{"title":"A Multiscale Connected UNet for the Segmentation of Lung Cancer Cells in Pathology Sections Stained Using Rapid On-Site Cytopathological Evaluation","authors":"","doi":"10.1016/j.ajpath.2024.05.011","DOIUrl":null,"url":null,"abstract":"<div><p>Lung cancer is an increasingly serious health problem worldwide, and early detection and diagnosis are crucial for successful treatment. With the development of artificial intelligence and the growth of data volume, machine learning techniques can play a significant role in improving the accuracy of early detection in lung cancer. This study proposes a deep learning-based segmentation algorithm for rapid on-site cytopathological evaluation (ROSE) to enhance the diagnostic efficiency of endobronchial ultrasound-guided transbronchial needle aspiration biopsy (EBUS-TBNA) during surgery. By utilizing the CUNet3+ network model, cell clusters, including cancer cell clusters, can be accurately segmented in ROSE-stained pathological sections. The model demonstrated high accuracy, with an F1-score of 0.9604, recall of 0.9609, precision of 0.9654, and accuracy of 0.9834 on the internal testing data set. It also achieved an area under the receiver-operating characteristic curve of 0.9972 for cancer identification. The proposed algorithm saved time for on-site diagnosis, improved EBUS-TBNA efficiency, and outperformed classical segmentation algorithms in accurately identifying lung cancer cell clusters in ROSE-stained images. It effectively reduced over-segmentation, decreased network parameters, and enhanced computational efficiency, making it suitable for real-time patient evaluation during surgical procedures.</p></div>","PeriodicalId":7623,"journal":{"name":"American Journal of Pathology","volume":null,"pages":null},"PeriodicalIF":4.7000,"publicationDate":"2024-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"American Journal of Pathology","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0002944024002104","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PATHOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Lung cancer is an increasingly serious health problem worldwide, and early detection and diagnosis are crucial for successful treatment. With the development of artificial intelligence and the growth of data volume, machine learning techniques can play a significant role in improving the accuracy of early detection in lung cancer. This study proposes a deep learning-based segmentation algorithm for rapid on-site cytopathological evaluation (ROSE) to enhance the diagnostic efficiency of endobronchial ultrasound-guided transbronchial needle aspiration biopsy (EBUS-TBNA) during surgery. By utilizing the CUNet3+ network model, cell clusters, including cancer cell clusters, can be accurately segmented in ROSE-stained pathological sections. The model demonstrated high accuracy, with an F1-score of 0.9604, recall of 0.9609, precision of 0.9654, and accuracy of 0.9834 on the internal testing data set. It also achieved an area under the receiver-operating characteristic curve of 0.9972 for cancer identification. The proposed algorithm saved time for on-site diagnosis, improved EBUS-TBNA efficiency, and outperformed classical segmentation algorithms in accurately identifying lung cancer cell clusters in ROSE-stained images. It effectively reduced over-segmentation, decreased network parameters, and enhanced computational efficiency, making it suitable for real-time patient evaluation during surgical procedures.
期刊介绍:
The American Journal of Pathology, official journal of the American Society for Investigative Pathology, published by Elsevier, Inc., seeks high-quality original research reports, reviews, and commentaries related to the molecular and cellular basis of disease. The editors will consider basic, translational, and clinical investigations that directly address mechanisms of pathogenesis or provide a foundation for future mechanistic inquiries. Examples of such foundational investigations include data mining, identification of biomarkers, molecular pathology, and discovery research. Foundational studies that incorporate deep learning and artificial intelligence are also welcome. High priority is given to studies of human disease and relevant experimental models using molecular, cellular, and organismal approaches.