• Skip to main content
UCI   |  Office of the Provost   |  Academic Initiatives
Donate
logo
  • Home
  • About
    • Mission & Vision
    • Message from the Leadership Team
  • People
    • Directors
    • Executive Advisory Committee Team
    • Staff
  • Events
  • News
  • Research & Innovation
    • Core Areas
    • Publications
  • Education & Services
    • Undergraduates
    • Medical Students
    • Workshops

Core Areas

You are here: Home / Research & Innovation / Core Areas
Stroke

Strokes represent the second most common cause of death worldwide

Neurodegeneration

Spatial patterns can inform disease mechanisms. We can map the patterns of cell states back to the region of the brain.

Oncology

Breast, Prostate, Glioblastoma and Lung Cancers

Stroke

Challenge: Strokes represent the second most common cause of death worldwide

At UCI, we are using artificial intelligence to detect, quantify, and alert clinicians to the  presence of a stroke in real time; providing  precious minutes to treat patients.

phdai

Stroke Collaborators:
Lydia Su, Ph.D. – Professor, Radiology & Physics
Peter Chang, M.D. – Co-Director for Center for AI in Diagnostic Medicine
Daniel Chow, M.D. – Co-Director for Center for AI in Diagnostic Medicine
Wengui Yu, M.D. Ph.D., Director, UCI Comprehensive Stroke & Cerebrovascular Center

https://uci-academic-initiatives.s3-us-west-1.amazonaws.com/MovieofStrokeDetection.mp4
stroke chart

Neurodegeneration

Challenge: People with Dementia

Spatial patterns can inform disease mechanisms

We can map the patterns of cell states back to the region of the brain.

Deep learning can help discover new patterns of cell states and provide new insights into decoding the 3D functional relationships of cells.

patterns of cells
people with dementia

Oncology

Foci: Breast, Prostate, Glioblastoma and Lung Cancers

Breast cancer:

Challenge: 

1 in 8 women will be diagnosed with breast cancer in their lifetime. 1 in 5 breast cancers will be missed by screening mammograms, which are missed opportunities for earlier treatment.  1 in 2 women will be inaccurately labeled with an abnormal mammogram over a 10-year period, which leads to unnecessary tests including invasive surgical biopsies.

We are working on:

  1. Introducing an AI enabled risk-stratified screening  approach that will reduce over-diagnosis while  maintaining the benefits of screening – a step towards personalizing medicine.
  2. Development of AI techniques that can objectively characterize breast tissue  inorder to determine risk.
breast tissue
breast tissue

AI automatically segmenting whole breast fibroglandular tissue, a known risk factor for breast cancer

Prostate cancer:

prostate

Deep learning enabled evaluation of prostate MRI with automated assessment and identification of nodules at risk for cancer.

Challenge: 1 out of 7 men are diagnosed with prostate cancer. Of 1,000 men offered PSA-based screening, 240 get a positive result, which may indicate prostate cancer.  Of those, 100 get a positive biopsy showing definite cancer.  80 choose surgery or radiation treatment.

We are working on:

  1. There is a lack of non-invasive  tools that can differentiate aggressive from non-aggressive  cancer types. As a result, only 1  death is avoided for  every 48 treated men.
  2. There is a lack of tools that  can distinguish patients who would benefit from existing  treatments versus those who would require newer treatment strategies, including targeted therapies

We seek to leverage deep learning with prostate MRIs to optimize detection of high  risk and low risk cancers. If successful, this  tool can be deployed clinically and be used  to guide clinical decision making.

Glioblastoma cancer:

Challenge: Glioblastoma is the most common  and aggressive form of brain cancer. 240,000 people worldwide are diagnosed with GBM annually.  It is the most deadly form of human  cancer with a median survival rate  of 14.6 months

We are working on:

GBMs’ underlying genetic variation between and within patients contributes to its poor prognosis.

  1. We have developed a virtual biopsy application achieved diagnostic accuracy of  94%, identifying relevant genetic mutations.
  2. Quantitative imaging assessment: our AI application  development portfolio includes  tools for series identification and an award-winning application for fully automated  brain tumor segmentation.
gliobastoma

We plan to develop a state-of-the-art deep learning approach  to answer these questions:

Can deep learning accurately identify unique GBM subtypes that  may have different sensitivities and resistances to therapy?

Can survival in GBM patients be predicted by integrating both  imaging and genomic data?

Can we describe the underlying genetic variation within GBMs by leveraging surgical sampling from  multiple regions within a tumor?

Contact us

UCI Calit2 Building
4100 E. Peltason Drive, Suite 4500
Irvine, CA 92617

healthai@uci.edu

About Us

UCI Precision Health through Artificial Intelligence Initiative aims to improve health by harnessing innovative data driven technologies, including AI.

© 2023 UC Regents.  Privacy Policy