Filip Malawski
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Filip Malawski has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Jakub Nalepa
Silesian University of Technology
3 shared publications - Jarosław Gośliński
Aisens Sp. z o. o., Lubeckiego 23A, 60-348 Poznań, Poland
3 shared publications - Karol Miszalski-Jamka
Graylight Imaging
3 shared publications - Katarzyna Jesionek
Graylight Imaging
3 shared publications - Marcin Kostur
Graylight Imaging
3 shared publications - Lukasz Czekierda
AGH University of Science and Technology
2 shared publications
Latest Publications
- Open Access
Enhancing Coronary Artery Calcium Scoring via Multi-Organ Segmentation on Non-Contrast Cardiac Computed Tomography
Despite coronary artery calcium scoring being considered a largely solved problem within the realm of medical artificial intelligence, this paper argues that significant improvements can still be made. By shifting the focus from pathology detection to a deeper understanding of anatomy, the novel algorithm proposed in the paper both achieves high accuracy in coronary artery calcium scoring and offers enhanced interpretability of the results. This approach not only aids in the precise quantification of calcifications in coronary arteries, but also provides valuable insights into the underlying anatomical structures. Through this anatomically-informed methodology, the paper shows how a nuanced understanding of the heart's anatomy can lead to more accurate and interpretable results in the field of cardiovascular health. We demonstrate the superior accuracy of the proposed method by evaluating it on an open-source multi-vendor dataset, where we obtain results at the inter-observer level, surpassing the current state of the art. Finally, the qualitative analyses show the practical value of the algorithm in such tasks as labeling coronary artery calcifications, identifying aortic calcifications, and filtering out false positive detections due to noise.
Open AccessEnhancing Coronary Artery Calcium Scoring via Multi-Organ Segmentation on Non-Contrast Cardiac Computed Tomography
Despite coronary artery calcium scoring being considered a largely solved problem within the realm of medical artificial intelligence, this paper argues that significant improvements can still be made. By shifting the focus from pathology detection to a deeper understanding of anatomy, the novel algorithm proposed in the paper both achieves high accuracy in coronary artery calcium scoring and offers enhanced interpretability of the results. This approach not only aids in the precise quantification of calcifications in coronary arteries, but also provides valuable insights into the underlying anatomical structures. Through this anatomically-informed methodology, the paper shows how a nuanced understanding of the heart's anatomy can lead to more accurate and interpretable results in the field of cardiovascular health. We demonstrate the superior accuracy of the proposed method by evaluating it on an open-source multi-vendor dataset, where we obtain results at the inter-observer level, surpassing the current state of the art. Finally, the qualitative analyses show the practical value of the algorithm in such tasks as labeling coronary artery calcifications, identifying aortic calcifications, and filtering out false positive detections due to noise.
- 11 December 2022
- Published by Springer Nature
- p. 336-346
Depth-Based vs. Color-Based Pose Estimation in Human Action Recognition
- 11 December 2022
- Published by Springer Nature
- p. 336-346
Depth-Based vs. Color-Based Pose Estimation in Human Action Recognition
- 30 September 2022
- Published by Springer Nature
- p. 8-17
Deep Learning Meets Computational Fluid Dynamics to Assess CAD in CCTA
- 30 September 2022
- Published by Springer Nature
- p. 8-17
Deep Learning Meets Computational Fluid Dynamics to Assess CAD in CCTA
- Open Access
- 24 March 2022
- Published by AGH University Press in Computer Science
- Vol. 23 (1) , 37-62
Immersive feedback in fencing weapon practice using mixed reality
Providing athletes, during sports training, with real-time feedback based on automatic analysis of motion is both useful and challenging. In this work, a novel system based on mixed reality is proposed and verified. The system allows for immersive, real-time, visual feedback in fencing weapon practice. Novel methods are introduced for 3D blade tracking from a single RGB camera, creating weapon action models by recording actions performed by the coach and evaluating fencers' performance against these models. Augmented reality glasses with see-through displays are employed and a method for coordinate mapping between virtual and real environments is proposed, which allows providing real-time visual cues and feedback by overlaying virtual trajectories on the real-world view. The system is verified experimentally in fencing bladework practice, with supervision of a fencing coach. Results indicate that the proposed system allows novice fencers to perform the exercises more correctly.
- 24 March 2022
- Published by AGH University Press in Computer Science
- Vol. 23 (1) , 37-62
Open AccessImmersive feedback in fencing weapon practice using mixed reality
Providing athletes, during sports training, with real-time feedback based on automatic analysis of motion is both useful and challenging. In this work, a novel system based on mixed reality is proposed and verified. The system allows for immersive, real-time, visual feedback in fencing weapon practice. Novel methods are introduced for 3D blade tracking from a single RGB camera, creating weapon action models by recording actions performed by the coach and evaluating fencers' performance against these models. Augmented reality glasses with see-through displays are employed and a method for coordinate mapping between virtual and real environments is proposed, which allows providing real-time visual cues and feedback by overlaying virtual trajectories on the real-world view. The system is verified experimentally in fencing bladework practice, with supervision of a fencing coach. Results indicate that the proposed system allows novice fencers to perform the exercises more correctly.
- Open Access
- 15 July 2021
- Published by Polish Academy of Sciences Chancellery in Bulletin Of The Polish Academy Of Sciences-Technical Sciences
- Vol. 69 (4) , 137934
Leveraging cloud environment flexibility to smoothen the transition to remote teaching during COVID-19 pandemic – a case study
Cloud-based computational environments can offer elastic and flexible services to wide audiences. Małopolska Educational Cloud was originally developed to support the day-to-day collaboration of geographically scattered schools with universities which organized online classes, led by university teachers, as an amendment to face-to-face teaching. Due to the centralized management and ubiquitous access, both the set of services provided by MEC and their usage patterns can be adjusted rapidly. In this paper we show how – during the COVID-19 pandemic – the flexibility of Małopolska Educational Cloud was leveraged to speed up the transition from in-class to remote teaching, both in the classes and schools which were already involved in the MEC project, and newly added ones. We also discuss the actions that were required to support the smooth transition and draw conclusions for the future.
- 15 July 2021
- Published by Polish Academy of Sciences Chancellery in Bulletin Of The Polish Academy Of Sciences-Technical Sciences
- Vol. 69 (4) , 137934
Open AccessLeveraging cloud environment flexibility to smoothen the transition to remote teaching during COVID-19 pandemic – a case study
Cloud-based computational environments can offer elastic and flexible services to wide audiences. Małopolska Educational Cloud was originally developed to support the day-to-day collaboration of geographically scattered schools with universities which organized online classes, led by university teachers, as an amendment to face-to-face teaching. Due to the centralized management and ubiquitous access, both the set of services provided by MEC and their usage patterns can be adjusted rapidly. In this paper we show how – during the COVID-19 pandemic – the flexibility of Małopolska Educational Cloud was leveraged to speed up the transition from in-class to remote teaching, both in the classes and schools which were already involved in the MEC project, and newly added ones. We also discuss the actions that were required to support the smooth transition and draw conclusions for the future.
- 6 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21 (4) , 5133-5142
Depth Versus Inertial Sensors in Real-Time Sports Analysis: A Case Study on Fencing
Automatic analysis of human motion in sports can provide useful feedback for athletes and coaches. Both depth and inertial sensors are commonly employed for this task. Each type of device has its strengths and weaknesses. Depth cameras allow for efficient tracking of joint positions, although they require a clear field of view. Inertial sensors are useful for determining acceleration and orientation but need to be mounted on the practicing person. In this paper, we perform a case study on fencing in order to investigate the usefulness of both data modalities in real-time qualitative motion analysis in sports. Qualitative analysis of motion goes beyond typical action recognition scenario as it requires the detection of actions in continuous movement as well as determining parameters of the performed motion. In this work a dedicated dataset of fencing footwork is introduced, including synchronized depth and inertial data. Methods for detection and qualitative analysis of the fencing lunge action are proposed and experiments are conducted in order to compare the accuracy and efficiency of analyzing fencing footwork with both depth and inertial sensors.
- 6 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21 (4) , 5133-5142
Depth Versus Inertial Sensors in Real-Time Sports Analysis: A Case Study on Fencing
Automatic analysis of human motion in sports can provide useful feedback for athletes and coaches. Both depth and inertial sensors are commonly employed for this task. Each type of device has its strengths and weaknesses. Depth cameras allow for efficient tracking of joint positions, although they require a clear field of view. Inertial sensors are useful for determining acceleration and orientation but need to be mounted on the practicing person. In this paper, we perform a case study on fencing in order to investigate the usefulness of both data modalities in real-time qualitative motion analysis in sports. Qualitative analysis of motion goes beyond typical action recognition scenario as it requires the detection of actions in continuous movement as well as determining parameters of the performed motion. In this work a dedicated dataset of fencing footwork is introduced, including synchronized depth and inertial data. Methods for detection and qualitative analysis of the fencing lunge action are proposed and experiments are conducted in order to compare the accuracy and efficiency of analyzing fencing footwork with both depth and inertial sensors.
- 1 May 2019
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 61, 198-208
Improving multimodal action representation with joint motion history context
- 1 May 2019
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 61, 198-208
Improving multimodal action representation with joint motion history context
- 2 February 2018
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 77 (18) , 23825-23850
System for multimodal data acquisition for human action recognition
- 2 February 2018
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 77 (18) , 23825-23850
System for multimodal data acquisition for human action recognition
- 4 August 2017
- Published by Wiley in Journal of Computer Assisted Learning
- Vol. 33 (6) , 633-648
Recognizing value of educational collaboration between high schools and universities facilitated by modern ICT
In this paper, we address the problem of an educational gap existing between high schools and universities: many students consider their choice of field of study as inappropriate, mostly due to insufficient information regarding the discipline and the university educational process. To solve this problem, we define an innovative, information and communication technology‐supported educational process enabling various ways of collaboration between high schools and universities. The goal of that process is to increase the knowledge of prospective students regarding the next level of their education. We propose an environment for the implementation of the educational process. The concepts have been verified in practise as part of the Małopolska Educational Cloud project across several disciplines. We discuss the achievements of the pilot phase of the project as well as its reception by educators and students. Based on evaluation reports and opinions from both educators and students, we claim that the proposed model for information and communication technology‐supported collaboration between high schools and universities can effectively reduce the educational gap.
- 4 August 2017
- Published by Wiley in Journal of Computer Assisted Learning
- Vol. 33 (6) , 633-648
Recognizing value of educational collaboration between high schools and universities facilitated by modern ICT
In this paper, we address the problem of an educational gap existing between high schools and universities: many students consider their choice of field of study as inappropriate, mostly due to insufficient information regarding the discipline and the university educational process. To solve this problem, we define an innovative, information and communication technology‐supported educational process enabling various ways of collaboration between high schools and universities. The goal of that process is to increase the knowledge of prospective students regarding the next level of their education. We propose an environment for the implementation of the educational process. The concepts have been verified in practise as part of the Małopolska Educational Cloud project across several disciplines. We discuss the achievements of the pilot phase of the project as well as its reception by educators and students. Based on evaluation reports and opinions from both educators and students, we claim that the proposed model for information and communication technology‐supported collaboration between high schools and universities can effectively reduce the educational gap.