SUMMARY
The research interests of Zeynettin (Z) Akkus, Ph.D., include quantitative imaging, artificial intelligence (AI) in medical and cancer imaging, digital pathology, cardiovascular imaging, and cardiovascular and neurological diseases.
Dr. Akkus develops quantitative imaging tools for diagnostic, prognostic and therapeutic purposes. He pursues imaging informatics research using AI for improving cardiology, radiology and pathology clinical workflows.
Focus areas
- Deep learning for medical images. Dr. Akkus has been working on developing deep learning tools for diagnosis, prognosis, and treatment response of cardiovascular, neurological, nephrological, pathological and endocrine diseases from medical images. He also works to standardize clinical measurements and improve clinical workflow.
- AI-empowered cardiac ultrasound (echocardiography). This work involves developing end-to-end AI-empowered echocardiography framework for image interpretation and providing a structured echocardiograph-AI report for clinic labs.
- Point-of-care ultrasound (POCUS) and wearable devices. Dr. Akkus is empowering POCUS with AI to provide preliminary diagnoses in emergency departments for triaging patients.
- Digital pathology. Dr. Akkus is building a digital pathology informatics framework using AI to provide solutions for processing large-size digital pathology images for disease diagnosis and prognosis.
Significance to patient care
The focus of Dr. Akkus' research is to perform data-intensive tasks in an organized and efficient fashion and provide structured reports for aiding physicians in clinical decision-making.
There is no doubt that imaging provides valuable insight into the pathophysiology of diseases and their response to therapy. As 3D and 4D imaging becomes routine, and with physiological and functional imaging increasing, medical imaging data is increasing in size and complexity. In addition to this, electronic health record (EHR) data contains patients' clinical history and laboratory data that enables physicians to interpret imaging findings in the appropriate clinical context, leading to a higher diagnostic accuracy, informative clinical decision-making and improved patient outcomes.
Professional highlights
- Innovation Award, “Rapid On-Site Evaluation of Endobronchial Ultrasound-Guided TBNA Specimens Using Artificial Intelligence,” Mayo Clinic Department of Laboratory Medicine and Pathology, 2022
- Member, Network of Digital Health Experts (NoDEx), U.S. Food and Drug Administration, 2020-present
- Invited associate editor, Medical Physics, 2018-present
- Associate editor, Journal of Medical Imaging and Health Informatics, 2017-present
- Early-career professional member, Medical Imaging, SPIE, 2017-present
- Member, Society for Imaging Informatics in Medicine, 2016-present
- Marie Ingalls Cardiovascular Research Career Development Award, Center for Clinical and Translational Science, Mayo Clinic, 2021-2024
- Recipient, Most downloaded paper award, "Deep learning for brain MRI segmentation: State of the Art and Future Directions," Journal of Digital Imaging, 2017
- Awarded $50K, Global Impact Award on Artificial Intelligence in Healthcare, NVIDIA, 2017
- Recipient, Outstanding Reviewer Award, The Journal of Ultrasonics, Elsevier, 2015
- Recipient, Best Student Paper Competition Award, IEEE Ultrasonics Symposium, Prague, 2013