Education & Training
Medical Imaging System Providing Disease Prognosis
WARF: P150022US02
Inventors: Vikas Singh, Vamsi Ithapu, Sterling Johnson, Ozioma Okonkwo
The Invention
Recent Alzheimer’s Disease (AD) clinical trials have faced challenges at the mild-to-moderate dementia stage. There’s consensus that trials should focus on AD stage, such as MCI or the presymptomatic stage. However, the heterogeneous nature of MCI makes it difficult to identify probably beneficiaries of treatment.
To address this, a multimodal imaging marker combines [F-18] fluorodeoxyglucose PET, amyloid frobetapir PET, and structural MRI with a deep learning algorithm for a trial enrichment criterion. It reduces sample estimates and leads to smaller trials with high statistical power compared to existing methods.
To address this, a multimodal imaging marker combines [F-18] fluorodeoxyglucose PET, amyloid frobetapir PET, and structural MRI with a deep learning algorithm for a trial enrichment criterion. It reduces sample estimates and leads to smaller trials with high statistical power compared to existing methods.
Applications
- Select MCIs likely to decline, improving trial efficiency
- Identifies patients who benefit most from treatment
- Tailors treatment to individual profiles
Key Benefits
- Fewer participants needed for trials
- Increased likelihood of detecting treatment effects
- Promising approach to personalized care
Stage of Development
In a study focused on evaluating the effectiveness of deep learning in predicting cognitive decline and neural changes in individuals with mild cognitive impairment (MCI) related to Alzheimer’s disease (AD), the algorithm was applied to PET and MRI imaging data. Results showed that the algorithm successfully identified low-risk subjects who were less likely to experience significant cognitive decline. By excluding these low-risk individuals, the study reduced the sample size needed for clinical trials.
Additional Information
For More Information About the Inventors
Tech Fields
For current licensing status, please contact Jeanine Burmania at [javascript protected email address] or 608-960-9846