Xiao Lab
Ying Xiao, Ph.D.
Professor, Department of Radiation Oncology
Perelman Center for Advanced Medicine
3400 Civic Center Blvd TRC-2
West Philadelphia, PA 19104
Office: 2156152247
Email Ying.Xiao@uphs.upenn.edu
Radiotherapy and Imaging Quality Assurance Services for Clinical Trials
We are an integral component of the Imaging and Radiation Oncology Core (IROC)PhiladelphiaQACenterwith emphasis on radiotherapy. We provide the following quality assurance services:
•Contribute to the development of appropriate quality assurance procedures for advanced medical imaging and radiotherapy.
•Consultation with NCTNgroups during the protocol development process. Assist in developing hypotheses and designing trials that are supported by effective quality assurance programs.
•Conduct and support research on radiotherapy treatment planning.
•Maintain qualification and credentialing standards and assist in ensuring that appropriate protocol-specified radiotherapy and advanced imaging are delivered.
•Maintain and update quality assurance policies and procedures.
•Assist in the submission of data, the review of cases, and the management of pre-and post-review data.
•Participate in the standardization of radiotherapy nomenclature updates.
•Provide dosimetry services for personalized radiopharmaceutical dosimetry, including Radium-223, Lutetium-177, and others.
Directions of Research
Our research focus falls into the following broad categories:
Knowledge-based planning quality research using Varian Rapidplan for both Intensity Modulated Radiotherapy (IMRT)and Intensity Modulated Proton Therapy (IMPT)plans.
Knowledge-based planning makes use of pre-existing clinical knowledge to generate an estimated dose volume histogram based on the anatomy and prescription information of the patient. RapidPlan enables a decrease in variability in the quality of treatment planning and increases patient care efficiency. We develop and train models using NRG clinical trial data and then use the model to evaluate the submitted radiotherapyplan for quality assurance purposes.
Deep Learning based Quantitative Quality Assurance of Structure Delineation
Precision in structure delineationis critical to the quality of radiotherapy. For contour quality assurance, our group investigates a variety of methods. Deep learning-based methods for auto-segmentation of patient structures have demonstrated high accuracy. Our group is currently developing auto-segmentation models for structuresin a variety of disease sites. Quantitative evaluation methodologies of the contour quality using these models are being developed.
Predictive Modeling for Outcome Driven Clinical Guidelines
A prediction model can incorporate features from demographic, diagnostic, dosimetric, and RT modality data. Typically, characteristics such as gender, age, ethnic origin, treatment modality, tumor clinical staging, tumor pathological staging, type of surgery, chemotherapy, and treatment techniques (IMRT/CRT, PBS/Double scattering) are included. Recent research from Radiomics hypothesized that medical imaging provides critical information about tumor physiology and could be used to improve cancer predictions. Along with the clinical characteristics previously mentioned, radiomics characteristics are extracted to model toxicities, overall survival (OS), and local recurrence (LR). Other aspects of Omics are considered, such as genomics and proteomics. Numerous machine learning techniques, such as Cox regression, random survival forest, and deep learning, are investigated. To provide clinical guidance, interpretable machine learning is being explored.
Standardization for AI Implementation
Standardisation plays a crucial, supportive and leading role in artificial intelligence. Clinical trials are the most reliable method of demonstrating the efficacy and safety of a treatment or clinical approach, as well as providing high-level evidence to justify artificial intelligence. Standardisation from NRGOncology (NRG) and the National Cancer Institute’s Clinical Trial Network (NCTN)has the potential to reduce variation in clinical treatment and patient outcome by eliminating potential errors, enabling broader application of artificial intelligence tools. NCTN, NRG and Imaging and Radiation Oncology Core (IROC) are in a unique position to help with standards development, advocacy and enforcement, all of which can benefit from artificial intelligence, as artificial intelligence has the ability to improve trial success rates by transforming crucial phases in clinical trial design, from study planning through to execution.
Voxel Level Dosimetry for Radiopharmaceutial Therapy
Radiopharmaceutical therapy (RPT) involves the systemic or local delivery of a radionuclide with the goal of specifically targeting and delivering radiation to cancer cells while minimizing radiation exposure to untargeted cells. Individual patient radiation doses and their correlation with tumor and normal tissue response to radiation are critical for analyzing the outcome of clinical trials combining RPT and new chemotherapeutic agents. Thus, we aimed to assist IROC in performing and ensuring the quality of personalized radioparmaceuticaldosimetry. Due to the fact that the radionuclideintake can vary between lesions and patients, dosimetry can be used to determine the biodistribution and absorbed dose in each lesion and throughout the body. Additionally, dosimetry will monitor biodistribution, particularly in critical organs.
Current Member
Huaizhi Geng, PhD (Research Associate)
Huaizhi.Geng@Pennmedicine.upenn.edu
(Jan. 2019-current)
Du Wang, MS (Research Assistant)
Du.Wang@Pennmedicine.upenn.edu
(Jan. 2019-current)
Sangho Lee, PhD (Research Associate)
Sangho.Lee@Pennmedicine.upenn.edu
(Dec. 2019-current)
Tawfik Giaddui, PhD (Jan 2015-Feb 2017)
Haoyu Zhong, MS (June 2016-Mar 2019)
Mi Huang, PhD (July 2016-July 2018)
Chingyun Cheng, PhD (Oct 2016-July 2018)
Kuo Men, PhD (July 2017-August 2019)
Nishanth Sasankan, PhD (Oct 2018-Nov 2019)
Chibueze Uche, PhD (Jan. 2019-June 2021)
Tingyu Wang, MS (Nov. 2020- June 2022)