This talk will discuss the role, effect, and quality of informatics in publicly funded research, from selection of proposals for funding to execution and sustainment. The case will be made that many current funding mechanisms are mismatched to the scope, needs, and impact of informatics research by comparing and contrasting informatics projects with traditional experimental R&D proposals. Causes for poor quality informatics projects will be enumerated and suggestions given to address them.
Definite diagnosis of cancer presence or recurrence is currently only possible via invasive biopsy or surgical intervention. Unfortunately, invasive biopsy, (a) in many cases is unnecessary due to absence of the disease, (b) have sampling errors depending on where the tissue sample is acquired from, and (c) could have irreparable and life-threatening side effects including mortality. Recently, artificial intelligence and radiomics have shown tremendous promise in leveraging imaging to non-invasively capture the landscape of tissue heterogeneity, previously not feasible by visual inspection. Similarly, one would leverage -omics and pathology information in conjunction with routine imaging to establish cross-scale associations towards designing more optimized personalized treatment options for cancer treatment.
In this talk, I will focus on my lab’s recent efforts in developing radiomic (extracting computerized sub-visual features from radiologic imaging), radio-genomic (identifying radiologic features associated with molecular phenotypes), and radio-pathomic (radiologic features associated with pathologic phenotypes) techniques to capture insights into the underlying tumor biology as observed on non-invasive routine imaging. I will focus on clinical applications of this work for predicting disease outcome, recurrence, progression and response to therapy specifically in the context of brain tumors. I will also discuss our current efforts in developing new radiomic features for post-treatment evaluation and predicting response to chemo-radiation treatment. I will conclude with a discussion on our recent findings in AI + experts, in the context of a clinically challenging problem of distinguishing benign radiation effects from tumor recurrence on routine MRI scans.
This special 90-minute session of the CBIIT Speaker Series will feature demos of three tools that were developed through funding by the Informatics Technology for Cancer Research (ITCR) Program.
- Jim Robinson from UCSD and Helga Thorvaldsdottir from the Broad Institute will present the Integrative Genomics Viewer
- Mary Goldman from UC Santa Cruz will present the Xena Functional Genomics Browser
- Alexander Krasnitz from Cold Spring Harbor Lab will present the Single Cell Genome Viewer
Cancer patients and their doctors choose from a range of different treatment options. But often the chosen treatment is ineffective, reducing quality and length of life and increasing cost. Today treatment decisions and outcomes occur in isolation. All4Cure has built a patient-centered, web-based, knowledge sharing platform that graphically portrays treatments and responses extracted from the medical records of de-identified patients with multiple myeloma (the second most common form of blood cancer) for comment by a community of participating patients, clinicians and researchers. Having assembled more than 580 participants we will describe examples of patients have benefited from their participation.