Surgivance Inc.

Rapid 3D Poc Digital Cancer Pathology by Unique Confocal Microscopy Instrumentation and Downstream Ai: a Simple, Efficient, Robust Direct-to-digital Approach to Meet Market Demand - Abstract Surgivance Is Developing a Digital Pathology “laboratory-in-a-box” That Produces and Analyzes High-resolution, 3D, Digital Pathology Images at a Patient’s Bedside Within Seconds. This Solution Combines Rapid Confocal Imaging Hardware With Artificial Intelligence (ai)-enabled Software That Automatically Recolorizes and Interprets the Digital Pathology Images, Enabling Highly Accurate and Reproducible Detection of Skin Cancer and Prediction of Outcomes. Over 7.1 Million Cases of Skin Cancer Are Diagnosed Annually in the Us Including Approximately 5.4 Million Cases of Basal and Squamous Cell Carcinomas (bcc/scc). Standard Skin Cancer Pathology Has Several Major Pain Points Including Lengthy Preanalytical Processing Times That Extend Procedure Duration and Limits Efficiency, the Need for Expensive, Bulky Equipment, and Complications From Image Artifacts Like Tissue Folding and Chopping. Ultimately, Histopathology Is the Rate-limiting Factor During Curative Skin Cancer Surgery, Causing Pain and Surgical Complications. This Increases the Cost-care Burden on the Heath System and Negatively Impacts Patient Outcomes. Surgivance’s Solution Will Provide Rapid, High-resolution, 3D Images and Automated Interpretation at the Point of Care, Improving Upon Current Tissue Specimen Processing and Imaging for Skin Cancer Removal, Enabling Electronic Medical Reading, and Reducing Operating Times. the Enabling Technology Is a Patented, Miniature, Rugged, Simpler Confocal Microscope, Integrated With Proprietary, Ai-enabled Interpretation Software. the Goal of This Direct to Phase Ii Project Is to Further Develop the Software Component to Improve the Detection of BCC, Expand Detection to SCC, and Provide Additional Clinical Validation of the Software. the Specific Aims Are: 1) Image Acquisition and Ai Algorithm Refinement. an Expanded Image Database of BCC and SCC Specimens Will Be Created for Further Algorithm Development and Training. the Ai Algorithms Will Then Be Refined for High Accuracy Detection of BCC and SCC; 2) Ai Algorithm Development for Prediction of Poor Outcome-associated Gene Expression. Using QPCR Data on Genes Linked to Poor Patient Outcomes, Surgivance Will Develop Algorithms for Predicting Gene Expression From Digital Pathology Alone; and 3) Clinical Validation and Usability Testing. Surgivance’s Software Will Be Evaluated in a Multicenter Study by Clinical Collaborators at Oregon Health and Science University, Northwell Health, and New York University, Who Will Confirm Clinical Performance Using Provided Sample Raw Confocal Images as Well as Confocal Images of Their Own and Offer Valuable Usability Feedback.