Ki67 cell typing from images using pretrained embeddings and clustering
K-CLUE: A Segmentation-to-Clustering Framework for Ki67 Cell Typing
Computer Vision and Pattern Recognition
Summary
Quantifying Ki67, a protein marker for tumor growth in breast cancer, usually requires training on labeled images for each dataset. The authors present K-CLUE, a method that identifies and classifies cells stained for Ki67 without needing any manual labeling or retraining. It first segments nuclei in images, extracts features using a pretrained model, then groups the cells using clustering to distinguish Ki67-positive from negative. Their study shows that by adjusting how features are processed, this clustering can be made reliable across different pretrained models, and their method performs well on real breast cancer image datasets.
What this means in practice
- •For medical image analysts: Automatically classify Ki67-positive and negative cells in breast cancer images without manual annotations or retraining for each dataset.
- •For biomedical software developers: Integrate pretrained visual embeddings with clustering for annotation-free tumor cell proliferation quantification in pathology tools.
Authors
Ana Beatriz Vieira, Sara P. Oliveira, Diana Montezuma, João Fraga, Jaime S. Cardoso, Arlindo L. Oliveira
Abstract
Ki67 is a key marker of tumor proliferation in breast cancer, but its quantification from immunohistochemistry images normally depends on supervised classifiers trained per dataset. We examine the role of frozen pretrained visual representations in annotation-free Ki67 cell typing. To this end, we use K-CLUE, a framework that segments individual nuclei, represents each nucleus with a pretrained encoder, reduces the resulting embeddings with principal component analysis, and separates Ki67-positive from Ki67-negative nuclei using k-means clustering, without task-specific training or manual annotations. Clustering the raw components is highly sensitive to the choice of encoder: across seven encoders, the Ki67-positive F1-score on matched MIST nuclei varies by 44 points, although Ki67 status remains linearly decodable from every representation, with supervised probe AUCs above 0.98. Analysis of the embedding spaces shows that clustering succeeds when DAB-related variation occupies the leading directions of variance. Whitening the retained principal components removes this dependence, reducing the spread across encoders to 1.00 F1-score point. Handcrafted color representations are also competitive, confirming that Ki67 status is strongly reflected in chromatic information, but they require an explicit choice of color space. In end-to-end evaluation, K-CLUE reaches F1-scores of 85.00% and 81.91% for Ki67-positive and Ki67-negative nuclei on MIST, and 79.59% and 81.16% on BCData, outperforming DeepLIIF and IHCScoreGAN on both datasets. These results show that pretrained representations can support annotation-free Ki67 typing when their variance structure is accounted for.