Data Scientist (Quarles) / Cancer Systems Imaging

MISSION STATEMENT


The mission of The University of Texas M. D. Anderson Cancer Center is to eliminate cancer in Texas, the nation, and the world through outstanding programs that integrate patient care, research and prevention, and through education for undergraduate and graduate students, trainees, professionals, employees and the public.



SUMMARY



The Cancer Systems Imaging lab led by Dr. Chad Quarles is seeking a highly motivated Data Scientist to support research in quantitative imaging and computational modeling for cancer detection, diagnosis, and treatment response assessment. The successful candidate will contribute to the development of novel algorithms, software tools, and pipelines for analyzing high-dimensional imaging and multi-omics data, supporting both translational and clinical research initiatives. This role will directly impact precision oncology projects by generating actionable insights from complex datasets.

 



Ideal Candidate:

The ideal candidate will have experience in designing, optimizing, and programming novel pulse sequences and image reconstruction algorithms (for clinical MRI systems) for neuro (brain and spine) and cancer (e.g., renal, head and neck, breast, prostate) imaging. We are particularly interested in expertise related to multi-contrast, quantitative physiologic and/or metabolic imaging, and high temporal and spatial resolution imaging.

JOB SPECIFIC COMPETENCIES



Algorithm Development for Quantitative Imaging:  

Design, implement, and optimize novel algorithms for the quantitative analysis of medical imaging data such as MRI, PET, and CT scans. Employ advanced techniques including signal processing, statistical modeling, and AI/ML to extract imaging biomarkers associated with tumor biology, disease progression, and therapeutic response. Collaborate with domain experts to refine algorithmic outputs for translational and clinical applications.

 

Multimodal Data Integration and Analysis: 

Analyze and integrate high-dimensional datasets from various sources including radiologic imaging, genomics, transcriptomics, pathology, and clinical metadata. Develop standardized and reproducible pipelines to preprocess, harmonize, and combine datasets. Apply statistical and computational methods to identify meaningful patterns and correlations across data modalities that inform hypotheses and clinical strategies.

 

Software Tool Development and Maintenance:  

Develop, test, and maintain customized software tools and pipelines that support automated and interactive image analysis workflows. Build user-friendly applications and command-line tools for tasks such as image segmentation, radiomics feature extraction, data annotation, and batch processing. Ensure that tools are robust, scalable, and adaptable for use in ongoing and future projects.

 

Deep Learning and Machine Learning Applications:  

Apply deep learning (e.g., CNNs, autoencoders) and traditional machine learning methods (e.g., SVM, random forest, gradient boosting) to build predictive and classification models using imaging and other biomedical data. Perform model training, evaluation, hyperparameter tuning, and interpretability analysis. Ensure reproducibility through standardized pipelines and collaborative model development practices.

 

Image Processing and Visualization:  

Implement image preprocessing steps including normalization, denoising, spatial registration, and segmentation of regions of interest. Generate high-quality static and interactive visualizations (e.g., heatmaps, overlays, 3D renderings) to communicate findings and highlight patterns in imaging or multimodal datasets. Work with scientific and clinical collaborators to design visual outputs that aid interpretation and decision-making.

 

Collaboration with Scientific and Clinical Teams:  

Work in close collaboration with imaging scientists, oncologists, radiologists, and researchers to understand scientific goals and tailor computational strategies accordingly. Participate in multidisciplinary team meetings, contribute to experimental design, and provide analytical input. Assist in translating computational results into insights suitable for manuscripts, grants, and clinical applications.

 

Documentation and Reporting:  

Maintain comprehensive and well-organized documentation for all analytical pipelines, codebases, and research outputs. Prepare clear data summaries, methods descriptions, and technical figures for inclusion in manuscripts, presentations, and lab reports. Contribute to code repositories with version-controlled updates and standardized usage instructions.

 

Data Management and Infrastructure Support:  

Support data organization and management across the lab’s imaging and biomedical datasets. Assist in configuring storage solutions and computation infrastructure (e.g., cloud platforms, high-performance computing clusters). Ensure compliance with data privacy and security protocols and institutional policies governing patient data and research integrity.

 

Quality Assurance and Reproducibility:  

Implement quality control processes for data inputs, model outputs, and system performance. Use reproducibility tools such as Git for code versioning, Conda or Docker for environment management, and workflow automation tools like Snakemake or Nextflow. Validate reproducibility across different datasets and analysis scenarios.

 

Professional Development and Training:  

Engage in ongoing learning and skill development in computational imaging, AI/ML, and biomedical informatics. Attend conferences, seminars, and training workshops. Mentor lab members and provide informal or formal training sessions on relevant computational tools, programming practices, and data analysis strategies.

 

Other duties as assigned