Semantic annotation for computational pathology: Multidisciplinary experience and best practice recommendations

• DOI: 10.48550/arxiv.2106.13689
• Publication Date: 2021-01-01
• Authors: Noorul Wahab; Islam M. Miligy; Katherine Dodd; Harvir Sahota; Michael S. Toss; Wenqi Lu; Mostafa Jahanifar; Mohsin Bilal; Simon Graham; Young Park; Giorgos Hadjigeor...; Abhir Bhalerao; Ayat G. Lashen; Asmaa Ibrahim; Ayaka Katayama; Henry O Ebili; Matthew Parkin; Tom Sorell; Shan E Ahmed Raza; Emily Hero; Hesham Eldaly; Yee Wah Tsang; Kishore Gopalakri...; David Snead; Emad A. Rakha; Nasir Rajpoot; Fayyaz Minhas
• Keywords: Best practice; Component (thermodynamics); Digital Pathology

Recent advances in whole slide imaging (WSI) technology have led to the development of a myriad computer vision and artificial intelligence (AI) based diagnostic, prognostic, predictive algorithms. Computational Pathology (CPath) offers an integrated solution utilize information embedded pathology WSIs beyond what we obtain through visual assessment. For automated analysis validation machine learning (ML) models, annotations at slide, tissue cellular levels are required. The annotation important constructs images is component CPath projects. Improper can result algorithms which hard interpret potentially produce inaccurate inconsistent results. Despite crucial role projects, there no well-defined guidelines or best practices on how should be carried out. In this paper, address shortcoming by presenting experience acquired during execution large-scale exercise involving multidisciplinary team pathologists, ML experts researchers as part image data Lake for Analytics, Knowledge Education (PathLAKE) consortium. We present real-world case study along with examples different types annotations, diagnostic algorithm, dictionary constructs. analyses reported work highlight practice recommendations that used over lifecycle project.