Search papers, labs, and topics across Lattice.
Segmenting overlapping, semi-transparent cells in microscopy typically fails because shared visual evidence and weak boundaries confound standard local region-of-interest models and rigid shape priors. To overcome this, QCell introduces a query-based architecture that decomposes and recombines latent object representations to reason globally about occluded structures, coupled with a contrastive query alignment loss to separate mixed instance features. The approach sets a new state of the art across multiple microscopy benchmarks, notably improving segmentation performance by +2.2 AP and +2.7 AJI on the ISBI2014 dataset alongside a new Organoid benchmark.
Disentangling overlapping, semi-transparent objects no longer requires rigid shape priors: recombining latent instance queries directly resolves ambiguous visual evidence, yielding a +2.7 AJI jump on ISBI2014.
Instance segmentation of overlapping cells in microscopy remains challenging due to semi-transparent structures that produce weak boundaries and mixed visual evidence in overlap regions. Existing methods address this through local regions of interest or shape priors but lack global reasoning across overlapping objects. We present QCell, a novel query-based model that de-overlaps cell instances in microscopy scenes. Our approach combines (i) an instance recombination module that decomposes and recombines query representations in latent space, enabling the model to reason about complete object structure under overlap, and (ii) a contrastive query alignment objective that combines distinctive instance feature learning and separation of overlapping cell queries. We additionally introduce a new Organoid dataset benchmark for overlapping cell segmentation. We show that QCell outperforms state-of-the-art methods across multiple benchmarks, achieving +2.2 AP and +2.7 AJI on ISBI2014. Code is available at https://github.com/SlavkoPrytula/QCell
