Advanced Techniques for Face Recognition under Challenging Environments

Automatically recognizing faces captured under uncontrolled environments has always been a challenging topic in the past decades. In this work, we investigate cohort score normalization that has been widely used in biometric verification as means to improve the robustness of face recognition under challenging environments. In particular, we introduce cohort score normalization into undersampled face recognition problem. Further, we develop an effective cohort normalization method specifically for the unconstrained face pair matching problem. Extensive experiments conducted on several well known face databases demonstrate the effectiveness of cohort normalization on these challenging scenarios. In addition, to give a proper understanding of cohort behavior, we study the impact of the number and quality of cohort samples on the normalization performance. The experimental results show that bigger cohort set size gives more stable and often better results to a point before the performance saturates. And cohort samples with different quality indeed produce different cohort normalization performance. Recognizing faces gone after alterations is another challenging problem for current face recognition algorithms. Face image alterations can be roughly classified into two categories: unintentional (e.g., geometrics transformations introduced by the acquisition devide) and intentional alterations (e.g., plastic surgery). We study the impact of these alterations on face recognition accuracy. Our results show that state-of-the-art algorithms are able to overcome limited digital alterations but are sensitive to more relevant modifications. Further, we develop two useful descriptors for detecting those alterations which can significantly affect the recognition performance. In the end, we propose to use the Structural Similarity (SSIM) quality map to detect and model variations due to plastic surgeries. Extensive experiments conducted on a plastic surgery face database demonstrate the potential of SSIM map for matching face images after surgeries.

Hierarchical clustering of flow cytometry data for the study of conventional central chondrosarcoma

We have investigated the use of hierarchical clustering of flow cytometry data to classify samples of conventional central chondrosarcoma, a malignant cartilage forming tumor of uncertain cellular origin, according to similarities with surface marker profiles of several known cell types. Human primary chondrosarcoma cells, articular chondrocytes, mesenchymal stem cells, fibroblasts, and a panel of tumor cell lines from chondrocytic or epithelial origin were clustered based on the expression profile of eleven surface markers. For clustering, eight hierarchical clustering algorithms, three distance metrics, as well as several approaches for data preprocessing, including multivariate outlier detection, logarithmic transformation, and z-score normalization, were systematically evaluated. By selecting clustering approaches shown to give reproducible results for cluster recovery of known cell types, primary conventional central chondrosacoma cells could be grouped in two main clusters with distinctive marker expression signatures: one group clustering together with mesenchymal stem cells (CD49b-high/CD10-low/CD221-high) and a second group clustering close to fibroblasts (CD49b-low/CD10-high/CD221-low). Hierarchical clustering also revealed substantial differences between primary conventional central chondrosarcoma cells and established chondrosarcoma cell lines, with the latter not only segregating apart from primary tumor cells and normal tissue cells, but clustering together with cell lines from epithelial lineage. Our study provides a foundation for the use of hierarchical clustering applied to flow cytometry data as a powerful tool to classify samples according to marker expression patterns, which could lead to uncover new cancer subtypes.

Normalization procedure for the Baptista Depression Scale - Adult Version (EBADEP-A): transferring of norms

Regarding the standardization of psychological assessment instruments, that is, the construction of referential interpretations of a test, we can find different procedures performed both by Classical Test Theory (CTT) and the Theory of Item Response (IRT). Especially in this case (IRT), we can admit one test as a default, so to use its standardization and transfer the cut-off point to another instrument. Based on this information, the present study aimed to provide a cutoff score for the Baptista Depression Scale - Adult Version (EBADEP-A) through procedures of norms-transfer based on the Center for Epidemiologic Studies – Depression Scale (CES-D). The EBADEP-A presented good distribution and ability to discriminate depressive symptoms, and the sample, consisting of Brazilian College students, received a cutoff score of 32 points. It is emphasized that this is an exploratory and preliminary study, and it is suggested further analyzes to be performed with clinical samples for which results can be corroborated or confronted.

Effect Of Roux-en-y Gastric Bypass On Nonalcoholic Fatty Liver Disease Evaluated Through Nafld Fibrosis Score: A Prospective Study.

Nonalcoholic fatty liver disease (NAFLD) is common among subjects who undergo bariatric surgery and its postsurgical improvement has been reported. This study aimed to determine the evolution of liver disease evaluated through NAFLD fibrosis score 12 months after surgery. It is a prospective cohort study which evaluated patients immediately before and 12 months following Roux-en-Y gastric bypass (RYGB). Mean score decreased from 1.142 to 0.066; surgery led to a resolution rate of advanced fibrosis of 55 %. Resolution was statistically associated with female gender, percentage of excess weight loss, postsurgical body mass index, postsurgical platelet count, and diabetes resolution. As previously reported by studies in which postsurgical biopsies were performed, RYGB leads to a great resolution rate of liver fibrosis. Since postsurgical biopsy is not widely available and has a significant risk, calculation of NAFLD fibrosis score is a simple tool to evaluate this evolution through a noninvasive approach.

[the Modified Us7 Score In The Assessment Of Synovitis In Early Rheumatoid Arthritis].

To evaluate the modified US7 score (MUS7 score SYN) in the assessment of patients with early rheumatoid arthritis (ERA). In addition, dorsal and palmar recesses of the wrists as well as of small joints of the hands and feet were examined for the presence of synovitis by means of a global assessment of joints. The study sample comprised 32 patients treated for arthritis, with an average disease duration of 13 months. An ultrasound machine with high frequency transducer was used. Hands were also X-rayed and analysed by Larsen score. Out of the 832 examined joints, synovitis was detected in 173 (20,79%), tenosynovitis in 22 (4,91%), and erosions in 3 (1,56%). Synovitis was predominantly detected in the dorsal recess (73,38%) of MCP and PIP joints, when compared with palmar recess (26%). The presence of synovitis in the joints evaluated correlated with clinical (HAQ-DI, DAS28), laboratory (ACPA, RF, CRP), and ultrasound results (r = 0,37 to r = 0,42; p = 0,04 to p = 0,003). We found correlation of the MUS7 score SYN of the gray scale US or of the power Doppler US with DAS28 (PCR) values (r = 0,38; p = 0,0332), and with CRP results (r = 0,39; p = 0,0280), respectively. The dorsal recess, the wrist, and small joints can be considered as important sites to detect synovitis by the MUS7 score SYN in patients with ERA.

Shwachman-Kulczycki score still useful to monitor cystic fibrosis severity

INTRODUCTION: The Shwachman-Kulczycki score was the first scoring system used in cystic fibrosis to assess disease severity. Despite its subjectivity, it is still widely used. OBJECTIVE: To study correlations among forced expiratory volume in one second (FEV1), chest radiography, chest computed tomography, 6-minute walk test, and Shwachman-Kulczycki score in patients with cystic fibrosis and to test whether the Shwachman-Kulczycki score is still useful in monitoring the severity of the disease. METHODS: A cross-sectional prospective study was performed to analyze the correlations (Spearman). Patients with clinically stable cystic fibrosis, aged 3-21 years, were included. RESULTS: 43 patients, 19F/24M, mean age 10.5 + 4.7 years, with a median Shwachman-Kulczycki score of 70 were studied. The median Brasfield and Bhalla scores were 17 and 10, respectively. The mean Z score for the 6-minute walk test was -1.1 + 1.106 and the mean FEV1 was 59 + 26 (as percentage of predicted values). The following significant correlations versus the Shwachman-Kulczycki score were found: FEV1 (r = 0.76), 6-minute walk test (r = 0.71), chest radiography (r = 0.71) and chest computed tomography (r = -0.78). When patients were divided according to FEV1, a statistically significantly correlation with the Shwachman-Kulczycki score was found only in patients with FEV1 <70% (r = 0.67). CONCLUSIONS: The Shwachman-Kulczycki score remains an useful tool for monitoring the severity of cystic fibrosis, adequately reflecting the functional impairment and chest radiography and tomography changes, especially in patients with greater impairment of lung function. When assessing patients with mild lung disease its limitations should be considered and its usefulness in such patients should be evaluated in larger populations.

Metabolic syndrome and dietary components are associated with coronary artery disease risk score in free-living adults: a cross-sectional study

Background: Coronary artery disease (CAD) is among the main causes of death in developed countries, and diet and lifestyle can influence CAD incidence. Objective: To evaluate the association of coronary artery disease risk score with dietary, anthropometric and biochemical components in adults clinically selected for a lifestyle modification program. Methods: 362 adults (96 men, 266 women, 53.9 +/- 9.4 years) fulfilled the inclusion criteria by presenting all the required data. The Framingham score was calculated and the IV Brazilian Guideline on Dyslipidemia and Prevention of Atherosclerosis was adopted for classification of the CAD risks. Anthropometric assessments included waist circumference (WC), body fat and calculated BMI (kg/m(2)) and muscle-mass index (MMI kg/m(2)). Dietary intake was estimated through 24 h dietary recall. Fasting blood was used for biochemical analysis. Metabolic Syndrome (MS) was diagnosed using NCEP-ATPIII (2001) criteria. Logistic regression was used to determine the odds of CAD risks according to the altered components of MS, dietary, anthropometric, and biochemical components. Results: For a sample with a BMI 28.5 +/- 5.0 kg/m(2) the association with lower risk (<10% CAD) were lower age (<60 years old), and plasma values of uric acid. The presence of MS within low, intermediary, and high CAD risk categories was 30.8%, 55.5%, and 69.8%, respectively. The independent risk factors associated with CAD risk score was MS and uric acid, and the protective factors were recommended intake of saturated fat and fiber and muscle mass index. Conclusion: Recommended intake of saturated fat and dietary fiber, together with proper muscle mass, are inversely associated with CAD risk score. On the other hand, the presence of MS and high plasma uric acid are associated with CAD risk score.

A score system for quality evaluation of RNA sequence tags: an improvement for gene expression profiling

Background: High-throughput molecular approaches for gene expression profiling, such as Serial Analysis of Gene Expression (SAGE), Massively Parallel Signature Sequencing (MPSS) or Sequencing-by-Synthesis (SBS) represent powerful techniques that provide global transcription profiles of different cell types through sequencing of short fragments of transcripts, denominated sequence tags. These techniques have improved our understanding about the relationships between these expression profiles and cellular phenotypes. Despite this, more reliable datasets are still necessary. In this work, we present a web-based tool named S3T: Score System for Sequence Tags, to index sequenced tags in accordance with their reliability. This is made through a series of evaluations based on a defined rule set. S3T allows the identification/selection of tags, considered more reliable for further gene expression analysis. Results: This methodology was applied to a public SAGE dataset. In order to compare data before and after filtering, a hierarchical clustering analysis was performed in samples from the same type of tissue, in distinct biological conditions, using these two datasets. Our results provide evidences suggesting that it is possible to find more congruous clusters after using S3T scoring system. Conclusion: These results substantiate the proposed application to generate more reliable data. This is a significant contribution for determination of global gene expression profiles. The library analysis with S3T is freely available at http://gdm.fmrp.usp.br/s3t/.S3T source code and datasets can also be downloaded from the aforementioned website.

Protein fold recognition score functions: Unusual construction strategies

We describe two ways of optimizing score functions for protein sequence to structure threading. The first method adjusts parameters to improve sequence to structure alignment. The second adjusts parameters so as to improve a score function's ability to rank alignments calculated in the first score function. Unlike those functions known as knowledge-based force fields, the resulting parameter sets do not rely on Boltzmann statistics, have no claim to representing free energies and are purely constructions for recognizing protein folds. The methods give a small improvement, but suggest that functions can be profitably optimized for very specific aspects of protein fold recognition, Proteins 1999;36:454-461. (C) 1999 Wiley-Liss, Inc.

Use of AST platelet ratio index (APRI Score) as an alternative to liver biopsy for treatment indication in chronic hepatitis C

Chronic hepatitis C (CHC) is one of the most important causes of chronic liver disease in the world, potentially resulting in cirrhosis, hepatocellular carcinoma, and the need for liver transplantation. Liver biopsy is currently performed before therapy indication. Although, it is the golden standard there are many reasons to avoid or delay the procedure. APRI Score is an easy, low cost and practice alternative method which was described as an alternative for assessing structural changes in chronic hepatitis C (CHC). The rationale of this study was to observe the accuracy of APRI Score in comparison to liver biopsy in 400 patients divided into two groups of 200 carriers (Validation and Experimental groups respectively) selected at random or according to liver fibrosis staging (METAVIR). The ROC curves showed a concordance among these two methods of 92% and 88.5% when 1.05 was the cut off (F3 and F4), and 87% and 83%, on 0.75 cut offs (F2-F4). The discordance in advanced fibrosis staging (F3 and F4) was only 16 (8%) and 22 (11%) out of 200 patients in the experimental and validation groups, respectively. In 26 (13%) out of 200 patients in the experimental group and 34 (17%) out of 200 patients in the validation group, there was discordance between APRI Score and liver biopsy in moderate and advanced fibrosis (F2-F4). In conclusion APRI is a serological marker that has satisfactory sensitivity and specificity together with a high predictive value and it can be useful either in the absence of a biopsy or to reduce the frequency with which biopsies need to be carried out to monitor the evolution of chronic hepatitis C and the right moment for treatment indication.

The Finnish Diabetes Risk Score (FINDRISC) as a screening tool for hepatic steatosis

Introduction. Hepatic steatosis due to non-alcoholic fatty liver disease is associated with obesity, dyslipidemia, insulin resistance, and type 2 diabetes. The Finnish Diabetes Risk Score (FINDRISC) is a prognostic screening tool to detect people at risk for type 2 diabetes without the use of any blood test. The objective of this study was to evaluate whether FINDRISC can also be used to screen for the presence of hepatic steatosis. Patients and methods. Steatosis was determined by ultrasound. The study sample consisted of 821 non-diabetic subjects without previous hepatic disease; 81% were men (mean age 45 +/- 9 years) and 19% women (mean age 41 +/- 10 years). Results. Steatosis was present in 44% of men and 10% of women. The odds ratio for one unit increase in the FINDRISC associated with the risk of steatosis was 1.30 (95% CI 1.25-1.35), similar for men and women. The area under the receiver operating characteristics curve for steatosis was 0.80 (95% CI 0.77-0.83); 0.80 in men (95% CI 0.77-0.83) and 0.83 (95% CI 0.73-0.93) in women. Conclusions. Our data suggest that the FINDRISC could be a useful primary screening tool for the presence of steatosis.

A prognostic score for AIDS-related diffuse large B-cell lymphoma in Brazil

The aim of this study was to evaluate a prognostic score for aids-related lymphoma (ARL). A retrospective study of 104 patients with ARL treated between January 1999 and December 2007 was conducted. Diffuse large B-cell lymphoma (DLBC) was the most observed histological type (79.8%). The median CD4 lymphocyte count at lymphoma diagnosis was 125 cells per microliter. Treatment response could be evaluated in 83 (79.8%) patients, and 38 (45.8%) reached complete remission (CR); overall response rate was 51.8% (95 CI = 38.5-65.1%). After a median follow-up of 48 months, the 4-year overall survival (OS) rate among all patients was 35.8%, with a median survival time of 9.7 months (95% CI = 5.5-13.9 months). The survival risk factors observed in multivariate analysis (previous AIDS and high-intermediate/high international prognostic index (IPI)) were combined to construct a risk score, which divided the whole patient population in three distinct groups as low, intermediate, and high risk. When this score was applied to DLBC patients, a clear distinction in response rates and in OS could be demonstrated. Median disease-free survival (DFS) for patients that achieved CR was not reached, and DFS in 4 years was 83.0%. Our results show that the reduced OS observed could be explained by poor immune status with advanced stage of disease seen in our population of HIV-positive patients. Further studies will be needed to clarify the role of different treatment approaches for ARL in the setting of marked immunosuppression and to identify a group of patients to whom intensive therapy could be performed with a curative intent.

A Palliative Prognostic Score for Terminally Ill Children and Adolescents With Cancer

Background. The loss of a child is considered the hardest moment in a parent`s life. Studies addressing length of survival under pediatric palliative care are rare. The aim of this study was to improve a survival prediction model for children in palliative care, as accurate information positively impacts parent and child preparation for palliative care. Procedure. Sixty-five children referred to a pediatric palliative care team were followed from August 2003 until December 2006. Variables investigated (also included in previous studies) were: diagnosis, home care provider, presence of anemia, and performance status score given by the home care provider. Clinical variables such as symptom number were also used to test the score`s ability to pre-validated using the above variables. The number of symptoms at transition to palliative care does not improve the score`s predictive ability. The sum of the single scores gives an overall score for each patient, dividing the population into three groups by probability of 60-day survival: Group A 80.0%, Group B 38.0%, and Group C 28.5% (P < 0.001). Conclusion. A pediatric palliative care score based on easily accessible variables is statistically significant in multivariate analysis. Factors that increase accuracy of life expectancy prediction enable adequate information to be given to patients and families, contributing to therapeutic decision-making issues. Pediatr Blood Cancer. 2010;55:1167-1171. (C) 2010 Wiley-Liss, Inc.

UPGRADING THE GLEASON SCORE IN EXTENDED PROSTATE BIOPSY: IMPLICATIONS FOR TREATMENT CHOICE

Purpose: To determine the incidence of overestimation of Gleason score (GS) in extended prostate biopsy, and consequently circumventing unnecessary aggressive treatment. Methods and Materials: This is a retrospective study of 464 patients who underwent prostate biopsy and radical prostatectomy between January 2001 and November 2007. The GS from biopsy and radical prostatectomy were compared. The incidence of overestimation of GS in biopsies and tumor volume were studied. Multivariate analysis was applied to find parameters that predict upgrading the GS in prostate biopsy. Results: The exact agreement of GS between prostate biopsy and radical prostatectomy occurred in 56.9% of cases. In 29.1% cases it was underestimated, and it was overestimated in 14%. One hundred and six (22.8%) patients received a diagnosis of high GS (8, 9, or 10) in a prostate biopsy. In 29.2% of cases, the definitive Gleason Score was 7 or lower. In cases in which GS was overestimated in the biopsy, tumors were significantly smaller. In multivariate analysis, the total percentage of tumor was the only independent factor in overestimation of GS. Tumors occupying less than 33% of cores had a 5.6-fold greater chance of being overestimated. Conclusion: In the extended biopsy era and after the International Society of Urological Pathology consensus on G, almost one third of tumors considered to have high GS at the biopsy may be intermediate-risk cancers. In that condition, tumors are smaller in biopsy. This should be remembered by professionals involved with prostate cancer to avoid overtreatment and undesirable side effects. (c) 2009 Elsevier Inc.