{"entity": "researcher", "timestamp": "2026-07-20T22:43:47.157Z", "family": "Egevad", "given": "Lars", "initials": "L", "orcid": "0000-0001-8531-222X", "affiliations": ["Department of Oncology-Pathology, Karolinska Institutet|, Karolinska University Hospital, Radiumhemmet P1:02, 171 76, Stockholm, Sweden. lars.egevad@ki.se."], "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/researcher/a7d46f1f5fc047dc8edb910eb4f0645c.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/researcher/a7d46f1f5fc047dc8edb910eb4f0645c"}}, "publications": [{"entity": "publication", "iuid": "323bbe2a3c6e444081e24c57fa16df77", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/323bbe2a3c6e444081e24c57fa16df77.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/323bbe2a3c6e444081e24c57fa16df77"}}, "title": "Artificial intelligence-assisted prostate cancer diagnosis for reduced use of immunohistochemistry.", "authors": [{"family": "Blilie", "given": "Anders", "initials": "A", "orcid": "0009-0002-9546-5443", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/d778d06e206948e5ac99017ce1ae8434.json"}}, {"family": "Mulliqi", "given": "Nita", "initials": "N"}, {"family": "Ji", "given": "Xiaoyi", "initials": "X"}, {"family": "Szolnoky", "given": "Kelvin", "initials": "K", "orcid": "0000-0002-0554-1872", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/5059c9f881d4434f9b64f3bb381478fe.json"}}, {"family": "Boman", "given": "Sol Erika", "initials": "SE", "orcid": "0009-0001-5733-3178", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/8a605b0dadad4b3696396827ebac9348.json"}}, {"family": "Titus", "given": "Matteo", "initials": "M", "orcid": "0009-0008-7893-7385", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/049f236217f147f78635b9d3a361db98.json"}}, {"family": "Gonzalez", "given": "Geraldine Martinez", "initials": "GM"}, {"family": "Asenjo", "given": "Jos\u00e9", "initials": "J"}, {"family": "Gambacorta", "given": "Marcello", "initials": "M"}, {"family": "Libretti", "given": "Paolo", "initials": "P"}, {"family": "Gudlaugsson", "given": "Einar", "initials": "E"}, {"family": "Kjosavik", "given": "Svein R", "initials": "SR", "orcid": "0000-0002-7004-5533", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/97167c1ee44443108098eb823bd18fa7.json"}}, {"family": "Egevad", "given": "Lars", "initials": "L", "orcid": "0000-0001-8531-222X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/a7d46f1f5fc047dc8edb910eb4f0645c.json"}}, {"family": "Janssen", "given": "Emiel A M", "initials": "EAM"}, {"family": "Eklund", "given": "Martin", "initials": "M", "orcid": "0000-0001-5032-5266", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/06721510ebc8462386e0e6fc6c84315b.json"}}, {"family": "Kartasalo", "given": "Kimmo", "initials": "K", "orcid": "0000-0002-9470-4783", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/7c6fc97c06ed456c8bdd1f03db8a9b72.json"}}], "type": "journal article", "published": "2025-10-15", "journal": {"title": "Commun Med (Lond)", "issn": "2730-664X", "volume": "5", "issue": "1", "pages": "425", "issn-l": null}, "abstract": "Prostate cancer diagnosis heavily relies on histopathological evaluation, which is subject to variability. While immunohistochemical staining (IHC) assists in distinguishing benign from malignant tissue, it increases workload, costs, and leads to diagnostic delays. Artificial intelligence (AI) presents a promising solution to reduce reliance on IHC by accurately classifying atypical glands and borderline morphologies in hematoxylin and eosin (H&E) stained tissue sections.\n\nIn this study, we evaluated an AI model's ability to minimize IHC use without compromising diagnostic accuracy. We retrospectively analyzed prostate core needle biopsies from routine diagnostics at three different pathology sites. These cohorts consisted exclusively of diagnostically challenging cases where pathologists had required IHC to finalize the diagnosis.\n\nWe show that the AI model achieves high performance, with area under the curve values ranging from 0.951 to 0.993 for detecting cancer in routine H&E-stained slides. When applying sensitivity-prioritized diagnostic thresholds, the model reduces the need for IHC staining by 44.4%, 42.0%, and 20.7% across the three cohorts, without a single false negative prediction. Among slides with a benign ground truth label, IHC use is reduced by up to 80.6%.\n\nThis AI model shows promise for reducing unnecessary IHC use in difficult prostate biopsy cases while maintaining diagnostic safety. Its integration into clinical workflows could streamline decision-making in prostate pathology and alleviate resource burdens.", "doi": "10.1038/s43856-025-01185-y", "pmid": "41094148", "labels": {"DDLS Fellow": null, "Kimmo Kartasalo": null}, "xrefs": [{"db": "pmc", "key": "PMC12528698"}, {"db": "pii", "key": "10.1038/s43856-025-01185-y"}], "notes": [], "created": "2025-10-30T15:41:17.882Z", "modified": "2026-06-03T09:44:07.037Z"}, {"entity": "publication", "iuid": "af5b1bed406e47ad890769e1d8f42bbd", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/af5b1bed406e47ad890769e1d8f42bbd.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/af5b1bed406e47ad890769e1d8f42bbd"}}, "title": "Hierarchical Vision Transformers for prostate biopsy grading: Towards bridging the generalization gap.", "authors": [{"family": "Grisi", "given": "Cl\u00e9ment", "initials": "C"}, {"family": "Kartasalo", "given": "Kimmo", "initials": "K", "orcid": "0000-0002-9470-4783", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/7c6fc97c06ed456c8bdd1f03db8a9b72.json"}}, {"family": "Eklund", "given": "Martin", "initials": "M", "orcid": "0000-0001-5032-5266", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/06721510ebc8462386e0e6fc6c84315b.json"}}, {"family": "Egevad", "given": "Lars", "initials": "L", "orcid": "0000-0001-8531-222X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/a7d46f1f5fc047dc8edb910eb4f0645c.json"}}, {"family": "van der Laak", "given": "Jeroen", "initials": "J", "orcid": "0000-0001-7982-0754", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/188f689ad0304f28b42bc9d3dbf6a56e.json"}}, {"family": "Litjens", "given": "Geert", "initials": "G", "orcid": "0000-0003-1554-1291", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/3792b285bcf04c11b268da1088160a9d.json"}}], "type": "journal article", "published": "2025-10-00", "journal": {"title": "Med Image Anal", "issn": "1361-8423", "volume": "105", "pages": "103663", "issn-l": null}, "abstract": "Practical deployment of Vision Transformers in computational pathology has largely been constrained by the sheer size of whole-slide images. Transformers faced a similar limitation when applied to long documents, and Hierarchical Transformers were introduced to circumvent it. This work explores the capabilities of Hierarchical Vision Transformers for prostate cancer grading in WSIs and presents a novel technique to combine attention scores smartly across hierarchical transformers. Our best-performing model matches state-of-the-art algorithms with a 0.916 quadratic kappa on the Prostate cANcer graDe Assessment (PANDA) test set. It exhibits superior generalization capacities when evaluated in more diverse clinical settings, achieving a quadratic kappa of 0.877, outperforming existing solutions. These results demonstrate our approach's robustness and practical applicability, paving the way for its broader adoption in computational pathology and possibly other medical imaging tasks. Our code is publicly available at https://github.com/computationalpathologygroup/hvit.", "doi": "10.1016/j.media.2025.103663", "pmid": "40644915", "labels": {"DDLS Fellow": null, "Kimmo Kartasalo": null}, "xrefs": [{"db": "pii", "key": "S1361-8415(25)00210-5"}], "notes": [], "created": "2025-10-30T15:42:14.631Z", "modified": "2025-11-04T09:38:52.902Z"}, {"entity": "publication", "iuid": "f905ca88a80f42109bb997cd17743470", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/f905ca88a80f42109bb997cd17743470.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/f905ca88a80f42109bb997cd17743470"}}, "title": "Development and retrospective validation of an artificial intelligence system for diagnostic assessment of prostate biopsies: study protocol.", "authors": [{"family": "Mulliqi", "given": "Nita", "initials": "N"}, {"family": "Blilie", "given": "Anders", "initials": "A", "orcid": "0009-0002-9546-5443", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/d778d06e206948e5ac99017ce1ae8434.json"}}, {"family": "Ji", "given": "Xiaoyi", "initials": "X"}, {"family": "Szolnoky", "given": "Kelvin", "initials": "K", "orcid": "0000-0002-0554-1872", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/5059c9f881d4434f9b64f3bb381478fe.json"}}, {"family": "Olsson", "given": "Henrik", "initials": "H", "orcid": "0000-0002-2270-2017", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/da0547e978264d9c88fc6a222dcbfd5f.json"}}, {"family": "Titus", "given": "Matteo", "initials": "M", "orcid": "0009-0008-7893-7385", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/049f236217f147f78635b9d3a361db98.json"}}, {"family": "Martinez Gonzalez", "given": "Geraldine", "initials": "G"}, {"family": "Boman", "given": "Sol Erika", "initials": "SE", "orcid": "0009-0001-5733-3178", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/8a605b0dadad4b3696396827ebac9348.json"}}, {"family": "Valkonen", "given": "Masi", "initials": "M", "orcid": "0000-0003-3091-2484", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/ae4841e8a4124dc79c921b3af09096fe.json"}}, {"family": "Gudlaugsson", "given": "Einar", "initials": "E"}, {"family": "Kjosavik", "given": "Svein Reidar", "initials": "SR", "orcid": "0000-0002-7004-5533", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/97167c1ee44443108098eb823bd18fa7.json"}}, {"family": "Asenjo", "given": "Jos\u00e9", "initials": "J"}, {"family": "Gambacorta", "given": "Marcello", "initials": "M"}, {"family": "Libretti", "given": "Paolo", "initials": "P"}, {"family": "Braun", "given": "Marcin", "initials": "M"}, {"family": "Kordek", "given": "Radzislaw", "initials": "R"}, {"family": "\u0141owicki", "given": "Roman", "initials": "R"}, {"family": "Hotakainen", "given": "Kristina", "initials": "K"}, {"family": "V\u00e4re", "given": "P\u00e4ivi", "initials": "P"}, {"family": "Pedersen", "given": "Bodil Ginnerup", "initials": "BG", "orcid": "0000-0003-2792-7343", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/926d2e6e88a049f8ba5e50dbdd4fe210.json"}}, {"family": "S\u00f8rensen", "given": "Karina Dalsgaard", "initials": "KD"}, {"family": "Ulh\u00f8i", "given": "Benedicte Parm", "initials": "BP"}, {"family": "Rantalainen", "given": "Mattias", "initials": "M"}, {"family": "Ruusuvuori", "given": "Pekka", "initials": "P", "orcid": "0000-0001-9086-9591", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/bb947cd395e84612a53569f4a39abd19.json"}}, {"family": "Delahunt", "given": "Brett", "initials": "B", "orcid": "0000-0002-5398-0300", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/433a3f884f95451383cc746925d9a08c.json"}}, {"family": "Samaratunga", "given": "Hemamali", "initials": "H"}, {"family": "Tsuzuki", "given": "Toyonori", "initials": "T", "orcid": "0000-0002-4855-4366", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/42c993c2c0ab4b50afa03134f70118d9.json"}}, {"family": "Janssen", "given": "Emilius Adrianus Maria", "initials": "EAM"}, {"family": "Egevad", "given": "Lars", "initials": "L", "orcid": "0000-0001-8531-222X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/a7d46f1f5fc047dc8edb910eb4f0645c.json"}}, {"family": "Kartasalo", "given": "Kimmo", "initials": "K", "orcid": "0000-0002-9470-4783", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/7c6fc97c06ed456c8bdd1f03db8a9b72.json"}}, {"family": "Eklund", "given": "Martin", "initials": "M", "orcid": "0000-0001-5032-5266", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/06721510ebc8462386e0e6fc6c84315b.json"}}], "type": "journal article", "published": "2025-07-07", "journal": {"title": "BMJ Open", "issn": "2044-6055", "volume": "15", "issue": "7", "pages": "e097591", "issn-l": "2044-6055"}, "abstract": "Histopathological evaluation of prostate biopsies using the Gleason scoring system is critical for prostate cancer diagnosis and treatment selection. However, grading variability among pathologists can lead to inconsistent assessments, risking inappropriate treatment. Similar challenges complicate the assessment of other prognostic features like cribriform cancer morphology and perineural invasion. Many pathology departments are also facing an increasingly unsustainable workload due to rising prostate cancer incidence and a decreasing pathologist workforce coinciding with increasing requirements for more complex assessments and reporting. Digital pathology and artificial intelligence (AI) algorithms for analysing whole slide images show promise in improving the accuracy and efficiency of histopathological assessments. Studies have demonstrated AI's capability to diagnose and grade prostate cancer comparably to expert pathologists. However, external validations on diverse data sets have been limited and often show reduced performance. Historically, there have been no well-established guidelines for AI study designs and validation methods. Diagnostic assessments of AI systems often lack preregistered protocols and rigorous external cohort sampling, essential for reliable evidence of their safety and accuracy.\n\nThis study protocol covers the retrospective validation of an AI system for prostate biopsy assessment. The primary objective of the study is to develop a high-performing and robust AI model for diagnosis and Gleason scoring of prostate cancer in core needle biopsies, and at scale evaluate whether it can generalise to fully external data from independent patients, pathology laboratories and digitalisation platforms. The secondary objectives cover AI performance in estimating cancer extent and detecting cribriform prostate cancer and perineural invasion. This protocol outlines the steps for data collection, predefined partitioning of data cohorts for AI model training and validation, model development and predetermined statistical analyses, ensuring systematic development and comprehensive validation of the system. The protocol adheres to Transparent Reporting of a multivariable prediction model of Individual Prognosis Or Diagnosis+AI (TRIPOD+AI), Protocol Items for External Cohort Evaluation of a Deep Learning System in Cancer Diagnostics (PIECES), Checklist for AI in Medical Imaging (CLAIM) and other relevant best practices.\n\nData collection and usage were approved by the respective ethical review boards of each participating clinical laboratory, and centralised anonymised data handling was approved by the Swedish Ethical Review Authority. The study will be conducted in agreement with the Helsinki Declaration. The findings will be disseminated in peer-reviewed publications (open access).", "doi": "10.1136/bmjopen-2024-097591", "pmid": "40623883", "labels": {"DDLS Fellow": null, "Kimmo Kartasalo": null}, "xrefs": [{"db": "pmc", "key": "PMC12258300"}, {"db": "pii", "key": "bmjopen-2024-097591"}], "notes": [], "created": "2025-10-30T15:40:42.132Z", "modified": "2025-11-04T09:40:10.515Z"}, {"entity": "publication", "iuid": "8edb5e1fae454101ad0818b70bbeee25", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/8edb5e1fae454101ad0818b70bbeee25.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/8edb5e1fae454101ad0818b70bbeee25"}}, "title": "The Role of Artificial Intelligence in the Evaluation of Prostate Pathology.", "authors": [{"family": "Egevad", "given": "Lars", "initials": "L", "orcid": "0000-0001-8531-222X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/a7d46f1f5fc047dc8edb910eb4f0645c.json"}}, {"family": "Camilloni", "given": "Andrea", "initials": "A"}, {"family": "Delahunt", "given": "Brett", "initials": "B"}, {"family": "Samaratunga", "given": "Hemamali", "initials": "H"}, {"family": "Eklund", "given": "Martin", "initials": "M"}, {"family": "Kartasalo", "given": "Kimmo", "initials": "K"}], "type": "journal article", "published": "2025-05-00", "journal": {"title": "Pathol Int", "issn": "1440-1827", "volume": "75", "issue": "5", "pages": "213-220", "issn-l": null}, "abstract": "Artificial intelligence (AI) is an emerging tool in diagnostic pathology, including prostate pathology. This review summarizes the possibilities offered by AI and also discusses the challenges and risks. AI has the potential to assist in the diagnosis and grading of prostate cancer. Diagnostic safety can be enhanced by avoiding the accidental underdiagnosis of small lesions. Another possible benefit is a greater degree of standardization of grading. AI for clinical use needs to be trained on large, high-quality data sets that have been assessed by experienced pathologists. A problem with the use of AI in prostate pathology is the plethora of benign mimics of prostate cancer and morphological variants of cancer that are too unusual to allow sufficient training of AI. AI systems need to be able to account for variations in local routines for cutting, staining, and scanning of slides. We also need to be aware of the risk that users will rely too much on the output of an AI system, leading to diagnostic errors and loss of clinical competence. The reporting pathologist must ultimately be responsible for accepting or rejecting the diagnosis proposed by AI.", "doi": "10.1111/pin.70015", "pmid": "40226937", "labels": {"DDLS Fellow": null, "Kimmo Kartasalo": null}, "xrefs": [{"db": "pmc", "key": "PMC12101047"}], "notes": [], "created": "2025-10-30T15:41:55.249Z", "modified": "2025-10-30T15:41:55.290Z"}, {"entity": "publication", "iuid": "f85fb3bc915e4840a3e68620ac3d82e6", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/f85fb3bc915e4840a3e68620ac3d82e6.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/f85fb3bc915e4840a3e68620ac3d82e6"}}, "title": "Interobserver reproducibility of cribriform cancer in prostate needle biopsies and validation of International Society of Urological Pathology criteria.", "authors": [{"family": "Egevad", "given": "Lars", "initials": "L", "orcid": "0000-0001-8531-222X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/a7d46f1f5fc047dc8edb910eb4f0645c.json"}}, {"family": "Delahunt", "given": "Brett", "initials": "B", "orcid": "0000-0002-5398-0300", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/433a3f884f95451383cc746925d9a08c.json"}}, {"family": "Iczkowski", "given": "Kenneth A", "initials": "KA"}, {"family": "van der Kwast", "given": "Theo", "initials": "T"}, {"family": "van Leenders", "given": "Geert J L H", "initials": "GJLH", "orcid": "0000-0003-2176-9102", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/06fb563d1d3243ffb42d4dbfb495eccf.json"}}, {"family": "Leite", "given": "Katia R M", "initials": "KRM", "orcid": "0000-0002-2615-7730", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/5186bb78617340128628091c878daeda.json"}}, {"family": "Pan", "given": "Chin-Chen", "initials": "C"}, {"family": "Samaratunga", "given": "Hemamali", "initials": "H"}, {"family": "Tsuzuki", "given": "Toyonori", "initials": "T", "orcid": "0000-0002-4855-4366", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/42c993c2c0ab4b50afa03134f70118d9.json"}}, {"family": "Mulliqi", "given": "Nita", "initials": "N"}, {"family": "Ji", "given": "Xiaoyi", "initials": "X"}, {"family": "Olsson", "given": "Henrik", "initials": "H"}, {"family": "Valkonen", "given": "Masi", "initials": "M"}, {"family": "Ruusuvuori", "given": "Pekka", "initials": "P"}, {"family": "Eklund", "given": "Martin", "initials": "M"}, {"family": "Kartasalo", "given": "Kimmo", "initials": "K"}], "type": "journal article", "published": "2023-05-00", "journal": {"title": "Histopathology", "issn": "1365-2559", "issn-l": "0309-0167", "volume": "82", "issue": "6", "pages": "837-845"}, "abstract": "There is strong evidence that cribriform morphology indicates a worse prognosis of prostatic adenocarcinoma. Our aim was to investigate its interobserver reproducibility in prostate needle biopsies.\r\n\r\nA panel of nine prostate pathology experts from five continents independently reviewed 304 digitised biopsies for cribriform cancer according to recent International Society of Urological Pathology criteria. The biopsies were collected from a series of 702 biopsies that were reviewed by one of the panellists for enrichment of high-grade cancer and potentially cribriform structures. A 2/3 consensus diagnosis of cribriform and noncribriform cancer was reached in 90% (272/304) of the biopsies with a mean kappa value of 0.56 (95% confidence interval 0.52-0.61). The prevalence of consensus cribriform cancers was estimated to 4%, 12%, 21%, and 20% of Gleason scores 7 (3 + 4), 7 (4 + 3), 8, and 9-10, respectively. More than two cribriform structures per level or a largest cribriform mass with \u22659 lumina or a diameter of \u22650.5 mm predicted a consensus diagnosis of cribriform cancer in 88% (70/80), 84% (87/103), and 90% (56/62), respectively, and noncribriform cancer in 3% (2/80), 5% (5/103), and 2% (1/62), respectively (all P < 0.01).\r\n\r\nCribriform prostate cancer was seen in a minority of needle biopsies with high-grade cancer. Stringent diagnostic criteria enabled the identification of cribriform patterns and the generation of a large set of consensus cases for standardisation.", "doi": "10.1111/his.14867", "pmid": "36645163", "labels": {"Kimmo Kartasalo": null, "DDLS Fellow": null}, "xrefs": [], "notes": [], "created": "2024-11-05T16:10:21.528Z", "modified": "2024-11-29T10:41:30.167Z"}, {"entity": "publication", "iuid": "34dd4118753048eab5325f80ccac79e7", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/34dd4118753048eab5325f80ccac79e7.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/34dd4118753048eab5325f80ccac79e7"}}, "title": "Estimating diagnostic uncertainty in artificial intelligence assisted pathology using conformal prediction.", "authors": [{"family": "Olsson", "given": "Henrik", "initials": "H", "orcid": "0000-0002-2270-2017", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/da0547e978264d9c88fc6a222dcbfd5f.json"}}, {"family": "Kartasalo", "given": "Kimmo", "initials": "K", "orcid": "0000-0002-9470-4783", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/7c6fc97c06ed456c8bdd1f03db8a9b72.json"}}, {"family": "Mulliqi", "given": "Nita", "initials": "N"}, {"family": "Capuccini", "given": "Marco", "initials": "M"}, {"family": "Ruusuvuori", "given": "Pekka", "initials": "P", "orcid": "0000-0001-9086-9591", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/bb947cd395e84612a53569f4a39abd19.json"}}, {"family": "Samaratunga", "given": "Hemamali", "initials": "H"}, {"family": "Delahunt", "given": "Brett", "initials": "B", "orcid": "0000-0002-5398-0300", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/433a3f884f95451383cc746925d9a08c.json"}}, {"family": "Lindskog", "given": "Cecilia", "initials": "C", "orcid": "0000-0001-5611-1015", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/21610a810a87459c962d6da3f2ad38ad.json"}}, {"family": "Janssen", "given": "Emiel A M", "initials": "EAM"}, {"family": "Blilie", "given": "Anders", "initials": "A"}, {"family": "ISUP Prostate Imagebase Expert Panel", "given": "", "initials": ""}, {"family": "Egevad", "given": "Lars", "initials": "L", "orcid": "0000-0001-8531-222X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/a7d46f1f5fc047dc8edb910eb4f0645c.json"}}, {"family": "Spjuth", "given": "Ola", "initials": "O", "orcid": "0000-0002-8083-2864", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/2c192389f99d4801b91f3350e07dfb9e.json"}}, {"family": "Eklund", "given": "Martin", "initials": "M", "orcid": "0000-0001-5032-5266", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/06721510ebc8462386e0e6fc6c84315b.json"}}], "type": "journal article", "published": "2022-12-15", "journal": {"title": "Nat Commun", "issn": "2041-1723", "issn-l": "2041-1723", "volume": "13", "issue": "1", "pages": "7761"}, "abstract": "Unreliable predictions can occur when an artificial intelligence (AI) system is presented with data it has not been exposed to during training. We demonstrate the use of conformal prediction to detect unreliable predictions, using histopathological diagnosis and grading of prostate biopsies as example. We digitized 7788 prostate biopsies from 1192 men in the STHLM3 diagnostic study, used for training, and 3059 biopsies from 676 men used for testing. With conformal prediction, 1 in 794 (0.1%) predictions is incorrect for cancer diagnosis (compared to 14 errors [2%] without conformal prediction) while 175 (22%) of the predictions are flagged as unreliable when the AI-system is presented with new data from the same lab and scanner that it was trained on. Conformal prediction could with small samples (N = 49 for external scanner, N = 10 for external lab and scanner, and N = 12 for external lab, scanner and pathology assessment) detect systematic differences in external data leading to worse predictive performance. The AI-system with conformal prediction commits 3 (2%) errors for cancer detection in cases of atypical prostate tissue compared to 44 (25%) without conformal prediction, while the system flags 143 (80%) unreliable predictions. We conclude that conformal prediction can increase patient safety of AI-systems.", "doi": "10.1038/s41467-022-34945-8", "pmid": "36522311", "labels": {"Kimmo Kartasalo": null, "DDLS Fellow": null}, "xrefs": [{"db": "pmc", "key": "PMC9755280"}, {"db": "pii", "key": "10.1038/s41467-022-34945-8"}], "notes": [], "created": "2024-11-05T16:10:20.350Z", "modified": "2024-11-29T09:28:59.239Z"}, {"entity": "publication", "iuid": "a9d473ca72164e18a3db61d78fef3d7a", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/a9d473ca72164e18a3db61d78fef3d7a.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/a9d473ca72164e18a3db61d78fef3d7a"}}, "title": "Detection of perineural invasion in prostate needle biopsies with deep neural networks.", "authors": [{"family": "Kartasalo", "given": "Kimmo", "initials": "K", "orcid": "0000-0002-9470-4783", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/7c6fc97c06ed456c8bdd1f03db8a9b72.json"}}, {"family": "Str\u00f6m", "given": "Peter", "initials": "P", "orcid": "0000-0002-1631-806X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/2798ea6ef2ed4ae88b78dd04d2f14437.json"}}, {"family": "Ruusuvuori", "given": "Pekka", "initials": "P", "orcid": "0000-0001-9086-9591", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/bb947cd395e84612a53569f4a39abd19.json"}}, {"family": "Samaratunga", "given": "Hemamali", "initials": "H"}, {"family": "Delahunt", "given": "Brett", "initials": "B", "orcid": "0000-0002-5398-0300", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/433a3f884f95451383cc746925d9a08c.json"}}, {"family": "Tsuzuki", "given": "Toyonori", "initials": "T", "orcid": "0000-0002-4855-4366", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/42c993c2c0ab4b50afa03134f70118d9.json"}}, {"family": "Eklund", "given": "Martin", "initials": "M", "orcid": "0000-0001-5032-5266", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/06721510ebc8462386e0e6fc6c84315b.json"}}, {"family": "Egevad", "given": "Lars", "initials": "L", "orcid": "0000-0001-8531-222X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/a7d46f1f5fc047dc8edb910eb4f0645c.json"}}], "type": "journal article", "published": "2022-07-00", "journal": {"title": "Virchows Arch.", "issn": "1432-2307", "issn-l": "0945-6317", "volume": "481", "issue": "1", "pages": "73-82"}, "abstract": "The presence of perineural invasion (PNI) by carcinoma in prostate biopsies has been shown to be associated with poor prognosis. The assessment and quantification of PNI are, however, labor intensive. To aid pathologists in this task, we developed an artificial intelligence (AI) algorithm based on deep neural networks. We collected, digitized, and pixel-wise annotated the PNI findings in each of the approximately 80,000 biopsy cores from the 7406 men who underwent biopsy in a screening trial between 2012 and 2014. In total, 485 biopsy cores showed PNI. We also digitized more than 10% (n = 8318) of the PNI negative biopsy cores. Digitized biopsies from a random selection of 80% of the men were used to build the AI algorithm, while 20% were used to evaluate its performance. For detecting PNI in prostate biopsy cores, the AI had an estimated area under the receiver operating characteristics curve of 0.98 (95% CI 0.97-0.99) based on 106 PNI positive cores and 1652 PNI negative cores in the independent test set. For a pre-specified operating point, this translates to sensitivity of 0.87 and specificity of 0.97. The corresponding positive and negative predictive values were 0.67 and 0.99, respectively. The concordance of the AI with pathologists, measured by mean pairwise Cohen's kappa (0.74), was comparable to inter-pathologist concordance (0.68 to 0.75). The proposed algorithm detects PNI in prostate biopsies with acceptable performance. This could aid pathologists by reducing the number of biopsies that need to be assessed for PNI and by highlighting regions of diagnostic interest.", "doi": "10.1007/s00428-022-03326-3", "pmid": "35449363", "labels": {"Kimmo Kartasalo": null, "DDLS Fellow": null}, "xrefs": [{"db": "pmc", "key": "PMC9226086"}, {"db": "pii", "key": "10.1007/s00428-022-03326-3"}], "notes": [], "created": "2024-11-05T16:09:36.259Z", "modified": "2024-11-29T09:29:14.824Z"}, {"entity": "publication", "iuid": "90b36d42fc5b4fb98ab07730320e52f5", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/90b36d42fc5b4fb98ab07730320e52f5.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/90b36d42fc5b4fb98ab07730320e52f5"}}, "title": "Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge.", "authors": [{"family": "Bulten", "given": "Wouter", "initials": "W", "orcid": "0000-0002-6129-5039", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/f592c80c84c34a70971251c380a8578b.json"}}, {"family": "Kartasalo", "given": "Kimmo", "initials": "K", "orcid": "0000-0002-9470-4783", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/7c6fc97c06ed456c8bdd1f03db8a9b72.json"}}, {"family": "Chen", "given": "Po-Hsuan Cameron", "initials": "PC", "orcid": "0000-0002-0083-4991", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/dd162c57871947aea109e009fc1d2daf.json"}}, {"family": "Str\u00f6m", "given": "Peter", "initials": "P", "orcid": "0000-0002-1631-806X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/2798ea6ef2ed4ae88b78dd04d2f14437.json"}}, {"family": "Pinckaers", "given": "Hans", "initials": "H"}, {"family": "Nagpal", "given": "Kunal", "initials": "K"}, {"family": "Cai", "given": "Yuannan", "initials": "Y"}, {"family": "Steiner", "given": "David F", "initials": "DF", "orcid": "0000-0003-1297-0023", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/a209b0168a394a09bd0cfe9cd1e1934b.json"}}, {"family": "van Boven", "given": "Hester", "initials": "H"}, {"family": "Vink", "given": "Robert", "initials": "R"}, {"family": "Hulsbergen-van de Kaa", "given": "Christina", "initials": "C"}, {"family": "van der Laak", "given": "Jeroen", "initials": "J", "orcid": "0000-0001-7982-0754", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/188f689ad0304f28b42bc9d3dbf6a56e.json"}}, {"family": "Amin", "given": "Mahul B", "initials": "MB", "orcid": "0000-0001-5943-3634", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/d7974058596e4429b0035f1eff340a4c.json"}}, {"family": "Evans", "given": "Andrew J", "initials": "AJ"}, {"family": "van der Kwast", "given": "Theodorus", "initials": "T", "orcid": "0000-0001-8640-5786", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/176f93a02e394a659619ae2ff57398e4.json"}}, {"family": "Allan", "given": "Robert", "initials": "R"}, {"family": "Humphrey", "given": "Peter A", "initials": "PA"}, {"family": "Gr\u00f6nberg", "given": "Henrik", "initials": "H", "orcid": "0000-0002-1073-2753", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/33927307bf964b2fa09e09c0c867b542.json"}}, {"family": "Samaratunga", "given": "Hemamali", "initials": "H"}, {"family": "Delahunt", "given": "Brett", "initials": "B"}, {"family": "Tsuzuki", "given": "Toyonori", "initials": "T", "orcid": "0000-0002-4855-4366", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/42c993c2c0ab4b50afa03134f70118d9.json"}}, {"family": "H\u00e4kkinen", "given": "Tomi", "initials": "T"}, {"family": "Egevad", "given": "Lars", "initials": "L", "orcid": "0000-0001-8531-222X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/a7d46f1f5fc047dc8edb910eb4f0645c.json"}}, {"family": "Demkin", "given": "Maggie", "initials": "M"}, {"family": "Dane", "given": "Sohier", "initials": "S"}, {"family": "Tan", "given": "Fraser", "initials": "F"}, {"family": "Valkonen", "given": "Masi", "initials": "M", "orcid": "0000-0003-3091-2484", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/ae4841e8a4124dc79c921b3af09096fe.json"}}, {"family": "Corrado", "given": "Greg S", "initials": "GS"}, {"family": "Peng", "given": "Lily", "initials": "L"}, {"family": "Mermel", "given": "Craig H", "initials": "CH", "orcid": "0000-0002-0816-3395", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/ff69bed2b4394cd8972c937ebb642c55.json"}}, {"family": "Ruusuvuori", "given": "Pekka", "initials": "P", "orcid": "0000-0001-9086-9591", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/bb947cd395e84612a53569f4a39abd19.json"}}, {"family": "Litjens", "given": "Geert", "initials": "G", "orcid": "0000-0003-1554-1291", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/3792b285bcf04c11b268da1088160a9d.json"}}, {"family": "Eklund", "given": "Martin", "initials": "M", "orcid": "0000-0001-5032-5266", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/06721510ebc8462386e0e6fc6c84315b.json"}}, {"family": "PANDA challenge consortium", "given": "", "initials": ""}], "type": "journal article", "published": "2022-01-00", "journal": {"title": "Nat. Med.", "issn": "1546-170X", "issn-l": "1078-8956", "volume": "28", "issue": "1", "pages": "154-163"}, "abstract": "Artificial intelligence (AI) has shown promise for diagnosing prostate cancer in biopsies. However, results have been limited to individual studies, lacking validation in multinational settings. Competitions have been shown to be accelerators for medical imaging innovations, but their impact is hindered by lack of reproducibility and independent validation. With this in mind, we organized the PANDA challenge-the largest histopathology competition to date, joined by 1,290 developers-to catalyze development of reproducible AI algorithms for Gleason grading using 10,616 digitized prostate biopsies. We validated that a diverse set of submitted algorithms reached pathologist-level performance on independent cross-continental cohorts, fully blinded to the algorithm developers. On United States and European external validation sets, the algorithms achieved agreements of 0.862 (quadratically weighted \u03ba, 95% confidence interval (CI), 0.840-0.884) and 0.868 (95% CI, 0.835-0.900) with expert uropathologists. Successful generalization across different patient populations, laboratories and reference standards, achieved by a variety of algorithmic approaches, warrants evaluating AI-based Gleason grading in prospective clinical trials.", "doi": "10.1038/s41591-021-01620-2", "pmid": "35027755", "labels": {"Kimmo Kartasalo": null, "DDLS Fellow": null}, "xrefs": [{"db": "pmc", "key": "PMC8799467"}, {"db": "pii", "key": "10.1038/s41591-021-01620-2"}], "notes": [], "created": "2024-11-05T16:09:31.876Z", "modified": "2024-11-29T09:30:09.852Z"}, {"entity": "publication", "iuid": "9900bd886963425bb691338c471bedf9", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/9900bd886963425bb691338c471bedf9.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/9900bd886963425bb691338c471bedf9"}}, "title": "OpenPhi: an interface to access Philips iSyntax whole slide images for computational pathology.", "authors": [{"family": "Mulliqi", "given": "Nita", "initials": "N"}, {"family": "Kartasalo", "given": "Kimmo", "initials": "K", "orcid": "0000-0002-9470-4783", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/7c6fc97c06ed456c8bdd1f03db8a9b72.json"}}, {"family": "Olsson", "given": "Henrik", "initials": "H", "orcid": "0000-0002-2270-2017", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/da0547e978264d9c88fc6a222dcbfd5f.json"}}, {"family": "Ji", "given": "Xiaoyi", "initials": "X"}, {"family": "Egevad", "given": "Lars", "initials": "L", "orcid": "0000-0001-8531-222X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/a7d46f1f5fc047dc8edb910eb4f0645c.json"}}, {"family": "Eklund", "given": "Martin", "initials": "M", "orcid": "0000-0001-5032-5266", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/06721510ebc8462386e0e6fc6c84315b.json"}}, {"family": "Ruusuvuori", "given": "Pekka", "initials": "P", "orcid": "0000-0001-9086-9591", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/bb947cd395e84612a53569f4a39abd19.json"}}], "type": "journal article", "published": "2021-11-05", "journal": {"title": "Bioinformatics", "issn": "1367-4811", "issn-l": "1367-4803", "volume": "37", "issue": "21", "pages": "3995-3997"}, "abstract": "Digital pathology enables applying computational methods, such as deep learning, in pathology for improved diagnostics and prognostics, but lack of interoperability between whole slide image formats of different scanner vendors is a challenge for algorithm developers. We present OpenPhi-Open PatHology Interface, an Application Programming Interface for seamless access to the iSyntax format used by the Philips Ultra Fast Scanner, the first digital pathology scanner approved by the United States Food and Drug Administration. OpenPhi is extensible and easily interfaced with existing vendor-neutral applications.\r\n\r\nOpenPhi is implemented in Python and is available as open-source under the MIT license at: https://gitlab.com/BioimageInformaticsGroup/openphi. The Philips Software Development Kit is required and available at: https://www.openpathology.philips.com. OpenPhi version 1.1.1 is additionally provided as Supplementary Data.\r\n\r\nSupplementary data are available at Bioinformatics online.", "doi": "10.1093/bioinformatics/btab578", "pmid": "34358287", "labels": {"Kimmo Kartasalo": null, "DDLS Fellow": null}, "xrefs": [{"db": "pmc", "key": "PMC8570784"}, {"db": "pii", "key": "6343446"}], "notes": [], "created": "2024-11-05T16:08:25.508Z", "modified": "2024-11-29T09:30:27.734Z"}, {"entity": "publication", "iuid": "09a071792cf64b67ab7ab31033715e90", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/09a071792cf64b67ab7ab31033715e90.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/09a071792cf64b67ab7ab31033715e90"}}, "title": "Interobserver reproducibility of perineural invasion of prostatic adenocarcinoma in needle biopsies.", "authors": [{"family": "Egevad", "given": "Lars", "initials": "L", "orcid": "0000-0001-8531-222X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/a7d46f1f5fc047dc8edb910eb4f0645c.json"}}, {"family": "Delahunt", "given": "Brett", "initials": "B", "orcid": "0000-0002-5398-0300", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/433a3f884f95451383cc746925d9a08c.json"}}, {"family": "Samaratunga", "given": "Hemamali", "initials": "H"}, {"family": "Tsuzuki", "given": "Toyonori", "initials": "T"}, {"family": "Olsson", "given": "Henrik", "initials": "H"}, {"family": "Str\u00f6m", "given": "Peter", "initials": "P", "orcid": "0000-0002-1631-806X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/2798ea6ef2ed4ae88b78dd04d2f14437.json"}}, {"family": "Lindskog", "given": "Cecilia", "initials": "C"}, {"family": "H\u00e4kkinen", "given": "Tomi", "initials": "T"}, {"family": "Kartasalo", "given": "Kimmo", "initials": "K"}, {"family": "Eklund", "given": "Martin", "initials": "M"}, {"family": "Ruusuvuori", "given": "Pekka", "initials": "P"}], "type": "journal article", "published": "2021-06-00", "journal": {"title": "Virchows Arch.", "issn": "1432-2307", "issn-l": "0945-6317", "volume": "478", "issue": "6", "pages": "1109-1116"}, "abstract": "Numerous studies have shown a correlation between perineural invasion (PNI) in prostate biopsies and outcome. The reporting of PNI varies widely in the literature. While the interobserver variability of prostate cancer grading has been studied extensively, less is known regarding the reproducibility of PNI. A total of 212 biopsy cores from a population-based screening trial were included in this study (106 with and 106 without PNI according to the original pathology reports). The glass slides were scanned and circulated among four pathologists with a special interest in urological pathology for assessment of PNI. Discordant cases were stained by immunohistochemistry for S-100 protein. PNI was diagnosed by all four observers in 34.0% of cases, while 41.5% were considered to be negative for PNI. In 24.5% of cases, there was a disagreement between the observers. The kappa for interobserver variability was 0.67-0.75 (mean 0.73). The observations from one participant were compared with data from the original reports, and a kappa for intraobserver variability of 0.87 was achieved. Based on immunohistochemical findings among discordant cases, 88.6% had PNI while 11.4% did not. The most common diagnostic pitfall was the presence of bundles of stroma or smooth muscle. It was noted in a few cases that collagenous micronodules could be mistaken for a nerve. The distance between cancer and nerve was another cause of disagreement. Although the results suggest that the reproducibility of PNI may be greater than that of prostate cancer grading, there is still a need for improvement and standardization.", "doi": "10.1007/s00428-021-03039-z", "pmid": "33534005", "labels": {"Kimmo Kartasalo": null, "DDLS Fellow": null}, "xrefs": [{"db": "pmc", "key": "PMC8203540"}, {"db": "pii", "key": "10.1007/s00428-021-03039-z"}], "notes": [], "created": "2024-11-05T16:08:21.035Z", "modified": "2024-11-29T10:45:08.430Z"}, {"entity": "publication", "iuid": "29745e524468452d8313b0884f8360b8", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/29745e524468452d8313b0884f8360b8.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/29745e524468452d8313b0884f8360b8"}}, "title": "Identification of areas of grading difficulties in prostate cancer and comparison with artificial intelligence assisted grading.", "authors": [{"family": "Egevad", "given": "Lars", "initials": "L", "orcid": "0000-0001-8531-222X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/a7d46f1f5fc047dc8edb910eb4f0645c.json"}}, {"family": "Swanberg", "given": "Daniela", "initials": "D"}, {"family": "Delahunt", "given": "Brett", "initials": "B"}, {"family": "Str\u00f6m", "given": "Peter", "initials": "P"}, {"family": "Kartasalo", "given": "Kimmo", "initials": "K"}, {"family": "Olsson", "given": "Henrik", "initials": "H"}, {"family": "Berney", "given": "Dan M", "initials": "DM"}, {"family": "Bostwick", "given": "David G", "initials": "DG"}, {"family": "Evans", "given": "Andrew J", "initials": "AJ"}, {"family": "Humphrey", "given": "Peter A", "initials": "PA"}, {"family": "Iczkowski", "given": "Kenneth A", "initials": "KA"}, {"family": "Kench", "given": "James G", "initials": "JG"}, {"family": "Kristiansen", "given": "Glen", "initials": "G"}, {"family": "Leite", "given": "Katia R M", "initials": "KRM"}, {"family": "McKenney", "given": "Jesse K", "initials": "JK"}, {"family": "Oxley", "given": "Jon", "initials": "J"}, {"family": "Pan", "given": "Chin-Chen", "initials": "C"}, {"family": "Samaratunga", "given": "Hemamali", "initials": "H"}, {"family": "Srigley", "given": "John R", "initials": "JR"}, {"family": "Takahashi", "given": "Hiroyuki", "initials": "H"}, {"family": "Tsuzuki", "given": "Toyonori", "initials": "T"}, {"family": "van der Kwast", "given": "Theo", "initials": "T"}, {"family": "Varma", "given": "Murali", "initials": "M"}, {"family": "Zhou", "given": "Ming", "initials": "M"}, {"family": "Clements", "given": "Mark", "initials": "M"}, {"family": "Eklund", "given": "Martin", "initials": "M"}], "type": "comparative study", "published": "2020-12-00", "journal": {"title": "Virchows Arch.", "issn": "1432-2307", "issn-l": "0945-6317", "volume": "477", "issue": "6", "pages": "777-786"}, "abstract": "The International Society of Urological Pathology (ISUP) hosts a reference image database supervised by experts with the purpose of establishing an international standard in prostate cancer grading. Here, we aimed to identify areas of grading difficulties and compare the results with those obtained from an artificial intelligence system trained in grading. In a series of 87 needle biopsies of cancers selected to include problematic cases, experts failed to reach a 2/3 consensus in 41.4% (36/87). Among consensus and non-consensus cases, the weighted kappa was 0.77 (range 0.68-0.84) and 0.50 (range 0.40-0.57), respectively. Among the non-consensus cases, four main causes of disagreement were identified: the distinction between Gleason score 3 + 3 with tangential cutting artifacts vs. Gleason score 3 + 4 with poorly formed or fused glands (13 cases), Gleason score 3 + 4 vs. 4 + 3 (7 cases), Gleason score 4 + 3 vs. 4 + 4 (8 cases) and the identification of a small component of Gleason pattern 5 (6 cases). The AI system obtained a weighted kappa value of 0.53 among the non-consensus cases, placing it as the observer with the sixth best reproducibility out of a total of 24. AI may serve as a decision support and decrease inter-observer variability by its ability to make consistent decisions. The grading of these cancer patterns that best predicts outcome and guides treatment warrants further clinical and genetic studies. Results of such investigations should be used to improve calibration of AI systems.", "doi": "10.1007/s00428-020-02858-w", "pmid": "32542445", "labels": {"Kimmo Kartasalo": null, "DDLS Fellow": null}, "xrefs": [{"db": "pmc", "key": "PMC7683442"}, {"db": "pii", "key": "10.1007/s00428-020-02858-w"}], "notes": [], "created": "2024-11-05T16:08:18.753Z", "modified": "2024-11-29T10:45:14.878Z"}, {"entity": "publication", "iuid": "09ab7a2cbe9041f19abb08c0d6434642", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/09ab7a2cbe9041f19abb08c0d6434642.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/09ab7a2cbe9041f19abb08c0d6434642"}}, "title": "The utility of artificial intelligence in the assessment of prostate pathology.", "authors": [{"family": "Egevad", "given": "Lars", "initials": "L", "orcid": "0000-0001-8531-222X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/a7d46f1f5fc047dc8edb910eb4f0645c.json"}}, {"family": "Str\u00f6m", "given": "Peter", "initials": "P", "orcid": "0000-0002-1631-806X", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/2798ea6ef2ed4ae88b78dd04d2f14437.json"}}, {"family": "Kartasalo", "given": "Kimmo", "initials": "K"}, {"family": "Olsson", "given": "Henrik", "initials": "H"}, {"family": "Samaratunga", "given": "Hemamali", "initials": "H"}, {"family": "Delahunt", "given": "Brett", "initials": "B", "orcid": "0000-0002-5398-0300", "researcher": {"href": "https://publications-affiliated.scilifelab.se/researcher/433a3f884f95451383cc746925d9a08c.json"}}, {"family": "Eklund", "given": "Martin", "initials": "M"}], "type": "editorial", "published": "2020-05-00", "journal": {"title": "Histopathology", "issn": "1365-2559", "issn-l": "0309-0167", "volume": "76", "issue": "6", "pages": "790-792"}, "abstract": null, "doi": "10.1111/his.14060", "pmid": "32402150", "labels": {"Kimmo Kartasalo": null, "DDLS Fellow": null}, "xrefs": [], "notes": [], "created": "2024-11-05T16:10:26.497Z", "modified": "2024-11-29T10:45:28.264Z"}]}