Publications by authors named "Anton Barchuk"

15 Publications

  • Page 1 of 1

Comparability and validity of cancer registry data in the northwest of Russia.

Acta Oncol 2021 Oct 23;60(10):1264-1271. Epub 2021 Aug 23.

Cancer Surveillance Branch, International Agency for Research on Cancer, Lyon, France.

Background: Despite the elaborate history of statistical reporting in the USSR, Russia established modern population-based cancer registries (PBCR) only in the 1990s. The quality of PBCRs data has not been thoroughly analyzed. This study aims at assessing the comparability and validity of cancer statistics in regions of the Northwestern Federal District (NWFD) of Russia.

Material And Methods: Data from ten Russian regional PBCRs covering ∼13 million (∼5 million in St. Petersburg) were processed in line with IARC/IACR and ENCR recommendations. We extracted and analyzed all registered cases but focused on cases diagnosed between 2008 and 2017. For comparability and validity assessment, we applied established qualitative and quantitative methods.

Results: Data collection in NWFD is in line with international standards. Distributions of diagnosis dates revealed higher variation in several regions, but overall, distributions are relatively uniform. The proportion of multiple primaries between 2008 and 2017 ranged from 6.7% in Vologda Oblast to 12.4% in Saint-Petersburg. We observed substantial regional heterogeneity for most indicators of validity. In 2013-2017, proportions of morphologically verified cases ranged between 61.7 and 89%. Death certificates only (DCO) cases proportion was in the range of 1-14% for all regions, except for Saint-Petersburg (up to 23%). The proportion of cases with a primary site unknown was between 1 and 3%. Certain cancer types (e.g., pancreas, liver, hematological malignancies, and CNS tumors) and cancers in older age groups showed lower validity.

Conclusion: While the overall level of comparability and validity of PBCRs data of four out of ten regions of NWFD of Russia meets the international standards, differences between the regions are substantial. The local instructions for cancer registration need to be updated and implemented. The data validity assessment also reflects pitfalls in the quality of diagnosis of certain cancer types and patient groups.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1080/0284186X.2021.1967443DOI Listing
October 2021

Seroprevalence of SARS-CoV-2 antibodies in Saint Petersburg, Russia: a population-based study.

Sci Rep 2021 06 21;11(1):12930. Epub 2021 Jun 21.

Institute for Interdisciplinary Health Research, European University at St. Petersburg, Shpalernaya Ulitsa, 1, St. Petersburg, Russia, 191187.

Properly conducted serological survey can help determine infection disease true spread. This study aims to estimate the seroprevalence of SARS-CoV-2 antibodies in Saint Petersburg, Russia accounting for non-response bias. A sample of adults was recruited with random digit dialling, interviewed and invited for anti-SARS-CoV-2 antibodies. The seroprevalence was corrected with the aid of the bivariate probit model that jointly estimated individual propensity to agree to participate in the survey and seropositivity. 66,250 individuals were contacted, 6,440 adults agreed to be interviewed and blood samples were obtained from 1,038 participants between May 27 and June 26, 2020. Naïve seroprevalence corrected for test characteristics was 9.0% (7.2-10.8) by CMIA and 10.5% (8.6-12.4) by ELISA. Correction for non-response decreased estimates to 7.4% (5.7-9.2) and 9.1% (7.2-10.9) for CMIA and ELISA, respectively. The most pronounced decrease in bias-corrected seroprevalence was attributed to the history of any illnesses in the past 3 months and COVID-19 testing. Seroconversion was negatively associated with smoking status, self-reported history of allergies and changes in hand-washing habits. These results suggest that even low estimates of seroprevalence can be an overestimation. Serosurvey design should attempt to identify characteristics that are associated both with participation and seropositivity.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41598-021-92206-yDOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8217236PMC
June 2021

History and current status of cancer registration in Russia.

Cancer Epidemiol 2021 08 2;73:101963. Epub 2021 Jun 2.

Cancer Surveillance Branch, International Agency for Research on Cancer, Lyon, France.

Background: Russia, then part of the Union of Soviet Socialist Republics (the USSR), introduced compulsory cancer registration in 1953, but a clear overall contemporary description of the cancer surveillance system in Russia is not available.

Methods: We summarized historical landmarks and the development of the standards of classification and coding of neoplasms in Russia and described current population-based cancer registries' (PBCR) procedures and practices.

Results: Cancer registration is organized according to the administrative division of the Russian Federation. More than 600,000 cases are registered annually. All medical facilities, without exception, are required to notify the PBCR about newly diagnosed cases, and each regional PBCR is responsible for registering all cancers diagnosed in citizens residing in the region. The data collection can be described as passive and exhaustive. Hematological malignancies, brain, and CNS tumors are often not referred to cancer hospitals in some regions, explaining the problems in registering these cancers.

Conclusion: Russia's cancer registration system is population-based, and practices seem to be generally internationally comparable. However, coding practices and national guidelines are still outdated and not up to the most recent international recommendations. Further analyses are needed to assess the comparability, validity, completeness, and timeliness of Russia's PBCRs data.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.canep.2021.101963DOI Listing
August 2021

Evaluation of the performance of SARS--CoV--2 antibody assays for a longitudinal population-based study of COVID--19 spread in St. Petersburg, Russia.

J Med Virol 2021 Oct 12;93(10):5846-5852. Epub 2021 Jun 12.

Department of Etiology and Epidemiology, Smorodintsev Research Institute of Influenza, Saint Petersburg, Russia.

Geographical variation in severe acute respiratory syndrome coronavirus 2 (SARS--CoV--2) spread requires seroprevalence studies based on local tests, but robust validation is needed. We summarize an evaluation of antibody tests used in a serological study of SARS--CoV--2 in Saint Petersburg, Russia. We validated three different antibody assays: chemiluminescent microparticle immunoassay (CMIA) Abbott Architect SARS--CoV--2 immunoglobulin G (IgG), enzyme- linked immunosorbent assay (ELISA) CoronaPass total antibodies test, and ELISA SARS--CoV--2--IgG--EIA--BEST. Clinical sensitivity was estimated with the SARS--CoV--2 polymerase chain reaction (PCR) test as the gold standard using manufacturer recommended cutoff. Specificity was estimated using pre-pandemic sera samples. The median time between positive PCR test results and antibody tests was 21 weeks. Measures of concordance were calculated against the microneutralization test (MNA).Sensitivity was equal to 91.1% (95% confidence intervbal [CI]: 78.8-97.5), 90% (95% CI: 76.4-96.4), and 63.1% (95% CI [50.2-74.7]) for ELISA Coronapass, ELISA Vector-Best, and CMIA Abbott, respectively. Specificity was equal to 100% for all the tests. Comparison of receiver operating characteristics has shown lower AUC for CMIA Abbott. The cut-off SC/O ratio of 0.28 for CMIA Abbott resulted in a sensitivity of 80% at the same level of specificity. Less than 33% of the participants with positive antibody test results had neutralizing antibodies in titers 1:80 and above. Antibody assays results and MNA correlated moderately. This study encourages the use of local antibody tests and sets the reference for seroprevalence correction. Available tests' sensitivity allows detecting antibodies within the majority of PCR- positive individuals. The Abbott assay sensitivity can be improved by incorporating a new cut-off. Manufacturers' test characteristics may introduce bias into the study results.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1002/jmv.27126DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8242745PMC
October 2021

Stomach Cancer Incidence and Mortality Trends among Circumpolar Nations.

Cancer Epidemiol Biomarkers Prev 2021 05 24;30(5):845-856. Epub 2021 Feb 24.

Cancer Control Research, BC Cancer, British Columbia, Canada.

Background: Stomach cancer incidence and mortality rates are declining across circumpolar nations, but the burden may not be distributed equally across subpopulations, including Indigenous peoples. Our objective was to examine stomach cancer incidence and mortality trends across circumpolar populations.

Methods: Cancer incidence and mortality data from 1999-2016 were obtained from the Canadian Cancer Registry, Canadian Vital Statistics, CDC WONDER, NORDCAN, Northwestern Russian cancer registries, and National Cancer Reports. The direct method was used to calculate 10-year rolling age-standardized incidence and mortality rates to the world (WHO 2000-2025) and 2011 Canadian standard populations. Standardized incidence rate ratios (SRR) were calculated. Data were stratified by sex, year, and region. U.S. data were broken down by race [White; American Indian/Alaska Native (AIAN)]. Race data were not available from non-U.S. cancer registries.

Results: Most populations showed declining incidence and mortality rates over time. Incidence rates among Greenland males and females, Alaska AIAN males and females, and Northern Canadian both sexes were elevated compared with regional counterparts and remained stable. The largest male SRR was observed among Alaska AIAN versus Alaska Whites [SRR = 3.82; 95% confidence interval (95% CI), 2.71-5.37]. The largest female SRR was observed among Alaska AIAN versus Alaska Whites (SRR = 4.10; 95% CI, 2.62-6.43).

Conclusions: Despite stomach cancer incidence and mortality rates declining overall, some northern and Indigenous populations experience elevated and stable incidence and mortality rates.

Impact: There is a need to address disparities observed among circumpolar subpopulations. Given similarities in incidence, mortality, and risk factor prevalence across circumpolar regions, addressing disparities could benefit from coordinated international action.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1158/1055-9965.EPI-20-1618DOI Listing
May 2021

Comparison of breast cancer and cervical cancer stage distributions in ten newly independent states of the former Soviet Union: a population-based study.

Lancet Oncol 2021 03 5;22(3):361-369. Epub 2021 Feb 5.

Cancer Surveillance Branch, International Agency for Research on Cancer, Lyon, France. Electronic address:

Background: Screening for breast cancer and cervical cancer in the newly independent states of the former Soviet Union is largely opportunistic, and countries in the region have among the highest cervical cancer incidence in the WHO European Region. We aimed to compare the stage-specific distributions and changes over time in breast cancer and cervical cancer incidence in the newly independent states of the former Soviet Union.

Methods: We collected breast cancer and cervical cancer incidence data from official statistics from Armenia, Azerbaijan, Belarus, Georgia, Kazakhstan, Kyrgyzstan, Republic of Moldova, Russian Federation, Ukraine, and Uzbekistan for the years 2008-17 by tumour, node, metastasis (TNM) stage, and by age where population-based cancer registry data were available. We used log-linear regression to quantify the changes over time in age-standardised rates.

Findings: During the period 2013-17, more than 50% of breast cancer cases across the analysed countries, and more than 75% of breast cancer cases in Belarus, Kazakhstan, and Ukraine, were registered at stages I-II. The proportion of stage I breast cancer cases was highest in the screening age group (50-69 years) compared with other ages in Moldova and the Russian registries, but was highest in those aged 15-49 years in Georgia and Ukraine. Breast cancer stage-specific incidence rates increased over time, most prominently for stage I cancers. For cervical cancer, the proportions of cancers diagnosed at a late stage (stages III and IV) were high, particularly in Moldova and Armenia (>50%). The proportion of stage I cervical cancer cases decreased with age in all countries, whereas the proportions of late stage cancers increased with age. Stage-specific incidence rates of cervical cancer generally increased over the period 2008-17.

Interpretation: Our results suggest modest progress in early detection of breast cancer in the newly independent states of the former Soviet Union. The high proportions of early-stage disease in the absence of mammography screening (eg, in Belarus) provide a benchmark for what is achievable with rapid diagnosis. For cervical cancer, there is a need to tackle the high burden and unfavourable stage-specific changes over time in the region. A radical shift in national policies away from opportunistic screening toward organised, population-based, quality-assured human papillomavirus vaccination and screening programmes is urgently needed.

Funding: Union for International Cancer Control, WHO Regional Office for Europe, and Ministry of Health of Ukraine.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/S1470-2045(20)30674-4DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8014987PMC
March 2021

A pragmatic approach to tackle the rising burden of breast cancer through prevention & early detection in countries 'in transition'.

Indian J Med Res 2020 10;152(4):343-355

Faculty of Social Sciences/Health Sciences, Tampere University, Tampere, Finland; N.N. Petrov National Research Medical Center of Oncology, Saint Petersburg, Russia.

Among the emerging economies Brazil, Russia, India, China and South Africa (together known as the BRICS countries) share collectively approximately 40 per cent of the global population and contribute to 25 per cent of the world gross domestic products. All these countries are facing the formidable challenge of rising incidence of breast cancer and significant number of premature deaths from the disease. A multidimensional approach involving prevention, early detection and improved treatment is required to counteract the growing burden of breast cancer. A growing trend in the prevalence of major preventable risk factors of breast cancer such as obesity, western dietary habits, lack of physical activity, consumption of alcohol and smoking is contributing significantly to the rising burden of the disease in BRICS nations. Specific interventions are needed at the individual and population levels to mitigate these risk factors, preferably within the broader framework of non-communicable disease control programme. Population-based quality assured mammography-based screening of the 50-69 yr old women can reduce breast cancer mortality at least by 20 per cent. However, none of the BRICS countries have been able to implement population-based organized screening programme. Large scale opportunistic screening with mammography targeting predominantly the younger women is causing harms to the women and wasting precious healthcare resources. There are recent national recommendations to screen women with mammography in Brazil and Russia and with clinical breast examination in China (along with ultrasound) and India. Given the challenges of implementing systematic screening of the population, the BRICS countries should prioritize the early diagnosis approach and invest in educating the women about the breast cancer symptoms, training the frontline health providers to clinically detect breast cancers and appropriately refer for diagnostic confirmation, and creating improved access to good quality diagnostic and treatment facilities for breast cancer. The early diagnosis approach has been proved to achieve downstaging and improve survival at a fraction of the resources needed for population screening. The countries also need to focus on improving the services and capacity for multidisciplinary treatment of breast cancer, histopathology and immunohistochemistry, safe administration of chemotherapy and palliative care.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.4103/ijmr.IJMR_1868_19DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8061594PMC
October 2020

Prostate cancer incidence and mortality in the Baltic states, Belarus, the Russian Federation and Ukraine.

BMJ Open 2019 10 9;9(10):e031856. Epub 2019 Oct 9.

Laboratory of Cancer Epidemiology, Nacionalinis vėžio institutas, Vilnius, Lithuania.

Background: Prostate cancer incidence varies internationally largely attributable to differences in prostate-specific antigen (PSA) use. The aim of this study was to provide the most recent detailed international epidemiological comparison of prostate cancer incidence and mortality in six north-eastern European countries (Belarus, Estonia, Latvia, Lithuania, the Russian Federation and Ukraine).

Methods: The number of incident prostate cancer cases was obtained from the countries national cancer registries. Prostate cancer mortality and corresponding population data were extracted from the WHO Mortality Database. Age-specific and age-standardised incidence and mortality rates were calculated (European Standard). The joinpoint regression model was used to provide an average annual percentage change and to detect points in time where significant changes in trends occurred. The observation period was between 13 (Ukraine) and 48 (Estonia) years regarding incidence and around 30 years regarding mortality.

Results: The comparison of prostate cancer incidence in six European countries showed almost sixfold differences in the age-adjusted rates in most recent years with highest incidence rates in Lithuania and Estonia. Through the observation period, overall a continuous rise was seen in incidence in all countries and a continuous rise in mortality, with a stabilisation in Estonia and a decrease in Lithuania in recent years. Data limitations included a descriptive design using ecological data.

Conclusions: A widespread use of PSA testing seems to be responsible for the changes in the epidemiology of the disease in north-eastern European countries. Substantial variation in the incidence of prostate cancer in the Baltic states suggests the possibility that PSA performance and utilisation spread have had a major influence on observed incidence trends, with a lack of effect on prostate cancer mortality.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1136/bmjopen-2019-031856DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6797259PMC
October 2019

Online breath analysis using metal oxide semiconductor sensors (electronic nose) for diagnosis of lung cancer.

J Breath Res 2019 10 23;14(1):016004. Epub 2019 Oct 23.

St Petersburg State University, Universitetskaya nab.7/9, 199034, St Petersburg, Russia.

The analysis of exhaled breath is drawing a high degree of interest in the diagnostics of various diseases, including lung cancer. Electronic nose (E-nose) technology is one of the perspective approaches in the field due to its relative simplicity and cost efficiency. The use of an E-nose together with pattern recognition algorithms allow 'breath-prints' to be discriminated. The aim of this study was to develop an efficient online E-nose-based lung cancer diagnostic method via exhaled breath analysis with the use of some statistical classification methods. A developed multisensory system consisting of six metal oxide chemoresistance gas sensors was employed in three temperature regimes. This study involved 118 individuals: 65 in the lung cancer group (cytologically verified) and 53 in the healthy control group. The exhaled breath samples of the volunteers were analysed using the developed E-nose system. The dataset obtained, consisting of the sensor responses, was pre-processed and split into training (70%) and test (30%) subsets. The training data was used to fit the classification models; the test data was used for the estimation of prediction possibility. Logistic regression was found to be an adequate data-processing approach. The performance of the developed method was promising for the screening purposes (sensitivity-95.0%, specificity-100.0%, accuracy-97.2%). This shows the applicability of the gas-sensitive sensor array for the exhaled breath diagnostics. Metal oxide sensors are highly sensitive, low-cost and stable, and their poor sensitivity can be enhanced by integrating them with machine learning algorithms, as can be seen in this study. All experiments were carried out with the permission of the N.N. Petrov Research Institute of Oncology ethics committee no. 15/83 dated March 15, 2017.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1088/1752-7163/ab433dDOI Listing
October 2019

Productivity losses associated with premature mortality due to cancer in Russia: A population-wide study covering 2001-2030.

Scand J Public Health 2019 Jul;47(5):482-491

6 Section of Cancer Surveillance, International Agency for Research on Cancer, France.

Productivity losses related to premature cancer mortality have been assessed for most developed countries but results for Russia are limited to cross-sectional reports. The aim of this study was to quantify productivity costs due to cancer mortality in Russia between 2001 and 2015 and project this to 2030. : Cancer mortality data (2001-2015) were acquired from the State Cancer Registry, whereas population data, labour force participation rates and annual earnings were retrieved from the Federal State Statistics Service. Cancer mortality was projected to 2030 and the human capital approach was applied to estimate productivity losses. : The total annual losses increased from US6.5b in 2001-2005 to US$8.1b in 2011-2015, corresponding to 0.24% of the annual gross domestic product. The value is expected to remain high in 2030 (US$7.5b, 0.14% of gross domestic product). Productivity losses per cancer death are predicted to grow faster in women (from US$18,622 to US$22,386) than in men (from US$25,064 to US$28,459). Total losses were found to be highest for breast cancer in women (US$0.6b, 20% of overall losses in women) and lung cancer in men (US$1.2b, 24%). The absolute predicted change of annual losses between 2011-2015 and 2026-2030 was greatest for cervix uteri (+US$214m) in women and for lip, oral and pharyngeal cancers in men (+US$182m).
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1177/1403494819845565DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6651608PMC
July 2019

Breast and cervical cancer incidence and mortality trends in Russia 1980-2013.

Cancer Epidemiol 2018 08 26;55:73-80. Epub 2018 May 26.

University of Tampere, Faculty of Social Sciences, Epidemiology Group, Arvo, Arvo Ylpön katu 34, 33520 Tampere, Finland. Electronic address:

Background: Breast and cervical cancer are among the leading causes of preventable cancer deaths in women in Russia. The aim of this study is to analyze changes in breast and cervical cancer incidence and mortality trends using data from the Russian State Cancer Registry.

Methods: The age-standardized rates of cervical cancer incidence (1993-2013) and mortality (1980-2013) were analyzed using piecewise linear regression. Age-period-cohort models were used to estimate the temporal effects and provide future predictions.

Results: Breast and cervical cancer incidence rates uniformly increased over two decades from 33.0 to 47.0 per 100,000 and from 10.6 to 14.2 per 100,000, respectively. Breast cancer mortality rates however declined from 17.6 to 15.7 in 2013, while cervical cancer mortality increased steadily from 5.6 to 6.7. Breakpoints in the risk occurred in cohorts born 1937-1953, indicating a recent generational decrease in breast cancer mortality, but a concomitant increase in cervical cancer. Cervical cancer has already surpassed breast cancer in terms of years of life lost (YLL) (23.4 per death vs 18.5 in 2009-2013), while future projections suggest that the annual YLL could reach 1.2 million for cervical cancer and (decline to) 1.8 million for breast cancer by the year 2030.

Conclusion: The temporal patterns of breast cancer incidence and mortality in Russia are in line with other countries in Europe, although cervical cancer rates and the risk of occurrence in recent generations is rapidly increasing; these trends underscore the need to place immediate priority in national cervical vaccination and screening programs.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.canep.2018.05.008DOI Listing
August 2018

Alternative Ways to Study Global Variation in Cancer-Related Research Activity.

Ann Surg Oncol 2018 11 19;25(12):3774-3775. Epub 2018 Mar 19.

Institute for Cancer Care at Mercy, Baltimore, USA.

View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1245/s10434-018-6426-5DOI Listing
November 2018

Productivity losses due to premature mortality from cancer in Brazil, Russia, India, China, and South Africa (BRICS): A population-based comparison.

Cancer Epidemiol 2018 04 30;53:27-34. Epub 2018 Jan 30.

International Agency for Research on Cancer, 150 Cours Albert Thomas, 69008, Lyon, France.

Background: Over two-thirds of the world's cancer deaths occur in economically developing countries; however, the societal costs of cancer have rarely been assessed in these settings. Our aim was to estimate the value of productivity lost in 2012 due to cancer-related premature mortality in the major developing economies of Brazil, the Russian Federation, India, China and South Africa (BRICS).

Methods: We applied an incidence-based method using the human capital approach. We used annual adult cancer deaths from GLOBOCAN2012 to estimate the years of productive life lost between cancer death and pensionable age in each country, valued using national and international data for wages, and workforce statistics. Sensitivity analyses examined various methodological assumptions.

Results: The total cost of lost productivity due to premature cancer mortality in the BRICS countries in 2012 was $46·3 billion, representing 0·33% of their combined gross domestic product. The largest total productivity loss was in China ($28 billion), while South Africa had the highest cost per cancer death ($101,000). Total productivity losses were greatest for lung cancer in Brazil, the Russian Federation and South Africa; liver cancer in China; and lip and oral cavity cancers in India.

Conclusion: Locally-tailored strategies are required to reduce the economic burden of cancer in developing economies. Focussing on tobacco control, vaccination programs and cancer screening, combined with access to adequate treatment, could yield significant gains for both public health and economic performance of the BRICS countries.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.canep.2017.12.013DOI Listing
April 2018

MRI Image Processing Based on Fractal Analysis

Asian Pac J Cancer Prev 2017 01 1;18(1):51-55. Epub 2017 Jan 1.

ITMO University, Saint Petersburg, Russia. Email:

Background: Cancer is one of the most common causes of human mortality, with about 14 million new cases and 8.2 million deaths reported in in 2012. Early diagnosis of cancer through screening allows interventions to reduce mortality. Fractal analysis of medical images may be useful for this purpose. Materials and Methods: In this study, we examined magnetic resonance (MR) images of healthy livers and livers containing metastases from colorectal cancer. The fractal dimension and the Hurst exponent were chosen as diagnostic features for tomographic imaging using Image J software package for image processings FracLac for applied for fractal analysis with a 120x150 pixel area. Calculations of the fractal dimensions of pathological and healthy tissue samples were performed using the box-counting method. Results: In pathological cases (foci formation), the Hurst exponent was less than 0.5 (the region of unstable statistical characteristics). For healthy tissue, the Hurst index is greater than 0.5 (the zone of stable characteristics). Conclusions: The study indicated the possibility of employing fractal rapid analysis for the detection of focal lesions of the liver. The Hurst exponent can be used as an important diagnostic characteristic for analysis of medical images.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.22034/APJCP.2017.18.1.51DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5563119PMC
January 2017

Evaluation of Machine Learning Algorithm Utilization for Lung Cancer Classification Based on Gene Expression Levels.

Asian Pac J Cancer Prev 2016 ;17(2):835-8

ITMO University, Saint Petersburg, Russia E-mail :

Background: Lung cancer remains one of the most common cancers in the world, both in terms of new cases (about 13% of total per year) and deaths (nearly one cancer death in five), because of the high case fatality. Errors in lung cancer type or malignant growth determination lead to degraded treatment efficacy, because anticancer strategy depends on tumor morphology.

Materials And Methods: We have made an attempt to evaluate effectiveness of machine learning algorithms in the task of lung cancer classification based on gene expression levels. We processed four publicly available data sets. The Dana-Farber Cancer Institute data set contains 203 samples and the task was to classify four cancer types and sound tissue samples. With the University of Michigan data set of 96 samples, the task was to execute a binary classification of adenocarcinoma and non-neoplastic tissues. The University of Toronto data set contains 39 samples and the task was to detect recurrence, while with the Brigham and Women's Hospital data set of 181 samples it was to make a binary classification of malignant pleural mesothelioma and adenocarcinoma. We used the k-nearest neighbor algorithm (k=1, k=5, k=10), naive Bayes classifier with assumption of both a normal distribution of attributes and a distribution through histograms, support vector machine and C4.5 decision tree. Effectiveness of machine learning algorithms was evaluated with the Matthews correlation coefficient.

Results: The support vector machine method showed best results among data sets from the Dana-Farber Cancer Institute and Brigham and Women's Hospital. All algorithms with the exception of the C4.5 decision tree showed maximum potential effectiveness in the University of Michigan data set. However, the C4.5 decision tree showed best results for the University of Toronto data set.

Conclusions: Machine learning algorithms can be used for lung cancer morphology classification and similar tasks based on gene expression level evaluation.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.7314/apjcp.2016.17.2.835DOI Listing
January 2017
-->