AI quantification of HER2-low and HER2-ultralow
Pathologists disagree about faint HER2 staining, yet that decision unlocks Enhertu. Let a validated algorithm do the counting.
Concordance for HER2 0 vs 1+ is poor (~25-50% agreement in some studies). AI-assisted scoring improves reproducibility and can quantify membrane staining continuously rather than in bins.
Pages like this
not linked directly; found by shared links- TrialDESTINY-Breast04
Shares HER2-low scoring → T-DXd, Calibrated reference slides so every lab scores HER2-low the same way, HER2-low and HER2-ultralow, Trastuzumab deruxtecan.
- TrialDESTINY-Breast06
Shares HER2-low scoring → T-DXd, Calibrated reference slides so every lab scores HER2-low the same way, HER2-low and HER2-ultralow, Trastuzumab deruxtecan.
- CompanyPathAI
Shares A standard evaluation pathway for AI-assisted pathology, from reader study to deployment, Version control and locked reference sets for AI algorithms used as companion diagnostics, AI-first reading for high-volume common cancer diagnoses, pathologist for the exceptions, Digital pathology & AI.
- CompanyPaige AI
Shares A standard evaluation pathway for AI-assisted pathology, from reader study to deployment, Version control and locked reference sets for AI algorithms used as companion diagnostics, AI-first reading for high-volume common cancer diagnoses, pathologist for the exceptions, Digital pathology & AI.
- IdeaRe-test the metastasis, not the old primary, before every change of treatment
Shares Immunohistochemistry (IHC), HER2-low and HER2-ultralow, Histopathology & immunohistochemistry, HR-positive / HER2-negative breast cancer.
- IdeaPathologist assistants plus AI triage to multiply pathologist capacity
Shares AI-first reading for high-volume common cancer diagnoses, pathologist for the exceptions, Digital pathology & AI, AI that is built but not validated or deployed.
- IdeaPublic gold-standard datasets for validating every cancer biomarker test
Shares Version control and locked reference sets for AI algorithms used as companion diagnostics, Digital pathology & AI, AI that is built but not validated or deployed, Biomarkers are not validated or standardised.
- IdeaMonitor biomarker positivity rates across labs in real time to catch assay drift
Shares Version control and locked reference sets for AI algorithms used as companion diagnostics, Histopathology & immunohistochemistry, Biomarkers are not validated or standardised.