A Large-scale Synthetic Pathological Dataset for Deep Learning-enabled Segmentation of Breast Cancer

Kexin Ding¹, Mu Zhou², He Wang³, Olivier Gevaert⁴, Dimitris Metaxas⁵ & Shaoting Zhang^6 ✉

Abstract

The success of training computer-vision models heavily relies on the support of large-scale, real-world images with annotations. Yet such an annotation-ready dataset is difficult to curate in pathology due to the privacy protection and excessive annotation burden. To aid in computational pathology, synthetic data generation, curation, and annotation present a cost-effective means to quickly enable data diversity that is required to boost model performance at different stages. In this study, we introduce a large-scale synthetic pathological image dataset paired with the annotation for nuclei semantic segmentation, termed as Synthetic Nuclei and annOtation Wizard (SNOW). The proposed SNOW is developed via a standardized workflow by applying the off-the-shelf image generator and nuclei annotator. The dataset contains overall 20k image tiles and 1,448,522 annotated nuclei with the CC-BY license. We show that SNOW can be used in both supervised and semi-supervised training scenarios. Extensive results suggest that synthetic-data-trained models are competitive under a variety of model training settings, expanding the scope of better using synthetic images for enhancing downstream data-driven clinical tasks.

¹Department of Computer Science, University of North Carolina at Charlotte, Charlotte, NC, 28262, USA.²Sensebrain Research, San Jose, CA, 95131, USA. ³Department of Pathology, Yale University, New Haven, CT,06520, USA. ⁴Stanford Center for Biomedical Informatics Research, Department of Medicine and Biomedical Data Science, Stanford University, Stanford, CA, 94305, USA. ⁵Department of Computer Science, Rutgers University, New Brunswick, NJ, 08901, USA. ⁶Shanghai Artificial Intelligence Laboratory, Shanghai, 200232, China.

✉e-mail: zhangshaoting@pjlab.org.cn