lazyslide_models.tile_prediction.PathProfilerQC

lazyslide_models.tile_prediction.PathProfilerQC#

class PathProfilerQC(model_path=None, token=None)#

pathprofilerqc GitHub Paper Params: 11.2M GPL-3.0 [Haghighat et al., 2022] Quality assessment of histology images

The prediction classes are:

Suggested Name	Description
diagnostic_quality	Whether usable for diagnosis (1=good)
visual_cleanliness	Normal & artefact-free (1=clean)
focus_issue	Focus issue: 1=severe, 0.5=slight, 0=none
staining_issue	Staining issue: 1=severe, 0.5=slight, 0=none
tissue_folding_present	Tissue folding present (1=yes)
misc_artifacts_present	Other artefacts present (1=yes)

predict(image)#: Predict the class of the input image using the PathProfiler model. The model expects a tensor of shape [B, C, H, W].