Oscar G F Geessink1,2,3, Alexi Baidoshvili3, Joost M Klaase4, Babak Ehteshami Bejnordi2, Geert J S Litjens1,2, Gabi W van Pelt5, Wilma E Mesker5, Iris D Nagtegaal1, Francesco Ciompi1,2, Jeroen A W M van der Laak6,7,8. 1. Department of Pathology, Radboud Institute for Health Sciences, Radboud University Medical Center, P.O.Box 9101, 6500 HB, Nijmegen, The Netherlands. 2. Diagnostic Image Analysis Group (DIAG), Radboud University Medical Center, Nijmegen, The Netherlands. 3. Laboratory for Pathology East Netherlands (LabPON), Hengelo, The Netherlands. 4. Department of Surgery, Medisch Spectrum Twente, Enschede, The Netherlands. 5. Department of Surgery, Leiden University Medical Center, Leiden, The Netherlands. 6. Department of Pathology, Radboud Institute for Health Sciences, Radboud University Medical Center, P.O.Box 9101, 6500 HB, Nijmegen, The Netherlands. Jeroen.vanderlaak@radboudumc.nl. 7. Diagnostic Image Analysis Group (DIAG), Radboud University Medical Center, Nijmegen, The Netherlands. Jeroen.vanderlaak@radboudumc.nl. 8. Center for Medical Image Science and Visualization, Linköping University, Linköping, Sweden. Jeroen.vanderlaak@radboudumc.nl.
Abstract
PURPOSE: Tumor-stroma ratio (TSR) serves as an independent prognostic factor in colorectal cancer and other solid malignancies. The recent introduction of digital pathology in routine tissue diagnostics holds opportunities for automated TSR analysis. We investigated the potential of computer-aided quantification of intratumoral stroma in rectal cancer whole-slide images. METHODS: Histological slides from 129 rectal adenocarcinoma patients were analyzed by two experts who selected a suitable stroma hot-spot and visually assessed TSR. A semi-automatic method based on deep learning was trained to segment all relevant tissue types in rectal cancer histology and subsequently applied to the hot-spots provided by the experts. Patients were assigned to a 'stroma-high' or 'stroma-low' group by both TSR methods (visual and automated). This allowed for prognostic comparison between the two methods in terms of disease-specific and disease-free survival times. RESULTS: With stroma-low as baseline, automated TSR was found to be prognostic independent of age, gender, pT-stage, lymph node status, tumor grade, and whether adjuvant therapy was given, both for disease-specific survival (hazard ratio = 2.48 (95% confidence interval 1.29-4.78)) and for disease-free survival (hazard ratio = 2.05 (95% confidence interval 1.11-3.78)). Visually assessed TSR did not serve as an independent prognostic factor in multivariate analysis. CONCLUSIONS: This work shows that TSR is an independent prognosticator in rectal cancer when assessed automatically in user-provided stroma hot-spots. The deep learning-based technology presented here may be a significant aid to pathologists in routine diagnostics.
PURPOSE:Tumor-stroma ratio (TSR) serves as an independent prognostic factor in colorectal cancer and other solid malignancies. The recent introduction of digital pathology in routine tissue diagnostics holds opportunities for automated TSR analysis. We investigated the potential of computer-aided quantification of intratumoral stroma in rectal cancer whole-slide images. METHODS: Histological slides from 129 rectal adenocarcinomapatients were analyzed by two experts who selected a suitable stroma hot-spot and visually assessed TSR. A semi-automatic method based on deep learning was trained to segment all relevant tissue types in rectal cancer histology and subsequently applied to the hot-spots provided by the experts. Patients were assigned to a 'stroma-high' or 'stroma-low' group by both TSR methods (visual and automated). This allowed for prognostic comparison between the two methods in terms of disease-specific and disease-free survival times. RESULTS: With stroma-low as baseline, automated TSR was found to be prognostic independent of age, gender, pT-stage, lymph node status, tumor grade, and whether adjuvant therapy was given, both for disease-specific survival (hazard ratio = 2.48 (95% confidence interval 1.29-4.78)) and for disease-free survival (hazard ratio = 2.05 (95% confidence interval 1.11-3.78)). Visually assessed TSR did not serve as an independent prognostic factor in multivariate analysis. CONCLUSIONS: This work shows that TSR is an independent prognosticator in rectal cancer when assessed automatically in user-provided stroma hot-spots. The deep learning-based technology presented here may be a significant aid to pathologists in routine diagnostics.
Entities:
Keywords:
Automated analysis; Computational pathology; Deep learning; Prognosis; Rectal carcinoma; Tumor-stroma ratio
Authors: Sophie C Hagenaars; Kiki M H Vangangelt; Gabi W Van Pelt; Zsófia Karancsi; Rob A E M Tollenaar; Andrew R Green; Emad A Rakha; Janina Kulka; Wilma E Mesker Journal: Breast Cancer Res Treat Date: 2022-04-16 Impact factor: 4.624
Authors: Min Seob Kwak; Hun Hee Lee; Jae Min Yang; Jae Myung Cha; Jung Won Jeon; Jin Young Yoon; Ha Il Kim Journal: Front Oncol Date: 2021-01-13 Impact factor: 6.244