2020
|
Szwierz, Jacek; Matczak, Piotr; Dąbrowski, Adam; Wójtowicz, Andrzej Video monitoring and the level of losses caused by crime. The case studies from selected Polish cities Journal Article Studia z Polityki Publicznej, 25 (1), pp. 51-69, 2020. Abstract | Links | BibTeX @article{szwierz2020monitoring,
title = {Video monitoring and the level of losses caused by crime. The case studies from selected Polish cities},
author = {Jacek Szwierz and Piotr Matczak and Adam Dąbrowski and Andrzej Wójtowicz},
doi = {10.33119/kszpp/2020.1.3},
year = {2020},
date = {2020-05-06},
journal = {Studia z Polityki Publicznej},
volume = {25},
number = {1},
pages = {51-69},
publisher = {Warsaw School of Economics},
abstract = {In Poland, similarly to other countries, there is no unambiguous agreed explanation to the reasons for the observed decline in crime. The article analyses the impact of video monitoring systems on losses caused by three categories of offenses: (a) car theft, theft with burglary, theft from cars; (b) damage to cars; (c) robbery. To answer the question whether the installation of video surveillance systems has an impact on security, the economic effect of installing cameras in eight Polish cities (Gdańsk, Katowice, Kielce, Lublin, Łódź, Poznań, Warszawa, Wrocław), where video surveillance systems are well developed, is examined. Determining whether the installation of cameras contributes to the reduction of losses caused by crime allows assessing the suitability of cameras for improving public safety.
The study partially confirms the effectiveness of video monitoring systems for a decrease in crime in the analysed categories of crime. However, other possible factors, in addition to the development of monitoring, may have an impact. Moreover, the impact is less pronounced in the case of the volume of losses caused by crime than the number of crimes. Thus, when assessing public policies regarding security, the number of offenses criterion is insufficient.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In Poland, similarly to other countries, there is no unambiguous agreed explanation to the reasons for the observed decline in crime. The article analyses the impact of video monitoring systems on losses caused by three categories of offenses: (a) car theft, theft with burglary, theft from cars; (b) damage to cars; (c) robbery. To answer the question whether the installation of video surveillance systems has an impact on security, the economic effect of installing cameras in eight Polish cities (Gdańsk, Katowice, Kielce, Lublin, Łódź, Poznań, Warszawa, Wrocław), where video surveillance systems are well developed, is examined. Determining whether the installation of cameras contributes to the reduction of losses caused by crime allows assessing the suitability of cameras for improving public safety.
The study partially confirms the effectiveness of video monitoring systems for a decrease in crime in the analysed categories of crime. However, other possible factors, in addition to the development of monitoring, may have an impact. Moreover, the impact is less pronounced in the case of the volume of losses caused by crime than the number of crimes. Thus, when assessing public policies regarding security, the number of offenses criterion is insufficient. |
Szubert, Sebastian; Szpurek, Dariusz; Wójtowicz, Andrzej; Żywica, Patryk; Stukan, Maciej; Sajdak, Stefan; Jabłoński, Sławomir; Wicherek, Łukasz; Moszyński, Rafał Performance of Selected Models for Predicting Malignancy in Ovarian Tumors in Relation to the Degree of Diagnostic Uncertainty by Subjective Assessment With Ultrasound Journal Article Journal of Ultrasound in Medicine, 5 (39), pp. 939-947, 2020, ISSN: 0278-4297. Abstract | Links | BibTeX @article{szubert2019performance,
title = {Performance of Selected Models for Predicting Malignancy in Ovarian Tumors in Relation to the Degree of Diagnostic Uncertainty by Subjective Assessment With Ultrasound},
author = {Sebastian Szubert and Dariusz Szpurek and Andrzej Wójtowicz and Patryk Żywica and Maciej Stukan and Stefan Sajdak and Sławomir Jabłoński and Łukasz Wicherek and Rafał Moszyński},
doi = {10.1002/jum.15178},
issn = {0278-4297},
year = {2020},
date = {2020-04-19},
journal = {Journal of Ultrasound in Medicine},
volume = {5},
number = {39},
pages = {939-947},
publisher = {John Wiley & Sons, Inc. Hoboken, USA},
abstract = {Objectives
The study's main aim was to evaluate the relationship between the performance of predictive models for differential diagnoses of ovarian tumors and levels of diagnostic confidence in subjective assessment (SA) with ultrasound. The second aim was to identify the parameters that differentiate between malignant and benign tumors among tumors initially diagnosed as uncertain by SA.
Methods
The study included 250 (55%) benign ovarian masses and 201 (45%) malignant tumors. According to ultrasound findings, the tumors were divided into 6 groups: certainly benign, probably benign, uncertain but benign, uncertain but malignant, probably malignant, and certainly malignant. The performance of the risk of malignancy index, International Ovarian Tumor Analysis assessment of different neoplasias in the adnexa model, and International Ovarian Tumor Analysis logistic regression model 2 was analyzed in subgroups as follows: SA‐certain tumors (including certainly benign and certainly malignant) versus SA‐probable tumors (probably benign and probably malignant) versus SA‐uncertain tumors (uncertain but benign and uncertain but malignant).
Results
We found a progressive decrease in the performance of all models in association with the increased uncertainty in SA. The areas under the receiver operating characteristic curve for the risk of malignancy index, logistic regression model 2, and assessment of different neoplasias in the adnexa model decreased between the SA‐certain and SA‐uncertain groups by 20%, 28%, and 20%, respectively. The presence of solid parts and a high color score were the discriminatory features between uncertain but benign and uncertain but malignant tumors.
Conclusions
Studies are needed that focus on the subgroup of ovarian tumors that are difficult to classify by SA. In cases of uncertain tumors by SA, the presence of solid components or a high color score should prompt a gynecologic oncology clinic referral.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Objectives
The study's main aim was to evaluate the relationship between the performance of predictive models for differential diagnoses of ovarian tumors and levels of diagnostic confidence in subjective assessment (SA) with ultrasound. The second aim was to identify the parameters that differentiate between malignant and benign tumors among tumors initially diagnosed as uncertain by SA.
Methods
The study included 250 (55%) benign ovarian masses and 201 (45%) malignant tumors. According to ultrasound findings, the tumors were divided into 6 groups: certainly benign, probably benign, uncertain but benign, uncertain but malignant, probably malignant, and certainly malignant. The performance of the risk of malignancy index, International Ovarian Tumor Analysis assessment of different neoplasias in the adnexa model, and International Ovarian Tumor Analysis logistic regression model 2 was analyzed in subgroups as follows: SA‐certain tumors (including certainly benign and certainly malignant) versus SA‐probable tumors (probably benign and probably malignant) versus SA‐uncertain tumors (uncertain but benign and uncertain but malignant).
Results
We found a progressive decrease in the performance of all models in association with the increased uncertainty in SA. The areas under the receiver operating characteristic curve for the risk of malignancy index, logistic regression model 2, and assessment of different neoplasias in the adnexa model decreased between the SA‐certain and SA‐uncertain groups by 20%, 28%, and 20%, respectively. The presence of solid parts and a high color score were the discriminatory features between uncertain but benign and uncertain but malignant tumors.
Conclusions
Studies are needed that focus on the subgroup of ovarian tumors that are difficult to classify by SA. In cases of uncertain tumors by SA, the presence of solid components or a high color score should prompt a gynecologic oncology clinic referral. |
2018
|
Dąbrowski, Adam; Matczak, Piotr; Wójtowicz, Andrzej; Leitner, Michael Identification of Experimental and Control Areas for CCTV Effectiveness Assessment—The Issue of Spatially Aggregated Data Journal Article ISPRS International Journal of Geo-Information, 7 (471), pp. 1-12, 2018, ISSN: 2220-9964. Abstract | Links | BibTeX @article{dabrowski2018identification,
title = {Identification of Experimental and Control Areas for CCTV Effectiveness Assessment—The Issue of Spatially Aggregated Data},
author = {Adam Dąbrowski and Piotr Matczak and Andrzej Wójtowicz and Michael Leitner},
doi = {10.3390/ijgi7120471},
issn = {2220-9964},
year = {2018},
date = {2018-12-01},
journal = {ISPRS International Journal of Geo-Information},
volume = {7},
number = {471},
pages = {1-12},
publisher = {MDPI AG},
abstract = {Progress in surveillance technology has led to the development of Closed-Circuit Television (CCTV) systems in cities around the world. Cameras are considered instrumental in crime reduction, yet existing research does not unambiguously answer the question whether installing them affects the number of crimes committed. The quasi-experimental method usually applied to evaluate CCTV systems’ effectiveness faces difficulties with data quantity and quality. Data quantity has a bearing on the number of crimes that can be conclusively inferred using the experimental procedure. Data quality affects the level of crime data aggregation. The lack of the exact location of a crime incident in the form of a street address or geographic coordinates hinders the selection procedure of experimental and control areas. In this paper we propose an innovative method of dealing with data limitations in a quasi-experimental study on the effectiveness of CCTV systems in Poland. As police data on crime incidents are geocoded onto a neighborhood or a street, we designed a method to overcome this drawback by applying similarity measures to time series and landscape metrics. The method makes it possible to determine experimental (test) and control areas which are necessary to conduct the study.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Progress in surveillance technology has led to the development of Closed-Circuit Television (CCTV) systems in cities around the world. Cameras are considered instrumental in crime reduction, yet existing research does not unambiguously answer the question whether installing them affects the number of crimes committed. The quasi-experimental method usually applied to evaluate CCTV systems’ effectiveness faces difficulties with data quantity and quality. Data quantity has a bearing on the number of crimes that can be conclusively inferred using the experimental procedure. Data quality affects the level of crime data aggregation. The lack of the exact location of a crime incident in the form of a street address or geographic coordinates hinders the selection procedure of experimental and control areas. In this paper we propose an innovative method of dealing with data limitations in a quasi-experimental study on the effectiveness of CCTV systems in Poland. As police data on crime incidents are geocoded onto a neighborhood or a street, we designed a method to overcome this drawback by applying similarity measures to time series and landscape metrics. The method makes it possible to determine experimental (test) and control areas which are necessary to conduct the study. |
Dyczkowski, Krzysztof; Stachowiak, Anna; Wójtowicz, Andrzej; Żywica, Patryk An uncertainty aware medical diagnosis support system Inproceedings Medina, Jesús ; Ojeda-Aciego, Manuel ; Verdegay, José Luis ; Perfilieva, Irina ; Bouchon-Meunier, Bernadette ; Yager, Ronald R (Ed.): Information Processing and Management of Uncertainty in Knowledge-Based Systems. Applications. IPMU 2018, pp. 381-390, Springer, Cham, 2018, ISBN: 978-3-319-91478-7. Abstract | Links | BibTeX @inproceedings{dyczkowski2018uncertainty,
title = {An uncertainty aware medical diagnosis support system},
author = {Krzysztof Dyczkowski and Anna Stachowiak and Andrzej Wójtowicz and Patryk Żywica},
editor = {Medina, Jesús and Ojeda-Aciego, Manuel and Verdegay, José Luis and Perfilieva, Irina and Bouchon-Meunier, Bernadette and Yager, Ronald R.},
url = {https://ai.wmi.amu.edu.pl/wp-content/uploads/2020/01/ipmu-2018-unc-aware.pdf},
doi = {10.1007/978-3-319-91479-4_32},
isbn = {978-3-319-91478-7},
year = {2018},
date = {2018-01-01},
booktitle = {Information Processing and Management of Uncertainty in Knowledge-Based Systems. Applications. IPMU 2018},
volume = {855},
pages = {381-390},
publisher = {Springer, Cham},
series = {Communications in Computer and Information Science},
abstract = {In the paper we describe a computer system that store and process uncertain data in such a way as to be able to obtain information essential to make an effective diagnosis while also indicating the uncertainty level of that diagnosis. We consider the problem of incompleteness and imprecision of medical data and discuss some issues connected with such kind of information - like modeling, making decision that is aware of the imperfection of data, evaluating results in the context of uncertain medical data. As an example we describe a method of supporting medical decision implemented in the OvaExpert system that is based on interval-valued fuzzy sets cardinality.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In the paper we describe a computer system that store and process uncertain data in such a way as to be able to obtain information essential to make an effective diagnosis while also indicating the uncertainty level of that diagnosis. We consider the problem of incompleteness and imprecision of medical data and discuss some issues connected with such kind of information - like modeling, making decision that is aware of the imperfection of data, evaluating results in the context of uncertain medical data. As an example we describe a method of supporting medical decision implemented in the OvaExpert system that is based on interval-valued fuzzy sets cardinality. |
2016
|
Żywica, Patryk; Dyczkowski, Krzysztof; Wójtowicz, Andrzej; Stachowiak, Anna; Szubert, Sebastian; Moszyński, Rafał Development of a fuzzy-driven system for ovarian tumor diagnosis Journal Article Biocybernetics and Biomedical Engineering, 36 (4), pp. 632–643, 2016, ISSN: 0208-5216. Abstract | Links | BibTeX @article{zywica2016development,
title = {Development of a fuzzy-driven system for ovarian tumor diagnosis},
author = {Patryk Żywica and Krzysztof Dyczkowski and Andrzej Wójtowicz and Anna Stachowiak and Sebastian Szubert and Rafał Moszyński},
url = {https://ai.wmi.amu.edu.pl/wp-content/uploads/2020/01/2016-bbe-development.pdf},
doi = {10.1016/j.bbe.2016.08.003},
issn = {0208-5216},
year = {2016},
date = {2016-01-01},
journal = {Biocybernetics and Biomedical Engineering},
volume = {36},
number = {4},
pages = {632--643},
publisher = {Elsevier},
abstract = {In this paper we present OvaExpert, an intelligent system for ovarian tumor diagnosis. We give an overview of its features and main design assumptions. As a theoretical framework the system uses fuzzy set theory and other soft computing techniques. This makes it possible to handle uncertainty and incompleteness of the data, which is a unique feature of the developed system. The main advantage of OvaExpert is its modular architecture which allows seamless extension of system capabilities. Three diagnostic modules are described, along with examples. The first module is based on aggregation of existing prognostic models for ovarian tumor. The second presents the novel concept of an Interval-Valued Fuzzy Classifier which is able to operate under data incompleteness and uncertainty. The third approach draws from cardinality theory of fuzzy sets and IVFSs and leads to a bipolar result that supports or rejects certain diagnoses.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In this paper we present OvaExpert, an intelligent system for ovarian tumor diagnosis. We give an overview of its features and main design assumptions. As a theoretical framework the system uses fuzzy set theory and other soft computing techniques. This makes it possible to handle uncertainty and incompleteness of the data, which is a unique feature of the developed system. The main advantage of OvaExpert is its modular architecture which allows seamless extension of system capabilities. Three diagnostic modules are described, along with examples. The first module is based on aggregation of existing prognostic models for ovarian tumor. The second presents the novel concept of an Interval-Valued Fuzzy Classifier which is able to operate under data incompleteness and uncertainty. The third approach draws from cardinality theory of fuzzy sets and IVFSs and leads to a bipolar result that supports or rejects certain diagnoses. |
Szubert, Sebastian; Wójtowicz, Andrzej; Żywica, Patryk Response to letter to the editor concerning validation of IOTA ADNEX model Journal Article Gynecologic Oncology Reports, 18 , pp. 51-52, 2016, ISSN: 2352-5789. Links | BibTeX @article{szubert2016response,
title = {Response to letter to the editor concerning validation of IOTA ADNEX model},
author = {Sebastian Szubert and Andrzej Wójtowicz and Patryk Żywica},
doi = {10.1016/j.gore.2016.10.009},
issn = {2352-5789},
year = {2016},
date = {2016-01-01},
journal = {Gynecologic Oncology Reports},
volume = {18},
pages = {51-52},
publisher = {Elsevier},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Wójtowicz, Andrzej; Żywica, Patryk; Stachowiak, Anna; Dyczkowski, Krzysztof Solving the problem of incomplete data in medical diagnosis via interval modeling Journal Article Applied Soft Computing, 47 , pp. 424-437, 2016, ISSN: 1568-4946. Abstract | Links | BibTeX @article{wojtowicz2016solving,
title = {Solving the problem of incomplete data in medical diagnosis via interval modeling},
author = {Andrzej Wójtowicz and Patryk Żywica and Anna Stachowiak and Krzysztof Dyczkowski},
url = {https://ai.wmi.amu.edu.pl/wp-content/uploads/2020/01/2015-asoc-solving.pdf
https://github.com/ovaexpert/ovarian-tumor-aggregation},
doi = {10.1016/j.asoc.2016.05.029},
issn = {1568-4946},
year = {2016},
date = {2016-01-01},
journal = {Applied Soft Computing},
volume = {47},
pages = {424-437},
publisher = {Elsevier},
abstract = {This paper presents an approach to making accurate and high-quality decisions under incomplete information. Our comprehensive approach includes interval modeling of incomplete data, uncertaintification of classical models and aggregation of incomplete results. We conducted a thorough evaluation of our approach using medical data for ovarian tumor diagnosis, where the problem of missing data is commonly encountered. The results confirmed that methods based on interval modeling and aggregation make it possible to reduce the negative impact of lack of data and lead to meaningful and accurate decisions. A diagnostic model developed in this way proved better than classical diagnostic models for ovarian tumor. Additionally, a framework in R that implements our method was created and is available for reproduction of our results. The proposed approach has been incorporated into a real-life diagnosis support system – OvaExpert.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
This paper presents an approach to making accurate and high-quality decisions under incomplete information. Our comprehensive approach includes interval modeling of incomplete data, uncertaintification of classical models and aggregation of incomplete results. We conducted a thorough evaluation of our approach using medical data for ovarian tumor diagnosis, where the problem of missing data is commonly encountered. The results confirmed that methods based on interval modeling and aggregation make it possible to reduce the negative impact of lack of data and lead to meaningful and accurate decisions. A diagnostic model developed in this way proved better than classical diagnostic models for ovarian tumor. Additionally, a framework in R that implements our method was created and is available for reproduction of our results. The proposed approach has been incorporated into a real-life diagnosis support system – OvaExpert. |
Szubert, Sebastian; Wójtowicz, Andrzej; Moszyński, Rafał; Żywica, Patryk; Dyczkowski, Krzysztof; Stachowiak, Anna; Sajdak, Stefan; Szpurek, Dariusz; Alcázar, Juan Luis External validation of the IOTA ADNEX model performed by two independent gynecologic centers Journal Article Gynecologic Oncology, 142 (3), pp. 490-495, 2016, ISSN: 0090-8258. Abstract | Links | BibTeX @article{szubert2016external,
title = {External validation of the IOTA ADNEX model performed by two independent gynecologic centers},
author = {Sebastian Szubert and Andrzej Wójtowicz and Rafał Moszyński and Patryk Żywica and Krzysztof Dyczkowski and Anna Stachowiak and Stefan Sajdak and Dariusz Szpurek and Juan Luis Alcázar},
doi = {10.1016/j.ygyno.2016.06.020},
issn = {0090-8258},
year = {2016},
date = {2016-01-01},
journal = {Gynecologic Oncology},
volume = {142},
number = {3},
pages = {490-495},
publisher = {Academic Press},
abstract = {OBJECTIVES:
The external, two-center validation of the IOTA ADNEX model for differential diagnosis of adnexal tumors.
METHODS:
A total of 204 patients with adnexal masses (134 benign and 70 malignant) treated at the Division of Gynecologic Surgery, Poznan University of Medical Sciences, Poland (Center I), and 123 patients (89 benign and 34 malignant) from the Department of Obstetrics and Gynecology, Clinica Universidad de Navarra, University of Navarra School of Medicine, Pamplona, Spain (Center II), were enrolled into the study.
RESULTS:
ADNEX achieved high accuracy in discriminating between malignant and benign ovarian tumors in both centers (79.9% and 81.3% in Centers I and II, respectively). Multiclass accuracy was substantially lower than in binary classification (malignant vs. benign): 64.2% and 74.0% in Centers I and II, respectively. Sensitivity and specificity for the diagnosis of specific tumor types in Center I were as follows: benign tumors - 72.4% and 94.3%; borderline tumors - 33.3% and 87.0%, stage I ovarian cancers - 00.0% and 91.8%; stage II-IV ovarian cancers - 68.2% and 83.1%; and metastatic tumors - 00.0% and 99.5%. Sensitivity and specificity in Center II were as follows: benign tumors - 75.3% and 97.1%; borderline tumors - 50.0% and 88.2%, stage I ovarian cancers - 40.0% and 97.5%; stage II-IV ovarian cancers - 95.0% and 88.3%; and metastatic tumors - 20.0% and 98.3%.
CONCLUSIONS:
ADNEX is characterized by very high accuracy in differentiating between malignant and benign adnexal tumors. However, prediction of ovarian tumor types could be more accurate.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
OBJECTIVES:
The external, two-center validation of the IOTA ADNEX model for differential diagnosis of adnexal tumors.
METHODS:
A total of 204 patients with adnexal masses (134 benign and 70 malignant) treated at the Division of Gynecologic Surgery, Poznan University of Medical Sciences, Poland (Center I), and 123 patients (89 benign and 34 malignant) from the Department of Obstetrics and Gynecology, Clinica Universidad de Navarra, University of Navarra School of Medicine, Pamplona, Spain (Center II), were enrolled into the study.
RESULTS:
ADNEX achieved high accuracy in discriminating between malignant and benign ovarian tumors in both centers (79.9% and 81.3% in Centers I and II, respectively). Multiclass accuracy was substantially lower than in binary classification (malignant vs. benign): 64.2% and 74.0% in Centers I and II, respectively. Sensitivity and specificity for the diagnosis of specific tumor types in Center I were as follows: benign tumors - 72.4% and 94.3%; borderline tumors - 33.3% and 87.0%, stage I ovarian cancers - 00.0% and 91.8%; stage II-IV ovarian cancers - 68.2% and 83.1%; and metastatic tumors - 00.0% and 99.5%. Sensitivity and specificity in Center II were as follows: benign tumors - 75.3% and 97.1%; borderline tumors - 50.0% and 88.2%, stage I ovarian cancers - 40.0% and 97.5%; stage II-IV ovarian cancers - 95.0% and 88.3%; and metastatic tumors - 20.0% and 98.3%.
CONCLUSIONS:
ADNEX is characterized by very high accuracy in differentiating between malignant and benign adnexal tumors. However, prediction of ovarian tumor types could be more accurate. |
Stachowiak, Anna; Dyczkowski, Krzysztof; Wójtowicz, Andrzej; Żywica, Patryk; Wygralak, Maciej A bipolar view on medical diagnosis in OvaExpert system Incollection Andreasen, Troels ; Christiansen, Henning ; Kacprzyk, Janusz ; Larsen, Henrik ; Pasi, Gabriella ; Pivert, Olivier ; De Tré, Guy ; Vila, Maria Amparo ; Yazici, Adnan ; Zadrożny, Sławomir (Ed.): Flexible Query Answering Systems 2015, 400 , pp. 483-492, Springer, Cham, 2016, ISBN: 978-3-319-26153-9. Abstract | Links | BibTeX @incollection{stachowiak2016bipolar,
title = {A bipolar view on medical diagnosis in OvaExpert system},
author = {Anna Stachowiak and Krzysztof Dyczkowski and Andrzej Wójtowicz and Patryk Żywica and Maciej Wygralak},
editor = {Andreasen, Troels and Christiansen, Henning and Kacprzyk, Janusz and Larsen, Henrik and Pasi, Gabriella and Pivert, Olivier and De Tré, Guy and Vila, Maria Amparo and Yazici, Adnan and Zadrożny, Sławomir},
url = {https://ai.wmi.amu.edu.pl/wp-content/uploads/2020/01/fqas-2016-bipolar.pdf},
doi = {10.1007/978-3-319-26154-6_37},
isbn = {978-3-319-26153-9},
year = {2016},
date = {2016-01-01},
booktitle = {Flexible Query Answering Systems 2015},
volume = {400},
pages = {483-492},
publisher = {Springer, Cham},
series = {Advances in Intelligent Systems and Computing},
abstract = {In the paper we present OvaExpert - a unique tool for supporting gynecologists in the diagnosis of ovarian tumor, combining classical diagnostic scales with modern methods of machine learning and soft computing. A distinguishing feature of the system is its comprehensiveness, which makes it usable at any stage of a diagnostic process. We gather all the results and solutions making up the system, some of which were described in our other publications, to provide an overall picture of OvaExpert and its capabilities. A special attention is paid to a property of supporting uncertainty modeling and processing, that is an essential part of the system.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
In the paper we present OvaExpert - a unique tool for supporting gynecologists in the diagnosis of ovarian tumor, combining classical diagnostic scales with modern methods of machine learning and soft computing. A distinguishing feature of the system is its comprehensiveness, which makes it usable at any stage of a diagnostic process. We gather all the results and solutions making up the system, some of which were described in our other publications, to provide an overall picture of OvaExpert and its capabilities. A special attention is paid to a property of supporting uncertainty modeling and processing, that is an essential part of the system. |
2015
|
Żywica, Patryk; Wójtowicz, Andrzej; Stachowiak, Anna; Dyczkowski, Krzysztof Improving medical decisions under incomplete data using interval-valued fuzzy aggregation Inproceedings Alonso, José M; Bustince, Humberto; Reformat, Marek (Ed.): 2015 Conference of the International Fuzzy Systems Association and the European Society for Fuzzy Logic and Technology (IFSA-EUSFLAT-15), pp. 577-584, Atlantis Press, 2015, ISBN: 978-94-62520-77-6. Abstract | Links | BibTeX @inproceedings{zywica2015improving,
title = {Improving medical decisions under incomplete data using interval-valued fuzzy aggregation},
author = {Patryk Żywica and Andrzej Wójtowicz and Anna Stachowiak and Krzysztof Dyczkowski},
editor = {José M. Alonso and Humberto Bustince and Marek Reformat},
url = {https://download.atlantis-press.com/article/23594.pdf},
doi = {10.2991/ifsa-eusflat-15.2015.83},
isbn = {978-94-62520-77-6},
year = {2015},
date = {2015-01-01},
booktitle = {2015 Conference of the International Fuzzy Systems Association and the European Society for Fuzzy Logic and Technology (IFSA-EUSFLAT-15)},
volume = {89},
pages = {577-584},
publisher = {Atlantis Press},
series = {Advances in Intelligent Systems Research},
abstract = {We state a problem concerning how to make an effective and proper decision in the presence of data incompleteness. As an example we consider a medical diagnostic system where the problem of missing data is commonly encountered. We propose and evaluate an approach that makes it possible to reduce the influence of missing data on the final result and to improve the quality of the decision. The process involves interval-valued fuzzy set modelling, uncertaintification of classical methods, and finally aggregation of the incomplete results. It was verified that the aggregation results in meaningful and accurate decisions despite the missing data.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
We state a problem concerning how to make an effective and proper decision in the presence of data incompleteness. As an example we consider a medical diagnostic system where the problem of missing data is commonly encountered. We propose and evaluate an approach that makes it possible to reduce the influence of missing data on the final result and to improve the quality of the decision. The process involves interval-valued fuzzy set modelling, uncertaintification of classical methods, and finally aggregation of the incomplete results. It was verified that the aggregation results in meaningful and accurate decisions despite the missing data. |
Dyczkowski, Krzysztof; Wójtowicz, Andrzej; Żywica, Patryk; Stachowiak, Anna; Moszyński, Rafał; Szubert, Sebastian An intelligent system for computer-aided ovarian tumor diagnosis Incollection Filev, Dimitar; Jabłkowski, Jan; Kacprzyk, Janusz; Krawczak, Maciej; Popchev, Ivan; Rutkowski, Leszek; Sgurev, Vassil; Sotirova, Evdokia; Szynkarczyk, Piotr; Zadrożny, Sławomir (Ed.): Intelligent Systems'2014, 323 , pp. 335-343, Springer, Cham, 2015, ISBN: 978-3-319-11309-8. Abstract | Links | BibTeX @incollection{dyczkowski2015intelligent,
title = {An intelligent system for computer-aided ovarian tumor diagnosis},
author = {Krzysztof Dyczkowski and Andrzej Wójtowicz and Patryk Żywica and Anna Stachowiak and Rafał Moszyński and Sebastian Szubert},
editor = {Dimitar Filev and Jan Jabłkowski and Janusz Kacprzyk and Maciej Krawczak and Ivan Popchev and Leszek Rutkowski and Vassil Sgurev and Evdokia Sotirova and Piotr Szynkarczyk and Sławomir Zadrożny},
url = {https://ai.wmi.amu.edu.pl/wp-content/uploads/2020/01/2014-is-intelligent.pdf},
doi = {10.1007/978-3-319-11310-4_29},
isbn = {978-3-319-11309-8},
year = {2015},
date = {2015-01-01},
booktitle = {Intelligent Systems'2014},
volume = {323},
pages = {335-343},
publisher = {Springer, Cham},
series = {Advances in Intelligent Systems and Computing},
abstract = {This article describes the fundamentals of an intelligent decision support system for the diagnosis of ovarian tumors. The system is designed to support diagnosis by less experienced gynecologists, and to gather data for continuous improvement of the quality of diagnosis. The theoretical basis for the construction of the system is the IF-sets framework, used to aggregate multiple decision-making methods, and simultaneously providing information about positive and negative diagnosis of a given tumor type.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
This article describes the fundamentals of an intelligent decision support system for the diagnosis of ovarian tumors. The system is designed to support diagnosis by less experienced gynecologists, and to gather data for continuous improvement of the quality of diagnosis. The theoretical basis for the construction of the system is the IF-sets framework, used to aggregate multiple decision-making methods, and simultaneously providing information about positive and negative diagnosis of a given tumor type. |
Stachowiak, Anna; Żywica, Patryk; Dyczkowski, Krzysztof; Wójtowicz, Andrzej An interval-valued fuzzy classifier based on an uncertainty-aware similarity measure Incollection Angelov, Plamen; Atanassov, Krassimir Todorov; Doukovska, Lyubka; Hadjiski, Mincho; Jotsov, Vladimir; Kacprzyk, Janusz; Kasabov, Nikola; Sotirov, Sotir; Szmidt, Eulalia; Zadrożny, Sławomir (Ed.): Intelligent Systems'2014, 322 , pp. 741-751, Springer, Cham, 2015, ISBN: 978-3-319-11313-5. Abstract | Links | BibTeX @incollection{stachowiak2015interval,
title = {An interval-valued fuzzy classifier based on an uncertainty-aware similarity measure},
author = {Anna Stachowiak and Patryk Żywica and Krzysztof Dyczkowski and Andrzej Wójtowicz},
editor = {Plamen Angelov and Krassimir Todorov Atanassov and Lyubka Doukovska and Mincho Hadjiski and Vladimir Jotsov and Janusz Kacprzyk and Nikola Kasabov and Sotir Sotirov and Eulalia Szmidt and Sławomir Zadrożny},
url = {https://ai.wmi.amu.edu.pl/wp-content/uploads/2020/01/2014-is-interval.pdf},
doi = {10.1007/978-3-319-11313-5_65},
isbn = {978-3-319-11313-5},
year = {2015},
date = {2015-01-01},
booktitle = {Intelligent Systems'2014},
volume = {322},
pages = {741-751},
publisher = {Springer, Cham},
series = {Advances in Intelligent Systems and Computing},
abstract = {In this paper we propose a new method for classifying uncertain data, modeled as interval-valued fuzzy sets. We develop the notion of an interval-valued prototype-based fuzzy classifier, with the idea of preserving full information including the uncertainty factor about data during the classification process. To this end, the classifier was based on the uncertainty-aware similarity measure, a new concept which we introduce and give an axiomatic definition for. Moreover, an algorithm for determining such a similarity value is proposed, and an application to supporting medical diagnosis is described.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
In this paper we propose a new method for classifying uncertain data, modeled as interval-valued fuzzy sets. We develop the notion of an interval-valued prototype-based fuzzy classifier, with the idea of preserving full information including the uncertainty factor about data during the classification process. To this end, the classifier was based on the uncertainty-aware similarity measure, a new concept which we introduce and give an axiomatic definition for. Moreover, an algorithm for determining such a similarity value is proposed, and an application to supporting medical diagnosis is described. |
Wójtowicz, Andrzej; Żywica, Patryk; Stachowiak, Anna; Dyczkowski, Krzysztof Interval-valued aggregation as a tool to improve medical diagnosis Inproceedings Baczyński, Michał; De Baets, Bernard ; Mesiar, Radko (Ed.): Proceedings of 8th International Summer School on Aggregation Operators (AGOP 2015), pp. 239-244, University of Silesia, July 7-10, 2015, Katowice, Poland, 2015, ISBN: 978-83-8012-519-3. Abstract | Links | BibTeX @inproceedings{wojtowicz2015interval,
title = {Interval-valued aggregation as a tool to improve medical diagnosis},
author = {Andrzej Wójtowicz and Patryk Żywica and Anna Stachowiak and Krzysztof Dyczkowski},
editor = {Michał Baczyński and Bernard {De Baets} and Radko Mesiar},
url = {https://ai.wmi.amu.edu.pl/wp-content/uploads/2020/01/2014-agop-aggregation.pdf},
isbn = {978-83-8012-519-3},
year = {2015},
date = {2015-01-01},
booktitle = {Proceedings of 8th International Summer School on Aggregation Operators (AGOP 2015)},
journal = {AGOP 2015},
pages = {239-244},
publisher = {University of Silesia},
address = {July 7-10, 2015, Katowice, Poland},
abstract = {In the paper we present experimental results on the problem of an effective decision making on incomplete data. In order to investigate this problem we examined a variety of interval aggregation methods. Exemplary results are based on a medical diagnosis support system. Our research shows that an application of the aggregation in this problem leads to promising results.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
In the paper we present experimental results on the problem of an effective decision making on incomplete data. In order to investigate this problem we examined a variety of interval aggregation methods. Exemplary results are based on a medical diagnosis support system. Our research shows that an application of the aggregation in this problem leads to promising results. |
2014
|
Wójtowicz, Andrzej; Żywica, Patryk; Szarzyński, Krzysztof; Moszyński, Rafał; Szubert, Sebastian; Dyczkowski, Krzysztof; Stachowiak, Anna; Szpurek, Dariusz; Wygralak, Maciej Dealing with Uncertainty in Ovarian Tumor Diagnosis Incollection Atanassov, Krassimir Todorov; Homenda, Władysław; Hryniewicz, Olgierd; Kacprzyk, Janusz; Krawczak, Maciej; Nahorski, Zbigniew; Szmidt, Eulalia; Zadrożny, Sławomir (Ed.): Modern Approaches in Fuzzy Sets, Intuitionistic Fuzzy Sets, Generalized Nets and Related Topics. Volume II: Applications, pp. 151-158, IBS PAN - SRI PAS, 2014, ISBN: 838947554-5. Abstract | Links | BibTeX @incollection{wojtowicz2014dealing,
title = {Dealing with Uncertainty in Ovarian Tumor Diagnosis},
author = {Andrzej Wójtowicz and Patryk Żywica and Krzysztof Szarzyński and Rafał Moszyński and Sebastian Szubert and Krzysztof Dyczkowski and Anna Stachowiak and Dariusz Szpurek and Maciej Wygralak},
editor = {Krassimir Todorov Atanassov and Władysław Homenda and Olgierd Hryniewicz and Janusz Kacprzyk and Maciej Krawczak and Zbigniew Nahorski and Eulalia Szmidt and Sławomir Zadrożny},
url = {https://ai.wmi.amu.edu.pl/wp-content/uploads/2020/01/2014-iwifsgn-dealing.pdf},
isbn = {838947554-5},
year = {2014},
date = {2014-01-01},
booktitle = {Modern Approaches in Fuzzy Sets, Intuitionistic Fuzzy Sets, Generalized Nets and Related Topics. Volume II: Applications},
pages = {151-158},
publisher = {IBS PAN - SRI PAS},
abstract = {In this paper we consider applications of bipolarity in modelling problems encountered in ovarian tumor diagnosis. We focus on imprecision of data obtained by a gynaecologist during examinations. We also present a wide range of predictive diagnostic models and propose a new idea for their improvement.},
keywords = {},
pubstate = {published},
tppubtype = {incollection}
}
In this paper we consider applications of bipolarity in modelling problems encountered in ovarian tumor diagnosis. We focus on imprecision of data obtained by a gynaecologist during examinations. We also present a wide range of predictive diagnostic models and propose a new idea for their improvement. |
Moszyński, Rafał; Żywica, Patryk; Wójtowicz, Andrzej; Szubert, Sebastian; Sajdak, Stefan; Stachowiak, Anna; Dyczkowski, Krzysztof; Wygralak, Maciej; Szpurek, Dariusz Menopausal status strongly influences the utility of predictive models in differential diagnosis of ovarian tumors: An external validation of selected diagnostic tools Journal Article Ginekologia Polska, 85 (12), pp. 892-899, 2014, ISSN: 0017-0011. Abstract | Links | BibTeX @article{moszynski2014menopausal,
title = {Menopausal status strongly influences the utility of predictive models in differential diagnosis of ovarian tumors: An external validation of selected diagnostic tools},
author = {Rafał Moszyński and Patryk Żywica and Andrzej Wójtowicz and Sebastian Szubert and Stefan Sajdak and Anna Stachowiak and Krzysztof Dyczkowski and Maciej Wygralak and Dariusz Szpurek},
url = {https://journals.viamedica.pl/ginekologia_polska/article/view/45789},
doi = {10.17772/gp/1879},
issn = {0017-0011},
year = {2014},
date = {2014-01-01},
journal = {Ginekologia Polska},
volume = {85},
number = {12},
pages = {892-899},
publisher = {Polskie Towarzystwo Ginekologiczne},
abstract = {OBJECTIVES:
The aim of this study was to externally validate the diagnostic performance of the International Ovarian Tumor Analysis logistic regression models (LR1 and LR2, 2005) and other popular prognostic models including the Timmerman logistic regression model (1999), the Alcazar model (2003), the risk of malignancy index (RMI, 1990), and the risk of malignancy algorithm (ROMA, 2009). We compared these models to subjective ultrasonographic assessment performed by an experienced ultrasonography specialist, and with our previously developed scales: the sonomorphologic index and the vascularization index. Furthermore, we evaluated diagnostic tests with regard to the menopausal status of patients.
MATERIALS AND METHODS:
This study included 268 patients with adnexal masses; 167 patients with benign ovarian tumors and 101 patients with malignant ovarian tumors were enrolled. All tumors were evaluated by using trans- vaginal ultrasonography according to the diagnostic criteria of the analyzed models.
MATERIALS AND METHODS:
This study included 268 patients with adnexal masses; 167 patients with benign ovarian tumors and 101 patients with malignant ovarian tumors were enrolled. All tumors were evaluated by using trans- vaginal ultrasonography according to the diagnostic criteria of the analyzed models.
RESULTS:
The subjective ultrasonographic assessment and all of the studied predictive models achieved similar diagnostic performance in the whole study population. However significant differences were observed when pre- and postmenopausal patients were analyzed separately In the subgroup of premenopausal patients, the highest area under the curve (AUC) was achieved by subjective ultrasonographic assessment (0.931), the Alcazar model (0.912), and LR1 (0.909). Alternatively in the group of postmenopausal patients, the highest AUC was noted for the Timmerman model (0.973), ROMA (0.951), and RMI (0.938).
CONCLUSIONS:
Menopausal status is a key factor that affects the utility of prognostic models for differential diagno sis of ovarian tumors. Diagnostic models of ovarian tumors are reasonable tools for predicting tumor malignancy},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
OBJECTIVES:
The aim of this study was to externally validate the diagnostic performance of the International Ovarian Tumor Analysis logistic regression models (LR1 and LR2, 2005) and other popular prognostic models including the Timmerman logistic regression model (1999), the Alcazar model (2003), the risk of malignancy index (RMI, 1990), and the risk of malignancy algorithm (ROMA, 2009). We compared these models to subjective ultrasonographic assessment performed by an experienced ultrasonography specialist, and with our previously developed scales: the sonomorphologic index and the vascularization index. Furthermore, we evaluated diagnostic tests with regard to the menopausal status of patients.
MATERIALS AND METHODS:
This study included 268 patients with adnexal masses; 167 patients with benign ovarian tumors and 101 patients with malignant ovarian tumors were enrolled. All tumors were evaluated by using trans- vaginal ultrasonography according to the diagnostic criteria of the analyzed models.
MATERIALS AND METHODS:
This study included 268 patients with adnexal masses; 167 patients with benign ovarian tumors and 101 patients with malignant ovarian tumors were enrolled. All tumors were evaluated by using trans- vaginal ultrasonography according to the diagnostic criteria of the analyzed models.
RESULTS:
The subjective ultrasonographic assessment and all of the studied predictive models achieved similar diagnostic performance in the whole study population. However significant differences were observed when pre- and postmenopausal patients were analyzed separately In the subgroup of premenopausal patients, the highest area under the curve (AUC) was achieved by subjective ultrasonographic assessment (0.931), the Alcazar model (0.912), and LR1 (0.909). Alternatively in the group of postmenopausal patients, the highest AUC was noted for the Timmerman model (0.973), ROMA (0.951), and RMI (0.938).
CONCLUSIONS:
Menopausal status is a key factor that affects the utility of prognostic models for differential diagno sis of ovarian tumors. Diagnostic models of ovarian tumors are reasonable tools for predicting tumor malignancy |
Czarnecki, Wojciech; Szarzyński, Krzysztof; Wójtowicz, Andrzej Designing a competition for autonomous robots with a restricted set of sensors with a case study of LEGO NXT Journal Article Journal of Automation, Mobile Robotics & Intelligent Systems, 8 (1), pp. 76-81, 2014, ISSN: 1897-8649. Abstract | Links | BibTeX @article{czarnecki2014designing,
title = {Designing a competition for autonomous robots with a restricted set of sensors with a case study of LEGO NXT},
author = {Wojciech Czarnecki and Krzysztof Szarzyński and Andrzej Wójtowicz},
doi = {10.14313/jamris_1-2014/10},
issn = {1897-8649},
year = {2014},
date = {2014-01-01},
journal = {Journal of Automation, Mobile Robotics & Intelligent Systems},
volume = {8},
number = {1},
pages = {76-81},
publisher = {PIAP - Industrial Research Institute for Automation and Measurements},
abstract = {Arrangements for a competition are not only difficult in terms of logistics of the event, but also require an assurance of quality. In this paper we analyze limitations which arise from design of the contest for robots equipped with a very poor sensor set. This issue is faintly explored – up to now research work usually has focused on results of a certain task and in addition it assumed almost having a freehand with a choice of components. The discussed question is significant on the grounds of primary principles: objectivity in grading, equal opportunities among participants and preservation of attractiveness of the tournament at the same time.
All of our actions have been evaluated through several years of existence of the PozRobot robotics contest. Over a three-year period we had an opportunity to test our approach on nearly 50 teams and almost 150 contestants from many Polish universities.
We analyze various aspects of performing the tournament and we indicate solutions to common problems, e.g. we touch upon dealing with an arena and objects which are placed on it. In particular, we propose a list of features which a well-designed competition should fulfill. To show our experience we describe an instance of a model competition. We outline new directions of further development of the contest, which are connected with a structure of the arena and possible changes in the limited set of the sensors.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Arrangements for a competition are not only difficult in terms of logistics of the event, but also require an assurance of quality. In this paper we analyze limitations which arise from design of the contest for robots equipped with a very poor sensor set. This issue is faintly explored – up to now research work usually has focused on results of a certain task and in addition it assumed almost having a freehand with a choice of components. The discussed question is significant on the grounds of primary principles: objectivity in grading, equal opportunities among participants and preservation of attractiveness of the tournament at the same time.
All of our actions have been evaluated through several years of existence of the PozRobot robotics contest. Over a three-year period we had an opportunity to test our approach on nearly 50 teams and almost 150 contestants from many Polish universities.
We analyze various aspects of performing the tournament and we indicate solutions to common problems, e.g. we touch upon dealing with an arena and objects which are placed on it. In particular, we propose a list of features which a well-designed competition should fulfill. To show our experience we describe an instance of a model competition. We outline new directions of further development of the contest, which are connected with a structure of the arena and possible changes in the limited set of the sensors. |