Artificial Intelligence-Based Segmentation of Residual Tumor in Histopathology of Pancreatic Cancer after Neoadjuvant Treatment

Autor:	Boris V. Janssen, Rutger Theijse, Johanna W. Wilmink, Marc G. Besselink, Stijn van Roessel, Arantza Farina, Antonie Berkel, Rik de Ruiter, Geert Kazemier, Olivier R. Busch, Onno J. de Boer, Pieter Valkema, J. Huiskens, Joanne Verheij
Přispěvatelé:	Graduate School, Surgery, AGEM - Amsterdam Gastroenterology Endocrinology Metabolism, Oncology, Pathology, ACS - Heart failure & arrhythmias, CCA - Imaging and biomarkers
Jazyk:	angličtina
Rok vydání:	2021
Předmět:	Cancer Research medicine.medical_specialty medicine.medical_treatment pancreatic cancer Residual Article Neoadjuvant treatment Pancreatic cancer medicine Segmentation neoadjuvant therapy Neoadjuvant therapy RC254-282 tumor response scoring business.industry Neoplasms. Tumors. Oncology. Including cancer and carcinogens medicine.disease artificial intelligence machine learning Oncology Nat histopathology Histopathology Artificial intelligence business F1 score
Zdroj:	Cancers Cancers, Vol 13, Iss 5089, p 5089 (2021) Cancers, 13(20):5089. Multidisciplinary Digital Publishing Institute (MDPI) Volume 13 Issue 20
ISSN:	2072-6694
Popis:	Background: Histologic examination of resected pancreatic cancer after neoadjuvant therapy (NAT) is used to assess the effect of NAT and may guide the choice for adjuvant treatment. However, evaluating residual tumor burden in pancreatic cancer is challenging given tumor response heterogeneity and challenging histomorphology. Artificial intelligence techniques may offer a more reproducible approach. Methods: From 64 patients, one H& E-stained slide of resected pancreatic cancer after NAT was digitized. Three separate classes were manually outlined in each slide (i.e., tumor, normal ducts, and remaining epithelium). Corresponding segmentation masks and patches were generated and distributed over training, validation, and test sets. Modified U-nets with varying encoders were trained, and F1 scores were obtained to express segmentation accuracy. Results: The highest mean segmentation accuracy was obtained using modified U-nets with a DenseNet161 encoder. Tumor tissue was segmented with a high mean F1 score of 0.86, while the overall multiclass average F1 score was 0.82. Conclusions: This study shows that artificial intelligence-based assessment of residual tumor burden is feasible given the promising obtained F1 scores for tumor segmentation. This model could be developed into a tool for the objective evaluation of the response to NAT and may potentially guide the choice for adjuvant treatment.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4d049f5949d480db2e4bcfb3a5cc3f13 http://europepmc.org/articles/PMC8533716 Zobrazit plný text záznamu Plný text ve formátu PDF Plný text ve formátu HTML
Nepřihlášeným uživatelům se plný text nezobrazuje	K zobrazení výsledku je třeba se přihlásit.