CellGenNet: A Knowledge-Distilled Framework for Robust Cell Segmentation in Cancer Tissues
This work addresses robust cell segmentation in cancer histopathology, enabling scalable analysis, but it appears incremental as it builds on existing semi-supervised and knowledge distillation methods.
The paper tackled the problem of accurate nuclei segmentation in microscopy whole slide images for cancer tissues by proposing CellGenNet, a knowledge distillation framework, which improved segmentation accuracy and generalization over baselines under limited supervision.
Accurate nuclei segmentation in microscopy whole slide images (WSIs) remains challenging due to variability in staining, imaging conditions, and tissue morphology. We propose CellGenNet, a knowledge distillation framework for robust cross-tissue cell segmentation under limited supervision. CellGenNet adopts a student-teacher architecture, where a capacity teacher is trained on sparse annotations and generates soft pseudo-labels for unlabeled regions. The student is optimized using a joint objective that integrates ground-truth labels, teacher-derived probabilistic targets, and a hybrid loss function combining binary cross-entropy and Tversky loss, enabling asymmetric penalties to mitigate class imbalance and better preserve minority nuclear structures. Consistency regularization and layerwise dropout further stabilize feature representations and promote reliable feature transfer. Experiments across diverse cancer tissue WSIs show that CellGenNet improves segmentation accuracy and generalization over supervised and semi-supervised baselines, supporting scalable and reproducible histopathology analysis.