Gokhan Anil
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Gokhan Anil has a total of 47 co-authors. Here are the top co-authors by number of shared publications:
Pawan Bhandari
Department of Automotive and Manufacturing Engineering, Minnesota State University, Mankato, MN
3 shared publications- Abinash Mahapatro
SIU School of Medicine, Springfield, IL, USA
2 shared publications - Ashley M. Brooks
Department of Nursing, Mayo Clinic Health System in Southwest Minnesota, Mankato, MN
2 shared publications - Brad A. Krier
Department of Nursing, Mayo Clinic Health System in Southwest Minnesota, Mankato, MN
2 shared publications - Hariprasad Reddy Korsapati
Mayo Clinic Health System, Mankato, MN, USA
2 shared publications - Abdulhadi Alotaibi
Department of Medicine, Vision Colleges, Riyadh, Saudi Arabia
1 shared publication
Latest Publications
- Open Access
- 4 September 2026
- Published by Springer Nature in Egyptian Journal of Radiology and Nuclear Medicine
- Vol. 57 (1) , 183
Deep learning-based segmentation of abdominal aortic aneurysm: a systematic review and meta-analysis of performance and clinical applicability
Background: Abdominal aortic aneurysm (AAA) management relies heavily on imaging for surveillance, treatment planning, and follow-up. Deep learning (DL)-based segmentation may improve the efficiency and reproducibility of AAA image analysis; however, reported performance varies across studies. This study aimed to systematically review and quantitatively summarize the performance of DL models for AAA-related segmentation. Methods: PubMed, Embase, Scopus, and Web of Science were searched for studies applying DL to AAA imaging in adults and reporting Dice score or intersection-over-union (IoU) as segmentation metrics. Each DL model evaluated on a held-out test set was treated as a separate model-level observation. Random-effects meta-analyses were used to pool Dice score and IoU. Subgroup analyses were performed by imaging modality, model category, and input dimensionality, and additional analyses provided structure-specific estimates for aneurysm sac, intraluminal thrombus (ILT), lumen, and EVAR-related segmentations. Results: Across all targets, overall segmentation performance was 0.81 (95% CI 0.78–0.83) for Dice score and 0.72 (95% CI 0.67–0.77) for IoU. In subgroup analyses by model category, pooled Dice scores were 0.83 (95% CI 0.80–0.86) for U-Net family models, 0.82 (95% CI 0.77–0.86) for transformer or hybrid models, and 0.76 (95% CI 0.72–0.81) for other convolutional neural networks. By imaging modality, Dice scores were 0.87 (95% CI 0.84–0.89) for contrast-enhanced CT (CECT), 0.83 (95% CI 0.78–0.88) for non-contrast CT (NCCT), 0.84 (95% CI 0.81–0.87) for MRI, 0.78 (95% CI 0.74–0.82) for CT angiography (CTA), and 0.95 (95% CI 0.92–0.98) for X-ray. IoU subgroup analyses showed broadly similar patterns by modality and model category. In structure-specific analyses, aneurysm sac segmentation achieved a pooled Dice of 0.87 (95% CI 0.85–0.89) and IoU of 0.80 (95% CI 0.68–0.93); ILT segmentation reached 0.72 (95% CI 0.62–0.81) and 0.67 (95% CI 0.57–0.77); lumen segmentation 0.84 (95% CI 0.73–0.95) and 0.92 (95% CI 0.80–1.00); and EVAR-related targets 0.76 (95% CI 0.67–0.86) and 0.66 (95% CI 0.55–0.77) for Dice and IoU, respectively. Conclusions: DL-based models demonstrate good segmentation performance for the AAA sac and lumen, indicating clinically acceptable accuracy for applications such as volumetric surveillance and surgical planning. Performance for ILT and EVAR-related structures is more variable, suggesting that human oversight remains advisable for these targets in clinical practice. These findings support the use of DL-based segmentation in research and highlight its potential for selected clinical applications. However, the evidence base remains heterogeneous and is derived from a limited number of studies, with most models lacking external validation. Larger, standardized, multicentre evaluations with robust external validation are needed to confirm and refine these estimates.
- 4 September 2026
- Published by Springer Nature in Egyptian Journal of Radiology and Nuclear Medicine
- Vol. 57 (1) , 183
Open AccessDeep learning-based segmentation of abdominal aortic aneurysm: a systematic review and meta-analysis of performance and clinical applicability
Background: Abdominal aortic aneurysm (AAA) management relies heavily on imaging for surveillance, treatment planning, and follow-up. Deep learning (DL)-based segmentation may improve the efficiency and reproducibility of AAA image analysis; however, reported performance varies across studies. This study aimed to systematically review and quantitatively summarize the performance of DL models for AAA-related segmentation. Methods: PubMed, Embase, Scopus, and Web of Science were searched for studies applying DL to AAA imaging in adults and reporting Dice score or intersection-over-union (IoU) as segmentation metrics. Each DL model evaluated on a held-out test set was treated as a separate model-level observation. Random-effects meta-analyses were used to pool Dice score and IoU. Subgroup analyses were performed by imaging modality, model category, and input dimensionality, and additional analyses provided structure-specific estimates for aneurysm sac, intraluminal thrombus (ILT), lumen, and EVAR-related segmentations. Results: Across all targets, overall segmentation performance was 0.81 (95% CI 0.78–0.83) for Dice score and 0.72 (95% CI 0.67–0.77) for IoU. In subgroup analyses by model category, pooled Dice scores were 0.83 (95% CI 0.80–0.86) for U-Net family models, 0.82 (95% CI 0.77–0.86) for transformer or hybrid models, and 0.76 (95% CI 0.72–0.81) for other convolutional neural networks. By imaging modality, Dice scores were 0.87 (95% CI 0.84–0.89) for contrast-enhanced CT (CECT), 0.83 (95% CI 0.78–0.88) for non-contrast CT (NCCT), 0.84 (95% CI 0.81–0.87) for MRI, 0.78 (95% CI 0.74–0.82) for CT angiography (CTA), and 0.95 (95% CI 0.92–0.98) for X-ray. IoU subgroup analyses showed broadly similar patterns by modality and model category. In structure-specific analyses, aneurysm sac segmentation achieved a pooled Dice of 0.87 (95% CI 0.85–0.89) and IoU of 0.80 (95% CI 0.68–0.93); ILT segmentation reached 0.72 (95% CI 0.62–0.81) and 0.67 (95% CI 0.57–0.77); lumen segmentation 0.84 (95% CI 0.73–0.95) and 0.92 (95% CI 0.80–1.00); and EVAR-related targets 0.76 (95% CI 0.67–0.86) and 0.66 (95% CI 0.55–0.77) for Dice and IoU, respectively. Conclusions: DL-based models demonstrate good segmentation performance for the AAA sac and lumen, indicating clinically acceptable accuracy for applications such as volumetric surveillance and surgical planning. Performance for ILT and EVAR-related structures is more variable, suggesting that human oversight remains advisable for these targets in clinical practice. These findings support the use of DL-based segmentation in research and highlight its potential for selected clinical applications. However, the evidence base remains heterogeneous and is derived from a limited number of studies, with most models lacking external validation. Larger, standardized, multicentre evaluations with robust external validation are needed to confirm and refine these estimates.
- Open Access
- 2 June 2026
- Published by Wolters Kluwer Health in Annals of Medicine & Surgery
- Vol. 88 (7) , 4272-4287
Exploring the landscape of artificial intelligence in dental and maxillofacial radiology: a bibliometric analysis of studies and trends
Background: The integration of artificial intelligence (AI) in dental and maxillofacial radiology is revolutionizing diagnostic accuracy and clinical decision-making. This bibliometric analysis investigates the research landscape, emerging trends, and scholarly impact of AI applications in this specialized field. Methods: A comprehensive search was conducted on 25 December 2024 using the Web of Science Core Collection database. Data analysis tools, including VOSviewer, CiteSpace, and Biblioshiny, were employed to examine publication trends, global contributions, collaborative networks, and keyword dynamics. Results: The analysis revealed a marked increase in AI-related publications in dental and maxillofacial radiology, particularly from 2016 onward. The number of studies rose steadily, reaching 218 publications in 2024. The United States led in research output, followed closely by China and South Korea, with KU Leuven emerging as the top-contributing institution. Reinhilde Jacobs was identified as the most prolific author, while Medical Physics was the most cited journal. Co-citation analysis highlighted influential works by authors such as J.H. Lee and F. Schwendicke . Keywords including “artificial intelligence,” “deep learning,” “CBCT,” and “classification” dominated research discussions, reflecting the field’s evolving focus. Recent research trends emphasize advanced applications in segmentation, accuracy enhancement, and predictive modeling. Conclusion: AI has become integral to the advancement of dental and maxillofacial radiology, offering significant improvements in diagnostic precision and treatment planning. This study underscores the importance of staying abreast of AI innovations to enhance patient care and foster future research opportunities. Researchers and clinicians are encouraged to adopt AI-driven approaches to maximize clinical efficiency and outcomes.
- 2 June 2026
- Published by Wolters Kluwer Health in Annals of Medicine & Surgery
- Vol. 88 (7) , 4272-4287
Open AccessExploring the landscape of artificial intelligence in dental and maxillofacial radiology: a bibliometric analysis of studies and trends
Background: The integration of artificial intelligence (AI) in dental and maxillofacial radiology is revolutionizing diagnostic accuracy and clinical decision-making. This bibliometric analysis investigates the research landscape, emerging trends, and scholarly impact of AI applications in this specialized field. Methods: A comprehensive search was conducted on 25 December 2024 using the Web of Science Core Collection database. Data analysis tools, including VOSviewer, CiteSpace, and Biblioshiny, were employed to examine publication trends, global contributions, collaborative networks, and keyword dynamics. Results: The analysis revealed a marked increase in AI-related publications in dental and maxillofacial radiology, particularly from 2016 onward. The number of studies rose steadily, reaching 218 publications in 2024. The United States led in research output, followed closely by China and South Korea, with KU Leuven emerging as the top-contributing institution. Reinhilde Jacobs was identified as the most prolific author, while Medical Physics was the most cited journal. Co-citation analysis highlighted influential works by authors such as J.H. Lee and F. Schwendicke . Keywords including “artificial intelligence,” “deep learning,” “CBCT,” and “classification” dominated research discussions, reflecting the field’s evolving focus. Recent research trends emphasize advanced applications in segmentation, accuracy enhancement, and predictive modeling. Conclusion: AI has become integral to the advancement of dental and maxillofacial radiology, offering significant improvements in diagnostic precision and treatment planning. This study underscores the importance of staying abreast of AI innovations to enhance patient care and foster future research opportunities. Researchers and clinicians are encouraged to adopt AI-driven approaches to maximize clinical efficiency and outcomes.
- 1 September 2025
- Published by Elsevier in American Journal of Infection Control
- Vol. 53 (12) , 1330-1336
Relaunch of an electronic monitoring system to sustain hand hygiene observations and compliance: A quality improvement study
- 1 September 2025
- Published by Elsevier in American Journal of Infection Control
- Vol. 53 (12) , 1330-1336
Relaunch of an electronic monitoring system to sustain hand hygiene observations and compliance: A quality improvement study
- 19 November 2024
- Published by SAGE Publications in Journal of Infection Prevention
- Vol. 26 (2) , 62-66
Real-time intervention to increase daily chlorhexidine bathing and reduce central line–associated bloodstream infections
Background: After an increase of central line–associated bloodstream infections (CLABSIs) at our community hospital in 2021, a case-control study suggested that patients with CLABSIs were 3.0 times more likely to have missed daily chlorhexidine gluconate (CHG) bathing than patients without CLABSIs. Objective: To increase the rate of daily CHG bathing in hospitalized patients with central lines and subsequently reduce the number of CLABSIs. Methods: Our pre-post intervention was launched on September 2022 and consisted of enhancements to the electronic health record (EHR) to simplify the identification of overdue CHG bathing instances to increase compliance, and therefore decrease the CLABSI rate at our hospital. A workflow was implemented Monday–Friday utilizing these EHR enhancements for active surveillance to engage frontline nursing staff and address gaps in care in real time. Results: After the initiative was implemented, adherence to daily CHG bathing increased from 94.9% to 95.3%, with a considerable disparity between weekdays (97.6%) and weekends (89.3%). After weekend data were excluded, the post-intervention increase in the adherence rate was statistically significant ( p = .003). Discussion: This initiative underscored the importance of involving health care informatics partners and showed how technology can bridge gaps in health care quality. Outreach and reminders effectively improved CHG bathing adherence by emphasizing the importance of consistent communication and follow-up.
- 19 November 2024
- Published by SAGE Publications in Journal of Infection Prevention
- Vol. 26 (2) , 62-66
Real-time intervention to increase daily chlorhexidine bathing and reduce central line–associated bloodstream infections
Background: After an increase of central line–associated bloodstream infections (CLABSIs) at our community hospital in 2021, a case-control study suggested that patients with CLABSIs were 3.0 times more likely to have missed daily chlorhexidine gluconate (CHG) bathing than patients without CLABSIs. Objective: To increase the rate of daily CHG bathing in hospitalized patients with central lines and subsequently reduce the number of CLABSIs. Methods: Our pre-post intervention was launched on September 2022 and consisted of enhancements to the electronic health record (EHR) to simplify the identification of overdue CHG bathing instances to increase compliance, and therefore decrease the CLABSI rate at our hospital. A workflow was implemented Monday–Friday utilizing these EHR enhancements for active surveillance to engage frontline nursing staff and address gaps in care in real time. Results: After the initiative was implemented, adherence to daily CHG bathing increased from 94.9% to 95.3%, with a considerable disparity between weekdays (97.6%) and weekends (89.3%). After weekend data were excluded, the post-intervention increase in the adherence rate was statistically significant ( p = .003). Discussion: This initiative underscored the importance of involving health care informatics partners and showed how technology can bridge gaps in health care quality. Outreach and reminders effectively improved CHG bathing adherence by emphasizing the importance of consistent communication and follow-up.
- Open Access
- 30 December 2023
- Published by BMJ in BMJ Open Quality
- Vol. 12 (4) , e002306
Quality improvement initiative to improve communication domains of patient satisfaction in a regional community hospital with Six Sigma methodology
Background Communication gaps, whether incomplete or fragmented communication, have been the cause of many disasters in human civilisation. Coordination of healthcare is directly related to proper communication and handoffs among multidisciplinary teams throughout multiple shifts during a patient’s hospitalisation. Local problem Patient surveys and direct patient feedback at Mayo Clinic Health System in Mankato, Minnesota, indicated that patient communication with physicians and nurses had declined in 2017 and 2018. Viewing this as an opportunity for improvement, our leadership initiated several changes to increase physician and nurse communication with patients, which resulted in no notable improvements. Methods A systematic quality improvement approach was implemented by using Six Sigma methodology. Stakeholders from multidisciplinary teams were assembled as the project team. The five steps of Six Sigma methodology (Define, Measure, Analyse, Improve and Control) were followed to create a quality improvement intervention. Intervention We developed a standardised and easy-to-use bedside team rounding tool to improve patient communication with physicians and nurses. Results Postintervention patient satisfaction top-box scores exceeded target improvements for both physician (from 78.5% to 82.0%, pConclusions Overwhelmingly positive patient feedback was achieved, and postintervention employee satisfaction was primarily positive when compared with preintervention satisfaction.
- 30 December 2023
- Published by BMJ in BMJ Open Quality
- Vol. 12 (4) , e002306
Open AccessQuality improvement initiative to improve communication domains of patient satisfaction in a regional community hospital with Six Sigma methodology
Background Communication gaps, whether incomplete or fragmented communication, have been the cause of many disasters in human civilisation. Coordination of healthcare is directly related to proper communication and handoffs among multidisciplinary teams throughout multiple shifts during a patient’s hospitalisation. Local problem Patient surveys and direct patient feedback at Mayo Clinic Health System in Mankato, Minnesota, indicated that patient communication with physicians and nurses had declined in 2017 and 2018. Viewing this as an opportunity for improvement, our leadership initiated several changes to increase physician and nurse communication with patients, which resulted in no notable improvements. Methods A systematic quality improvement approach was implemented by using Six Sigma methodology. Stakeholders from multidisciplinary teams were assembled as the project team. The five steps of Six Sigma methodology (Define, Measure, Analyse, Improve and Control) were followed to create a quality improvement intervention. Intervention We developed a standardised and easy-to-use bedside team rounding tool to improve patient communication with physicians and nurses. Results Postintervention patient satisfaction top-box scores exceeded target improvements for both physician (from 78.5% to 82.0%, pConclusions Overwhelmingly positive patient feedback was achieved, and postintervention employee satisfaction was primarily positive when compared with preintervention satisfaction.
- Open Access
- 22 September 2022
- Published by Elsevier in Mayo Clinic Proceedings: Innovations, Quality & Outcomes
- Vol. 6 (5) , 475-483
A Digitally Capable Mobile Health Clinic to Improve Rural Health Care in America: A Pilot Quality Improvement Study
- 22 September 2022
- Published by Elsevier in Mayo Clinic Proceedings: Innovations, Quality & Outcomes
- Vol. 6 (5) , 475-483
Open AccessA Digitally Capable Mobile Health Clinic to Improve Rural Health Care in America: A Pilot Quality Improvement Study
- Open Access
- 1 February 2020
- Published by Elsevier in Mayo Clinic Proceedings: Innovations, Quality & Outcomes
- Vol. 4 (1) , 3-7
Midwife Laborist Model in a Collaborative Community Practice
- 1 February 2020
- Published by Elsevier in Mayo Clinic Proceedings: Innovations, Quality & Outcomes
- Vol. 4 (1) , 3-7
Open AccessMidwife Laborist Model in a Collaborative Community Practice