Turn the map of immune cells inside a tumour into a standardised test
Whether immune cells are next to cancer cells matters more than how many there are. Turning that spatial picture into a reliable, standardised test would predict response better.
Spatial features such as the distance from cytotoxic T cells to tumour cells, the presence of immune-excluded phenotypes and B-cell aggregates outperform PD-L1 and tumour mutational burden in retrospective series. No spatial assay has been standardised as a companion diagnostic, and platform variability, staining variability and analytical drift are unaddressed. Reference tissue standards and a locked analysis pipeline are the prerequisites.
- No one can predict who responds to immunotherapy · Checkpoint drugs cure some patients and do nothing for most. We still cannot tell the two apart before treating.
- Biomarkers are not validated or standardised · Tests that decide who gets a drug are often not validated prospectively and are measured differently in every lab.
- AI that is built but not validated or deployed · Thousands of cancer AI models are published; a handful are in clinical use, and fewer have shown they help patients.
Pages like this
not linked directly; found by shared links- IdeaStandards for spatial and multiplex tissue biomarkers before they reach the clinic
Shares 10x Genomics, Tumour-infiltrating lymphocytes (TILs), Hot vs cold tumours, Single-cell & spatial profiling.
- TechnologySpatial-omics-guided treatment selection
Shares BostonGene, 10x Genomics, Tumour-infiltrating lymphocytes (TILs), Pathology & radiology foundation models.
- IdeaMap which tumour clones sit next to which immune cells before choosing therapy
Shares 10x Genomics, Tumour-infiltrating lymphocytes (TILs), Hot vs cold tumours, Single-cell & spatial profiling.
- IdeaAI second reads to stop borderline lesions being upgraded to cancer
Shares Paige AI, Pathology & radiology foundation models, Digital pathology & AI, AI that is built but not validated or deployed.
- IdeaVersion control and locked reference sets for AI algorithms used as companion diagnostics
Shares Paige AI, Pathology & radiology foundation models, Digital pathology & AI, AI that is built but not validated or deployed.
- IdeaAI-first reading for high-volume common cancer diagnoses, pathologist for the exceptions
Shares Lunit, Paige AI, Pathology & radiology foundation models, Digital pathology & AI.
- IdeaPool every immunotherapy trial's biomarker data into one commons
Shares Tumour proportion score (TPS), Pathology & radiology foundation models, Single-cell & spatial profiling, AI that is built but not validated or deployed.
- IdeaClear the suppressive neutrophils out of pancreatic tumours first
Shares Hot vs cold tumours, Single-cell & spatial profiling, Digital pathology & AI, No one can predict who responds to immunotherapy.