{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/pathologist-level-classification-of","title":"Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks","arxiv_id":"1901.11489","date":"2019-01-31","proceeding":null,"authors":["Jason W. Wei","Laura J. Tafe","Yevgeniy A. Linnik","Louis J. Vaickus","Naofumi Tomita","Saeed Hassanpour"],"abstract":"Classification of histologic patterns in lung adenocarcinoma is critical for\ndetermining tumor grade and treatment for patients. However, this task is often\nchallenging due to the heterogeneous nature of lung adenocarcinoma and the\nsubjective criteria for evaluation. In this study, we propose a deep learning\nmodel that automatically classifies the histologic patterns of lung\nadenocarcinoma on surgical resection slides. Our model uses a convolutional\nneural network to identify regions of neoplastic cells, then aggregates those\nclassifications to infer predominant and minor histologic patterns for any\ngiven whole-slide image. We evaluated our model on an independent set of 143\nwhole-slide images. It achieved a kappa score of 0.525 and an agreement of\n66.6% with three pathologists for classifying the predominant patterns,\nslightly higher than the inter-pathologist kappa score of 0.485 and agreement\nof 62.7% on this test set. All evaluation metrics for our model and the three\npathologists were within 95% confidence intervals of agreement. If confirmed in\nclinical practice, our model can assist pathologists in improving\nclassification of lung adenocarcinoma patterns by automatically pre-screening\nand highlighting cancerous regions prior to review. Our approach can be\ngeneralized to any whole-slide image classification task, and code is made\npublicly available at https://github.com/BMIRDS/deepslide.","url_abs":"http://arxiv.org/abs/1901.11489v1","url_pdf":"http://arxiv.org/pdf/1901.11489v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"pathologist-level-classification-of","repo_url":"https://github.com/BMIRDS/deepslide","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"lung-cancer-diagnosis","task_name":"Lung Cancer Diagnosis"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"whole-slide-images","task_name":"whole slide images"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.11489","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}