echemi logo
Product
  • Product
  • Supplier
  • Inquiry
    Home > Active Ingredient News > Antitumor Therapy > Application of deep learning in CT images: The use of convolutional neural networks to automatically detect lung nodules for subsequent management.

    Application of deep learning in CT images: The use of convolutional neural networks to automatically detect lung nodules for subsequent management.

    • Last Update: 2020-07-17
    • Source: Internet
    • Author: User
    Search more information of high quality chemicals, good prices and reliable suppliers, visit www.echemi.com
    The application of deep learning in CT images: automatic detection of pulmonary nodules by convolutional neural network for follow-up management was published by Defu medical press in the Journal of cancer management and research. The contents were summarized as follows: Objective: To compare the computer-aided detection based on 3D convolutional neural network (CNN) Detection (CAD) model and different levels of experience of radiologists in the detection of pulmonary nodules on thin slice CT.patients and methods: a retrospective analysis of 1109 patients who received continuous thin-layer CT follow-up in our hospital.through the supplement of experts, the 3d-cnn pulmonary nodule detection model was retrained, and the reference standard was determined by a consensus group composed of two radiologists.in the test set, the free response receiver operating characteristic (FROC) analysis was performed on the CAD model after retraining and three radiologists with different experience levels to evaluate the detection efficiency.results: the detection efficiency of CAD model after retraining was significantly better than that of the network before training (sensitivity: 93.09% vs 38.44%) and radiologists (average sensitivity: 93.09% vs 50.22%), and there was no significant increase in the false positive number of each scan (1.64 vs 0.68).in the training set, according to the fleischner Association guidelines, 922 nodules less than 3 mm in 211 patients were assessed as high-risk and CT follow-up was recommended.there were 101 solid nodules, 15 of which were diagnosed with lung cancer.conclusion: the CAD model based on 3d-cnn is an accurate and effective tool for pulmonary nodule detection after supplementary retraining by experts, and it also provides a favorable means for subsequent monitoring of pulmonary nodules.key words: computer aided detection; computed tomography; pulmonary nodules; convolutional neural network / / Defu paper video program online! Please scan this QR code! / /
    This article is an English version of an article which is originally in the Chinese language on echemi.com and is provided for information purposes only. This website makes no representation or warranty of any kind, either expressed or implied, as to the accuracy, completeness ownership or reliability of the article or any translations thereof. If you have any concerns or complaints relating to the article, please send an email, providing a detailed description of the concern or complaint, to service@echemi.com. A staff member will contact you within 5 working days. Once verified, infringing content will be removed immediately.

    Contact Us

    The source of this page with content of products and services is from Internet, which doesn't represent ECHEMI's opinion. If you have any queries, please write to service@echemi.com. It will be replied within 5 days.

    Moreover, if you find any instances of plagiarism from the page, please send email to service@echemi.com with relevant evidence.