Automated Detection and Classification of Micro-Calcifications in Mammograms Using Artifical Neural Nets

Early Mortality Following Diagnosis of Multiple Myeloma; Analysis of Patients Entered into the UK Medical Research Council Trials 1980–2002.

To examine the precision of the perinatal death certificate (PDC) and ascertain the possible sources of error in the certification of neonatal deaths. The 'Main' and 'Other' causes of death recorded on the PDC were obtained from the Registry of Births, Deaths and Marriages and compared with those from a clinicopathological summary (CPS) completed after all pending laboratory results and/or autopsy information were available. There were 179 neonatal deaths during the 7 year period under review. The PDC and CPS main causes of death were concordant in 103 of 179 infants (58%) and discordant in the remaining 76 infants (42%). The PDC main cause of death was incorrectly classified in 61 of 76 infants (80%) with discordant findings and was incompletely classified in the remaining 15 infants (20%). The following discordancies were recorded for the 61 infants with an incorrect classification: (i) transposition of the 'Main' and 'Other' causes of death, resulting in a sequencing discordancy in 14 infants (23%); (ii) recording a non-pathological condition as the main cause of death in 40 infants (66%); and (iii) recording an incorrect pathological condition as the main cause of death in seven infants (11%). Eight of the 61 (13%) incorrect classifications and four of the 15 (27%) incomplete classifications were associated with laboratory and/or autopsy data being unavailable when the PDC was completed. The concordancy between the PDC and CPS would have increased from 58 to 91% if the 'Main' and 'Other' causes of death had been sequenced correctly, if the main cause of death had been ascribed to a pathological disease rather than a non-pathological condition and if corrective information from pending laboratory tests and/or autopsy examination had been made available to the Registry of Births, Deaths and Marriages.

Introdução: A mortalidade materna é considerada um problema de saúde pública, tendo a hipertensão arterial como umas das principais causas obstétricas diretas. Objetivo: Descrever o perfil epidemiológico da mortalidade materna por doença hipertensiva no Piauí, nos anos de 2007 a 2016. Métodos: Trata-se de um estudo descritivo, com abordagem quantitativa, que utilizou informações de óbitos maternos relacionados à hipertensão da base de dados do Sistema de Informação da Mortalidade e de nascidos vivos do Sistema de Informação sobre Nascidos Vivos dos anos de 2007 a 2016, no Piauí, disponíveis no DATASUS. Resultados: Dos 441 óbitos maternos, 103 (23,3%) foram relacionados à doença hipertensiva. A maioria dos óbitos ocorreu no interior do estado (86,4%), no ano de 2008 (20,4%), no hospital (88,3%), no puerpério (65,0%), sendo a eclâmpsia a principal causa de morte (67,0%). As mulheres que mais morreram foram as pardas (67,9%), casadas (29,1%) e solteiras (29,1%), na faixa etária de 20 a 29 anos (40,8%) e com 8 a 11 anos de estudo (20,4%). A Razão de Mortalidade Materna para o período foi de 20,8 mortes/100 mil nascidos vivos. Conclusões: As doenças hipertensivas constituem-se como uma das principais causas de óbito materno no Piauí, cuja implementação das políticas de enfrentamento vigentes não tem sido suficiente para determinar um padrão decrescente na ocorrência dos óbitos por essas causas.
 
 Palavras-chave: Mortalidade materna. Hipertensão. Saúde da mulher.

This paper presents and compares two image processing methods for differentiating benign from malignant microcalcifications in mammograms. The gold standard method for differentiating benign from malignant microcalcifications is biopsy, which is invasive. The goal of the proposed methods is to reduce rate of biopsies with negative results. In the first method, we extract 17 shape features from each mammogram. These features are related to shapes of individual microcalcifications or to their clusters. In the second method, we extract 44 texture features from each mammogram using co-occurrence method of Haralick. Next, we select best features from each set using a genetic algorithm, to maximize area under ROC curve. This curve is created using a k-nearest neighbor (kNN) classifier and a malignancy criterion. Finally, we evaluate the methods by comparing ROC's with greatest areas obtained using each method. We applied the proposed methods, with different values of k in kNN classifier, to 74 malignant and 29 benign microcalcification clusters. Truth for each mammogram was established based on the biopsy results. We found greatest area under ROC curve for each set of features used in each method. For shape features this area was 0.82 (k = 7) and for Haralick features it was 0.72(k=9).

Objective Administered in a timely manner, current evidence-based interventions could reduce neonatal deaths from infections, intrapartum injuries and complications due to prematurity. The three delays model (delay in seeking care, in arriving at a health facility, and in receiving adequate care), which has been applied to understanding maternal deaths, may be useful for understanding neonatal deaths. We assess the main causes of neonatal deaths in Rwanda and their associated delays. Methods Using a cross-sectional study design, we evaluated data from 2012 from 40 facilities in which babies were delivered. Audit committees in each facility reviewed each neonatal death in the facility and reported finding to the Ministry of Health using structured questionnaires. Information from questionnaires were centralized in an electronic database. At the end of 2012, records from 40 health facilities across Rwanda's five provinces (mainly district hospitals) were available in the database and were used for this analysis.Results Of the 1324 neonates, the major causes of death were: asphyxia and its complications (36.7%), lower respiratory tract infections (LRTI) (22.5%), and prematurity (22.4%). At least one delay was experienced by nearly three-quarters of neonates: Maternal Delay in Seeking Care 22.1%, Maternal Delay in Arrival to Care 11.2%, Maternal Delay in Adequate Care 14.2%, Neonatal Delay in Seeking Care 8.1%, Neonatal Delay in Arrival to Care 9.3%, and Neonatal Delay in Adequate Care 29.1%. Neonates with each of the main causes of death had statistically significantly increased odds of experiencing Maternal Delay in Seeking Care. Asphyxia deaths had increased odds of experiencing all three Maternal Delays. LRTI deaths had increased odds of all three Neonatal Delays. Conclusion Delays for women in seeking obstetrical care is a critical factor associated with the main causes of neonatal death in Rwanda. Improving obstetrical care quality could reduce neonatal deaths due to asphyxia. Likewise, reducing all three delays could reduce neonatal deaths due to LRTI.

This paper attempts to pinpoint different techniques for Pectoral Muscle (PM) segmentation, Microcalcification (MC) detection and classification in digital mammograms. The segmentation of PM and detection of MC and its classification are mostly based on image processing and data mining techniques. The review centered on major techniques in image processing and data mining that is employed for PM segmentation, MC detection and classification in digital mammograms. Breast cancer is one of the significant causes of death among women aged above 40. Mammography is considered the most successful means for prompt and timely detection of breast cancers. One notable visual indication of the malignant growth is the appearance of Masses, Architectural Distortions, and Microcalcification Clusters (MCCs). There are some disadvantages and hurdles for mankind viewers, and it is hard for radiologists to supply both precise and steady assessment for a large number of mammograms created in extensive screening. Computer Aided Detection has been employed to help radiologists in detecting MC and MCCs. The automatic recognition of malignant MCCs could be very helpful for diagnostic purpose. In this paper, we summarize the methods of automatic detection and classification of MCs in digitized mammograms. Pectoral muscle segmentation techniques are also summarized. The techniques used for segmentation of PM, MC detection and classification in a digitized mammogram are reviewed.

Coronary Heart Disease (CHD) or cardiovascular disease is currently one of the main and first causes of death in developed and developing countries, including Indonesia. By 2010, globally this disease will be the leading cause of death in developing countries, replacing deaths from infection. It is estimated that worldwide, CHD in 2020 will be the most common first killer, accounting for 36% of all deaths, this figure is twice as high as the death rate from cancer. In Indonesia, it is reported that CHD (which is grouped into diseases of the circulatory system) is the main and first cause of all deaths, which is 26.4%, this figure is four times higher than the death rate caused by cancer (6%). In other words, approximately one in four people who die in Indonesia is due to CHD. Various risk factors have an important role in the emergence of CHD, ranging from aspects of metabolism, hemostasis, immunology, infection, and many other interrelated factors. Coronary heart disease is a condition due to narrowing, blockage or abnormalities of the coronary arteries. Coronary heart disease is caused by narrowing or blockage of coronary arteries. This narrowing or blockage can stop blood flow to the heart muscle which is often characterized by pain (Yenrina, Krisnatuti, 1999). Coronary heart disease is heart disease due to abnormalities in the coronary vessels, namely the arteries that deliver blood to the aorta to the tissue that protects the heart cavities (Kartohoesodo, 1982). Coronary heart disease (CHD) is currently one of the main causes of death in developed and developing countries (Ministry of Health, 2006). Combined data from Clientman et al and GUSTO-I showed that the mortality rate in the first 30 days of hospitalization for patients with AMI was 52% before admission, 19% within 24 hours of hospitalization, 8% during 48 hours of hospitalization, and 21% after 30 days. . Globally, of the 55 million deaths in a year, 30% are caused by cardiovascular disease, of which almost 50% are due to AMI attacks (Yusuf, S et al 2001). (USU.ac.id)

There is a misconception that the main cause of death among women is breast cancer, even among physicians, who may neglect cardiovascular preventive measures in this gender Aim: To assess the knowledge among physicians about the main cause of death among women. A survey was answered by 231 physicians attending a Cardiology and a Gynecology Meeting. Sixty eight percent of respondents indicated that cardiovascular diseases are the main cause of death among women. A higher proportion of specialists than trainees, answered correctly the question (72 and 56% respectively). No gender differences in the answers were recorded. The knowledge about cardiovascular risk in women should be reinforced among physicians.

Survival, Causes of Death, and Risk Factors Associated With Mortality in Spanish Systemic Sclerosis Patients: Results From a Single University Hospital

OP0030 Associated Factors with Mortality and Derivation of A Simple 5-Factors To Predict Mortality in Ssc-Patients in The Eustar Cohort

A carefully classified dataset of perinatal mortality will retain the most significant information on the causes of death. Such information is needed for health care policy development, surveillance and international comparisons, clinical services and research. For comparability purposes, we propose a classification system that could serve all these needs, and be applicable in both developing and developed countries. It is developed to adhere to basic concepts of underlying cause in the International Classification of Diseases (ICD), although gaps in ICD prevent classification of perinatal deaths solely on existing ICD codes.We tested the Causes of Death and Associated Conditions (Codac) classification for perinatal deaths in seven populations, including two developing country settings. We identified areas of potential improvements in the ability to retain existing information, ease of use and inter-rater agreement. After revisions to address these issues we propose Version II of Codac with detailed coding instructions.The ten main categories of Codac consist of three key contributors to global perinatal mortality (intrapartum events, infections and congenital anomalies), two crucial aspects of perinatal mortality (unknown causes of death and termination of pregnancy), a clear distinction of conditions relevant only to the neonatal period and the remaining conditions are arranged in the four anatomical compartments (fetal, cord, placental and maternal).For more detail there are 94 subcategories, further specified in 577 categories in the full version. Codac is designed to accommodate both the main cause of death as well as two associated conditions. We suggest reporting not only the main cause of death, but also the associated relevant conditions so that scenarios of combined conditions and events are captured.The appropriately applied Codac system promises to better manage information on causes of perinatal deaths, the conditions associated with them, and the most common clinical scenarios for future study and comparisons.

BackgroundLate-onset systemic lupus erythematosus (SLE) is designated as that developing after the age of 50 [1], [2]. It has been associated with a different prevalence of clinical manifestations, disease activity,...

BackgroundCoronary heart disease has been reported to be the major cause of death of postmenopausal women in industrialized countries. The risk for women of dying from myocardial infarction is significantly greater than the risk of dying from cancer. The aim of this study was to compare previous observations regarding causes of death with the results from the Population Study of Women in Gothenburg. We also examined how causes of deaths vary among different age cohorts.MethodsThis follow-up report based on the prospective observational Population Study of Women in Gothenburg, Sweden was confined to mortality in two age cohorts: 180 women born in 1914 and 398 women born in 1918. These women were representative of the female population in Gothenburg in these age groups. Women were followed for 32 years, from 1968–1969 to 2000–2001. During the follow-up period, data on mortality were obtained from the population registry and the Cause of Death Register. Women’s death certificates were also examined.ResultsIn women aged between 60 and 80 years, cancer accounted for 30% of deaths, myocardial infarction for 19%, and stroke for 14%. In women who died after the age of 80 years, myocardial infarction was a more common cause of death than cancer.ConclusionsCancer accounts for most years lost from a woman’s normal life span. Myocardial infarction was a more common cause of death than cancer only in women above the age of 80 years. Although myocardial infarction is a common cause of death among women, cancer is a more common cause of death at younger ages. This should be emphasized when planning care, prevention, and research involving women’s health.

Breast cancer is one of the main causes of death in women and ranks first in cancer cases in Indonesia. Therefore, an early detection and prevention of breast cancer is necessary, one of which is through mammography procedures. A machine learning classifier such as Support Vector Machines (SVM) could be used as an aid to the doctors and radiologist in diagnosing breast cancer from the mammogram images. The aim of this paper is to compare two feature extraction methods used in SVM, namely the Gray Level Co-Occurrence Matrix (GLCM) and first order with two kernels for each method, namely Gaussian and Polynomial. Classification using SVM method is carried out by testing several parameters such as the value of C, gamma, degree and varying the pixel spacing values ​​in GLCM, which usually in previous studies only used the default pixel spacing. The dataset consists of 500 mammogram images containing 250 benign and malignant images, respectively. This study is expected to find out the best method with the highest accuracy between these two texture feature extractions and and able to distinguish between benign and malignant classes correctly. The result achieved that Gray Level Co-Occurrence Matrix (GLCM) feature extraction method with both Gaussian and Polynomial kernel yields the best performance with an accuracy of 89%.

Objective To compare the causes of death of dyeing and textile factory workers with death from the Guangzhou population Methods Causes of death of these workers were recorded and the standardized proportional mortality ratios (SPMR) was calculated Results ① The noise level was ranged 87 8 102 7 dB(A) and the cotton dust concentration was ranged 0.67 1.59 mg/m 3 at the textile workshop. ② The main causes of death were shown to be tumors (43 3%, 29/67) and cardiovascular diseases(32 8%, 22/67) ③ The values of SPMR showed that the worker were more likely to die from malignant tumors or cardiovascular diseases than the Guangzhou population, especially in liver cancer in males and in breast cancer in females. In males, the SPMR of liver cancer was 655 74% in dyeing workers In females, that of breast cancer was 869 57% in textile workers They were all significantly higher than the same gender’s PMR of the Guangzhou population Conclusion The carcinogenicity of dyestuffs and their intermediate products cannot be ignored Whether textile workers had higher breast cancer risk than the population needs further investigation Banning of smoking in the workplace should be strongly advocated.