SwePub
Sök i LIBRIS databas

  Utökad sökning

WFRF:(Samaratunga Hemamali)
 

Sökning: WFRF:(Samaratunga Hemamali) > Artificial intellig...

  • Strom, PeterKarolinska Institutet,Karolinska Inst, Dept Med Epidemiol & Biostat, Stockholm, Sweden (författare)

Artificial intelligence for diagnosis and grading of prostate cancer in biopsies : a population-based, diagnostic study

  • Artikel/kapitelEngelska2020

Förlag, utgivningsår, omfång ...

  • Elsevier,2020
  • printrdacarrier

Nummerbeteckningar

  • LIBRIS-ID:oai:DiVA.org:uu-407437
  • https://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-407437URI
  • https://doi.org/10.1016/S1470-2045(19)30738-7DOI
  • http://kipublications.ki.se/Default.aspx?queryparsed=id:142968046URI

Kompletterande språkuppgifter

  • Språk:engelska
  • Sammanfattning på:engelska

Ingår i deldatabas

Klassifikation

  • Ämneskategori:ref swepub-contenttype
  • Ämneskategori:art swepub-publicationtype

Anmärkningar

  • BackgroundAn increasing volume of prostate biopsies and a worldwide shortage of urological pathologists puts a strain on pathology departments. Additionally, the high intra-observer and inter-observer variability in grading can result in overtreatment and undertreatment of prostate cancer. To alleviate these problems, we aimed to develop an artificial intelligence (AI) system with clinically acceptable accuracy for prostate cancer detection, localisation, and Gleason grading.MethodsWe digitised 6682 slides from needle core biopsies from 976 randomly selected participants aged 50–69 in the Swedish prospective and population-based STHLM3 diagnostic study done between May 28, 2012, and Dec 30, 2014 (ISRCTN84445406), and another 271 from 93 men from outside the study. The resulting images were used to train deep neural networks for assessment of prostate biopsies. The networks were evaluated by predicting the presence, extent, and Gleason grade of malignant tissue for an independent test dataset comprising 1631 biopsies from 246 men from STHLM3 and an external validation dataset of 330 biopsies from 73 men. We also evaluated grading performance on 87 biopsies individually graded by 23 experienced urological pathologists from the International Society of Urological Pathology. We assessed discriminatory performance by receiver operating characteristics and tumour extent predictions by correlating predicted cancer length against measurements by the reporting pathologist. We quantified the concordance between grades assigned by the AI system and the expert urological pathologists using Cohen's kappa.FindingsThe AI achieved an area under the receiver operating characteristics curve of 0·997 (95% CI 0·994–0·999) for distinguishing between benign (n=910) and malignant (n=721) biopsy cores on the independent test dataset and 0·986 (0·972–0·996) on the external validation dataset (benign n=108, malignant n=222). The correlation between cancer length predicted by the AI and assigned by the reporting pathologist was 0·96 (95% CI 0·95–0·97) for the independent test dataset and 0·87 (0·84–0·90) for the external validation dataset. For assigning Gleason grades, the AI achieved a mean pairwise kappa of 0·62, which was within the range of the corresponding values for the expert pathologists (0·60–0·73).InterpretationAn AI system can be trained to detect and grade cancer in prostate needle biopsy samples at a ranking comparable to that of international experts in prostate pathology. Clinical application could reduce pathology workload by reducing the assessment of benign biopsies and by automating the task of measuring cancer length in positive biopsy cores. An AI system with expert-level grading performance might contribute a second opinion, aid in standardising grading, and provide pathology expertise in parts of the world where it does not exist.

Ämnesord och genrebeteckningar

Biuppslag (personer, institutioner, konferenser, titlar ...)

  • Kartasalo, KimmoKarolinska Institutet,Tampere Univ, Fac Med & Hlth Technol, Tampere, Finland,Cleveland Clin, Pathol & Lab Med Inst, Cleveland, OH 44106 USA (författare)
  • Olsson, HenrikKarolinska Institutet,Karolinska Inst, Dept Med Epidemiol & Biostat, Stockholm, Sweden (författare)
  • Solorzano, Leslie,1989-Uppsala universitet,Bildanalys och människa-datorinteraktion(Swepub:uu)lesso657 (författare)
  • Delahunt, BrettUniv Otago, Wellington Sch Med & Hlth Sci, Dept Pathol & Mol Med, Wellington, New Zealand (författare)
  • Berney, Daniel M.Queen Mary Univ London, Barts Canc Inst, London, England (författare)
  • Bostwick, David G.Bostwick Labs, Orlando, FL USA (författare)
  • Evans, Andrew J.Toronto Gen Hosp, Univ Hlth Network, Toronto, ON, Canada (författare)
  • Grignon, David J.Indiana Univ Sch Med, Dept Pathol & Lab Med, Indianapolis, IN 46202 USA (författare)
  • Humphrey, Peter A.Yale Univ, Sch Med, Dept Pathol, New Haven, CT 06510 USA (författare)
  • Iczkowski, Kenneth A.Med Coll Wisconsin, Dept Pathol, Milwaukee, WI 53226 USA (författare)
  • Kench, James G.Royal Prince Alfred Hosp, Dept Tissue Pathol & Diagnost Oncol, Sydney, NSW, Australia;Univ Sydney, Cent Clin Sch, Sydney, NSW, Australia (författare)
  • Kristiansen, GlenUniv Hosp Bonn, Inst Pathol, Bonn, Germany (författare)
  • van der Kwast, Theodorus H.Toronto Gen Hosp, Univ Hlth Network, Toronto, ON, Canada (författare)
  • Leite, Katia R. M.Karolinska Institutet,Univ Sao Paulo, Sch Med, Dept Urol Lab Med Res, Sao Paulo, Brazil,Karolinska Inst, Dept Med Epidemiol & Biostat, Stockholm, Sweden (författare)
  • McKenney, Jesse K.Cleveland Clin, Pathol & Lab Med Inst, Cleveland, OH 44106 USA (författare)
  • Oxley, JonSouthmead Hosp, Dept Cellular Pathol, Bristol, Avon, England (författare)
  • Pan, Chin-ChenTaipei Vet Gen Hosp, Dept Pathol, Taipei, Taiwan (författare)
  • Samaratunga, HemamaliAquesta Uropathol & Univ Queensland, Brisbane, Qld, Australia (författare)
  • Srigley, John R.Univ Toronto, Dept Lab Med & Pathobiol, Toronto, ON, Canada (författare)
  • Takahashi, HiroyukiJikei Univ, Dept Pathol, Sch Med, Tokyo, Japan (författare)
  • Tsuzuki, ToyonoriAichi Med Univ, Sch Med, Dept Surg Pathol, Nagakute, Aichi, Japan (författare)
  • Varma, MuraliUniv Wales Hosp, Dept Cellular Pathol, Cardiff, Wales (författare)
  • Zhou, MingUniv Texas Southwestern Med Ctr Dallas, Dept Pathol, Dallas, TX 75390 USA (författare)
  • Lindberg, JohanKarolinska Institutet,Karolinska Inst, Dept Med Epidemiol & Biostat, Stockholm, Sweden (författare)
  • Lindskog, CeciliaUppsala universitet,Klinisk och experimentell patologi(Swepub:uu)cecli129 (författare)
  • Ruusuvuori, PekkaTampere Univ, Fac Med & Hlth Technol, Tampere, Finland (författare)
  • Wählby, Carolina,professor,1974-Uppsala universitet,Bildanalys och människa-datorinteraktion,Science for Life Laboratory, SciLifeLab(Swepub:uu)cli05194 (författare)
  • Gronberg, HenrikKarolinska Institutet,Karolinska Inst, Dept Med Epidemiol & Biostat, Stockholm, Sweden;St Goran Hosp, Dept Oncol, Stockholm, Sweden (författare)
  • Rantalainen, MattiasKarolinska Inst, Dept Med Epidemiol & Biostat, Stockholm, Sweden (författare)
  • Egevad, LarsKarolinska Institutet,Karolinska Inst, Dept Pathol & Oncol, Stockholm, Sweden (författare)
  • Eklund, MartinKarolinska Institutet,Karolinska Inst, Dept Med Epidemiol & Biostat, Stockholm, Sweden (författare)
  • Karolinska InstitutetKarolinska Inst, Dept Med Epidemiol & Biostat, Stockholm, Sweden (creator_code:org_t)

Sammanhörande titlar

  • Ingår i:The Lancet Oncology: Elsevier21:2, s. 222-2321470-20451474-5488

Internetlänk

Hitta via bibliotek

Till lärosätets databas

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Stäng

Kopiera och spara länken för att återkomma till aktuell vy