Breast Cancer, Margin Assessment
Conditions
Brief summary
This analytical performance study aims to validate the SPCTRone system for use in breast conserving surgery of breast cancer patients. By collecting spectral biomarkers and correlating these with the golden standard of histopathological assessment by a pathologist, we aim to train and optimize an AI model that is able to achieve the following outcomes with classifying tissues: * Sensitivity (percentage of classified positive margins of actual positive margins): ≥ 96% CI 95.5-97.5% * Specificity (percentage of classified free margins of actual free margins): 96% CI 95.5-97.5% * Accuracy (total correctly classified margins): ≥ 96% CI 95.5-97.5% * Negative predictive value (amount of true negative - free margins - among the classified negative margins): ≥ 95% CI 94.5-96.5%
Interventions
None listed
Sponsors
Study design
Eligibility
Inclusion criteria
* Age ≥18 years * Confirmed diagnosis breast cancer for which surgical procedure is needed * Planned for breast conserving surgery
Exclusion criteria
* Person that undergoes breast amputation without confirmed cancer diagnosis
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Diagnostic performance of SPCTRone system to assess margin status of breast cancer specimens | Through study completion, an average of 6 months | Diagnostic performance indicators are: Sensitivity, Specificity, Negative Predictive Value, and Accuracy. |
Countries
Netherlands