Postdoc Fellow — AI Radiomics for Early Pancreatic Cancer

Johns Hopkins University; Baltimore (MD); On-site; USD 57,000 - 70,000; Full time

Benefits offered by this job

Competitive salary

Vacation

Excellent benefits

Job summary

The Johns Hopkins University School of Medicine, Department of Radiology, seeks a full-time post-doctoral research fellow to join the FELIX 2.0 laboratory in Baltimore, MD, focusing on radiomics and deep learning from contrast-enhanced CT images to improve early pancreatic cancer detection.

The successful candidate will work with large clinical datasets, compare machine-learning approaches, validate models prospectively, coordinate expert interpretation, and contribute to manuscript preparation

Qualifications

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

Responsibilities

• Data Curation: Collect and organize datasets with clinical information to support studies.
• Radiomics Pipeline Development: Design and optimize radiomics pipelines for CT image characterization.
• Machine and Deep learning: Develop and implement ML/DL algorithms for detection and prediction on CT images.
• Performance Evaluation: Statistically benchmark diverse approaches.
• Model Assessment and Deployment: Evaluate model limitations and deploy improvements for generalizability.
• Communication and Reporting: Prepare reports and present findings to PI.
• Manuscript Preparation: Author research manuscripts for publication.

Skills

Python

C++

R

MATLAB

Deep learning

Statistics

Scientific writing

Medical imaging

Education

Master or Ph.D. in computer science, biomedical engineering, or related field

Job description

The Johns Hopkins University School of Medicine, Department of Radiology, seeks a full-time post-doctoral research fellow to join the FELIX 2.0 laboratory in Baltimore, MD, focusing on radiomics and deep learning from contrast-enhanced CT images to improve early pancreatic cancer detection.

The successful candidate will work with large clinical datasets, compare machine-learning approaches, validate models prospectively, coordinate expert interpretation, and contribute to manuscript preparation