Xiangrong Qi
University of California-Los Angeles, CA·Medicine & Clinical Research
Rectal cancer makes up about a third of colorectal cancers, the second leading cause of cancer death in the U.S. It is increasingly diagnosed in people under 50.
- Fields
Medicine & Clinical Research
Biomedical Engineering
Computer Science
- Topics
rectal cancer
radiation therapy
radiotherapy
- Grants
- 1 known grant, through May 2031
What they work on
- Build an interpretable radiomics pipeline that uses a convolutional neural network to extract features from multi-modal images, with multi-objective feature selection and a model interpreter, to predict rectal cancer response to radiation.
- Develop germline genetic signatures from a panel of microRNA-based inherited biomarkers to predict whether long-course chemoradiation or short-course radiation will produce a complete response in locally advanced rectal cancer.
- Develop tiered fusion models that combine imaging and germline signatures to estimate response likelihood and treatment effects, and derive individualized rules for choosing long-course or short-course radiation.
More about the research
Patients with locally advanced rectal cancer usually receive radiation before surgery, given either as long-course chemoradiation, weeks of radiation combined with chemotherapy, or as short-course radiation followed by chemotherapy. A complete response, in which the tumor disappears, can sometimes let patients skip surgery altogether. But neither option works best for everyone, and doctors have no reliable way to predict which one will work for a given patient.
Why it matters
Radiation therapy is part of treatment for over 60% of cancer patients, yet it is rarely tailored to the individual. A tool that predicts which radiation schedule will give a rectal cancer patient the best response could help doctors and patients choose treatment. It could raise the chance of avoiding surgery, improve outcomes and lengthen survival, while making cost-effective short-course radiation available to those likely to benefit.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Karin Hardiman
University of Alabama at Birmingham, AL·Medicine & Clinical Research
Determine whether the sialic-acid-adding enzyme ST6Gal-1 makes rectal cancer cells resist chemoradiation by inhibiting apoptosis, using cell sorting, sequencing, shRNA knockdown and patient tumor samples.
Xinyi Li
Clemson University, SC·Mathematics & Statistics
Develop interpretable statistical learning methods for single-stage individualized treatment rules that combine medical imaging, genomics and clinical variables, with valid uncertainty quantification and statistical inference.
Hui Lin
University of California-San Francisco, CA·Medicine & Clinical Research
Build White Matter Infiltrative Risk maps by identifying which white matter tracts glioblastoma tends to invade across more than 500 patients and combining them with each patient's DTI fiber density maps.
The school
University of California-Los Angeles: 84 labs on PI Pages, $1.9B a year on research, 803 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.