Lars Egevad, Andrea Camilloni, Brett Delahunt, Hemamali Samaratunga, Martin Eklund, Kimmo Kartasalo
{"title":"人工智能在前列腺病理评估中的作用。","authors":"Lars Egevad, Andrea Camilloni, Brett Delahunt, Hemamali Samaratunga, Martin Eklund, Kimmo Kartasalo","doi":"10.1111/pin.70015","DOIUrl":null,"url":null,"abstract":"<p><p>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.</p>","PeriodicalId":19806,"journal":{"name":"Pathology International","volume":" ","pages":"213-220"},"PeriodicalIF":2.5000,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12101047/pdf/","citationCount":"0","resultStr":"{\"title\":\"The Role of Artificial Intelligence in the Evaluation of Prostate Pathology.\",\"authors\":\"Lars Egevad, Andrea Camilloni, Brett Delahunt, Hemamali Samaratunga, Martin Eklund, Kimmo Kartasalo\",\"doi\":\"10.1111/pin.70015\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>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.</p>\",\"PeriodicalId\":19806,\"journal\":{\"name\":\"Pathology International\",\"volume\":\" \",\"pages\":\"213-220\"},\"PeriodicalIF\":2.5000,\"publicationDate\":\"2025-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12101047/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Pathology International\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1111/pin.70015\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/4/14 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q2\",\"JCRName\":\"PATHOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Pathology International","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1111/pin.70015","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/4/14 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"PATHOLOGY","Score":null,"Total":0}
The Role of Artificial Intelligence in the Evaluation of Prostate Pathology.
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.
期刊介绍:
Pathology International is the official English journal of the Japanese Society of Pathology, publishing articles of excellence in human and experimental pathology. The Journal focuses on the morphological study of the disease process and/or mechanisms. For human pathology, morphological investigation receives priority but manuscripts describing the result of any ancillary methods (cellular, chemical, immunological and molecular biological) that complement the morphology are accepted. Manuscript on experimental pathology that approach pathologenesis or mechanisms of disease processes are expected to report on the data obtained from models using cellular, biochemical, molecular biological, animal, immunological or other methods in conjunction with morphology. Manuscripts that report data on laboratory medicine (clinical pathology) without significant morphological contribution are not accepted.