Jeanne Shen
Stanford University, CA·Medicine & Clinical Research
Colorectal cancer (CRC) is the third most commonly diagnosed cancer and the second leading cause of cancer death worldwide. After surgery, doctors must decide which patients should receive adjuvant therapy, the extra treatment such as chemotherapy given to prevent the cancer from coming back.
- Fields
Medicine & Clinical Research
Computer Science
Biomedical Engineering
- Topics
colorectal cancer
deep learning
machine learning
- Grants
- 1 known grant, through Apr 2028
What they work on
- Build a publicly available, expert-annotated multimodal colorectal cancer dataset. It will combine pathology whole-slide images, preoperative CT and MRI scans, and structured electronic medical record data.
- Develop deep learning models that predict recurrence risk in surgically resectable Stage I-III colorectal cancer patients from each data type alone: pathology, radiology or medical records.
- Test whether multimodal deep learning models that combine pathology, radiology and medical record data outperform single-modality models and current standard risk-stratification methods.
More about the research
Current methods for identifying patients at high risk of recurrence are inadequate. Yet every surgical patient already has tissue slides and medical scans that could hold more predictive information than is now used.
Why it matters
Patients with Stage I-III colorectal cancer could benefit from more accurate predictions of recurrence risk. Better predictions would help doctors give adjuvant therapy to those most likely to benefit and spare others unnecessary treatment. The tools would rely on routine pathology slides, scans and medical records, so they could be widely accessible. The public dataset and models could also support other researchers and be extended to other cancer types.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Hua Li
Washington University in St Louis, MO·Biomedical Engineering
Develop a learning-based prognostic model that predicts cervical cancer treatment response and outcome by integrating RNA biomarkers, radiologic and histologic images, and clinicopathologic data from about 600 patients at two institutions.
Shiaowen Hsu
Duke University, NC·Medicine & Clinical Research
Test whether minimal residual disease cells from colorectal cancer patients that resist standard-of-care chemotherapy are more likely to metastasize and cause recurrence, using MicroOrganoSpheres grown from portal venous blood collected during surgery.
Daniela Raicu
DePaul University, IL·Computer Science
Develop a Semantic Deep-learning Neural Network (SDNN), a deep-learning model enhanced with knowledge of what visual features mean, that generates visual patterns and example images resembling the concepts radiologists use to read lung nodules.
The school
Stanford University: 87 labs on PI Pages, $1.6B a year on research, 739 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.