Research Fellow – Diagnostic Imaging Felix Lab Full-time

Research Fellow – Diagnostic Imaging Felix Lab

The Johns Hopkins University School of Medicine Department of Radiology in the Russell H. Morgan Department of Radiology and Radiological Science in Baltimore, MD is seeking a post-doc research fellow to be hired in the FELIX 2.0 laboratory. This is a full time, post-doc position. We offer a competitive salary, vacation and excellent benefits.

The FELIX 2.0 laboratory aims to change the trajectory of how pancreatic cancer is detected, how patients are evaluated, and improve outcomes. Its mission is to harness the power of artificial intelligence, help radiologists and clinicians in detecting pancreatic cancer when it could have otherwise been missed. This is an innovative way of approaching what has been a challenge for many decades. Between Johns Hopkins Medicine, the Lustgarten Foundation, and Microsoft AI for Good, the FELIX 2.0 laboratory is pooling vast resources to improve how we do things, especially considering recent advancements in AI technology.

The position will include developing radiomics and deep learning models from contrast-enhanced computed tomography images to improve the early detection of pancreatic tumors and improve patient management. Different machine-learning approaches will be compared, and models validated on data prospectively collected. The position will include working with internal and external databases. The candidate will contribute to coordinating expert interpretation and manuscript writing under supervision.

Specific duties/responsibilities include:

• Data curation: Collect and organize datasets along with relevant clinical information to support and drive research studies
• Radiomics pipeline development: Design and optimize robust radiomics pipelines for characterization of CT images.
• Machine and deep learning: Develop and implement machine learning and deep learning algorithms to built detection and prediction models for CT images
• Performance evaluation: Conduct rigorous statistical analyses to benchmark and compare the performance of diverse approaches.
• Model assessment and deployment: Evaluate model limitations and implement new approaches for deploying models, enhancing their generalizability and real-world applicability.
• Communication and reporting: Prepare reports and study findings to present to PI.
• Manuscript preparation: Author high-quality research manuscripts for publication in peer-reviewed journals.

Special knowledge, skills & abilities include:

• Proficiency in programming language such as Python, C++, R and MATLAB.
• Strong theoretical understanding and practical experience in deep learning-based machine learning or natural language processing.
• Strong background in statistical modeling.
• Strong scientific writing skills.
• Expertise in medical imaging processing or previous work in collaboration with healthcare professionals will be a plus.

Qualifications:

• Master or Ph.D. in computer science, biomedical engineering, or a related field.
• One year of experience with machine leaning, deep learning and data analysis.