectomy or were adherent to cervical cancer screening guidelines. Logistic regression analyses, item analysis, Cronbach’s alpha, exploratory factor analysis, and tests were used to analyze data. Chapter 4 involved collection of data from an online survey with a sample (n=878) provided by Dynata. Participants evaluated 9 scenarios that varied along 4 attributes: HPV self-collection kit type (vaginal swab or urine collection), HPV self-collection kit delivery (mail, pharmacy pick-up, or clinic pick-up), HPV self-collection kit return (mail, pharmacy drop-off, or clinic drop-off), and HPV test result communication (mail, phone call, or text message). Ratings-based conjoint analysis (RBCA) determined how each attribute influenced the ratings of each scenario.

Purpose: Given that CRC Screening disparities in people experiencing homelessness has been heavily understudied, the purpose of this study is to assess how existing knowledge and access to resources about CRC screenings affect the ability to obtain CRC screenings in people experiencing homelessness in Central Florida. Methods: In March 2023, a team of researchers surveyed subjects who do not have stable housing in two Central Florida locations: a local shelter and a resource center serving the predominantly unsheltered. The survey assessed current understanding of CRC screenings and available/lacking resources necessary for completing CRC screening in this population. There was a total sample size of 75 participants, with 36 participants from the shelter and 39 from the service center location. Our inclusion criteria included those who are undomiciled, age 45 and over who speak Spanish or English. Results:The results indicate that there is a statistical difference between those who are screened and not screened when assessing provider counseling (p Conclusion: Because data was collected in locations that provided resources, this study may not be representative of all undomiciled individuals in Florida, especially in rural areas. Our results imply a need for provider counseling, patient education and access to a primary care provider. More research needs to be conducted from the physician perspective to understand the context of existing barriers to CRC screening.

Yes / Objectives; To evaluate radiation doses for all low-dose CT scans performed during the first year of a lung screening trial. Methods; For all lung screening scans that were performed using a CT protocol that delivered image quality meeting the RSNA QIBA criteria, , radiation dose metrics, participant height, weight, gender and age were recorded. Values of CTDIvol and DLP were evaluated as a function of weight in order to assess the performance of the scan protocol across the participant cohort. Calculated effective doses were used to establish the additional lifetime attributable cancer risks arising from trial scans. Results; Median values of CTDIvol, DLP and effective dose (IQR) from the 3521 scans were 1.1mGy (0.70), 42.4mGycm (24.9) and 1.15mSv (0.67), whilst for 60-80kg participants the values were 1.0mGy (0.30), 35.8mGycm (11.4) and 0.97mSv (0.31). A statistically significant correlation between CTDIvol and weight was identified for males (r=0.9123, p<0.001) and females (r=0.9052, p<0.001), however the effect of gender on CTDIvol was not statistically significant (p=0.2328) despite notable differences existing at the extremes of the weight range. The additional lifetime attributable cancer risks from a single scan were in the range 0.001-0.006%. Conclusions; Low radiation doses can be achieved across a typical lung screening cohort using scan protocols that have been shown to deliver high levels of image quality. The observed dose levels may be considered as typical values for lung screening scans on similar types of scanner for an equivalent participant cohort. Advances in Knowledge; Presentation of typical radiation dose levels for CT lung screening examinations in a large UK trial. Effective radiation doses can be of the order of 1mSv for standard sized participants. Lifetime attributable cancer risks resulting from a single LDCT scan did not exceed 0.006%. / The Yorkshire Lung Screening Trial is funded by Yorkshire Cancer Research (award reference L403).

African American women tend to have lower attendance rates at cervical cancer screenings compared to the attendance rates of women from other ethnic groups. The purpose of this research project was to understand how perceptions of African American women affects attendance of future cervical cancer screenings. The goal was to understand what contributes to low attendance. Previous research did not focus on factors contributing or interfering with appointment attendance among African American women, aged 30-65. The conceptual framework was based on individual health behavior. The research questions examined lived experiences affecting attendance of cervical cancer screenings, attendance of future screenings, and perceptions of experiences. Data collection was based on a phenomenological approach. Open-ended questions were used to gather descriptions of 5 participants' experiences via telephone interviews. These interviews were recorded, transcribed, and coded for recurring themes and patterns. Findings revealed 3 emergent themes related to the attendance of screenings: being knowledgeable of the purpose of cervical cancer screening, a female examiner performing the screening, and the encouragement of family and friends. The implications for social change would be increased knowledge among African American women aged 30-65 and the medical community.

The term "teachable moment" (TM) has been used to describe a life transition or event which motivates an individual to change a behavior or presents an opportunity to intervene to prompt behavior change. We examined whether receipt of a false positive ovarian cancer (OC) screening result may represent a TM. 403 women participating in an OC screening program completed questionnaires assessing demographic, clinical, behavioral, and psychosocial information. The TM was operationalized as expressed interest in receiving health-related information. We hypothesized that among women receiving a false positive screening test result, those women who had experienced greater personal perceived risk for OC as well as distress would be more interested in receiving health-related information than women receiving a normal result. Analyses revealed that women receiving a false positive screening result were less interested in receiving health-related information than women receiving a normal screening result. For women receiving a false positive result, expressed interest in receipt of health-related information was only modestly related to distress and related even less to perceptions of OC risk. Our data do not support viewing a false positive OC screening result as a TM. Potential explanations for the current findings as well as recommendations for future research investigating the TM are discussed.

Despite the existence of breast cancer screening that could promote early diagnosis and survival of breast cancer, high mortality rates of breast cancer persist among Filipino women. The purpose of the qualitative study was to describe the perceptions, beliefs, and behaviors of Filipino women working as Overseas Filipino Workers (OFWs) in Saudi Arabia. Face-to-face interviews were conducted with 20 Filipino women between the ages of 40 to 60 years who were recruited voluntarily using purposeful sampling technique. Guided by the structures of health belief model (HBM), the study used an inductive coding technique to elicit common themes from the raw data. The study established that the participants' screening behaviors were influenced by family history of breast cancer, the financial and emotional burden of the disease and its treatment, the benefit of early detection, mobility to participate, culture and language barriers, and the social media. The study also demonstrated that the desire to participate in breast cancer screening is influenced by the participants' perception of susceptibility and perception of severity to breast cancer. The findings of the study could create a positive social change as it may inform the practice of public health providers, influence the drafting of informed policies for comprehensive breast health care, and improve access to preventive health services for Filipino women OFWs. Furthermore, the study could empower Filipino women in their personal health decision making, especially when working in other countries where good health is the working capital and a precondition for survival.

No description available.

The purpose of this study was to determine the factors related to young black men’s intention to screen for prostate cancer as well as their engagement in prostate cancer risk-reduction behaviors. The study tested the significance of the constructs – age, attitude (direct and indirect), social influence, comfortability, cues to action, health screening experiences and knowledge – in predicting young black men’s intention to screen for prostate cancer; as well as the significance of the constructs – age, cues to action, exercise and knowledge – in predicting engagement in prostate cancer risk-reduction behaviors. Demographic/personal factors were also explored in related to the model predictors. Web-based and paper-pencil surveys were administered to 279 black men aged between 18 – 40 years from the Austin area. Three focus groups were conducted to collect information regarding young black men’s behavioral beliefs toward prostate cancer screening as well as their comfortability with prostate examinations. The number of usable surveys was 267. Using direct and indirect measures, the combination of attitude, social influence, comfortability (indirect model), and knowledge explained 41.0 and 43.0 percent of the variance in intention to screen for prostate cancer, respectively; with social influence being the strongest predictor ([Beta]=0.41; p <0.01 for the direct model and [Beta]=0.47 for the indirect model). For the model with prostate cancer risk-reduction as the outcome variable, the model accounted for 10.0 percent of the variance in behavior with only knowledge ([Beta]=0.19; p=0.03) as significant predictor. Interventions that address young black men’s attitude, social influence, comfortability, and knowledge may be necessary to increase young men’s intention to screen for prostate cancer when it is recommended by a physician. Additionally, factors surrounding exercise and knowledge may be important in increasing young men’s engagement in prostate cancer risk-reduction behaviors. Future studies using intention as a predictor of young men’s behavior are needed to assess the influence of intention on prostate cancer screening. / text