Postdoctoral Fellow - Interventional Radiology Research

University of Texas MD Anderson Cancer Center; Houston (TX); On-site; USD 64,000 - 76,000; Full time

Job summary

MD Anderson Cancer Center in Houston is seeking a postdoctoral fellow in the Department of Interventional Radiology, led by Iwan Paolucci, PhD, to advance machine learning and reinforcement learning for sequential medical decision making in adaptive imaging and treatment optimization.

The fellow will work with researchers and clinicians, publish findings, present at seminars and conferences, and contribute to ongoing projects across AI, imaging, and oncology using ML, RL, and Markov decision

Qualifications

• Ph.D. in natural sciences, computer sciences, data science, applied mathematics, engineering, or related field.
• Experience with ML, RL, deep learning, medical image analysis, or computational modeling preferred.
• Strong communication and collaboration with clinical and research partners.

Responsibilities

• Design and implement RL algorithms for sequential medical decision-making in imaging and treatment planning.
• Collaborate with clinical and research teams; present findings in reports and publications.
• Translate research into reproducible methods and contribute to seminars and conferences.

Skills

Reinforcement learning

Medical imaging

Machine learning

Sequential decision making

Job description

Artificial Intelligence, Reinforcement Learning, Medical decision making, image analysis

A postdoctoral fellowship position is available in the Department of Interventional Radiology in the laboratory of Iwan Paolucci, PhD in machine learning and reinforcement learning for sequential medical decision making.

This postdoctoral fellow will engage in highly productive interdisciplinary research projects at the intersection of artificial intelligence, medical imaging, and oncology. The fellow will expand their knowledge and skills in machine learning, reinforcement learning, and Markov decision processes, applying these methods for sequential decision-making problems in adaptive imaging and treatment optimization. The fellow will have opportunities to contribute to ongoing research projects and will be encouraged to explore and develop new areas of research interest with guidance from the mentor. The fellow will be expected to work closely with research and clinical collaborators, communicate findings via reports, abstracts, presentations, and publications, and actively participate in seminars, conferences, and related academic endeavors.

Dr. Paolucci is a Biomedical Engineer with a Computer Science background, and his research interests focus includes artificial intelligence and stereotactic and robotic image-guidance for the treatment of hepatobiliary malignancies with a strong focus on thermal ablation of primary and secondary malignant liver tumors. In his research he develops and evaluates algorithms for various aspects of the procedures from patient selection to planning all the way to post-procedure follow-up assessment. Another major focus is on the prediction of oncologic outcome trajectories following loco-regional treatments and treatment recommendation systems using clinical information, imaging and genomics. Applied techniques range from traditional machine learning to deep learning and Bayesian modelling approaches.

All duties and responsibilities are carried out in compliance with institutional policies, ethical research standards, and applicable federal and state regulations.

LEARNING OBJECTIVES

• Design, implement, and validate reinforcement learning algorithms for sequential decision-making applications, such as adaptive imaging protocols or treatment planning optimization.
• Develop proficiency in formulating medical decision-making problems as Markov decision processes, including defining state spaces, action spaces, and reward functions appropriate to clinical decision-making tasks.
• Apply core machine learning methods to medical imaging data, including model training, validation, and performance evaluation using clinically relevant metrics.
• Translate research findings into scientific communication, including manuscripts, conference presentations, and grant proposals, while collaborating with clinical and research partners across the institution.

ELIGIBILITY REQUIREMENTS

Applicants should hold a Ph.D. in one of the natural sciences, computer sciences, data science, applied mathematics, engineering, or related fields. Experience with machine learning, reinforcement learning, Markov decision processed, deep learning techniques, medical image analysis, or computational modeling is preferred.

ADDITIONAL APPLICATION INFORMATION

Offsite work arrangements are subject to approval and may be modified or revoked at any time based on business needs, performance considerations, or regulatory requirements.

POSITION INFORMATION

MD Anderson offers full-time postdoc positions with a salary ranging from $64,000 to $76,000. depending on the number of years of postgraduate experience. The University of Texas MD Anderson Cancer Center offers excellent benefits, including medical, dental, paid time off, retirement, tuition benefits, educational opportunities, and individual and team recognition

Offsite work arrangements are subject to approval and may be modified or revoked at any time based on business needs, performance considerations, or regulatory requirements.

This position may be responsible for maintaining the security and integrity of critical infrastructure, as defined in Section 113.001(2) of the Texas Business and Commerce Code and therefore may require routine reviews and screening. The ability to satisfy and maintain all requirements necessary to ensure the continued security and integrity of such infrastructure is a condition of hire and continued employment.

It is the policy of The University of Texas MD Anderson Cancer Center to provide equal employment opportunity without regard to race, color, religion, age, national origin, sex, gender, sexual orientation, gender identity/expression, disability, protected veteran status, genetic information, or any other basis protected by institutional policy or by federal, state or local laws unless such distinction is required by law.