Skip to main content

Table 7 Impact of CLIP Pretraining Data (Averaged Results across Kumar, CPM-15, CPM-17, and TNBC Datasets)

From: Instance-level semantic segmentation of nuclei based on multimodal structure encoding

Pretraining data

DICE

AJI

PQ

Natural images only

0.815

0.655

0.735

+Pathological images

0.830

0.670

0.750

  1. Including pathological images in pretraining significantly improves performance on nuclei segmentation tasks
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us