LG-NuSegHop: A Local-to-Global Self-Supervised Pipeline For Nuclei Instance Segmentation
This work addresses the labor-intensive and costly annotation problem in medical imaging for pathologists, offering a transparent and generalizable solution, though it is incremental as it builds on prior knowledge and existing methods.
The paper tackles nuclei instance segmentation in histology images by proposing LG-NuSegHop, a self-supervised pipeline that uses no manually annotated data, achieving competitive performance with fully supervised methods and outperforming other self-supervised approaches on three public datasets.
Nuclei segmentation is the cornerstone task in histology image reading, shedding light on the underlying molecular patterns and leading to disease or cancer diagnosis. Yet, it is a laborious task that requires expertise from trained physicians. The large nuclei variability across different organ tissues and acquisition processes challenges the automation of this task. On the other hand, data annotations are expensive to obtain, and thus, Deep Learning (DL) models are challenged to generalize to unseen organs or different domains. This work proposes Local-to-Global NuSegHop (LG-NuSegHop), a self-supervised pipeline developed on prior knowledge of the problem and molecular biology. There are three distinct modules: (1) a set of local processing operations to generate a pseudolabel, (2) NuSegHop a novel data-driven feature extraction model and (3) a set of global operations to post-process the predictions of NuSegHop. Notably, even though the proposed pipeline uses { no manually annotated training data} or domain adaptation, it maintains a good generalization performance on other datasets. Experiments in three publicly available datasets show that our method outperforms other self-supervised and weakly supervised methods while having a competitive standing among fully supervised methods. Remarkably, every module within LG-NuSegHop is transparent and explainable to physicians.