Ai Metrics, LLC
AI Metrics is a radiology software company founded by Dr. Andrew Smith, MD, PhD, with a mission to help radiologists deliver faster, more accurate evaluations of cancer patients through AI-enabled solutions. The company focuses on improving workflows, reporting, and diagnostic accuracy in radiology, particularly in cancer imaging, to reduce radiologist burnout and enhance patient care.
Industries
Nr. of Employees
small (1-50)
Patents
Computer-assisted tumor response assessment and evaluation of the vascular tumor burden
US-11350900-B2
View DetailsComputer-assisted tumor response assessment and evaluation of the vascular tumor burden
US-10743829-B2
View DetailsComputer-assisted tumor response assessment and evaluation of the vascular tumor burden
US-10413266-B2
View DetailsMethod for standardizing target lesion selection and tracking on medical images
US-10219768-B2
View DetailsMethods for color enhanced detection of bone density from CT images and methods for opportunistic screening using same
US-10169851-B2
View DetailsComputer-assisted tumor response assessment and evaluation of the vascular tumor burden
US-9931093-B2
View Details
Computer-assisted tumor response assessment and evaluation of the vascular tumor burden
US-11350900-B2
View DetailsComputer-assisted tumor response assessment and evaluation of the vascular tumor burden
US-10743829-B2
View DetailsComputer-assisted tumor response assessment and evaluation of the vascular tumor burden
US-10413266-B2
View DetailsMethod for standardizing target lesion selection and tracking on medical images
US-10219768-B2
View DetailsMethods for color enhanced detection of bone density from CT images and methods for opportunistic screening using same
US-10169851-B2
View DetailsComputer-assisted tumor response assessment and evaluation of the vascular tumor burden
US-9931093-B2
View DetailsProducts
Cancer imaging analysis software platform
A cloud-capable imaging analysis platform for advanced cancer reads that combines guided workflows, automated tumor detection/measurement, longitudinal response analytics (RECIST), and automated visual reports to accelerate and standardize oncology imaging interpretation.
CT-derived liver surface nodularity biomarker module
A CT-based digital biomarker implementation that quantifies liver surface nodularity to aid staging of liver fibrosis and prediction of liver-related events from routine CT exams.
Cancer imaging analysis software platform
A cloud-capable imaging analysis platform for advanced cancer reads that combines guided workflows, automated tumor detection/measurement, longitudinal response analytics (RECIST), and automated visual reports to accelerate and standardize oncology imaging interpretation.
CT-derived liver surface nodularity biomarker module
A CT-based digital biomarker implementation that quantifies liver surface nodularity to aid staging of liver fibrosis and prediction of liver-related events from routine CT exams.
Services
Secure cloud deployment and technical integration with existing PACS, RIS, and EMR systems; supports Active Directory authentication and contextual image display on existing viewers. Includes collaboration with site IT teams to enable installation and integration.
Partnerships and participation in multi-institutional comparative-effectiveness studies and clinical research to validate performance metrics such as read time, accuracy, error reduction, and inter-observer agreement.
Implementation of automated visualized reporting into clinical workflows and training for radiologists on guided review processes that reduce manual reporting burden and standardize outputs for oncologists.
Secure cloud deployment and technical integration with existing PACS, RIS, and EMR systems; supports Active Directory authentication and contextual image display on existing viewers. Includes collaboration with site IT teams to enable installation and integration.
Partnerships and participation in multi-institutional comparative-effectiveness studies and clinical research to validate performance metrics such as read time, accuracy, error reduction, and inter-observer agreement.
Implementation of automated visualized reporting into clinical workflows and training for radiologists on guided review processes that reduce manual reporting burden and standardize outputs for oncologists.
Expertise Areas
- Oncologic imaging workflow automation
- Clinical validation and comparative-effectiveness studies
- Digital biomarker development for CT
- Medical imaging AI model development
Key Technologies
- Deep learning for medical imaging
- Automated lesion detection and measurement
- Longitudinal imaging analytics
- RECIST 1.1 computational implementation
News & Updates
AI Metrics' research on liver fibrosis detection was awarded the 'Best of AJR' in the Gastrointestinal Imaging section for 2022.
The company raised $1.26MM in a bridge financing round to accelerate R&D for its AI-enabled cancer imaging technology.
AI Metrics' software consistently delivers cancer imaging reads in half the time, helping reduce radiologist workload and burnout.
Discussion on how AI solutions have gained acceptance in clinical settings, especially in CT imaging, and the importance of trust and clinical impact.
Insights on how AI can provide higher quality, standardized reports, and address challenges like limited expertise, complex reads, and communication barriers.
Research on liver fibrosis detection awarded in the Gastrointestinal Imaging section by the American Journal of Roentgenology.
AI Metrics' research on liver fibrosis detection was awarded the 'Best of AJR' in the Gastrointestinal Imaging section for 2022.
The company raised $1.26MM in a bridge financing round to accelerate R&D for its AI-enabled cancer imaging technology.
AI Metrics' software consistently delivers cancer imaging reads in half the time, helping reduce radiologist workload and burnout.
Discussion on how AI solutions have gained acceptance in clinical settings, especially in CT imaging, and the importance of trust and clinical impact.
Insights on how AI can provide higher quality, standardized reports, and address challenges like limited expertise, complex reads, and communication barriers.
Research on liver fibrosis detection awarded in the Gastrointestinal Imaging section by the American Journal of Roentgenology.