{"paper":{"title":"Pathologist-Level Grading of Prostate Biopsies with Artificial Intelligence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.IV"],"primary_cat":"cs.CV","authors_text":"(10) Department of Pathology, (11) Department of Tissue Pathology, (12) Institute of Pathology, (13) Department of Urology, (14) Pathology, (15) Department of Cellular Pathology, (16) Department of Pathology, (17) Aquesta Uropathology, (18) Department of Laboratory Medicine, (19) Department of Pathology, (20) Department of Surgical Pathology, (21) Department of Cellular Pathology, (22) Department of Pathology, (23) Department of Immunology, 24), (24) BioImage Informatics Facility of SciLifeLab, 25), (25) Department of Oncology, (26) Department of Oncology, (2) Faculty of Medicine, (3) Centre for Image Analysis, (4) Department of Pathology, (5) Barts Cancer Institute, (6) Bostwick Laboratories, (7) Laboratory Medicine Program, (8) Department of Pathology, (9) Department of Pathology, Aichi Medical University, Andrew J. Evans (7), Australia, Biostatistics, Bonn, Brazil, Brett Delahunt (4), Brisbane, Bristol, Canada, Cardiff, Carolina W\\\"ahlby (3, Cecilia Bergstr\\\"om (23), Central Clinical School, Chin-Chen Pan (16), Cleveland, Cleveland Clinic, CT, Dallas, Daniel M. Berney (5), David G. Bostwick (6), David J. Grignon (8), Department of Information Technology, Diagnostic Oncology, Finland, FL, Genetics, Germany, Glen Kristiansen (12), Health Sciences, Health Technology, Hemamali Samaratunga (17), Henrik Gr\\\"onberg (1, Henrik Olsson (1), Hiroyuki Takahashi (19), IN, Indianapolis, Indiana University School of Medicine, James G. Kench (11), Japan, Jesse K. McKenney (14), Jikei University School of Medicine, Johan Lindberg (1), John R. Srigley (18), Jon Oxley (15), Karolinska Institutet, Katia R.M. Leite (13), Kenneth A. Iczkowski (10), Kimmo Kartasalo (2), Laboratory Medicine, Laboratory Medicine Institute, Laboratory of Medical Research, Lars Egevad (26), Leslie Solorzano (3), London, Martin Eklund (1) ((1) Department of Medical Epidemiology, Mattias Rantalainen (1), Medical College of Wisconsin, Milwaukee, Ming Zhou (22), Molecular Medicine, Murali Varma (21), Nagoya, New Haven, New Zealand, NSW, OH, ON, Orlando, Pathobiology, Pathology, Pekka Ruusuvuori (2), Peter A. Humphrey (9), Peter Str\\\"om (1), QLD, Queen Mary University of London, Royal Prince Alfred Hospital, S\\~ao Paulo, School of Medicine, Southmead Hospital, S:t G\\\"oran Hospital, Stockholm, Sweden, Sweden), Sydney, Taipei, Taipei Veterans General Hospital, Taiwan, Tampere, Tampere University, Theodorus H. van der Kwast (7), Tokyo, Toronto, Toronto General Hospital, Toyonori Tsuzuki (20), TX, UK, University Health Network, University Hospital Bonn, University Hospital of Wales, University of Otago, University of Queensland, University of S\\~ao Paulo Medical School, University of Sydney, University of Toronto, Uppsala, Uppsala University, USA, UT Southwestern Medical Center, Wellington, Wellington School of Medicine, WI, Yale University School of Medicine","submitted_at":"2019-07-02T13:52:02Z","abstract_excerpt":"Background: An increasing volume of prostate biopsies and a world-wide shortage of uro-pathologists puts a strain on pathology departments. Additionally, the high intra- and inter-observer variability in grading can result in over- and undertreatment of prostate cancer. Artificial intelligence (AI) methods may alleviate these problems by assisting pathologists to reduce workload and harmonize grading.\n  Methods: We digitized 6,682 needle biopsies from 976 participants in the population based STHLM3 diagnostic study to train deep neural networks for assessing prostate biopsies. The networks wer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.01368","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}