Item request has been placed! ×
Item request cannot be made. ×
loading  Processing Request

Histopathological Tissue Segmentation of Lung Cancer with Bilinear CNN and Soft Attention.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
اقرأ على الانترنت اقرأ أكثر حفظ في قائمتي
  • معلومة اضافية
    • المصدر:
      Publisher: Hindawi Pub. Co Country of Publication: United States NLM ID: 101600173 Publication Model: eCollection Cited Medium: Internet ISSN: 2314-6141 (Electronic) NLM ISO Abbreviation: Biomed Res Int Subsets: MEDLINE
    • بيانات النشر:
      Original Publication: New York, NY : Hindawi Pub. Co.
    • الموضوع:
      Image Processing, Computer-Assisted*/methods ; Lung Neoplasms*/diagnostic imaging; Algorithms ; Attention ; Humans ; Neural Networks, Computer
    • نبذة مختصرة :
      Automatic tissue segmentation in whole-slide images (WSIs) is a critical task in hematoxylin and eosin- (H&E-) stained histopathological images for accurate diagnosis and risk stratification of lung cancer. Patch classification and stitching the classification results can fast conduct tissue segmentation of WSIs. However, due to the tumour heterogeneity, large intraclass variability and small interclass variability make the classification task challenging. In this paper, we propose a novel bilinear convolutional neural network- (Bilinear-CNN-) based model with a bilinear convolutional module and a soft attention module to tackle this problem. This method investigates the intraclass semantic correspondence and focuses on the more distinguishable features that make feature output variations relatively large between interclass. The performance of the Bilinear-CNN-based model is compared with other state-of-the-art methods on the histopathological classification dataset, which consists of 107.7 k patches of lung cancer. We further evaluate our proposed algorithm on an additional dataset from colorectal cancer. Extensive experiments show that the performance of our proposed method is superior to that of previous state-of-the-art ones and the interpretability of our proposed method is demonstrated by Grad-CAM.
      Competing Interests: The authors declare no competing interest.
      (Copyright © 2022 Rui Xu et al.)
    • References:
      Cancers (Basel). 2020 Sep 16;12(9):. (PMID: 32947928)
      Annu Int Conf IEEE Eng Med Biol Soc. 2017 Jul;2017:4050-4053. (PMID: 29060786)
      Med Image Anal. 2021 Feb;68:101903. (PMID: 33352373)
      Cancers (Basel). 2019 Oct 28;11(11):. (PMID: 31661863)
      BMC Med. 2021 Mar 29;19(1):80. (PMID: 33775248)
      Med Image Anal. 2019 Dec;58:101563. (PMID: 31561183)
      Ann Glob Health. 2019 Jan 22;85(1):. (PMID: 30741509)
      Lancet Digit Health. 2020 Nov;2(11):e594-e606. (PMID: 33163952)
      PLoS Med. 2019 Jan 24;16(1):e1002730. (PMID: 30677016)
      Neurocomputing. 2016 May 26;191:214-223. (PMID: 28154470)
      Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. 2016 Jun-Jul;2016:2424-2433. (PMID: 27795661)
      Comput Methods Programs Biomed. 2020 Oct;194:105528. (PMID: 32470903)
      EBioMedicine. 2020 Nov;61:103054. (PMID: 33039706)
      Front Genet. 2020 Sep 04;11:547327. (PMID: 33101377)
      IEEE J Biomed Health Inform. 2021 Feb;25(2):429-440. (PMID: 33216724)
    • الموضوع:
      Date Created: 20220718 Date Completed: 20220719 Latest Revision: 20220719
    • الموضوع:
      20240829
    • الرقم المعرف:
      PMC9283032
    • الرقم المعرف:
      10.1155/2022/7966553
    • الرقم المعرف:
      35845926