Please use this identifier to cite or link to this item: https://dspace.crs4.it/jspui/handle/1138/48
Title: AI Support for Accelerating Histopathological Slide Examinations of Prostate Cancer in Clinical Studies
Authors: Del Rio, Mauro 
Lianas, Luca 
Aspegren, Oskar 
Busonera, Giovanni 
Versaci, Francesco 
Zelic, Renata 
Vincent, Per H 
Leo, Simone 
Pettersson, Andreas 
Akre, Olof 
Pireddu, Luca 
Affiliations: Center for Advanced Studies, Research, and Development in Sardinia (CRS4), Pula (CA), Italy 
Center for Advanced Studies, Research, and Development in Sardinia (CRS4), Pula (CA), Italy 
Department of Clinical Pathology and Cancer Diagnostics, Karolinska University Hospital, SE-17176 Stockholm, Sweden; Department of Molecular Medicine and Surgery, Karolinska Institutet, SE-17176 Stockholm, Sweden KI, Sweden 
Center for Advanced Studies, Research, and Development in Sardinia (CRS4), Pula (CA), Italy 
Center for Advanced Studies, Research, and Development in Sardinia (CRS4), Pula (CA), Italy 
Department of Pelvic Cancer, Karolinska University Hospital,SE-17176 Stockholm, Sweden; Department of Molecular Medicine and Surgery, Karolinska Institutet, SE-17176 Stockholm, Sweden KI, Sweden 
Center for Advanced Studies, Research, and Development in Sardinia (CRS4), Pula (CA), Italy 
Center for Advanced Studies, Research, and Development in Sardinia (CRS4), Pula (CA), Italy 
Department of Pelvic Cancer, Karolinska University Hospital,SE-17176 Stockholm, Sweden; Department of Molecular Medicine and Surgery, Karolinska Institutet, SE-17176 Stockholm, Sweden KI, Sweden 
Department of Pelvic Cancer, Karolinska University Hospital,SE-17176 Stockholm, Sweden; Department of Molecular Medicine and Surgery, Karolinska Institutet, SE-17176 Stockholm, Sweden KI, Sweden 
Center for Advanced Studies, Research, and Development in Sardinia (CRS4), Pula (CA), Italy 
Editors: Mazzeo, Pier Luigi 
Frontoni, Emanuele 
Sclaroff, Stanley 
Distante, Cosimo 
Editors' affiliations: Consorzio Nazionale delle Ricerche, Lecce, Italy 
Università Politecnica delle Marche, Ancona, Italy 
Boston University, Boston, MA, USA 
Consorzio Nazionale delle Ricerche, Lecce, Italy 
Keywords: Digital pathology;Artificial Intelligence;Workflows
Issue Date: 7-Aug-2022
Publisher: Springer
Project: Deep-Learning and HPC to Boost Biomedical Applications for Health 
Providing an open collaborative space for digital biology in Europe 
Scalable Visual and Data-intensive Computing 
Related Publication(s): International Conference on Image Analysis and Processing
Journal: Lecture Notes in Computer Science 
Volume: 13373
Conference: 21st International Conference on IMAGE ANALYSIS AND PROCESSING 
Abstract: 
While studies in pathology are essential for the progress in the diagnostic and prognostic techniques in the field, pathologist time is becoming an increasingly scarce resource, and can indeed become the limiting factor in the feasibility of studies to be performed. In this work, we demonstrate how the Digital Pathology platform by CRS4, for supporting research studies in digital pathology, has been augmented by the addition of AI-based features to accelerate image examination to reduce the pathologist time required for clinical studies. The platform has been extended to provide computationally generated annotations and visual cues to help the pathologist prioritize high-interest image areas. The system includes an image annotation pipeline with DeepHealth-based deep learning models for tissue identification and prostate cancer identification. Annotations are viewed through the platform’s virtual microscope and can be controlled interactively (e.g., thresholding, coloring). Moreover, the platform captures inference provenance information and archives it as RO-Crate artifacts containing data and metadata required for reproducibility. We evaluate the models and the inference pipeline, achieving AUC of 0.986 and 0.969 for tissue and cancer identification, respectively, and verifying linear dependence of execution speed on image tissue content. Finally, we describe the ongoing clinical validation of the contribution, including preliminary results, and discuss feedback from clinical professionals regarding the overall approach.
Description: 
Link to publisher's page: https://link.springer.com/chapter/10.1007/978-3-031-13321-3_48
URI: https://dspace.crs4.it/jspui/handle/1138/48
DOI: 10.1007/978-3-031-13321-3_48
Appears in Collections:CRS4 publications

Files in This Item:
File Description SizeFormat
accelerating_slide_examination.pdfFull text849,11 kBAdobe PDFView/Open
Show full item record

Google ScholarTM

Check

Altmetric

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.