High throughput assessment of biomarkers in tissue microarrays using artificial intelligence: PTEN loss as a proof-of-principle in multi-center prostate cancer cohorts

Autor(es):Mostrar menos -

Harmon, Stephanie A. ^{[1, 2]} ; Patel, Palak G. ^{[3, 4, 5]} ; Sanford, Thomas H. ^{[1, 6]} ; Caven, Isabelle ^{[3, 4]} ; Iseman, Rachael ^{[3, 4]} ; Vidotto, Thiago ^[7] ; Picanco, Clarissa ^[7] ; Squire, Jeremy A. ^{[3, 7]} ; Masoudi, Samira ^[1] ; Mehralivand, Sherif ^[1] ; Choyke, Peter L. ^[1] ; Berman, David M. ^{[3, 4]} ; Turkbey, Baris ^[1] ; Jamaspishvili, Tamara ^{[3, 4]}

Afiliação do(s) autor(es)

^[1] NCI, Mol Imaging Branch, NIH, Bethesda, MD 20892 - USA

^[2] Frederick Natl Lab Canc Res, Clin Res Directorate, Frederick, MD - USA

^[3] Queens Univ, Dept Pathol & Mol Med, Kingston, ON - Canada

^[4] Queens Univ, Div Canc Biol & Genet, Canc Res Inst, Kingston, ON - Canada

^[5] Hosp Sick Children, Dept Cell Biol, Arthur & Sonia Labatt Brain Tumour Res Ctr, Toronto, ON - Canada

^[6] SUNY Upstate Med Univ, Dept Urol, Syracuse, NY 13210 - USA

^[7] Univ Sao Paulo, Ribeirao Preto Med Sch, Dept Genet, Ribeirao Preto - Brazil

• Tipo de documento: Artigo Científico
• Fonte: MODERN PATHOLOGY; v. 34, n. 2 SEP 2020.
• Citações Web of Science: 1

Resumo

Phosphatase and tensin homolog (PTEN) loss is associated with adverse outcomes in prostate cancer and has clinical potential as a prognostic biomarker. The objective of this work was to develop an artificial intelligence (AI) system for automated detection and localization of PTEN loss on immunohistochemically (IHC) stained sections. PTEN loss was assessed using IHC in two prostate tissue microarrays (TMA) (internal cohort,n = 272 and external cohort,n = 129 patients). TMA cores were visually scored for PTEN loss by pathologists and, if present, spatially annotated. Cores from each patient within the internal TMA cohort were split into 90% cross-validation (N = 2048) and 10% hold-out testing (N = 224) sets. ResNet-101 architecture was used to train core-based classification using a multi-resolution ensemble approach (x5, x10, and x20). For spatial annotations, single resolution pixel-based classification was trained from patches extracted at x20 resolution, interpolated to x40 resolution, and applied in a sliding-window fashion. A final AI-based prediction model was created from combining multi-resolution and pixel-based models. Performance was evaluated in 428 cores of external cohort. From both cohorts, a total of 2700 cores were studied, with a frequency of PTEN loss of 14.5% in internal (180/1239) and external 13.5% (43/319) cancer cores. The final AI-based prediction of PTEN status demonstrated 98.1% accuracy (95.0% sensitivity, 98.4% specificity; median dice score = 0.811) in internal cohort cross-validation set and 99.1% accuracy (100% sensitivity, 99.0% specificity; median dice score = 0.804) in internal cohort test set. Overall core-based classification in the external cohort was significantly improved in the external cohort (area under the curve = 0.964, 90.6% sensitivity, 95.7% specificity) when further trained (fine-tuned) using 15% of cohort data (19/124 patients). These results demonstrate a robust and fully automated method for detection and localization of PTEN loss in prostate cancer tissue samples. AI-based algorithms have potential to streamline sample assessment in research and clinical laboratories. (AU)

• Processo FAPESP: 15/09111-5 - Investigação de Biomarcadores Genômicos para Aplicação Clínica no Câncer de Próstata
• Beneficiário: Jeremy Andrew Squire
• Modalidade de apoio: Auxílio à Pesquisa - Regular
• Processo FAPESP: 17/08614-9 - O Papel de PTEN na Resposta Inflamatória Mediada por STAT1 e STAT3 no Câncer de Próstata
• Beneficiário: Thiago Vidotto
• Modalidade de apoio: Bolsas no Exterior - Estágio de Pesquisa - Doutorado
• Processo FAPESP: 15/22785-5 - O Papel da Perda do Gene PTEN na Facilitação da Resposta Inflamatória no Câncer de Prótata
• Beneficiário: Thiago Vidotto
• Modalidade de apoio: Bolsas no Brasil - Doutorado