Abstract
Recent advances in whole‐slide imaging (WSI) technology have led to the development of a myriad of computer vision and artificial intelligence‐based diagnostic, prognostic, and predictive algorithms. Computational Pathology (CPath) offers an integrated solution to utilise information embedded in pathology WSIs beyond what can be obtained through visual assessment. For automated analysis of WSIs and validation of machine learning (ML) models, annotations at the slide, tissue, and cellular levels are required. The annotation of important visual constructs in pathology images is an important component of CPath projects. Improper annotations can result in algorithms that are hard to interpret and can potentially produce inaccurate and inconsistent results. Despite the crucial role of annotations in CPath projects, there are no well‐defined guidelines or best practices on how annotations should be carried out. In this paper, we address this shortcoming by presenting the experience and best practices acquired during the execution of a large‐scale annotation exercise involving a multidisciplinary team of pathologists, ML experts, and researchers as part of the Pathology image data Lake for Analytics, Knowledge and Education (PathLAKE) consortium. We present a real‐world case study along with examples of different types of annotations, diagnostic algorithm, annotation data dictionary, and annotation constructs. The analyses reported in this work highlight best practice recommendations that can be used as annotation guidelines over the lifecycle of a CPath project.
Highlights
Recent developments in imaging technology, digitization of glass slides and Artificial Intelligence (AI) have spurred an ongoing revolution in clinical histopathology workflows and enabled automated analysis of digital pathology whole slide images (WSIs)
To address the above challenges in annotations for Computational Pathology (CPath) projects, we propose a comprehensive set of annotation guidelines in this paper based on our practical experience and recent involvement with PathLAKE exemplar projects
There has been some work on standardizing the ontologies of medical terms such as SNOMED CT [42], National Cancer Institute Thesaurus (NCIt) [43], and foundational model of anatomy (FMA) [44], protocols for histopathology images need standardization
Summary
Recent developments in imaging technology, digitization of glass slides and Artificial Intelligence (AI) have spurred an ongoing revolution in clinical histopathology workflows and enabled automated analysis of digital pathology whole slide images (WSIs). Before the sample can be analyzed digitally, the tissue must be sampled, processed, sectioned, subjected to antigen retrieval, and stained using chemical, immunohistochemical (IHC), or immunofluorescent (IF) techniques and digitized with a slide scanner resulting in very large (100,000 × 100,000 pixels resolution) whole slide images (WSIs) Each of these steps introduces preanalytical or analytical incongruencies which, on top of tumor heterogeneity and biological variability, makes it challenging to obtain consistent input data for computational analysis. To address the above challenges in annotations for CPath projects, we propose a comprehensive set of annotation guidelines in this paper based on our practical experience and recent involvement with PathLAKE exemplar projects We hope this will pave the way for the interoperability of annotation protocols and the improved generalizability of algorithms via multicenter validation
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have