Improving the Annotation Process in Computational Pathology: A Pilot Study with Manual and Semi-automated Approaches on Consumer and Medical Grade Devices.

Autor: Cazzaniga G; Department of Medicine and Surgery, Pathology, IRCCS Fondazione San Gerardo Dei Tintori, University of Milano-Bicocca, Via Pergolesi, 33, 20900, Monza, Italy., Del Carro F; Department of Medicine and Surgery, Pathology, IRCCS Fondazione San Gerardo Dei Tintori, University of Milano-Bicocca, Via Pergolesi, 33, 20900, Monza, Italy., Eccher A; Department of Medical and Surgical Sciences for Children and Adults, University of Modena and Reggio Emilia, University Hospital of Modena, Modena, Italy., Becker JU; Institute of Pathology, University Hospital of Cologne, Cologne, Germany., Gambaro G; Division of Nephrology, Department of Medicine, University of Verona, Verona, Italy., Rossi M; Division of Nephrology, Department of Medicine, University of Verona, Verona, Italy., Pieruzzi F; Clinical Nephrology, Fondazione IRCCS San Gerardo Dei Tintori, Monza, Italy.; School of Medicine and Surgery, University of Milano-Bicocca, Milan, Italy., Fraggetta F; Pathology Unit, Azienda Sanitaria Provinciale (ASP) Catania, 'Gravina' Hospital, Caltagirone, Italy., Pagni F; Department of Medicine and Surgery, Pathology, IRCCS Fondazione San Gerardo Dei Tintori, University of Milano-Bicocca, Via Pergolesi, 33, 20900, Monza, Italy., L'Imperio V; Department of Medicine and Surgery, Pathology, IRCCS Fondazione San Gerardo Dei Tintori, University of Milano-Bicocca, Via Pergolesi, 33, 20900, Monza, Italy. vincenzo.limperio@unimib.it.
Jazyk: angličtina
Zdroj: Journal of imaging informatics in medicine [J Imaging Inform Med] 2024 Sep 04. Date of Electronic Publication: 2024 Sep 04.
DOI: 10.1007/s10278-024-01248-x
Abstrakt: The development of reliable artificial intelligence (AI) algorithms in pathology often depends on ground truth provided by annotation of whole slide images (WSI), a time-consuming and operator-dependent process. A comparative analysis of different annotation approaches is performed to streamline this process. Two pathologists annotated renal tissue using semi-automated (Segment Anything Model, SAM)) and manual devices (touchpad vs mouse). A comparison was conducted in terms of working time, reproducibility (overlap fraction), and precision (0 to 10 accuracy rated by two expert nephropathologists) among different methods and operators. The impact of different displays on mouse performance was evaluated. Annotations focused on three tissue compartments: tubules (57 annotations), glomeruli (53 annotations), and arteries (58 annotations). The semi-automatic approach was the fastest and had the least inter-observer variability, averaging 13.6 ± 0.2 min with a difference (Δ) of 2%, followed by the mouse (29.9 ± 10.2, Δ = 24%), and the touchpad (47.5 ± 19.6 min, Δ = 45%). The highest reproducibility in tubules and glomeruli was achieved with SAM (overlap values of 1 and 0.99 compared to 0.97 for the mouse and 0.94 and 0.93 for the touchpad), though SAM had lower reproducibility in arteries (overlap value of 0.89 compared to 0.94 for both the mouse and touchpad). No precision differences were observed between operators (p = 0.59). Using non-medical monitors increased annotation times by 6.1%. The future employment of semi-automated and AI-assisted approaches can significantly speed up the annotation process, improving the ground truth for AI tool development.
(© 2024. The Author(s).)
Databáze: MEDLINE