Marisa Cobanaj
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Marisa Cobanaj has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
Amelia Fiske
Affiliation Institute of History and Ethics in Medicine, Department of Clinical Medicine, TUM School of Medicine and Health, Technical University of Munich, Munich, Germany
2 shared publications- Aswin Hoffmann
OncoRay—National Center for Radiation Research in Oncology
2 shared publications - Carmen Criscitiello
Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy; Division of New Drugs and Early Drug Development for Innovative Therapies, European Institute of Oncology IRCCS, Milan, Italy
2 shared publications - Chiara Corti
Breast Oncology Program, Dana-Farber Cancer Institute, Boston, MA, USA; Harvard Medical School, Boston, MA, USA; Division of New Drugs and Early Drug Development, European Institute of Oncology, IRCCS, Milan, Italy; Department of Oncology and Hematology-Oncology (DIPO), University of Milan, Milan, Italy
2 shared publications - Erik Traneus
RaySearch Laboratories AB
2 shared publications - Felix Horst
OncoRay—National Center for Radiation Research in Oncology
2 shared publications
Latest Publications
- Open Access
- 19 November 2026
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 71 (22) , 225013
Spot-wise compensation of proton beam deflection and radiation field deformation in the transverse magnetic field of an in-beam MR scanner using a research version of a commercial treatment planning system
Objective . Magnetic resonance-integrated proton therapy (MRiPT) offers the potential for high-precision, image-guided particle therapy but is challenged by magnetic field (MF)-induced proton beam deflection and radiation field deformation. Unless compensated for, these effects compromise dose conformity and prohibit clinical implementation. This work aims to develop and experimentally validate a spot-wise compensation method capable of restoring proton dose distributions in the presence of a measured three-dimensional magnetic vector field map within a clinical treatment planning system (TPS). Approach . A spot-wise compensation framework was implemented in a research version of RayStation, a TPS commercially available for clinical use. The method compensates both lateral beam deflection and MF-induced radiation field deformation by shifting individual pencil-beam spots based on displacement vectors derived from dose calculations in water phantoms using the measured MF of an in-beam MR scanner integrated with a horizontal proton beamline. Two complementary strategies were implemented: a patient-specific approach based on plan-specific displacement calculations, and a generic approach using precomputed displacement maps derived from a reference phantom. Compensation performance was evaluated in representative clinical cases. Dose distributions were experimentally validated using 2D ionisation chamber array measurements. Main results . Both compensation methods effectively restored target coverage, dose homogeneity, and organ-at-risk sparing to the level of no-MF reference plans. The patient-specific method generally achieved a higher performance, whereas the generic compensation method enabled rapid automated correction with sufficient accuracy for clinical workflows involving deep-seated tumours. Local γ -analysis demonstrated excellent agreement between measured and calculated doses, with pass rates exceeding 98.5% for 3%/3 mm criteria. Significance . This work demonstrates that compensation of MF-induced proton beam deflection and field deformation can be achieved entirely within a research version of the RayStation TPS using measured, MR scanner-specific MF data. The proposed method provides a scalable, robust framework for future MRiPT clinical applications.
- 19 November 2026
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 71 (22) , 225013
Open AccessSpot-wise compensation of proton beam deflection and radiation field deformation in the transverse magnetic field of an in-beam MR scanner using a research version of a commercial treatment planning system
Objective . Magnetic resonance-integrated proton therapy (MRiPT) offers the potential for high-precision, image-guided particle therapy but is challenged by magnetic field (MF)-induced proton beam deflection and radiation field deformation. Unless compensated for, these effects compromise dose conformity and prohibit clinical implementation. This work aims to develop and experimentally validate a spot-wise compensation method capable of restoring proton dose distributions in the presence of a measured three-dimensional magnetic vector field map within a clinical treatment planning system (TPS). Approach . A spot-wise compensation framework was implemented in a research version of RayStation, a TPS commercially available for clinical use. The method compensates both lateral beam deflection and MF-induced radiation field deformation by shifting individual pencil-beam spots based on displacement vectors derived from dose calculations in water phantoms using the measured MF of an in-beam MR scanner integrated with a horizontal proton beamline. Two complementary strategies were implemented: a patient-specific approach based on plan-specific displacement calculations, and a generic approach using precomputed displacement maps derived from a reference phantom. Compensation performance was evaluated in representative clinical cases. Dose distributions were experimentally validated using 2D ionisation chamber array measurements. Main results . Both compensation methods effectively restored target coverage, dose homogeneity, and organ-at-risk sparing to the level of no-MF reference plans. The patient-specific method generally achieved a higher performance, whereas the generic compensation method enabled rapid automated correction with sufficient accuracy for clinical workflows involving deep-seated tumours. Local γ -analysis demonstrated excellent agreement between measured and calculated doses, with pass rates exceeding 98.5% for 3%/3 mm criteria. Significance . This work demonstrates that compensation of MF-induced proton beam deflection and field deformation can be achieved entirely within a research version of the RayStation TPS using measured, MR scanner-specific MF data. The proposed method provides a scalable, robust framework for future MRiPT clinical applications.
- Open Access
- 7 October 2026
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 71 (19) , 195023
Dosimetric validation of proton beam deflection and field shape deformation in a measured transverse magnetic field of an in-beam MR scanner using a novel dose calculation functionality in a research version of a commercial treatment planning system
Objective. Integrating in-beam magnetic resonance imaging (MRI) with proton therapy (PT) introduces magnetic fields (MFs) that affect proton beam transport and therefore require accurate incorporation into the treatment planning system (TPS) for magnetic resonance (MR)-integrated PT (MRiPT). This study experimentally validates Monte Carlo-based proton dose calculation in the presence of the MF in a research version of the commercial TPS RayStation for MRiPT, using a measured three-dimensional (3D) magnetic vector field map of a 0.32 T in-beam MR scanner combined with a horizontal proton pencil beam scanning beam line. Approach. An MR-compatible mapping framework was used to acquire a high-resolution 3D magnetic vector field map, subsequently implemented into the TPS following coordinate transformations. Proton spot patterns and square radiation fields at 100, 150, and 220 MeV were delivered with and without the MF present. Dose distributions in air were measured using a 2D ionisation chamber array at multiple positions and compared with TPS dose calculations by analysing lateral beam shifts and field shape deformations with local γ -analysis. Clinically relevant patient treatment fields were evaluated at different water-equivalent depths (WEDs) in a phantom. Main results. Implementation of the measured magnetic vector field map preserved field vector magnitude, orientation and spatial alignment within the TPS. Dose measurements showed energy- and position-dependent MF-induced effects, which were accurately reproduced by the TPS. Agreement in lateral beam shifts was within 1–3 mm, and γ -pass rates exceeded 97% for a 3%/3 mm local criterion (10% dose threshold). Similar agreement was observed for patient treatment fields throughout all WEDs. Significance. This work validates the TPS capability to accurately model MF-induced proton beam transport in air as well as in a water-equivalent phantom. The present workflow establishes a foundation for proton treatment planning in the presence of MFs and thereby contributes to the clinical implementation of MRiPT.
- 7 October 2026
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 71 (19) , 195023
Open AccessDosimetric validation of proton beam deflection and field shape deformation in a measured transverse magnetic field of an in-beam MR scanner using a novel dose calculation functionality in a research version of a commercial treatment planning system
Objective. Integrating in-beam magnetic resonance imaging (MRI) with proton therapy (PT) introduces magnetic fields (MFs) that affect proton beam transport and therefore require accurate incorporation into the treatment planning system (TPS) for magnetic resonance (MR)-integrated PT (MRiPT). This study experimentally validates Monte Carlo-based proton dose calculation in the presence of the MF in a research version of the commercial TPS RayStation for MRiPT, using a measured three-dimensional (3D) magnetic vector field map of a 0.32 T in-beam MR scanner combined with a horizontal proton pencil beam scanning beam line. Approach. An MR-compatible mapping framework was used to acquire a high-resolution 3D magnetic vector field map, subsequently implemented into the TPS following coordinate transformations. Proton spot patterns and square radiation fields at 100, 150, and 220 MeV were delivered with and without the MF present. Dose distributions in air were measured using a 2D ionisation chamber array at multiple positions and compared with TPS dose calculations by analysing lateral beam shifts and field shape deformations with local γ -analysis. Clinically relevant patient treatment fields were evaluated at different water-equivalent depths (WEDs) in a phantom. Main results. Implementation of the measured magnetic vector field map preserved field vector magnitude, orientation and spatial alignment within the TPS. Dose measurements showed energy- and position-dependent MF-induced effects, which were accurately reproduced by the TPS. Agreement in lateral beam shifts was within 1–3 mm, and γ -pass rates exceeded 97% for a 3%/3 mm local criterion (10% dose threshold). Similar agreement was observed for patient treatment fields throughout all WEDs. Significance. This work validates the TPS capability to accurately model MF-induced proton beam transport in air as well as in a water-equivalent phantom. The present workflow establishes a foundation for proton treatment planning in the presence of MFs and thereby contributes to the clinical implementation of MRiPT.
- Open Access
- 31 July 2025
- Published by Associação de Medicina Intensiva Brasileira in Critical Care Science
- Vol. 37, e20250380
Understanding artificial intelligence in critical care: opportunities, risks, and practical applications
Artificial intelligence technologies are rapidly advancing and significantly impacting healthcare, particularly in critical care environments where rapid, precise decision-making is crucial. They promise reductions in clinical errors, enhanced diagnostic accuracy, optimized treatment plans, and better resource allocation. Artificial intelligence applications are widespread across medical fields, with numerous artificial intelligence/machine learning-enabled medical devices approved by […] ABSTRACT Artificial intelligence technologies are rapidly advancing and significantly impacting healthcare, particularly in critical care environments where rapid, precise decision-making is crucial. They promise reductions in clinical errors, enhanced diagnostic accuracy, optimized treatment plans, and better resource allocation. Artificial intelligence applications are widespread across medical fields, with numerous artificial intelligence/machine learning-enabled medical devices approved by […]
- 31 July 2025
- Published by Associação de Medicina Intensiva Brasileira in Critical Care Science
- Vol. 37, e20250380
Open AccessUnderstanding artificial intelligence in critical care: opportunities, risks, and practical applications
Artificial intelligence technologies are rapidly advancing and significantly impacting healthcare, particularly in critical care environments where rapid, precise decision-making is crucial. They promise reductions in clinical errors, enhanced diagnostic accuracy, optimized treatment plans, and better resource allocation. Artificial intelligence applications are widespread across medical fields, with numerous artificial intelligence/machine learning-enabled medical devices approved by […] ABSTRACT Artificial intelligence technologies are rapidly advancing and significantly impacting healthcare, particularly in critical care environments where rapid, precise decision-making is crucial. They promise reductions in clinical errors, enhanced diagnostic accuracy, optimized treatment plans, and better resource allocation. Artificial intelligence applications are widespread across medical fields, with numerous artificial intelligence/machine learning-enabled medical devices approved by […]
- Open Access
- 23 July 2024
- Published by Public Library of Science (PLoS) in PLOS Digital Health
- Vol. 3 (7) , e0000486
Diversity and inclusion: A hidden additional benefit of Open Data
The recent imperative by the National Institutes of Health to share scientific data publicly underscores a significant shift in academic research. Effective as of January 2023, it emphasizes that transparency in data collection and dedicated efforts towards data sharing are prerequisites for translational research, from the lab to the bedside. Given the role of data access in mitigating potential bias in clinical models, we hypothesize that researchers who leverage open-access datasets rather than privately-owned ones are more diverse. In this brief report, we proposed to test this hypothesis in the transdisciplinary and expanding field of artificial intelligence (AI) for critical care. Specifically, we compared the diversity among authors of publications leveraging open datasets, such as the commonly used MIMIC and eICU databases, with that among authors of publications relying exclusively on private datasets, unavailable to other research investigators (e.g., electronic health records from ICU patients accessible only to Mayo Clinic analysts). To measure the extent of author diversity, we characterized gender balance as well as the presence of researchers from low- and middle-income countries (LMIC) and minority-serving institutions (MSI) located in the United States (US). Our comparative analysis revealed a greater contribution of authors from LMICs and MSIs among researchers leveraging open critical care datasets (treatment group) than among those relying exclusively on private data resources (control group). The participation of women was similar between the two groups, albeit slightly larger in the former. Notably, although over 70% of all articles included at least one author inferred to be a woman, less than 25% had a woman as a first or last author. Importantly, we found that the proportion of authors from LMICs was substantially higher in the treatment than in the control group (10.1% vs. 6.2%, p<0.001), including as first and last authors. Moreover, we found that the proportion of US-based authors affiliated with a MSI was 1.5 times higher among articles in the treatment than in the control group, suggesting that open data resources attract a larger pool of participants from minority groups (8.6% vs. 5.6%, p<0.001). Thus, our study highlights the valuable contribution of the Open Data strategy to underrepresented groups, while also quantifying persisting gender gaps in academic and clinical research at the intersection of computer science and healthcare. In doing so, we hope our work points to the importance of extending open data practices in deliberate and systematic ways.
- 23 July 2024
- Published by Public Library of Science (PLoS) in PLOS Digital Health
- Vol. 3 (7) , e0000486
Open AccessDiversity and inclusion: A hidden additional benefit of Open Data
The recent imperative by the National Institutes of Health to share scientific data publicly underscores a significant shift in academic research. Effective as of January 2023, it emphasizes that transparency in data collection and dedicated efforts towards data sharing are prerequisites for translational research, from the lab to the bedside. Given the role of data access in mitigating potential bias in clinical models, we hypothesize that researchers who leverage open-access datasets rather than privately-owned ones are more diverse. In this brief report, we proposed to test this hypothesis in the transdisciplinary and expanding field of artificial intelligence (AI) for critical care. Specifically, we compared the diversity among authors of publications leveraging open datasets, such as the commonly used MIMIC and eICU databases, with that among authors of publications relying exclusively on private datasets, unavailable to other research investigators (e.g., electronic health records from ICU patients accessible only to Mayo Clinic analysts). To measure the extent of author diversity, we characterized gender balance as well as the presence of researchers from low- and middle-income countries (LMIC) and minority-serving institutions (MSI) located in the United States (US). Our comparative analysis revealed a greater contribution of authors from LMICs and MSIs among researchers leveraging open critical care datasets (treatment group) than among those relying exclusively on private data resources (control group). The participation of women was similar between the two groups, albeit slightly larger in the former. Notably, although over 70% of all articles included at least one author inferred to be a woman, less than 25% had a woman as a first or last author. Importantly, we found that the proportion of authors from LMICs was substantially higher in the treatment than in the control group (10.1% vs. 6.2%, p<0.001), including as first and last authors. Moreover, we found that the proportion of US-based authors affiliated with a MSI was 1.5 times higher among articles in the treatment than in the control group, suggesting that open data resources attract a larger pool of participants from minority groups (8.6% vs. 5.6%, p<0.001). Thus, our study highlights the valuable contribution of the Open Data strategy to underrepresented groups, while also quantifying persisting gender gaps in academic and clinical research at the intersection of computer science and healthcare. In doing so, we hope our work points to the importance of extending open data practices in deliberate and systematic ways.
- Open Access
Diversity and inclusion: A hidden additional benefit of Open Data
The recent imperative by the National Institutes of Health to share scientific data publicly underscores a significant shift in academic research. Effective as of January 2023, it emphasizes that transparency in data collection and dedicated efforts towards data sharing are prerequisites for translational research, from the lab to the bedside. Given the role of data access in mitigating potential bias in clinical models, we hypothesize that researchers who leverage open-access datasets rather than privately-owned ones are more diverse. In this brief report, we proposed to test this hypothesis in the transdisciplinary and expanding field of artificial intelligence (AI) for critical care. Specifically, we compared the diversity among authors of publications leveraging open datasets, such as the commonly used MIMIC and eICU databases, with that among authors of publications relying exclusively on private datasets, unavailable to other research investigators (e.g., electronic health records from ICU patients accessible only to Mayo Clinic analysts). To measure the extent of author diversity, we characterized gender balance as well as the presence of researchers from low- and middle-income countries (LMIC) and minority-serving institutions (MSI). Our comparative analysis revealed a greater contribution of authors from LMICs and MSIs among researchers leveraging open critical care datasets than among those relying exclusively on private data resources. The participation of women was similar between the two groups, albeit slightly larger in the former. Notably, although over 70% of all articles included at least one author inferred to be a woman, less than 25% had a woman as a first or last author. Importantly, we found that the proportion of authors from LMICs was substantially higher in the treatment than in the control group (10.1% vs. 6.2%, p<0.001), including as first and last authors. Moreover, we found that the proportion of US-based authors affiliated with a MSI was 1.5 times higher among articles in the treatment than in the control group, suggesting that open data resources attract a larger pool of participants from minority groups (8.6% vs. 5.6%, p<0.001). Thus, our study highlights the valuable contribution of the Open Data strategy to underrepresented groups, while also quantifying persisting gender gaps in academic and clinical research at the intersection of computer science and healthcare. In doing so, we hope our work points to the importance of extending open data practices in deliberate and systematic ways. Author Summary: In light of the significance of data access to the mitigation of bias in clinical models, we hypothesize that researchers who leverage existing open-access datasets rather than privately-owned ones are more diverse. In this brief report, we propose to test this hypothesis in the transdisciplinary and expanding field of artificial intelligence for critical care. Specifically, we compare the diversity among authors of publications leveraging open datasets, such as the commonly used MIMIC and eICU databases, with that among authors of publications relying exclusively on private datasets, unavailable to other research investigators. To measure the extent of author diversity, we characterize gender balance, geographic diversity (i.e., the number of countries with which authors are affiliated and the income categories these countries map to), and the presence of researchers from minority-serving institutions located in the United States. Furthermore, we comment on the challenges of increasing the participation of researchers from underrepresented groups and suggest changes that can be made to the current Open Data strategy to enhance representation in authorship in the next decade. By evaluating the association between data accessibility and author diversity, our study pinpoints actionable steps that the broader field of clinical AI can take to foster inclusion in the scientific community and mitigate blind spots in data preparation and/or model development.
Open AccessDiversity and inclusion: A hidden additional benefit of Open Data
The recent imperative by the National Institutes of Health to share scientific data publicly underscores a significant shift in academic research. Effective as of January 2023, it emphasizes that transparency in data collection and dedicated efforts towards data sharing are prerequisites for translational research, from the lab to the bedside. Given the role of data access in mitigating potential bias in clinical models, we hypothesize that researchers who leverage open-access datasets rather than privately-owned ones are more diverse. In this brief report, we proposed to test this hypothesis in the transdisciplinary and expanding field of artificial intelligence (AI) for critical care. Specifically, we compared the diversity among authors of publications leveraging open datasets, such as the commonly used MIMIC and eICU databases, with that among authors of publications relying exclusively on private datasets, unavailable to other research investigators (e.g., electronic health records from ICU patients accessible only to Mayo Clinic analysts). To measure the extent of author diversity, we characterized gender balance as well as the presence of researchers from low- and middle-income countries (LMIC) and minority-serving institutions (MSI). Our comparative analysis revealed a greater contribution of authors from LMICs and MSIs among researchers leveraging open critical care datasets than among those relying exclusively on private data resources. The participation of women was similar between the two groups, albeit slightly larger in the former. Notably, although over 70% of all articles included at least one author inferred to be a woman, less than 25% had a woman as a first or last author. Importantly, we found that the proportion of authors from LMICs was substantially higher in the treatment than in the control group (10.1% vs. 6.2%, p<0.001), including as first and last authors. Moreover, we found that the proportion of US-based authors affiliated with a MSI was 1.5 times higher among articles in the treatment than in the control group, suggesting that open data resources attract a larger pool of participants from minority groups (8.6% vs. 5.6%, p<0.001). Thus, our study highlights the valuable contribution of the Open Data strategy to underrepresented groups, while also quantifying persisting gender gaps in academic and clinical research at the intersection of computer science and healthcare. In doing so, we hope our work points to the importance of extending open data practices in deliberate and systematic ways. Author Summary: In light of the significance of data access to the mitigation of bias in clinical models, we hypothesize that researchers who leverage existing open-access datasets rather than privately-owned ones are more diverse. In this brief report, we propose to test this hypothesis in the transdisciplinary and expanding field of artificial intelligence for critical care. Specifically, we compare the diversity among authors of publications leveraging open datasets, such as the commonly used MIMIC and eICU databases, with that among authors of publications relying exclusively on private datasets, unavailable to other research investigators. To measure the extent of author diversity, we characterize gender balance, geographic diversity (i.e., the number of countries with which authors are affiliated and the income categories these countries map to), and the presence of researchers from minority-serving institutions located in the United States. Furthermore, we comment on the challenges of increasing the participation of researchers from underrepresented groups and suggest changes that can be made to the current Open Data strategy to enhance representation in authorship in the next decade. By evaluating the association between data accessibility and author diversity, our study pinpoints actionable steps that the broader field of clinical AI can take to foster inclusion in the scientific community and mitigate blind spots in data preparation and/or model development.
- 15 March 2024
- Published by Elsevier
- p. 1-23
Artificial intelligence in cancer research and precision medicine
- 15 March 2024
- Published by Elsevier
- p. 1-23
Artificial intelligence in cancer research and precision medicine
- Open Access
- 19 December 2023
- Published by Elsevier in European Journal of Cancer
- Vol. 198, 113504
Advancing equitable and personalized cancer care: Novel applications and priorities of artificial intelligence for fairness and inclusivity in the patient care workflow
- 19 December 2023
- Published by Elsevier in European Journal of Cancer
- Vol. 198, 113504
Open AccessAdvancing equitable and personalized cancer care: Novel applications and priorities of artificial intelligence for fairness and inclusivity in the patient care workflow