Important Info
If interested, please email (Dr. Ahmed El Kaffas) elkaffas@stanford.edu
Translational Postdoctoral Scholar for Advancing Multi-Parametric 3D Tissue Characterization, Contrast Ultrasound Visualization and Quantification in the Clinic
We are increasing ultrasound’s clinical impact as a bedside, inexpensive, radiation free and non-invasive imaging modality. To do so, we are introducing new state-of-the-art imaging technologies for targeted molecular ultrasound imaging and developing quantitative and machine learning approaches to mine unique ultrasound signals to answer pertinent clinical questions. Special emphasis is put on imaging cancer including liver, pancreatic, renal, and prostate cancer, as well liver diseases such as fibrosis, steatosis and inflammation. Our mission is to integrate novel tissue characterization imaging strategies with ultrasound into multi-modal clinical protocols for improved patient management and care.
We are seeking candidates interested in clinical and translational imaging (including direct involvement in clinical studies), machine learning, ultrasound image processing and quantification methods; candidates will be supported by several NIH grants in the Translational Ultrasound Lab @ Stanford. This is an opportunity to be exposed to clinical studies/the regulatory process, data analysis, algorithm development, validation of medical imaging biomarkers, grant writing/NIH. Candidates will have the opportunity to work directly with clinicians and researchers in gathering data, as well as team members across several labs that include clinician/scientist in radiology, urology and GI/hepatology to explore image quantification methodologies in the context of ultrasound, and experimental work to validate these parameters.
- PhD and/or MD in a relevant field with demonstrated ability to work independently.
- Previous Python experience, specifically in the context of image processing, and/or use of ultrasound in the clinic, is necessary.
Having at least one of the following would be useful:
- Machine learning, deep learning and statistical modelling
- Quantitative ultrasound methods (i.e. speckle methods, spectroscopy methods, and others)
- Interest in being exposed to clinical ultrasound imaging work, including working with fellows and a clinical team to support data collection and patient recruitment
- Experience with bash scripting, and working with NIFTI data and associated toolboxes
- Tensorflow, ITK, Pytorch, MevisLab, Matlab, C/C++
- Trace field modelling from any imaging modality
- General experience with mathematical modelling
- Open CV or other programming languages for image processing
- Ultrasound research and/or imaging; direct clinical sonography experience
- An updated CV
- Complete contact information for three references
- Cover letter describing past research experience, career goals and future research interests