The regulatory field for digital pathology (DP) has advanced significantly. A major milestone was accomplished when the FDA allowed the first vendor to market their device for primary diagnostic use in the USA and published in the classification order that this device, and substantially equivalent devices of this generic type, should be classified into class II instead of class III as previously proposed. The Digital Pathology Association (DPA) regulatory task force had a major role in the accomplishment of getting the application request for Whole Slide Imaging (WSI) Systems recommended for a de novo. This article reviews the past and emerging regulatory environment of WSI for clinical use in the USA. A WSI system with integrated subsystems is defined in the context of medical device regulations. The FDA technical performance assessment guideline is also discussed as well as parameters involved in analytical testing and clinical studies to demonstrate that WSI devices are safe and effective for clinical use.

Background: Generating good training datasets is essential for machine learning-based nuclei detection methods. However, creating exhaustive nuclei contour annotations, to derive optimal training data from, is often infeasible. Methods: We compared different approaches for training nuclei detection methods solely based on nucleus center markers. Such markers contain less accurate information, especially with regard to nuclear boundaries, but can be produced much easier and in greater quantities. The approaches use different automated sample extraction methods to derive image positions and class labels from nucleus center markers. In addition, the approaches use different automated sample selection methods to improve the detection quality of the classification algorithm and reduce the run time of the training process. We evaluated the approaches based on a previously published generic nuclei detection algorithm and a set of Ki-67-stained breast cancer images. Results: A Voronoi tessellation-based sample extraction method produced the best performing training sets. However, subsampling of the extracted training samples was crucial. Even simple class balancing improved the detection quality considerably. The incorporation of active learning led to a further increase in detection quality. Conclusions: With appropriate sample extraction and selection methods, nuclei detection algorithms trained on the basis of simple center marker annotations can produce comparable quality to algorithms trained on conventionally created training sets.