Mindpeak Breast Ki-67

0-click whole-slide analysis of every tumor cell. When a compatible Ki-67 image is opened, analysis runs automatically across the entire slide—no region drawing, no manual counting. The algorithm locates invasive tumor, classifies every tumor cell as Ki-67-positive or Ki-67-negative, and returns a color-coded overlay within seconds. Manual Ki-67 assessment depends heavily on which cells a researcher chooses to count and where those cells are located, and that choice is the single best-documented source of variability in Ki-67 scoring. Complete coverage removes this variability because the score reflects the whole slide rather than a selected field. Every classified cell is displayed, allowing the reported index to be traced back to the cells that produced it, and the overlay also serves as the audit trail. Every tissue fragment on the slide is included, so a quiescent area weighs on the index exactly as a proliferative one does.

Region-level interrogation of the whole slide images. The 0-click analysis covers the whole slide output, but the output is not locked to it. Using the standard annotation tools, subregions can be drawn on top of the completed analysis and scored individually, each returning its own proliferation score and its own positive and negative cell counts. This supports two capabilities that whole slide scoring alone cannot provide. Tissue can be excluded from consideration, such as a second core, a poorly fixed fragment, crush artifact, or an area the researcher assesses as unrepresentative. Proliferation can also be compared between regions, making intratumoral heterogeneity measurable rather than impressionistic. Region analyses sit alongside the whole slide analysis rather than replacing it, so both remain available, each with the count behind it.

The proliferation index is computed as the proportion of Ki-67-positive tumor cells across an exhaustive count of every tumor cell on the slide. By contrast, manual practice employs a visual estimate over a limited number of cells, which is why the same slide can yield materially different indices in different hands, and why Ki-67 has been one of the least reproducible measurements. Counting every cell the same way each time turns the index from an interpretation into a calculation, and the full count stays visible rather than disappearing into a single figure.

Tumor cells only, so the index is not diluted. Ki-67 marks proliferating cells of any lineage, and lymphocytes, stromal cells, and other non-tumor cells in the tumor bed are frequently positive. Mindpeak Breast Ki-67 first identifies invasive tumor tissue and then classifies only those cells as Ki-67-positive or Ki-67-negative, so the index is derived from the tumor population alone rather than from all Ki 67 stained cells present on the slide. Samples with a dense inflammatory infiltrate are most susceptible to overestimation with visual estimation. Because every classified cell is displayed as an overlay on the tissue, a researcher can see precisely which population was counted and confirm that the boundary has been drawn where they would have placed it.

A transparent score, on your scanner and your stainer. Results are returned as a proliferation score together with the positive and negative tumor cell counts used to generate it, providing visibility into the basis of the analysis, rather than relying on an implied result. Individual markup classes can be displayed or hidden while reviewing, allowing the researcher to inspect positive or negative cell populations independently before accepting the analysis. The application was evaluated across six whole slide scanners and a microscope camera, with the analysis shown to be consistent across scanner, staining system, reagent, and operator.